Failure prediction of at least one tintable window

Abstract

Data from measurements are combined with a learning module to identify and predict dysfunction of a colorable window. These measurements may be based, at least in part, on data accumulated during the regular operation of a colorable window.

Description

Technical Field

[0001] Related applications

[0002] This application claims U.S. Provisional Patent Application No. 63 / 106,058, filed October 27, 2020, entitled "Tintable Wind Failure Prediction"; U.S. Provisional Patent Application No. 63 / 240,117, filed September 2, 2021, entitled "Occupant-Centered Predictive Control of Devices in Facilities"; U.S. Provisional Patent Application No. 63 / 109,306, filed November 3, 2020, entitled "Accounting for Devices in a Facility"; and U.S. Provisional Patent Application No. 63 / 109,306, filed June 24, 2021, entitled "Virtual Viewing of Devices in a Facility". This application also claims priority to U.S. Provisional Patent Application No. 63 / 214,741, entitled "Control Methods and Systems Using External 3D Modeling and Neural Networks," filed February 5, 2021, which claims priority to International Patent Application No. PCT / US19 / 46524, entitled "Control Methods and Systems Using External 3D Modeling and Neural Networks," filed August 14, 2019.International Patent Application No. PCT / US19 / 46524 claims U.S. Provisional Patent Application No. 62 / 764,821, filed August 15, 2018, entitled "Control Methods and Systems Using External 3D Modeling and Neural Networks"; U.S. Provisional Patent Application No. 62 / 745,920, filed October 15, 2018, entitled "Control Methods and Systems Using External 3D Modeling and Neural Networks"; and U.S. Provisional Patent Application No. 62 / 745,920, filed February 14, 2019, entitled "Control Methods and Systems Using External 3D Modeling and Neural Networks". The benefit and priority of U.S. Provisional Patent Application No. 62 / 805,841, entitled "3D MODELING AND NEURAL NETWORKS". International Patent Application No. PCT / US19 / 46524 is also a partial continuation application of International Patent Application No. PCT / US19 / 23268, filed on March 20, 2019, entitled "Control methods and systems using external 3D modeling and schedule-based computation." This international patent application claims against U.S. Provisional Patent Application No. 62 / 646,260, filed on March 21, 2018, entitled "Methods and systems for controlling tiny windows with cloud detection," and U.S. Provisional Patent Application No. 62 / 646,260, filed on May 3, 2018, entitled "Control methods and systems using external 3D modeling and schedule-based computation." The benefit and priority of U.S. Provisional Patent Application No. 62 / 666,572 entitled “External 3D Modeling and Schedule-Based Computing”.International Patent Application No. PCT / US19 / 23268 is also a partial continuation of U.S. Patent Application No. 16 / 013,770, filed on June 20, 2018, entitled "Control Method for Tintable Windows," which is a continuation of U.S. Patent Application No. 15 / 347,677, filed on November 9, 2016, entitled "Control Method for Tintable Windows." U.S. Patent Application No. 15 / 347,677 is a partial continuation-into-continuation of International Patent Application No. PCT / US15 / 29675, filed May 7, 2015, entitled "Control Method for Tintable Windows." This international patent application claims the benefit and priority of U.S. Provisional Application No. 61 / 991,375, filed May 9, 2014, also entitled "Control Method for Tintable Windows." U.S. Patent Application No. 15 / 347,677 is also a partial continuation-into-continuation of U.S. Patent Application No. 13 / 772,969, filed February 21, 2013, also entitled "Control Method for Tintable Windows." International Patent Application No. PCT / US19 / 46524, filed on August 14, 2019, is also a partial continuation of U.S. Patent Application No. 16 / 438,177, filed on June 11, 2019, entitled "Applications for Controlling Optically Switchable Devices." This U.S. Patent Application No. 14 / 391,122, filed on October 7, 2014, also entitled "Applications for Controlling Optically Switchable Devices."U.S. Patent Application No. 14 / 391,122, filed on October 7, 2014, entered the National Stage Entry of International Patent Application No. PCT / US13 / 36456, filed on April 12, 2013, entitled "Applications for Controlling Optically Switchable Devices". This international patent application claims priority and benefits over U.S. Provisional Patent Application No. 61 / 624,175, filed on April 13, 2012, also entitled "Applications for Controlling Optically Switchable Devices". This application also claims priority to a portion of a successor application to International Patent Application No. PCT / US2021 / 017603, filed February 11, 2021, entitled "Predictive Modeling for Tintable Windows," which claims priority to, for example, U.S. Provisional Patent Application No. 63 / 145,333, filed February 3, 2021, entitled "Predictive Modeling for Tintable Windows," and U.S. Provisional Patent Application No. 63 / 145,333, filed February 12, 2020, entitled "Virtual Sky Sensors and Supervised Classification of Sensor Radiation for Weather." Priority claims are made to U.S. Provisional Patent Application No. 62 / 975,677 entitled "Predictive Modeling for Tintable Windows," filed September 8, 2020; and U.S. Provisional Patent Application No. 63 / 075,569 entitled "Predictive Modeling for Tintable Windows," filed September 8, 2020. Each of these applications is incorporated herein by reference in its entirety and for all purposes. Prior Technology

[0003] Some tinted windows can be electronically controlled. Such control allows for the regulation of the amount of light (e.g., heat) passing through the window, thereby providing the tinted window with the opportunity to function as an energy-saving device by adjusting (e.g., absorbing, diffusing, and / or reflecting) the incident light. Various types of tinted windows exist, such as electrochromic windows.

[0004] Electrochromism is a phenomenon in which a material exhibits reversible, electrochemically mediated changes in its optical properties when placed in different electronic energy states, for example, by experiencing a change in voltage. Optical properties may include color, transmittance, absorptivity, and / or reflectivity. Electrochromic materials can be incorporated into windows for example, for residential, commercial, industrial, and / or other applications. An electrochromic coating can be a (e.g., thin) film coating on window glass. The color, transmittance, absorptivity, and / or reflectivity of such windows can be altered by inducing changes in the electrochromic material. For example, an electrochromic window is a window that can be darkened or brightened electronically. In some embodiments, a (e.g., small) voltage applied to an electrochromic device (EC) of the window will darken the EC; reversing the voltage polarity will brighten the EC. Although electrochromism was discovered in the 1960s, electrochromic devices, and especially electrochromic windows, still have various problems. Despite many recent advances in electrochromic technology, devices, software, and related methods of manufacturing and / or using electrochromic devices, their full commercial potential has not yet been realized. Other methods for achieving hue changes in colorable windows are available (e.g., as disclosed herein).

[0005] Failures in tintable windows can become noticeable and affect their visual appeal and / or functionality. Identification, maintenance, and / or replacement of tintable windows and associated equipment (e.g., controllers) can be costly, time-consuming, labor-intensive, and / or logistical. This is especially true in large facilities with multiple tintable windows. To reduce the burden on users of facilities with malfunctioning tintable windows, tintable window providers may wish to minimize any time required to maintain and / or replace (e.g., potentially) malfunctioning windows, particularly when the window to be replaced is not in stock and therefore must be manufactured, which can significantly delay the replacement process.

[0006] It is advantageous to identify (e.g., potentially) functional failure windows in advance. Similarly, it is advantageous to at least partially automate the process of identifying any (e.g., potentially) functional failure windows. Advantages may include providing at least some relief for such maintenance and / or replacement tasks. For example, it may (i) provide an opportunity to replace a functional failure window before it becomes an obvious functional failure, (ii) ensure an inventory of potentially functional failure windows (e.g., so that they will be available for replacement when they fail), (iii) provide a time buffer to coordinate and execute the window maintenance and / or replacement process, and / or (iv) provide an opportunity to proactively perform corrective measurements before a window (e.g., obviously) fails (and / or deteriorates). Summary of the Invention

[0007] The various approaches revealed in this article alleviate at least some of the shortcomings mentioned above.

[0008] For example, data from a colorable window controller system is combined with a learning module (e.g., incorporating artificial intelligence (AI) and / or machine learning) to predict and / or identify colorable window malfunctions. Such data (e.g., from the control system) can be accumulated in one or more databases. The accumulated data can be collected during the routine operation of the colorable window. The data can be correlated with the routine operation of the colorable window (e.g., current and / or voltage data are correlated with changing and / or maintaining the color of the colorable window). The data can be large in volume (e.g., accumulated over a period of time and / or for multiple colorable windows). The architecture can be configured to retrieve accumulated data from one or more databases, aggregate the data, and use the data, for example, by analyzing one or more fault signatures, to analyze the maintenance (e.g., including faults) of any colorable window. Statistical measurements obtained from the routine operation of the colorable window (e.g., current and / or voltage measurements) can be used to identify one or more fault signatures.

[0009] In another embodiment, a method for predicting failures of tintable windows in a facility includes: (a) acquiring one or more measurements related to a hue transition of a tintable window placed in the facility, wherein the hue transition is from a first hue to a second hue; (b) analyzing one or more measurements acquired by considering data that (i) is related to the type of one or more measurements, (ii) is related to the hue transition from the first hue to the second hue, and (iii) is a characteristic of an incomplete hue transition and / or a non-characteristic hue transition from the first hue to the second hue; and (c) using the analysis to predict failures in the tinting of the tintable window.

[0010] In some embodiments, a first hue is brighter than a second hue. In some embodiments, a first hue is darker than a second hue. In some embodiments, a first hue is a transparent or absorbing hue relative to the visible spectrum. In some embodiments, a second hue is a transparent or absorbing hue relative to the visible spectrum. In some embodiments, a hue transition includes a complete hue transition from the first hue to the second hue. In some embodiments, a complete hue transition does not contain any detectable interruptions. In some embodiments, the method further includes data that takes into account characteristics of a complete and / or characteristic hue transition from the first hue to the second hue. In some embodiments, the data includes (A) data of a complete and / or characteristic hue transition or (B) characteristics of an incomplete hue transition and / or a non-characteristic hue transition. In some embodiments, one or more measurements include voltage and / or current measurements. In some embodiments, current measurements are obtained instantaneously during a hue transition. In some embodiments, one or more measurements include open-circuit voltage measurements. In some embodiments, one or more measurements include one or more measurements from at least one sensor. In some embodiments, at least one sensor is located within a facility. In some embodiments, at least one sensor is located outside a facility. In some embodiments, at least one sensor includes a sensor configured to sense electromagnetic radiation. In some embodiments, electromagnetic radiation includes infrared radiation or visible light radiation visible to the average user. In some embodiments, at least one sensor includes a temperature sensor. In some embodiments, at least one sensor includes a thermocouple, an infrared sensor, or a solar intensity meter. In some embodiments, at least one sensor includes a light sensor. In some embodiments, at least one sensor includes an irradiance sensor. In some embodiments, at least one sensor includes a colorable window. In some embodiments, at least one sensor includes an acoustic, motion, vibration, temperature, and / or electromagnetic sensor. In some embodiments, the method further includes using analysis to determine a reliability value for at least one sensor. In some embodiments, the method further includes using the reliability value to adjust one or more measurements of at least one sensor to form one or more adjusted sensor measurements. In some embodiments, the method further includes using one or more adjusted sensor measurements to update the reliability value. In some embodiments, the method further includes processing one or more adjusted sensor measurements by considering (A) the facility, (B) historical sensor measurements, (C) sensor measurement benchmarks, and / or (D) modeling to produce a result. In some embodiments, the method further includes using the result and / or the reliability value to produce a prediction of subsequent colorable window failures of the facility. In some embodiments, one or more measurements include the time of measurement, the identifier of the colorable window, or the orientation of the colorable window. In some embodiments, the colorable window includes an electrochromic structure, and one or more measurements relate to the current transmitted through the electrochromic structure.In some embodiments, one or more measurements include open-circuit voltage measurements. In some embodiments, the method further includes performing open-circuit voltage measurements during ramping and / or holding periods. In some embodiments, hue transition is achieved by voltage and / or current having ramps and / or holding periods. In some embodiments, hue transition is achieved by voltage and / or current having a plurality of ramps and / or a plurality of holding periods. In some embodiments, at least one of the plurality of holding periods is above a level considered safe for continuous operation of the tintable window. In some embodiments, the tintable window is located inside a building of the facility. In some embodiments, the tintable window is located on the envelope of a building of the facility. In some embodiments, incomplete hue transition and / or non-characteristic hue transition has a type having at least one identifiable data signature. In some embodiments, the data includes historical data and / or synthetic data. In some embodiments, the data includes data obtained from the facility. In some embodiments, the data includes data obtained from a facility different from the facility. In some embodiments, the tintable window is located in a building of the facility, and the data includes data obtained from the building. In some embodiments, the colorable window is positioned within a building of the facility, and the data includes data acquired from a building different from the building. In some embodiments, the colorable window has a size, and the associated data is related to one or more measurements acquired from one or more different windows that have or substantially have a size. In some embodiments, the data includes data acquired within at least about 10, 50, 100, or 1,000 occurrences of a hue change. In some embodiments, the data includes data acquired within at least about 12, 25, 52, 104, or 156 weeks. In some embodiments, machine learning is used to analyze the data. In some embodiments, the machine learning utilizes a plurality of modules. In some embodiments, at least two of the plurality of modules receive the same weight in the machine learning analysis. In some embodiments, at least two of the plurality of modules receive different weights in the machine learning analysis. In some embodiments, the machine learning includes deep learning. In some embodiments, the machine learning does not include deep learning. In some embodiments, the learning set for machine learning includes historical data and / or synthetic data. In some embodiments, analyzing one or more measurements includes comparison with threshold values. In some embodiments, threshold values ​​include values ​​or functions. In some embodiments, the function is a time-dependent function. In some embodiments, machine learning includes utilizing a learning set. In some embodiments, the learning set includes one or more historical measurements acquired over a period of time. In some embodiments, the time is adjustable. In some embodiments, the adjustability is performed by a user. In some embodiments, analyzing one or more measurements includes performing one or more mathematical transformations. In some embodiments, the one or more mathematical transformations include Boolean operations.In some embodiments, one or more mathematical transformations include at least one derivation or at least one integration. In some embodiments, machine learning includes neural network analysis and / or visual analysis. In some embodiments, analyzing one or more measurements includes any data signature specific to the facility, the window type of the colorable window, weather conditions, time of day, time of year, the relative geographic location of the colorable window within the facility, and / or the geographic location of the facility. In some embodiments, the data includes one or more measurements having the same type as the one or more measurements obtained in (a). In some embodiments, the data includes a transition from a first hue to a second hue. In some embodiments, an incomplete hue transition and / or a non-characteristic hue transition is a hue transition of a faulty colorable window. In some embodiments, the use of analysis includes providing alarms and / or reports of faults in colorable windows. In some embodiments, providing alarms and / or reports includes predicting the time of a visible fault that is visible to the average person. In some embodiments, providing alarms and / or reports includes scheduling maintenance. In some embodiments, the colorable window is a first colorable window, and the provision of alarms and / or reports includes: scheduling the inventory of another colorable window and / or scheduling the manufacture of another colorable window to replace the first colorable window. In some embodiments, the prediction of faults occurs before any defective hue transitions become visible to the average person. In some embodiments, the analysis predicts faults in the shading of a colorable window. In some embodiments, the method further includes adjusting control schemes to facilitate hue transitions via the colorable window.

[0011] In another embodiment, there is a non-transitory computer-readable program instruction for predicting colorable window failures in a facility, which, when executed by one or more processors, causes one or more processors to perform or directly perform one or more operations of any of the methods disclosed above.

[0012] In some embodiments, at least one processor is part of a hierarchical control system. In some embodiments, at least one processor is at least one controller, includes at least one controller, or is included in at least one controller. In some embodiments, at least two operations are executed by the same processor. In some embodiments, at least two operations are executed by different processors. In some embodiments, at least one of one or more processors is located in a cloud device. In some embodiments, program instructions are recorded on one or more non-transitory computer-readable media.

[0013] In another embodiment, a non-transitory computer-readable program instruction for predicting malfunctions of colorable windows in a facility, wherein, when executed by one or more processors, the non-transitory computer-readable program instruction causes one or more processors to perform operations including: (a) acquiring one or more measurements related to a hue transition of a colorable window placed in the facility, or guiding the acquisition of the one or more measurements, wherein the hue transition is from a first hue to a second hue; (b) analyzing the one or more measurements acquired by considering data, or guiding the analysis of the one or more measurements, wherein the data (i) is related to the type of the one or more measurements, (ii) is related to the hue transition from the first hue to the second hue, and (iii) is a characteristic of an incomplete hue transition and / or a non-characteristic hue transition from the first hue to the second hue; and (c) using the analysis or guiding the use of the analysis to predict malfunctions in the coloring of the colorable window.

[0014] In another embodiment, an apparatus for predicting colorable window failures in a facility includes at least one controller configured to perform or directly perform one or more operations of any of the methods disclosed above.

[0015] In another embodiment, an apparatus for predicting faults in tintable windows in a facility includes at least one controller configured to: (a) acquire one or more measurements relating to a hue transition of a tintable window placed in the facility, or guide the acquisition of the one or more measurements, wherein the hue transition is from a first hue to a second hue; (b) analyze the one or more measurements acquired by considering data, or guide the analysis of the one or more measurements, wherein the data (i) is related to the type of the one or more measurements, (ii) is related to the hue transition from the first hue to the second hue, and (iii) is a characteristic of an incomplete hue transition and / or a non-characteristic hue transition from the first hue to the second hue; and (c) use the analysis or guide the use of the analysis to predict faults in the tinting of the tintable window.

[0016] In some embodiments, at least one controller is included in a hierarchical control system. In some embodiments, at least one controller is configured to include a feedback control scheme. In some embodiments, at least one controller includes a local controller configured to be directly coupled to a colorable window. In some embodiments, direct coupling includes uninterrupted wiring from the local controller to the colorable window. In some embodiments, uninterrupted wiring is achieved by circuitry. In some embodiments, at least one controller includes circuitry. In some embodiments, the circuitry includes computer-readable programmable instructions storing control logic and data. In some embodiments, at least one controller includes circuitry. In some embodiments, the device further includes a processor that communicates with or incorporates the computer-readable programmable instructions. In some embodiments, at least one controller is configured to (i) be operatively coupled to at least one sensor, and (ii) direct at least one sensor to acquire one or more measurements related to a hue change in the colorable window. In some embodiments, at least one controller is configured to execute a feedback control scheme utilizing at least one sensor or to direct the execution of such feedback control scheme. In some embodiments, at least one controller is configured to change the hue of the colorable window by using or directing the use of such feedback control scheme. In some embodiments, a first hue is brighter than a second hue. In some embodiments, a first hue is darker than a second hue. In some embodiments, the first hue is a transparent or absorbing hue relative to the visible spectrum. In some embodiments, the second hue is a transparent or absorbing hue relative to the visible spectrum. In some embodiments, a hue transition includes a complete hue transition from the first hue to the second hue. In some embodiments, a complete hue transition does not contain any detectable interruptions. In some embodiments, at least one controller is configured to consider or guide the consideration of data indicating a complete and / or characteristic hue transition from the first hue to the second hue. In some embodiments, the data includes (A) data of a complete and / or characteristic hue transition or (B) characteristics of an incomplete and / or non-characteristic hue transition. In some embodiments, at least one controller is configured to perform or guide the execution of one or more measurements, including voltage and / or current measurements. In some embodiments, at least one controller is configured to perform or guide the execution of current measurements in real time during a hue transition. In some embodiments, one or more measurement values ​​include open-circuit voltage measurement values. In some embodiments, one or more measurement values ​​include one or more measurement values ​​from at least one sensor. In some embodiments, at least one sensor is disposed in a facility. In some embodiments, at least one sensor is located outside the facility. In some embodiments, at least one sensor includes a sensor configured to sense electromagnetic radiation. In some embodiments, the electromagnetic radiation includes infrared radiation, or visible light radiation visible to the average user.In some embodiments, at least one sensor includes a temperature sensor. In some embodiments, at least one sensor includes a thermocouple, an infrared sensor, or a solar intensity meter. In some embodiments, at least one sensor includes a light sensor. In some embodiments, at least one sensor includes an irradiance sensor. In some embodiments, at least one sensor includes a colorable window. In some embodiments, at least one sensor includes an acoustic, motion, vibration, temperature, and / or electromagnetic sensor. In some embodiments, at least one controller is configured to use analysis or guide the use of such analysis to determine a reliability value for at least one sensor. In some embodiments, at least one controller is further configured to use the reliability value or guide the use of such reliability value to adjust one or more measurements of at least one sensor to form one or more adjusted sensor measurements. In some embodiments, at least one controller is further configured to update the reliability value or guide the update of such reliability value using one or more adjusted sensor measurements. In some embodiments, at least one controller is further configured to process one or more adjusted sensor measurements or guide the processing of such one or more adjusted sensor measurements by considering (A) facility, (B) historical sensor measurements, (C) sensor measurement references, and / or (D) modeling, to produce a result. In some embodiments, at least one controller is further configured to use the result and / or reliability value or guide the use of the result and / or the reliability value to produce a prediction of subsequent colorizable window failures of the facility. In some embodiments, one or more measurements include the time of measurement, the identifier of the colorizable window, or the orientation of the colorizable window. In some embodiments, the colorizable window includes an electrochromic structure, and one or more measurements are related to the current transmitted through the electrochromic structure. In some embodiments, one or more measurements include voltage and / or current measurements. In some embodiments, one or more measurements include open-circuit voltage measurements. In some embodiments, at least one controller is configured to perform open-circuit voltage measurements or guide the execution of such open-circuit voltage measurements during ramping and / or holding periods. In some embodiments, tone transition is achieved by voltage and / or current having ramps and / or holds. In some embodiments, tone transition is achieved by voltage and / or current having a plurality of ramps and / or holds. In some embodiments, at least one of the holds is above a level considered safe for continuous operation of the tintable window. In some embodiments, the tintable window is located inside the building of the facility. In some embodiments, the tintable window is located on the building envelope of the facility. In some embodiments, incomplete tone transition and / or non-characteristic tone transition has a type having at least one identifiable data signature. In some embodiments, the data includes historical data and / or synthetic data. In some embodiments, the data includes data obtained from the facility. In some embodiments, the data includes data obtained from a facility different from the facility.In some embodiments, a colorable window is disposed within a building of the facility, and the data includes data acquired from the building. In some embodiments, a colorable window is disposed within a building of the facility, and the data includes data acquired from a building different from the building. In some embodiments, the colorable window has a size, and the associated data is related to one or more measurements acquired from one or more different windows having or substantially having a size. In some embodiments, the data includes data acquired within at least about 10, 50, 100, or 1,000 occurrences of a hue change. In some embodiments, the data includes data acquired within at least about 12, 25, 52, 104, or 156 weeks. In some embodiments, at least one controller is configured to analyze the data or guide the analysis of the data using machine learning analytics. In some embodiments, the machine learning analytics utilizes a plurality of modules. In some embodiments, at least two of the plurality of modules receive the same weight in the machine learning analytics. In some embodiments, at least two of the plurality of modules receive different weights in the machine learning analytics. In some embodiments, the machine learning analytics includes deep learning. In some embodiments, the machine learning analytics does not include deep learning. In some embodiments, at least one controller is configured to use or guide the use of a learning set for machine learning analysis. In some embodiments, the learning set includes historical data and / or synthetic data. In some embodiments, at least one controller is configured to analyze or guide the analysis of one or more measurements by comparing one or more measurements to thresholds. In some embodiments, thresholds include values ​​or functions. In some embodiments, the function is a time-dependent function. In some embodiments, at least one controller is configured to perform or guide the execution of machine learning by utilizing the learning set. In some embodiments, the learning set includes one or more historical measurements acquired over a time period. In some embodiments, the time period is adjustable. In some embodiments, the time period is adjustable by a user. In some embodiments, at least one controller is configured to analyze or guide the analysis of one or more measurements by performing one or more mathematical manipulations. In some embodiments, one or more mathematical transformations include Boolean operations. In some embodiments, one or more mathematical transformations include at least one derivation or at least one integration. In some embodiments, at least one controller is configured to perform or guide the execution of machine learning by using neural network analysis and / or visual analysis. In some embodiments, at least one controller is configured to analyze or guide the analysis of one or more measurements by using the following: a data signature specific to the facility, window type of a colorable window, weather conditions, time of day, time of year, relative geographic location of a colorable window in the facility, and / or geographic location of the facility.In some embodiments, the data includes one or more measurements of the same type as those obtained in (a). In some embodiments, the data includes a transition from a first hue to a second hue. In some embodiments, an incomplete hue transition and / or a non-characteristic hue transition is a hue transition of a faulty colorable window. In some embodiments, at least one controller is configured to use analysis or guide the use of analysis by providing alarms and / or reports of faults in colorable windows. In some embodiments, providing alarms and / or reports includes predicting the time of a visible fault that is visible to the average person. In some embodiments, providing alarms and / or reports includes scheduling maintenance. In some embodiments, the colorable window is a first colorable window, and the providing alarms and / or reports include: scheduling the inventory of another colorable window and / or scheduling the manufacture of another colorable window to replace the first colorable window. In some embodiments, at least one controller is configured to predict or guide the prediction of any defective hue transition before it becomes visible to the average person. In some embodiments, at least one controller is configured to predict or guide the prediction of faults in the coloring of a colorable window, at least in part, by adjusting the control scheme to facilitate the hue transition of the colorable window.

[0017] In another embodiment, a system for predicting colorable window failures in a facility includes: a network configured to: (I) be operatively coupled to the colorable window of the facility; and (II) transmit one or more signals associated with any of the methods disclosed above.

[0018] In another embodiment, a system for predicting faults in tintable windows in a facility includes: a network configured to: (a) acquire one or more measurements related to a hue transition of a tintable window disposed in the facility, wherein the hue transition is from a first hue to a second hue; (b) transmit analysis of the one or more measurements, wherein data is considered that (i) is related to the type of the one or more measurements, (ii) is related to the hue transition from the first hue to the second hue, and (iii) is a characteristic of an incomplete hue transition and / or a non-characteristic hue transition from the first hue to the second hue; and (c) transmit an indication of a predicted fault in the tinting of the tintable window, wherein the analysis is used to form a prediction.

[0019] In some embodiments, the network is configured to utilize a single cable for transmitting power and communications. In some embodiments, the network is configured to transmit signals conforming to multiple wireless communication protocols. The communications may be one or more types of communications. The communications may include cellular communications conforming to at least second-generation (2G), third-generation (3G), fourth-generation (4G), or fifth-generation (5G) cellular communication protocols. In some embodiments, the communications include media communications that facilitate still images, music, or streaming animation (e.g., movies or videos). In some embodiments, the network is configured to transmit signals conforming to building control protocols.

[0020] In another embodiment, an apparatus for predicting colorable window failures in a facility includes: a set of devices for the facility, the set of devices including one or more devices housed in a housing, the one or more devices including sensors configured to (A) measure the environment of the facility and (B) output sensor measurements, the sensor measurements being configured for use in any of the methods disclosed above.

[0021] An apparatus for predicting faults in colorable windows in a facility, the apparatus comprising: a set of devices of the facility, the set of devices including sensors disposed in a housing, the sensors being configured to (A) measure the environment of the facility and (B) output sensor measurements, the sensor measurements being configured to determine one or more outputs including: (a) an analysis of one or more measurements relating to a hue transition of a colorable window disposed in the facility, wherein the hue transition is from a first hue to a second hue, wherein the analysis is formed by considering data (i) relating to the type of one or more measurements, (ii) relating to the hue transition from the first hue to the second hue and (iii) being a characteristic of an incomplete hue transition and / or a non-characteristic hue transition from the first hue to the second hue; and (b) a prediction of faults in the coloring of the colorable window, wherein the prediction is formed using the analysis.

[0022] In some embodiments, the sensors of the device set include different types of sensors. In some embodiments, the sensors include: carbon dioxide sensors, carbon monoxide sensors, volatile organic chemical sensors, environmental noise sensors, visible light sensors, temperature sensors, motion sensors, or humidity sensors. In some embodiments, the device set includes a transmitter or transceiver. In some embodiments, the device set is configured to facilitate the control of the facility, and where applicable, the control of the facility includes control of the environment, safety, data, or health associated with the facility. In some embodiments, the device set is housed in or attached to a fixture of the facility. In some embodiments, the fixture includes a frame portion. In some embodiments, a network is operatively coupled to at least one colorable window and facilitates the control of at least one colorable window. In some embodiments, the colorable window includes an electrochromic window. In some embodiments, a network is operatively coupled to at least one other device of the facility and facilitates the control of at least one other device of the facility. In some embodiments, at least one other device of the facility is configured to change the environment of the facility. In some embodiments, at least one other device of the facility includes a cooler, a heater, a colorable window, a heating, cooling, and air conditioning (HVAC) system, or lighting. In some embodiments, at least one other device of the facility is configured to control the energy expenditure of the facility.

[0023] In some embodiments, the network is a local area network. In some embodiments, the network includes cables configured to transmit power and communication in a single cable. Communication may be one or more types of communication. Communication may include cellular communication that complies with at least second-generation (2G), third-generation (3G), fourth-generation (4G), or fifth-generation (5G) cellular communication protocols. In some embodiments, communication includes media communication that facilitates still images, music, or streaming of animation (e.g., movies or videos). In some embodiments, communication includes data communication (e.g., sensor data). In some embodiments, communication includes control communication, such as for controlling the operability of one or more nodes coupled to the network. In some embodiments, the network includes a first (e.g., cabling) network installed in the facility. In some embodiments, the network includes a (e.g., cabling) network installed in the enclosure of the facility (e.g., in the enclosure of a building included in the facility).

[0024] In another embodiment, the present invention provides systems, devices (e.g., controllers) and / or one or more non-transitory computer-readable media (e.g., software) for implementing any of the methods disclosed herein.

[0025] In another embodiment, the present invention provides methods for using any of the systems, computer-readable media and / or devices disclosed herein, for example for their intended purposes.

[0026] In another embodiment, the device includes at least one controller programmed to direct a mechanism for implementing (e.g., carrying out) any of the methods disclosed herein, the at least one controller being configured to be operatively coupled to the mechanism. In some embodiments, at least two operations (e.g., of the methods) are directed / executed by the same controller. In some embodiments, at least two operations are directed / executed by different controllers.

[0027] In another embodiment, the device includes at least one controller configured (e.g., programmed) to implement (e.g., enforce) any of the methods disclosed herein. At least one controller can implement any of the methods disclosed herein. In some embodiments, at least two operations (e.g., of the methods) are initiated / executed by the same controller. In some embodiments, at least two operations are initiated / executed by different controllers.

[0028] In some embodiments, one of the at least one controllers is configured to perform two or more operations. In some embodiments, two different controllers of the at least one controller are configured to each perform different operations.

[0029] In another embodiment, the system includes at least one controller programmed to direct the operation of at least one other device (or a component thereof) and the device (or its component thereof), wherein the at least one controller is operatively coupled to the device (or its component thereof). The device (or its component thereof) may include any device (or its component thereof) disclosed herein. At least one controller may be configured to direct any device (or its component thereof) disclosed herein. At least one controller may be configured to be operatively coupled to any device (or its component thereof) disclosed herein. In some embodiments, at least two operations of a device are directed by the same controller. In some embodiments, at least two operations are directed by different controllers.

[0030] In another embodiment, a computer software product storing program instructions (e.g., recorded on one or more non-transitory media) that, when read by at least one processor (e.g., a computer), causes at least one processor to direct the apparatus disclosed herein to perform (e.g., implement) any of the methods disclosed herein, wherein at least one processor is configured to be operatively coupled to the apparatus. The apparatus may comprise any device (or any component thereof) disclosed herein. In some embodiments, at least two operations (e.g., of a device) are directed / executed by the same processor. In some embodiments, at least two operations are directed / executed by different processors.

[0031] In another embodiment, the present invention provides non-transitory computer-readable program instructions (e.g., included in a program product comprising one or more non-transitory media) comprising machine executable code that, when executed by one or more processors, performs any of the methods disclosed herein. In some embodiments, (e.g., of the methods) at least two operations are initiated / executed by the same processor. In some embodiments, at least two operations are initiated / executed by different processors.

[0032] In another embodiment, the invention provides one or more non-transitory computer-readable media containing machine-executable code that, when executed by one or more processors, implements instructions for a controller (e.g., as disclosed herein). In some embodiments, at least two operations (e.g., for the controller) are initiated / executed by the same processor. In some embodiments, at least two operations are initiated / executed by different processors.

[0033] In another embodiment, the present invention provides a computer system comprising one or more computer processors and one or more non-transitory computer-readable media coupled thereto. The non-transitory computer-readable media contains machine-executable code that, when executed by the one or more processors, implements any of the methods disclosed herein and / or provides guidance to one or more controllers disclosed herein.

[0034] In another embodiment, the present invention provides non-transitory computer-readable program instructions that, when read by one or more processors, cause one or more processors to perform any operation of the methods disclosed herein, any operation performed (or configured to be performed) by the devices disclosed herein, and / or any operation guided (or configured to be guided) by the devices disclosed herein.

[0035] In some embodiments, program instructions are recorded on one or more non-transitory computer-readable media. In some embodiments, at least two of the operations are executed by one or more processors. In some embodiments, at least two of the operations are each executed by different processors of one or more processors.

[0036] In another embodiment, the invention provides a network configured to transmit any communication (e.g., signals) and / or (e.g., electrical) power that facilitates any of the operations disclosed herein. Communication may include control communication, cellular communication, media communication, and / or data communication. Data communication may include sensor data communication and / or processed data communication. The network may be configured to comply with one or more protocols that facilitate such communication. For example, the communication protocol used by the network (e.g., with a BMS) may be the Building Automation and Control Network Protocol (BACnet). For example, the communication protocol may facilitate cellular communication that complies with at least a 2nd, 3rd, 4th, or 5th generation cellular communication protocol.

[0037] The contents of this Invention Contents section are provided as a simplified introduction to the present invention and are not intended to limit the scope of any invention disclosed herein or the scope of the appended patent applications.

[0038] Further features and advantages of the invention will become apparent to those skilled in the art from the following embodiments, wherein only illustrative embodiments of the invention are shown and described. It should be recognized that the invention can have other and different embodiments, and that certain details thereof can be modified in various obvious ways without departing from the invention. Therefore, the drawings and descriptions should be considered illustrative rather than restrictive in nature.

[0039] These and other features and embodiments will be described in more detail with reference to the drawings. Incorporate by reference

[0040] All publications, patents and patent applications mentioned in this specification are incorporated herein by reference as if they were specifically and individually instructed to be incorporated by reference. Simple Explanation of the Diagram

[0041] The novel features of this invention are set forth in detail in the appended claims. A better understanding of the features and advantages of the invention will be obtained with reference to the following detailed description and the accompanying drawings (also referred to herein as "Fig. / Figs."), in which illustrative embodiments utilizing the principles of the invention are described in detail:

[0042] Figure 1A shows a cross-sectional side view of a colorable window constructed as an insulated glass unit (IGU).

[0043] Figure 1B shows a perspective cross-sectional view of the corner portion of an Integrated Glass Unit (IGU);

[0044] Figure 2A is a schematic cross-section of an electrochromic device in or transitioning to a decolorized state.

[0045] Figure 2B is a schematic cross-section of the electrochromic device of Figure 2A in a colored state or in transition to a colored state;

[0046] Figure 3A is a graph showing the current distribution of an electrochromic window that uses a simple voltage control algorithm to induce an optical state transition (e.g., coloring) in an electrochromic device;

[0047] Figure 3B is a graph depicting the total charge delivered over time and the voltage applied over time during the electrochromic color transition;

[0048] Figure 4 is a block diagram illustrating an embodiment of a building's control system;

[0049] Figure 5 is a block diagram showing the control system and its various components;

[0050] Figure 6 is a block diagram illustrating an example of a system comprising a sensor array organized into sensor modules;

[0051] Figure 7 shows a schematic example of the processing system;

[0052] Figure 8 is a block diagram showing an example of the configuration of a sensor set in a closed structure and associated measurement values;

[0053] Figure 9A is a graph of charge as a function of time, depicting the set of tonal transitions from hue to the darkest hue;

[0054] Figure 9B is a graph depicting the leakage current as a function of time, representing the set of tonal transitions from hue to the darkest hue.

[0055] Figure 10 is a flowchart illustrating an example of a method for predicting colorable window faults;

[0056] Figure 11 is a flowchart illustrating an example of a method for predicting colorable window faults and learning fault signatures for colorable window faults;

[0057] Figure 12 is a flowchart illustrating an example of a method for generating alarms and / or reports in response to the identification of a colorable window at risk of failure;

[0058] Figure 13 is a flowchart illustrating an example of a method for processing sensor readings to produce results;

[0059] Figure 14 is a flowchart illustrating an example of a method for determining the reliability of sensor readings; and

[0060] Figure 15 shows an example of a controller used to control one or more sensors.

[0061] The figures and their components may not be drawn to scale. Various components in the figures described herein may not be drawn to scale. Implementation

[0062] While various embodiments of the invention have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Numerous variations, modifications, and substitutions will arise in those skilled in the art without departing from the invention. It should be understood that various alternatives may be made to the embodiments of the invention described herein.

[0063] Terms such as "a / an" and "the" are not intended to refer to a single entity, but rather to include general categories that can be used to describe specific instances. The terms used herein are used to describe specific embodiments of the invention, but their use does not limit the invention.

[0064] Unless otherwise specified, when referring to a range, the range is intended to be inclusive. For example, a range between value 1 and value 2 is intended to be inclusive and includes both value 1 and value 2. An inclusive range will span any value from about value 1 to about value 2. As used herein, the terms "proximate" or "near" include "immediately adjacent," "adjacent," "in contact with," and "close to."

[0065] As used herein, including in the scope of the patent application, the conjunction "and / or" in phrases such as "comprising X, Y, and / or Z" means any combination or plurality of X, Y, and Z. For example, such a phrase means including X. For example, such a phrase means including Y. For example, such a phrase means including Z. For example, such a phrase means including X and Y. For example, such a phrase means including X and Z. For example, such a phrase means including Y and Z. For example, such a phrase means including a plurality of X. For example, such a phrase means including a plurality of Y. For example, such a phrase means including a plurality of Z. For example, such a phrase means including a plurality of X and a plurality of Y. For example, such a phrase means including a plurality of X and a plurality of Z. For example, such a phrase means including a plurality of Y and a plurality of Z. For example, this type of phrase means including plural X and Y. For example, this type of phrase means including plural X and Z. For example, this type of phrase means including plural Y and Z. For example, this type of phrase means including X and plural Y. For example, this type of phrase means including X and plural Z. For example, this type of phrase means including Y and plural Z. The conjunction "and / or" has the same effect as the phrase "X, Y, Z or any combination thereof or plural thereof". The conjunction "and / or" has the same effect as the phrase "one or more of X, Y, Z or any combination thereof".

[0066] The terms "operationally coupled" or "operationally connected" refer to a first element (e.g., a mechanism) coupled (e.g., connected) to a second element to allow intended operation of the second and / or first element. Coupling can include physical or non-physical coupling (e.g., communication coupling). Non-physical coupling can include signal-induced coupling (e.g., wireless coupling). Coupling can include physical coupling (e.g., physical connection) or non-physical coupling (e.g., via wireless communication). Operationally coupled coupling can include communication coupling.

[0067] A component (e.g., a mechanism) that is configured to perform a function includes structural features that enable the component to perform that function. Structural features may include electrical features, such as circuits or circuit components. Structural features may include actuators. Structural features may include circuits (e.g., comprising electrical or optical circuitry). Electrical circuitry may include one or more wires. Optical circuitry may include at least one optical component (e.g., a beam splitter, mirror, lens, and / or optical fiber). Structural features may include mechanical features. Mechanical features may include latches, springs, closures, hinges, chassis, supports, fixtures, or cantilever brackets, etc. Performing a function may involve utilizing logic features. Logic features may include programmed instructions. Programmed instructions may be executed by at least one processor (e.g., see Figure 7). Programmed instructions may be stored or encoded on a medium accessible by one or more processors. Furthermore, in the following description, the phrases “available for,” “adapted for,” “configured for,” “designed for,” “programmed for,” or “capable” may be used interchangeably where appropriate.

[0068] In some embodiments, sensor data is combined with machine learning (including artificial intelligence (AI)) to predict and / or identify malfunctions of colorable windows (e.g., to aid in predictive maintenance). Large amounts of data (e.g., at least about one million, ten million, one hundred million, or one trillion raw data points) can be accumulated over time in conjunction with window control and / or operation. The framework disclosed herein is configured to retrieve data (e.g., control data and / or other sensor data) associated with window hue changes from a database (e.g., accumulated during the normal operation of the colorable window), aggregate that data, and use the data to analyze and / or predict window malfunctions. Such a framework can allow, for example, the predictive maintenance of any window exhibiting an identified fault signature using statistical measurements (e.g., current, voltage, open-circuit voltage, or any other sensor measurement as disclosed herein).

[0069] In some embodiments, the enclosure comprises an area defined by at least one structure. The at least one structure may include at least one wall. The enclosure may include and / or enclose one or more sub-enclosures. The at least one wall may comprise metal (e.g., steel), clay, stone, plastic, glass, plaster (e.g., gypsum), polymer (e.g., polyurethane, styrene, or vinyl), asbestos, fiberglass, concrete (e.g., reinforced concrete), wood, paper, or ceramic. The at least one wall may comprise electrical wiring, brick, blocks (e.g., cinder blocks), ceramic tiles, drywall, or a frame (e.g., a steel frame).

[0070] In some embodiments, the enclosure includes one or more openings. The one or more openings may be reversibly closed. The one or more openings may be permanently open. The basic length dimension of the one or more openings may be smaller than the basic length dimension of the wall defining the enclosure. The basic length dimension may include the diameter, length, width, or height of the defining circle. The surface of the one or more openings may be smaller than the surface of the wall defining the enclosure. The opening surface may be a percentage of the total surface area of ​​the wall. For example, the opening surface may be measured as at most about 30%, 20%, 10%, 5%, or 1% of the wall. The wall may include a floor, ceiling, or sidewalls. The closable opening may be closed by at least one window or door. The enclosure may be at least part of a facility. The facility may include a building. The enclosure may include at least part of a building. The building may be a private building and / or a commercial building. The building may include one or more floors. A building (such as its floors) may include at least one of the following: rooms, halls, lofts, attics, basements, balconies (such as interior or exterior balconies), stairwells, corridors, elevator shafts, facades, mezzanines, penthouses, garages, porches (such as enclosed porches), terraces (such as enclosed terraces), cafeterias, and / or pipework. In some embodiments, the enclosure may be stationary and / or movable (such as a train, airplane, cruise ship, vehicle, or rocket).

[0071] In some embodiments, a plurality of devices may be operatively coupled to a control system in a manner that allows communication. The plurality of devices may be housed in a facility (e.g., including a building and / or room). The control system may include a hierarchy of controllers. Devices may include transmitters, sensors, or windows (e.g., IGUs). Devices may be any of the devices disclosed herein. At least two of the plurality of devices may be of the same type. For example, two or more IGUs may be coupled to the control system. At least two of the plurality of devices may be of different types. For example, sensors and transmitters may be coupled to the control system. The plurality of devices may sometimes comprise at least 20, 50, 100, 500, 1000, 2500, 5000, 7500, 10000, 50000, 100000, or 500000 devices. The plurality of devices may have any number of devices between the aforementioned numbers (e.g., 20 to 500,000 devices, 20 to 50 devices, 50 to 500 devices, 500 to 2,500 devices, 1,000 to 5,000 devices, 5,000 to 10,000 devices, 10,000 to 100,000 devices, or 100,000 to 500,000 devices). For example, the number of windows in a floor may be at least 5, 10, 15, 20, 25, 30, 40, or 50. The number of windows in a floor may be any number between the aforementioned numbers (e.g., 5 to 50, 5 to 25, or 25 to 50). Sometimes, the devices may be in a multi-story building. At least a portion of the floors of a multi-story building may have devices controlled by a control system (e.g., at least a portion of the floors of a multi-story building may be controlled by a control system). For example, a multi-story building may have at least 2, 8, 10, 25, 50, 80, 100, 120, 140, or 160 floors controlled by a control system. The number of floors (e.g., devices therein) controlled by the control system may be any number between the aforementioned numbers (e.g., 2 to 50, 25 to 100, or 80 to 160). A floor may have an area of ​​at least about 150 m², 250 m², 500 m², 1000 m², 1500 m², or 2000 square meters (m²). A floor may have an area between any of the aforementioned floor area values ​​(e.g., about 150 m² to about 2000 m², about 150 m² to about 500 m², about 250 m² to about 1000 m², or about 1000 m² to about 2000 m²). The building may contain an area of ​​at least approximately 1,000 square feet (sqft), 2,000 sqft, 5,000 sqft, 10,000 sqft, 100,000 sqft, 150,000 sqft, 200,000 sqft, or 500,000 sqft.The building may comprise an area between any of the areas mentioned above (e.g., approximately 1000 sqft to approximately 5000 sqft, approximately 5000 sqft to approximately 500000 sqft, or approximately 1000 sqft to approximately 500000 sqft). The building may comprise an area of ​​at least approximately 100 m², 200 m², 500 m², 1000 m², 5000 m², 10000 m², 25000 m², or 50000 m². The building may comprise an area between any of the areas mentioned above (e.g., approximately 100 m² to approximately 1000 m², approximately 500 m² to approximately 25000 m², or approximately 100 m² to approximately 50000 m²). The facility may comprise a commercial building or a residential building. A commercial building may include tenants and / or owners. A residential facility may comprise multi-family or single-family buildings. Residential facilities may include apartment buildings. Residential facilities may include single-family homes. Residential facilities may include multi-family homes (e.g., apartments). Residential facilities may include townhouses. Facilities may include residential and commercial portions. Facilities may contain at least about 1, 2, 5, 10, 50, 100, 150, 200, 250, 300, 350, 400, 420, 450, 500, or 550 windows (e.g., tinted windows). These windows may be divided into multiple zones (e.g., at least in part based on the orientation, facade, floor, ownership, utilization rate, any other assignment measure, random assignment, or any combination thereof of the enclosure (e.g., room) where the windows are located). The allocation of windows to zones may be static or dynamic (e.g., based on a trial-and-error method). Each zone may contain at least about 2, 5, 10, 12, 15, 30, 40, or 46 windows.

[0072] Some of the disclosed embodiments provide network infrastructure within an enclosed space (e.g., a facility such as a building). The network infrastructure can be used for various purposes, such as providing communication and / or power services. The network infrastructure can provide direct and / or indirect communication between devices coupled to the network (e.g., colorable windows and / or controllers). Communication services may include high-frequency broadband (e.g., wireless and / or wired) communication services. Communication services may be directed to occupants of the facility and / or users outside the facility (e.g., a building). The network infrastructure may work in conjunction with or partially replace the infrastructure of one or more cellular operators. The network infrastructure may be located in a facility including colorable (e.g., electrically switchable, or electronically colorable) windows. Examples of components of the network infrastructure include high-speed reload. The network infrastructure may include at least one cable (e.g., coaxial cable and / or optical cable), switch, physical antenna, transceiver, sensor, transmitter, receiver, radio, processor, and / or controller (which may include a processor). The network infrastructure may be operatively coupled to and / or include a wireless network. Network infrastructure may include cabling. One or more sensors may be deployed (e.g., installed) in the environment as part of and / or after the network is installed. The network may be configured for cellular communication, for example, using at least third-generation (3G), fourth-generation (4G), or fifth-generation (5G) communication standards. The network may be configured to transmit power and communication over the same cable (e.g., coaxial cable). The network may be a local area network. The network may include cabling configured to transmit power and communication over a single cable. Communication may be one or more types of communication. Communication may include cellular communication conforming to at least second-generation (2G), third-generation (3G), fourth-generation (4G), or fifth-generation (5G) cellular communication protocols. Communication may include media communication that facilitates still images, music, or animation streaming (e.g., movies or videos). Communication may include data communication (e.g., sensor data). Communication may include control communication, such as operatively coupled to one or more nodes of the network for control purposes. The network may include a first (e.g., cabling) network installed within the facility. The network may also include (e.g., cabling) networks installed within the facility's enclosure (e.g., within the enclosure of a building included in the facility).

[0073] In another embodiment, the present invention provides a network configured for transmitting any communication (e.g., signals) and / or (e.g., electrical) power that facilitates any of the operations disclosed herein. Communication may include control communication, cellular communication, media communication, and / or data communication. Data communication may include sensor data communication and / or processed data communication. The network may be configured to comply with one or more protocols that facilitate such communication. For example, the communication protocol used by the network (e.g., with a BMS) may include the Building Automation and Control Network Protocol (BACnet). The network may be configured (e.g., including hardware that facilitates) communication protocols including: BACnet (e.g., BACnet / SC), LonWorks, Modbus, KNX, European Home Appliance Systems Protocol (EHS), BatiBUS, European Installed Bus (EIB or Instabus), Zigbee, Z-wave, Insteon, X10, Bluetooth, or WiFi. The network may be configured to transmit control-related protocols. Communication protocols can facilitate cellular communication that adheres to at least 2nd, 3rd, 4th, or 5th generation cellular communication protocols. (E.g., cabling) The network can include tree, linear, or star topologies. The network can contain interactive work and / or distributed application models for various tasks in building automation. The control system provides schemes for configuring and / or managing resources on the network. The network can allow portions of distributed applications to be combined in different nodes that are operationally coupled to the network. The network can provide a communication system with messaging protocols and a model for stacking communication at each node (capable of managing distributed applications (e.g., with a common core)). The control system may include programmable logic controllers (PLCs).

[0074] In various embodiments, the network infrastructure supports a control system for one or more windows, such as color-sensitive (e.g., electrochromic) windows. The control system may include one or more controllers operatively coupled (e.g., directly or indirectly) to one or more windows. While the disclosed embodiments describe color-sensitive windows (also referred to herein as "optically switchable windows" or "smart windows"), such as electrochromic windows, the concepts disclosed herein can be applied to other types of switchable optical devices, including liquid crystal devices, electrochromic devices, suspended particle devices (SPDs), NanoChromics displays (NCDs), organic electroluminescent displays (OELDs). The display assembly may be attached to a portion of a transparent body, such as a window. Color-sensitive windows may be installed in (non-temporary) installations such as buildings, and / or in temporary installations (e.g., vehicles) such as automobiles, RVs, buses, trains, airplanes, helicopters, ships, or vessels.

[0075] In some embodiments, such as upon application of a stimulus, a tintable window presents a (e.g., controllable and / or reversible) change in at least one optical property of the window. The change may be continuous. The change may be directed at discrete hue levels (e.g., at least about 2, 4, 8, 16, or 32 hue levels). The optical property may include hue or transmittance. Hue may include color. Transmittance may have one or more wavelengths. Wavelengths may include ultraviolet, visible, or infrared wavelengths. The stimulus may include optical, electrical, and / or magnetic stimuli. For example, the stimulus may include an applied voltage and / or current. One or more tintable windows may be used to control lighting and / or glare conditions, for example, by regulating the transmission of solar energy through them. One or more tintable windows may be used to control the temperature inside a building, for example, by regulating the transmission of solar energy through the window. Solar energy control can control the heat load imposed on the interior of an facility (e.g., a building). Control may be manual and / or automatic. Control may be used to maintain one or more requested (e.g., environmental) conditions, such as occupant comfort. Control may include reducing energy consumption of heating, ventilation, air conditioning, and / or lighting systems. At least two of the heating, ventilation, and air conditioning systems may be induced by a single system. At least two of the heating, ventilation, and air conditioning systems may be induced by a single system. Heating, ventilation, and air conditioning may be induced by a single system (hereinafter referred to as "HVAC"). In some cases, the color-sensitive window may respond to (e.g., and communicatively coupled to) one or more environmental sensors and / or user controls. The color-sensitive window may include (e.g., may be) an electrochromic window. The window may be located from the interior to the exterior of a structure (e.g., facility, such as a building). However, this is not necessary. The color-sensitive window may be operated using liquid crystal devices, suspended particle devices, microelectromechanical systems (MEMS) devices (such as micro-shutters), or any technology known or to be developed later that is configured to control the transmission of light through the window. Windows (e.g., having MEMS devices for tinting) are described in U.S. Patent No. 10,359,681, filed May 15, 2015 and published July 23, 2019, entitled "MULTI-PANE WINDOWS INCLUDING ELECTROCHROMIC DEVICES AND ELECTROMECHANICAL SYSTEMS DEVICES," which is incorporated herein by reference in its entirety. In some cases, one or more tinting windows may be located within the interior of a building, such as between a conference room and a corridor. In some cases, one or more tinting windows may be used in automobiles, trains, airplanes, and other vehicles, for example, replacing passive and / or non-tinting windows.

[0076] In some embodiments, the tintable window includes an electrochromic device (referred to herein as an "EC device" (abbreviated herein as ECD) or "EC"). The EC device (e.g., an electrochromic configuration) may include at least one coating comprising at least one layer. The at least one layer may comprise an electrochromic material. In some embodiments, the electrochromic material exhibits a change from one optical state to another, for example, when a potential is applied across the EC device. The transition of the electrochromic layer from one optical state to another may be caused, for example, by reversible, semi-reversible, or irreversible ion insertion (e.g., by means of embedding) and corresponding injection of charge-balanced electrons into the electrochromic material. For example, the transition of the electrochromic layer from one optical state to another may be caused, for example, by reversible ion insertion (e.g., by means of embedding) and corresponding injection of charge-balanced electrons into the electrochromic material. Reversibility may refer to the expected lifetime of the ECD. Semi-reversibility refers to a measurable (e.g., noticeable) degradation of the tint reversibility of the window within one or more tinting cycles. In some cases, a portion of the ions responsible for the optical transitions are irreversibly bound to the electrochromic material (e.g., and the hue state induced (changed) by this window is irreversibly its original hue state). In various EC devices, at least some (e.g., all) of the irreversibly bound ions can be used to compensate for "blind charges" in the material (e.g., ECD).

[0077] In some embodiments, suitable ions include cations. Cations may include lithium ions (Li+) and / or hydrogen ions (H+) (i.e., protons). In some embodiments, other ions may be suitable. The insertion of cations can enter (e.g., metal) oxides. Changes in the insertion state of ions (e.g., cations) into oxides can induce a visible change in the hue (e.g., color) of the oxide. For example, the oxide can change from a colorless state to a colored state. For example, inserting lithium ions into tungsten oxide (WO3-y (0 < y ≤ ~0.3)) can cause tungsten oxide to change from a transparent state to a colored (e.g., blue) state. As described herein, the EC device coating is located within the viewable portion of a colorable window, such that the coloring of the EC device coating can be used to control the optical state of the colorable window.

[0078] Figure 1A shows a cross-sectional view of an example of a tintable window embodied in an insulating glass unit (“IGU”) 100 according to some embodiments. Figure 1B shows a perspective view of the IGU of Figure 1A. The IGU window pane, also referred to herein as a “pane,” can be a single-substrate or multi-substrate construction, such as a laminate of two substrates. IGUs (especially those with double or triple pane configurations) offer several advantages over single-pane configurations. For example, multi-pane configurations offer enhanced thermal insulation, sound insulation, environmental friendliness, and / or durability compared to single-pane configurations. Multi-pane configurations provide enhanced protection for the ECD, for example, because the electrochromic film and associated layers and conductive interconnects can be formed on the inner surface of the multi-pane IGU and protected by an inert gas filling in the internal volume (e.g., 108) of the IGU. The inert gas filling provides at least some of the (thermal) insulation functions of the IGU. Electrochromic IGUs have been given thermal insulation capabilities by means of a colorable coating that absorbs (or reflects) heat and light.

[0079] Figures 1A and 1B illustrate examples of embodiments of an IGU 100 including a first pane 104 having a first surface S1 and a second surface S2. In some embodiments, the first surface S1 of the first pane 104 faces the external environment, such as the outdoors or an external environment. The IGU 100 includes a second pane 106 having a first surface S3 and a second surface S4. In some embodiments, the second surface S4 of the second pane 106 faces the internal environment, such as the internal environment of a temporary or non-temporary facility (e.g., a room, building, or vehicle).

[0080] In some embodiments, each of the first pane 104 and the second pane 106 is transparent or translucent (e.g., at least for light in the visible spectrum). For example, at least one of panes 104 and 106 (e.g., each) may be formed of glass materials, particularly architectural glass or other shatterproof glass materials, such as silicon oxide (SOx) based glass materials. As a more specific example, each of the first pane 104 and the second pane 106 may be a soda-lime glass substrate or a float glass substrate. Such glass substrates may consist of, for example, about 75% silicon dioxide (SiO2) and Na2O, CaO, and certain trace additives. However, each of the first pane 104 and the second pane 106 may be formed of any material having suitable optical, electrical, thermal, and mechanical properties. For example, other suitable substrates that can be used as one or both of the first pane 104 and the second pane 106 may include other glass materials and plastic, semi-plastic and thermoplastic materials (e.g., poly(methyl methacrylate), polystyrene, polycarbonate, allyl diglyceride carbonate, SAN (styrene-acrylonitrile copolymer), poly(4-methyl-1-pentene), polyester, polyamide) or mirror materials. In some embodiments, at least one of the first pane 104 and the second pane 106 (e.g., each) may be strengthened, for example, by tempering, heating or chemical strengthening.

[0081] In some embodiments, the first pane 104 and the second pane 106, as well as the IGU 100, are generally rectangular solids. In some embodiments, other shapes are possible and may be desired (e.g., circular, elliptical, triangular, curved, convex, or concave shapes). In some particular embodiments, the length "L" of each of the first pane 104 and the second pane 106 may be in the range of approximately 20 inches (in.) to approximately 10 feet (ft.), the width "W" of each of the first pane 104 and the second pane 106 may be in the range of approximately 20 inches to approximately 10 feet, and the thickness "T" of each of the first pane 104 and the second pane 106 may be in the range of approximately 0.3 millimeters (mm) to approximately 10 millimeters (but other lengths, widths, or thicknesses (both smaller and larger) are possible and may be desired based on the specific needs of the user, administrator, supervisor, builder, architect, or owner). In instances where the thickness T of substrate 104 is less than 3 millimeters (mm), the substrate may be laminated to an additional substrate that is thicker (e.g., and protects the thin substrate 104). Additionally, while IGU 100 includes two panes (104 and 106), in some other embodiments, IGU may include three or more panes. Furthermore, in some embodiments, one or more of the panes may themselves be a laminated structure of two, three, or more layers or sub-panels.

[0082] In the examples shown in Figures 1A and 1B, the first pane 104 and the second pane 106 are spaced apart from each other by spacers 118, typically of a frame structure, to form an internal volume 108. In some embodiments, the internal volume is filled with a gas or gas mixture containing argon (Ar), but in other embodiments, the internal volume 108 may be filled with another gas or gas mixture. This other gas or gas mixture may contain an inert gas (e.g., krypton (Kr) or xenon (Xn)), another (non-inert) gas, or a mixture of gases (e.g., air). Filling the internal volume 108 with a gas containing Ar, Kr, or Xn reduces conductive heat transfer through the IGU 100. Without wishing to be theoretically limited, this could be due to the low thermal conductivity of such gases and / or improved sound insulation due to their increased atomic weight. In some other embodiments, the internal volume 108 may be evacuated with air or any other gas. The spacer 118 determines the height of the internal volume 108; that is, the spacing between the first pane 104 and the second pane 106. In some embodiments, the spacing between the first pane 104 and the second pane 106 is in the range of approximately 6 mm to approximately 30 mm. The width of the spacer 118 may be in the range of approximately 5 mm to approximately 25 mm (but other widths are possible and may be desired).

[0083] Although not shown in the cross-sectional view, spacer 118 is a frame structure formed around all sides of IGU 100 (e.g., the top, bottom, left, and right sides of IGU 100). For example, spacer 118 may be formed of foam or plastic material. However, in some other embodiments, spacer may be formed of metal or other conductive material, for example, a metal tube or channel structure having at least three sides, with two sides for sealing to each of the substrates and one side for supporting and separating the windows and serving as a surface to which a sealant is applied. The sealant may include a polymeric material, such as polyisobutylene (PIB). The polymeric material may be water-resistant (e.g., hydrophobic). The polymeric material may add structural support to the IGU assembly. Examples of polymeric materials may include silicone, polyurethane, or similar structural sealants that form watertight and / or airtight seals.

[0084] In some embodiments, a window controller is associated with one or more colorable windows and configured to control the optical state of the windows, for example, by applying stimuli to the windows. For example, by applying voltage and / or current to the colorable window (e.g., an EC device coating). The window controller may have many sizes, formats, and / or orientations relative to the optically switchable window it controls. The controller may be attached to a window pane of an IGU or laminate, either within a frame housing the IGU or laminate, or in a separate orientation. As previously mentioned, a colorable window may include one, two, three, or more individual electrochromic panes (electrochromic devices on a transparent substrate). Individual panes of an electrochromic window may have an electrochromic coating having one or more independent colorable zones. The controller may control all electrochromic coatings associated with such windows, whether the electrochromic coating is monolithic or zoned.

[0085] In some embodiments, the window controller is typically located near the tintable window if it is not directly attached to the tintable window, IGU, or frame. The frame may comprise vertical or horizontal frames. For example, the window controller may be located adjacent to the window, on the surface of one of the window panes, within a wall immediately adjacent to the window, or within the frame of a self-contained window assembly (e.g., within a vertical or horizontal frame). In some embodiments, the window controller is an in-situ controller. The in-situ window controller may be part of the window assembly, IGU, and / or laminate. The in-situ window may not need to be matched with the electrochromic window and can be installed in the field (e.g., during deployment). For example, the controller may be integrated with the window as part of an assembly (e.g., at the factory) and deployed as a unit.

[0086] In some embodiments, the controller may be separable from the window and deployed as two separate units. For example, the controller may be mounted in a portion of the window frame of the window assembly. In some embodiments, the controller may be part of the IGU or the laminate assembly. For example, the controller may be mounted on a pane of the IGU, between panes of the IGU, or on a pane of the laminate. Where the controller is located on a visible portion of the IGU, at least a portion of the controller may be substantially transparent. An example of a glass controller can be seen in U.S. Patent No. 10,303,035 B2, filed November 14, 2015, entitled "Self-Contained EC IGU," published May 28, 2019, and which is incorporated herein by reference in its entirety.

[0087] In some embodiments, the controller may be provided as more than one component, wherein at least one component (e.g., including a memory component storing information about the associated electrochromic window) is provided as a component of the window assembly, and at least one other component is separate and configured to cooperate with the at least one component, which is a component of the window assembly, IGU, or laminate. In some embodiments, the controller may be an assembly of operatively coupled (e.g., interconnected) portions not housed in a single housing (e.g., housed in different housings). Separate controller portions may be spaced apart from each other (e.g., separated by gaps). At least one of the controller portions (e.g., or the entire window controller) may be housed in the window frame and / or in the seals of the IGU. In some embodiments, the controller is a compact unit, e.g., enclosed in a single housing. In some embodiments, the controller portions are separated into at least two or more operatively coupled components, e.g., mating members and housing assemblies, by physically combining them. The controller (or at least a portion thereof) may be (i) close to the glass and / or not in the visible area of ​​the glass, or (ii) mounted on the glass in the visible area.

[0088] In some embodiments, such as prior to installation of the tintable window, at least a portion (e.g., the entirety) of the window controller is incorporated into or onto the IGU and / or window frame. In some embodiments, such as prior to installation of the tintable window, at least a portion (e.g., the entirety) of the window controller is installed in the same building as the tintable window. In one embodiment, such as prior to leaving the manufacturing facility, the controller is incorporated into or onto the IGU and / or window frame. In one embodiment, the controller is incorporated into the IGU (e.g., substantially) within the seal. In another embodiment, the controller is incorporated into or onto the IGU, for example, partially, substantially, or entirely within the perimeter defined by the primary seal between the sealing separator and the substrate.

[0089] In cases where the characteristics of an electrochromic device change over time (e.g., due to degradation), a characterization function can be used. The characterization function can, for example, be used to update control parameters. These control parameters can be used to drive hue state transitions. In another instance, if already installed in an electrochromic window unit, a controller (e.g., controller logic) can be used to calibrate the control parameters. For example, the control parameters can be calibrated to match the intended installation. In some embodiments, the control parameters can be recalibrated after installation to match the expected performance characteristics of the electrochromic window.

[0090] In some embodiments, the controller includes a docking assembly. The docking assembly may have portions common to any electrochromic window. The docking assembly may be associated with each window at the factory. After window installation or otherwise in the field, a second component of the controller may be combined with the docking assembly to complete the electrochromic window controller assembly. The docking assembly may include a chip programmed with physical characteristics and / or parameters at the factory. The physical characteristics and / or parameters may include characteristics of the specific window to which the docking assembly is attached. These characteristics may include, for example, the surface of the window that will face the interior of the building after installation (sometimes referred to as surface 4 or "S4"). The second component (sometimes referred to as a "carrier," "housing," "casing," or "controller") may be paired with the docking assembly. When powered, the second component may read the chip and configure itself to power the window, for example, based on specific characteristics and / or parameters stored on the chip. In this way, shipping the window requires (e.g., only) having its associated parameters stored on the chip. For example, the chip may be integrated with the window, while more sophisticated circuitry and / or components may be added later (e.g., after installation). For example, more sophisticated circuitry and components can be transported and installed separately (e.g., by the window manufacturer) after the window is installed (e.g., after the installer (e.g., a glazing worker) has installed the window). In some embodiments, the chip is included in the wires (or wired connectors) attached to the window controller. Such wires (e.g., with connectors) may be referred to as "pigeons".

[0091] In some embodiments, an "IGU" includes two or more (e.g., substantially) transparent substrates. According to some embodiments, the transparent substrates include two panes of a transparent material (e.g., glass), wherein at least one pane (e.g., acting as a substrate) includes an electrochromic device disposed thereon. The panes may have a partition disposed therebetween. The IGU may be hermetically sealed (e.g., humidity and / or gas-tight), having an internal area isolated from the surrounding environment. The window assembly may include an IGU or a separate laminate. The window assembly may include one or more electrical wires for connecting the IGU, the laminate, and / or one or more electrochromic devices to a voltage source, exchanger, and the like. The window assembly may include a frame supporting the IGU and / or the laminate. The window assembly may include a window controller (e.g., as described herein) and / or one or more components of the window controller (e.g., a docking element).

[0092] As used herein, the term "outer" refers to the area closer to the external environment. The term "inner" refers to the area closer to the interior of the building. For example, in the case of an IGU with two panes, the pane positioned closer to the external environment is called the outer pane or outer pane. The pane positioned closer to the interior of the building is called the inner pane or inner pane. As illustrated in Figures 1A and 1B, the different surfaces of the IGU can be referred to as S1, S2, S3, and S4 (assuming a two-pane IGU). S1 refers to the outer pane's outward-facing surface (e.g., a surface that can be physically touched by someone standing outside). S2 refers to the outer pane's inward-facing surface. S3 refers to the inner pane's outward-facing surface. S4 refers to the inner pane's inward-facing surface (i.e., a surface that can be physically touched by someone standing inside the building). In other words, starting from the outermost surface of the IGU and counting inwards, the surfaces are labeled S1 to S4. This trend continues in the case of an IGU with three panes (where S6 is a surface that can be physically touched by someone standing inside the building). In some embodiments employing two panes, an optically switchable device (e.g., an electrochromic device) is disposed on surface S2. In some embodiments, one or more of the surfaces have a structure for blocking the transmission of electromagnetic radiation. Figure 1B illustrates an example of an "IMI" disposed on S2 (a shielding stack of multiple conductive layers). Further examples of the shielding stack structure can be found in U.S. Patent Application Publication No. 2018 / 0090992, entitled "Window Antennas for Emitting Radio Frequency Signals," published March 29, 2018 and filed September 19, 2017, which is incorporated herein by reference in its entirety.Examples of window controllers and their features are presented in U.S. Patent Application No. 13 / 449,248, filed April 17, 2012, entitled "Controller for Optically Switchable Windows"; U.S. Patent Application No. 13 / 449,251, filed April 17, 2012, entitled "Controller for Optically Switchable Windows"; U.S. Patent Application No. 15 / 334,835, filed October 26, 2016, entitled "Controllers for Optically Switchable Devices"; and U.S. Patent Application No. 15 / 334,835, filed March 3, 2017, entitled "Method of Compositioning Electrochromic Windows". In the international patent application No. PCT / US17 / 20805 concerning "WINDOWS", each of those applications is incorporated herein by reference in its entirety.

[0093] When a building is equipped with tinted windows, window controllers can be connected to each other and / or to other entities (e.g., devices) via a communication network. This communication network may be referred to as a "window control network" or "window network." The network and the various devices (e.g., controllers, IGUs, transmitters, antennas, and / or sensors) connected via the network (e.g., wired and / or wireless power transmission and / or communication) are referred to herein as a "window control system" or "control system." The window control system can provide tinting instructions to the window controllers. The window control network can provide window information to the main controller or other network entities (e.g., devices), and the like. Examples of window information include the current tinting status and / or other information collected by the window controllers. In some cases, the window controllers have one or more associated sensors. One or more associated sensors may include, for example, light sensors, temperature sensors, occupancy sensors, particulate matter sensors, sound sensors, pressure sensors, speed sensors, motion sensors, and / or gas sensors (measuring gas type, velocity, and / or concentration) that provide sensing information via the network. In some cases, information transmitted via a window communication network need not affect window control. For example, information received at a first window configured to receive Wi-Fi or LiFi signals can be transmitted via the communication network to a second window configured to wirelessly broadcast the information as, for example, Wi-Fi or LiFi signals. The window control network is not limited to providing information for controlling colorable windows, but may be able to convey communication information for other devices that interface with the communication network, such as HVAC systems, lighting systems, security systems, personal computing devices, and the like.

[0094] Figure 2A is a schematic cross-section of an electrochromic device in a decolorized state (or transitioning to a decolorized state). According to a specific embodiment, the electrochromic device 200 includes a tungsten oxide electrochromic layer (EC) 206 and a nickel-tungsten oxide counter-electrode layer (CE) 210. The electrochromic device 200 includes a substrate 202, a conductive layer (CL) 204, an ion-conducting layer (IC) 208, and a conductive layer (CL) 214.

[0095] Power source 216 is configured to apply potential and / or current to electrochromic stack 220 via suitable connections (e.g., busbars) to conductive layers 204 and 214. In some embodiments, the voltage source is configured to apply a potential of a few volts to drive the device from one optical state to another. The polarity of the potential causes ions (in this example, lithium ions) to primarily reside (as indicated by the dashed arrow) in the nickel-tungsten oxide counter electrode layer 210.

[0096] Figure 2B is a schematic cross-section of the electrochromic device 200 shown in Figure 2A but in a colored state (or transitioned to a colored state). In Figure 2B, the polarity of the voltage source 216 is opposite to that in Figure 2A. This makes the electrochromic layer 206 in Figure 2B more negative to accept additional lithium ions, thereby transitioning to a colored state. As indicated by the dashed arrow, lithium ions are transported across the ion-conducting layer 208 to the tungsten oxide electrochromic layer 206. The tungsten oxide electrochromic layer 206 is shown in a colored state. The nickel tungsten oxide counter electrode 210 is shown in a colored state. The nickel tungsten oxide gradually becomes less transparent because it relinquishes (deintercalates) lithium ions. In this example, there is a synergistic effect, where the transition of both layers 206 and 210 to a colored state is additive in reducing the amount of light transmitted through the stack and substrate.

[0097] As described herein, an electrochromic device may include an electrochromic (EC) electrode layer and a counter electrode (CE) layer separated by an ion-conducting (IC) layer, the ion-conducting layer being highly conductive to ions and highly resistive to electrons. The ion-conducting layer prevents short circuits between the electrochromic layer and the counter electrode layer. The ion-conducting layer helps maintain the charge of the electrochromic and counter electrode layers, thereby maintaining their bleached or colored state. In some electrochromic devices (e.g., with dissimilar layers), components are formed in a stack, the stack including an ion-conducting layer sandwiched between the electrochromic electrode layer and the counter electrode layer. The boundary between these three stacked components may be defined by abrupt changes in composition and / or microstructure. The device may have three dissimilar layers with two abrupt interfaces.

[0098] According to some embodiments, the counter electrode and the electrochromic electrode are formed adjacent to each other, sometimes in direct contact, without the need to deposit an ion-conducting layer separately between them. In some embodiments, an electrochromic device with an interface region (e.g., rather than a dissimilar IC layer) is employed. Electrochromic devices and methods of fabrication thereof can be found in U.S. Patent No. 8,300,298, U.S. Patent Application No. 12 / 772,075 entitled "Electrochromic Devices" filed April 30, 2010, U.S. Patent Application No. 12 / 814,277 entitled "Electrochromic Devices" filed June 11, 2010, and U.S. Patent Application No. 12 / 814,279 entitled "Electrochromic Devices" filed June 11, 2010. Each of the three aforementioned patent applications and the aforementioned patent titled "Electrochromic Devices" names Zhongchun Wang et al. as inventors, and each of them is incorporated herein by reference in its entirety.

[0099] Figure 3A illustrates an example of the current distribution of an electrochromic window that employs a simple voltage control algorithm to induce an optical state transition (e.g., coloring) in an electrochromic device. In the graph, the ion current density (I) is expressed as a function of time. Different types of electrochromic devices may have depicted current distributions. In one example, a cathode electrochromic material such as tungsten oxide is used in combination with a nickel-tungsten oxide counter electrode. In such devices, a negative current indicates coloring, and a positive current indicates bleaching. The depicted distribution shown in Figure 3A is generated by ramping the voltage to a set level and then holding the voltage to maintain the optical state.

[0100] The current peak 301 is associated with a change in optical state (e.g., coloring and bleaching, e.g., clearing). The current peak represents the charge delivery required to color or bleach the device. The shaded area below the peak represents the total charge required to color or bleach the device (e.g., clearing). The portion of the curve after the initial current spike (part 303) represents the leakage current when the device is in the new optical state. In some embodiments, the leakage current is at most about 0.1 mA per square centimeter. In some embodiments, the leakage current corresponds to a leakage voltage of at most about 0.25 mV per square foot or at most about 50 V per 200,000 square feet. In some embodiments, the leakage current is extremely slow and therefore appears as a horizontal line in the graph shown in Figure 3A. Disconnecting the voltage difference (e.g., ions spontaneously migrating back in the absence of an induced voltage) can take at least about 1, 3, 5, or 10 years.

[0101] In the example shown in Figure 3A, voltage distribution 305 is superimposed on the current curve. The voltage distribution follows a sequence: negative ramp (307), negative hold (309), positive ramp (311), and positive hold (313). It should be noted that the voltage remains constant after reaching its maximum value and for the duration during which the device remains in its defined optical state. Voltage ramp 307 drives the device to its new tinted state. Voltage ramps may or may not have the same absolute slope value. Voltage hold periods may or may not have the same duration. Voltage ramp periods may or may not have the same duration. Voltage hold 309 maintains the device in the tinted state until voltage ramp 311 drives the transition from tinted to transparent in the opposite direction. In some switching algorithms, current and / or voltage limits are imposed. For example, current and / or voltage are not permitted to exceed defined levels, for example, to prevent damage to the device. In some embodiments, the electrochromic device is irreversibly damaged when subjected to current and / or voltage within a time frame exceeding a time threshold. In some switching algorithms, the permitted current exceeds the imposed current limit for a short period (within which the device is not damaged). In some switching algorithms, the permitted voltage exceeds the imposed voltage limit for a short period (within which the device is not damaged).

[0102] In some embodiments, the rate of coloring is a function of not only the applied voltage but also temperature and the voltage ramp rate. In some embodiments, both voltage and temperature affect lithium diffusion; for example, the amount of charge passing through (and therefore the intensity of this current peak) increases with voltage and temperature. Voltage and temperature can be interdependent. This interdependence can imply that a lower voltage can be used at a higher temperature to achieve the same switching speed as a higher voltage at a lower temperature. This temperature response can be used in voltage-based switching algorithms. Such algorithms may require active temperature monitoring to change the applied voltage. Temperature can be used to determine which voltage to apply to influence rapid switching without damaging the device.

[0103] The various embodiments described herein utilize some form of feedback to actively control transitions in an optically switchable device. In some embodiments, the feedback is at least partially based on non-optical characteristics. When certain electrical conditions are applied, the electrical characteristics of the voltage and / or current response of the optically switchable device may be taken into consideration.

[0104] In some embodiments, electrical feedback is used to ensure that the optically switchable device is maintained within a safe window of operating conditions. Excessive current or voltage supplied to the device can damage it. The feedback method presented herein may be referred to as a damage prevention feedback method. In some embodiments, damage prevention feedback may be the only feedback used. Alternatively, the damage prevention feedback method may be combined with other feedback methods described herein. In other embodiments, damage prevention feedback is not used, but different types of feedback described below are used.

[0105] Figure 3B shows an example of a graph depicting the total charge delivered over time and the voltage applied over time during an electrochromic tinting transition. The window in this illustrative example is approximately 24 x 24 inches in size. The total charge delivered is called the tint charge count and is measured in coulombs (C). The total charge delivered is plotted on the left-hand y-axis of the graph, and the applied voltage is plotted on the right-hand y-axis. Line 302 corresponds to the total charge delivered, and line 304 corresponds to the applied voltage. Furthermore, line 306 corresponds to the threshold charge (threshold charge density multiplied by the area of ​​the window), and line 308 corresponds to the target open-circuit voltage. The threshold charge and target open-circuit voltage can be used to monitor / control the optical transition.

[0106] The voltage curve 304 in Figure 3B begins with a ramp used to drive the component, where the voltage magnitude rises to a drive voltage of approximately -2.5 volts (V). After the initial period of applying the drive voltage, the voltage begins to spike upwards at regular intervals. These voltage spikes occur when the electrochromic device is being probed. Probing occurs by applying an open-circuit condition to the device. The open-circuit condition causes an open-circuit voltage VoC (also “Voc” herein), which corresponds to the voltage spikes seen in the curve. This open-circuit voltage VoC is a real-time measurement and is shown during the hold period. VoC can be measured during the ramp period (not shown in the example of Figure 3B). Between each probe of the open-circuit voltage, there is an additional period in which the applied voltage is the drive voltage. As the electrochromic device is changing, EC is periodically probed to test the open-circuit voltage (e.g., to monitor the change). For each case, the target open-circuit voltage, represented by line 308, is selected to be approximately -1.4V. The holding voltage is approximately -1.2V in each case. Therefore, the target open-circuit voltage deviates from the holding voltage by approximately 0.2V.

[0107] In the transition example shown in Figure 3B, the open-circuit voltage exceeds the target open-circuit voltage at approximately 1500 seconds. Because the relevant voltage is negative in this example, it is represented as a point on the graph, where the open-circuit voltage spike first drops below the target open-circuit voltage. The total delivered charge count curve 302 starts at zero and rises monotonically. The delivered charge reaches the critical charge at approximately 1500 seconds. This time is very close to the time at which the target open-circuit voltage is met. After both conditions are met, the voltage switches from the driving voltage to the holding voltage, approximately 1500 seconds later.

[0108] In another embodiment, optical transitions are monitored by a voltage sensing pad positioned directly on the transparent conductive layer (TCL). This allows direct measurement of the Veff at the center of the device between the buses where Veff is minimized. In this case, when the measured Veff at the center of the device reaches a target voltage, such as a holding voltage, the controller indicates that the optical transition is complete. In various embodiments, the use of sensors can reduce (e.g., eliminate) the benefits of using a target voltage offset from a self-holding voltage. For example, when a sensor is present, offset may not be required and the target voltage may (e.g., substantially) be equal to the holding voltage. In the case of using voltage sensors, at least one sensor may be present on each TCL. The voltage sensor may be positioned at an intermediate distance between the buses, for example, away from one side of the device (near the edge), such that it does not affect (or minimally affects) the viewing area. The voltage sensor may be concealed from view, for example, by placing it close to spacers, dividers, and / or frames that prevent the viewer from seeing the sensor.

[0109] In some embodiments, the voltage sensing pad (e.g., the sensor) may be a conductive strip pad. The pad may be as small as about 1 mm² (square millimeters). The pad may be about 10 mm² or smaller. A four-wire system may be used in embodiments utilizing the voltage sensor (e.g., the sensing pad).

[0110] In some embodiments, the method (e.g., implemented by a control system) may specify the total duration of the transition. For example, the controller may be programmed to monitor the progress of the transition from a start state to an end state using a modified detection algorithm. This progress may be monitored by periodically reading current values ​​in response to a decrease in the applied voltage magnitude, such as using detection techniques described above (e.g., using VoC). Detection techniques may be implemented using a decrease in the applied current (e.g., measuring open-circuit voltage). The current and / or voltage response indicates how close the optical transition is to completion. In some embodiments, the response is compared to a threshold current and / or voltage over a specific period of time (e.g., the time elapsed since the optical transition was initiated). In some embodiments, the progress of the current and / or voltage response is compared, for example, using sequential pulses and / or checks. The slope (e.g., steepness) of the progress may indicate when the end state is likely to be reached. A linear extension of this threshold current can be used to predict when the transition will be completed and when it will be sufficiently completed to allow the drive voltage to decrease to the holding voltage.

[0111] Regarding algorithms used to ensure that the optical transition from the first state to the second state occurs within a defined timeframe, for example, when the interpretation of the impulse response indicates that the transition is not progressing rapidly enough to meet the required speed of the transition, the controller can be configured (or designed) to increase the driver voltage, such as to accelerate the transition. In some embodiments, when it is determined that the transition is not progressing rapidly enough, the transition switches to a mode driven by the applied current. The current is large enough to increase the speed of the transition, but not so large that it degrades or damages the electrochromic device (e.g., irreversibly). In some embodiments, the maximum suitable safe current may be referred to as Isafe. Examples of Isafe can be in the range of approximately 5 μA / cm² to 250 μA / cm². In the current-controlled drive mode, the applied voltage is allowed to fluctuate during the optical transition. Then, during this current-controlled drive step, the controller can periodically probe by, for example, dropping to a holding voltage and checking the completion of the transition in the same manner as when using a constant drive voltage.

[0112] In some embodiments, the detection technique may determine whether the optical transition is progressing as expected. A transition that is not progressing as expected can be described as 'non-characteristic'. As understood herein, a non-characteristic hue transition is a deviation from the normal switching parameters of the object window. When the detection technique (e.g., VoC voltage detection) determines that the optical transition is progressing too slowly, it may take steps to accelerate the transition. For example, it may increase the drive voltage. The technique may determine that the optical transition is progressing too quickly and there is a risk of damage to the device. When such a determination is made, the detection technique may take steps to slow down the transition. As an example, the controller may decrease the drive voltage.

[0113] In some applications, groups of windows are configured to match transition rates. This matching can be performed by adjusting voltage and / or drive current, at least in part based on feedback obtained during probing (e.g., by pulse or open-circuit measurements). In embodiments where transitions are controlled by monitoring current response, the magnitude of the current response can be compared between windows. Windows can be controlled by a local controller. The local controller can be part of a (e.g., hierarchical) control system. Groups of windows (e.g., at least 2, 3, 4, 5, 6, 7, 8, 9, or 10 windows) can be controlled by the same local controller (e.g., a window controller). For example, comparisons can be performed for a window or for each window in a group of windows to determine how to scale the drive potential and / or drive current of the window (e.g., each window in the group). Comparisons can be performed between a window at a first time and its past performance at a time prior to the first time. Comparisons can be performed between a first window and a second window. Comparisons can be performed between a window and an average window performance (e.g., where the average window performance is the requested, optimal, and / or average window performance). The rate of change of open-circuit voltage can be used as an indicator of changes in window performance (e.g., degradation).

[0114] In some embodiments, the window controllers described herein are suitable for integration with a Building Management System (BMS). A BMS is a computer-based control system installed in a facility (e.g., a building) that controls (e.g., monitors) the building's mechanical and / or electrical equipment, such as ventilation, lighting, power systems, elevators, fire protection systems, and / or security systems. A BMS consists of: hardware, including interconnection with one or more computers via communication channels; and associated software, used to maintain conditions in the facility, for example, according to the preferences of occupants and / or building managers. For example, a local area network such as Ethernet can be used to implement a BMS. The software may be at least partially based on, for example, Internet protocols and / or open standards. One example of such software is software from Tridium Corporation (Richmond, Virginia). A common communication protocol used by BMSs is BACnet (Building Automation and Control Network).

[0115] Building Management Systems (BMS) are most commonly found in large buildings and typically function at least to control the building's environment. For example, a BMS can control temperature, carbon dioxide levels, and / or humidity within a building. Various mechanical devices controlled by the BMS exist, such as heaters, air conditioners, blowers, vents, and the like. To control the building environment, the BMS can, for example, turn any of these various devices on and off under defined conditions. In some embodiments, a core function of the BMS is to maintain a comfortable, safe, and / or healthy environment for the building's occupants, for example, while minimizing energy demands (e.g., heating and / or cooling costs and / or requirements). The BMS can be used to optimize the synergy between various systems (e.g., in terms of power consumption and / or cost). Such synergy can, for example, be used to save energy and reduce building operating costs.

[0116] In some embodiments, the control system (e.g., its components, such as a window controller) is integrated with the BMS. The window controller can be configured to control one or more colorable windows. In some embodiments, one or more colorable windows include at least one all-solid-state and inorganic electrochromic device. In some embodiments, the colorable window includes an organic EC device. In some embodiments, one or more electrochromic windows include only all-solid-state and inorganic windows. In some embodiments, the electrochromic window is a polymorphic electrochromic window as described in U.S. Patent Application No. 12 / 851,514, filed August 5, 2010, entitled "MULTIPANE ELECTROCHROMIC WINDOWS," which is incorporated herein by reference in its entirety.

[0117] Figure 4 illustrates an example of a schematic diagram of an embodiment of BMS 400 configured to manage several systems of building 401, including security systems, heating / ventilation / air conditioning (HVAC), building lighting, electrical systems, elevators, fire protection systems, and the like. Security systems may include magnetic card access, revolving gates, solenoid-driven door locks, surveillance cameras, burglar alarms, metal detectors, and the like. Fire protection systems may include fire alarm and extinguishing systems, including water pipe control. Lighting systems may include interior lighting, exterior lighting, emergency warning lights, emergency exit signs, and emergency floor exit lighting. Electrical systems may include a main generator, backup generators, and an uninterruptible power supply (UPS) grid.

[0118] BMS 400 manages and controls system 402. In this example, control system 402 is depicted as a distributed network of window controllers, including a main controller 403, intermediate network controllers 405a and 405b, and end or leaf controllers 410 as local controllers. End or leaf controllers 410 may be similar to the window controllers previously described in conjunction with Figures 1A and 1B. For example, the main controller 403 may be close to BMS 400, and each floor of building 401 may have one or more intermediate network controllers 405a and 405b, while each window of the building has its own end controller 410. Controller 410 may directly control one or more electrochromic windows of building 401. Direct control means that there is no intervening controller between the window controller and the window. For example, the window controller may be coupled to one or more colorable windows via wiring that is not interrupted by another controller.

[0119] At least one of the controllers 410 may be located in a separate position relative to the electrochromic window it controls. At least one of the controllers 410 may be integrated into the electrochromic window. For simplicity, ten electrochromic windows of building 401 are depicted as being controlled by control system 402. A large number of electrochromic windows may exist in a building controlled by control system 402. Control system 402 does not need to be a distributed network of window controllers. For example, a single end controller controlling the function of a single electrochromic window falls within the scope of the embodiments disclosed herein.

[0120] One example of the disclosed embodiments is a BMS that includes a multi-purpose control system, such as that described herein. By incorporating feedback from the control system, the BMS can provide, for example, enhanced: (1) environmental control, (2) energy saving, (3) security, (4) flexibility in control options, (5) improved reliability and service life of other systems (e.g., due to less dependence on them and therefore less maintenance), (6) information availability and diagnostics, (7) effective use by personnel, and various combinations thereof, for example, because colorable windows can be automatically controlled.

[0121] In some embodiments, the BMS may be absent or may be present but not communicating with the control system, or may communicate with the control system at a higher level. In some embodiments, the control system may provide, for example, enhanced: (1) environmental control, (2) energy saving, (3) security, (4) flexibility in control options, (5) improved reliability and service life of other systems (e.g., due to less dependence on them and therefore less maintenance), (6) information availability and diagnostics, (7) effective use by personnel, and various combinations thereof, for example, because the colorable window can be automatically controlled. In some embodiments, maintenance of the BMS does not interrupt the control and / or operation of the colorable window.

[0122] In some cases, the BMS 400 system can be operated according to daily, monthly, quarterly, and / or annual schedules. For example, the lighting control system (shown as "lights" in Figure 4), HVAC system, control system 402, and security system can be operated on a 24-hour schedule, taking into account when people are in the building during the workday. At night, the building can enter energy-saving mode, and during the day, the system can operate in a way that minimizes the building's energy consumption while providing comfort for occupants. As another example, the system can be shut down or enter energy-saving mode during holiday periods.

[0123] Scheduling information can be combined with geographic information. Geographic information may include the building's latitude and / or longitude. Geographic information may include information about the orientation of each side of the building (e.g., facade). Using this information, different rooms on different sides of the building can be controlled in different ways. For example, for an east-facing room in winter, the window controller can indicate that the window is not tinted in the morning. Without tinting, the room can warm up due to sunlight entering the room. The lighting control panel can dim the indicator lights due to sunlight. West-facing windows can be controlled by the room occupant in the morning, for example, because the tinting of west-facing windows may not affect energy efficiency. However, the operating modes of east-facing and west-facing windows can be switched at night (e.g., when the sun sets, west-facing windows are not tinted to allow sunlight to enter, bringing heat and lighting).

[0124] In the example of Figure 4, building 401 includes a building network, a BMS, and colorizable windows for the building's exterior windows. The network is operatively (e.g., communicatively) coupled to one or more sensors. For example, the building's exterior windows may be windows that separate the building's interior from its exterior. Light from the building's exterior windows affects interior lighting within the building approximately 20 feet or 30 feet from the windows. Spaces within the building more than approximately 20 feet or 30 feet from the exterior windows may receive very little light from them. Such spaces in the building far from the exterior windows may be illuminated by the building's lighting system. The temperature inside the building may be affected by external light and / or external temperature. For example, on cold days and when the building is heated by a heating system, rooms closer to doors and / or windows will lose heat faster than interior areas of the building and will be colder than interior areas.

[0125] In some embodiments, the network is operatively coupled to external sensors. A building may include external sensors on its roof. A building may include external sensors associated with at least one (e.g., each) exterior window. A building may include external sensors on one or more (e.g., each) sides of the building. (E.g., external sensors on each side of the building) may track the irradiance of one side of the building as the sun changes position during the day.

[0126] When the window controller is integrated into a building network (e.g., including BMS 400), outputs from external sensors can be input to the BMS 400 network and provided as input to the local end controller 410. For example, in some embodiments, output signals from two or more sensors are received. In some embodiments, only one output signal is received, and in some other embodiments, three, four, five, or more outputs are received. These output signals can be received via the building network (e.g., and / or BMS).

[0127] In some embodiments, the received output signal includes, for example, signals indicating energy consumption and / or power consumption by heating systems, cooling systems, and / or lighting within a facility (e.g., including at least one building). For instance, the energy consumption or power consumption of the facility's heating systems, cooling systems, and / or lighting can be monitored to provide signals indicating energy consumption or power consumption. The device can interface with or be attached to the building's electrical circuitry and / or wiring to achieve this monitoring. Alternatively, the building's electrical system can be installed to monitor the power consumed by the heating systems, cooling systems, and / or lighting of individual rooms or groups of rooms within the facility.

[0128] A hue command can be provided to change the current hue of a colorable window to determine a hue level (e.g., a target hue level). For example, referring to Figure 4, this could include a master controller 403 issuing commands to one or more intermediate network controllers 405a and / or 405b, which in turn issues commands to one or more end controllers 410 controlling the windows of the building. The end controllers 410 can apply voltage and / or current to the windows to drive the hue change according to the command.

[0129] In some embodiments, a building including electrochromic windows and a BMS may participate in and / or participate in a demand response program operated by one or more utilities that supply electricity to the facility. The program may be one that reduces the facility's energy consumption when a peak load is anticipated. Utilities may issue a warning signal prior to the anticipated peak load. For example, a warning may be issued a day, in the morning, or approximately one hour before the anticipated peak load. Peak loads may be anticipated during hot summer days, for example, when cooling systems / air conditioners draw large amounts of electricity from utilities. The warning signal may be received by the facility's control system (e.g., and / or BMS). The control system and / or BMS may then instruct the window controller to switch the appropriate electrochromic device in the electrochromic window to a darker or lighter hue level when a peak load is anticipated to help reduce power consumption in the building's cooling and / or heating systems (e.g., to mitigate weather conditions).

[0130] In some embodiments, the tintable windows of a building's exterior windows can be grouped into zones, with the tintable windows in each zone indicated in a similar manner. For example, groups of electrochromic windows on different floors or different sides of a building can be in different zones. For instance, on the first floor of a building, all east-facing electrochromic windows can be in zone 1, all south-facing electrochromic windows can be in zone 2, all west-facing electrochromic windows can be in zone 3, and all north-facing electrochromic windows can be in zone 4. As another example, all electrochromic windows on the first floor of a building can be in zone 1, all electrochromic windows on the second floor can be in zone 2, and all electrochromic windows on the third floor can be in zone 3. As yet another example, all east-facing electrochromic windows can be in zone 1, all south-facing electrochromic windows can be in zone 2, all west-facing electrochromic windows can be in zone 3, and all north-facing electrochromic windows can be in zone 4. As yet another example, an east-facing electrochromic window on a floor can be divided into different zones. Any number of colorable windows on the same side and / or different sides and / or different floors of a building can be assigned to a zone. A window zone can be divided at least in part by: (i) the functionality of the room on which it is located (e.g., a meeting room window, an office window, a cafeteria window), (ii) the floor on which it is located, (iii) the facade on which it is located, (iv) the owner or tenant of the facility portion on which it is located, or (v) any combination thereof.

[0131] In some embodiments, colorable windows within a partition may be controlled by the same window controller or by different window controllers (e.g., receiving the same orientation). In some other embodiments, the window controllers controlling windows within a partition may receive the same output signal from a sensor. The window controllers controlling windows within a partition may use the same functionality or lookup table to determine the hue level of windows within the partition.

[0132] In some embodiments, colorable (e.g., electrochromic) windows in a partition may be controlled by a window controller that receives output signals from (e.g., transmittance) sensors. In some embodiments, the (e.g., transmittance) sensors may be mounted close to the windows in the partition. For example, the (e.g., transmittance) sensors may be mounted in or on a frame containing an IGU (e.g., mounted in or on a vertical, horizontal, or vertical window frame of the frame). In some embodiments, colorable windows in a partition (such as windows on one side of a building) may be controlled by a window controller that receives output signals from (e.g., transmittance) sensors.

[0133] In some embodiments, a sensor (e.g., a light sensor and / or an IR sensor) may provide an output signal to a window controller to control a colorable (e.g., electrochromic) window in a first partition (e.g., a master partition). The window controller may control colorable windows in a second partition (e.g., a slave partition) in the same manner as the first partition. In some other embodiments, another window controller may control colorable windows in a second partition in the same manner as the first partition.

[0134] In some embodiments, a user (e.g., a building manager, an occupant of a room in the second partition, or another person) can manually instruct a colorable window in the second partition (e.g., from the control partition) to enter a hue level, such as a tinted (e.g., colored) state (level) or a transparent state. For example, manual instruction may include using a tint or transparent command, or a command from a user console (e.g., of the BMS). In some embodiments, when the hue level of a window in the second partition is overwritten by such a manual command, the colorable window in the first partition (i.e., the master control partition) remains under the control of a window controller receiving output from a transmittance sensor. The second partition may remain in manual command mode for a period of time, for example, and then return to the control of a window controller receiving output from a (e.g., transmittance) sensor. For example, the second partition may remain in manual mode for one hour after receiving an overwrite command, for example, and then return to the control of a window controller receiving output from a (e.g., transmittance) sensor. The sensor may be any sensor disclosed herein.

[0135] In some embodiments, a user (e.g., a building manager, an occupant of a room in a first partition, or another person) may manually instruct a window in a first partition (e.g., a master partition) to enter a hue level, such as a tinted (e.g., colored) state or a transparent state. For example, manual instruction may include using a hue or a command from a user console (e.g., a BMS). In some embodiments, when the hue level of a window in a first partition is overwritten with such a manual command, a colorable window in a second partition (e.g., from a control partition) remains under the control of a window controller receiving output from an external sensor. The first partition may remain in manual command mode for a period of time and then return to the control of a window controller receiving output from (e.g., transmittance and / or external) sensors. For example, the first partition may remain in manual mode for a period of time (e.g., one hour) after receiving an overwrite command and then return to the control of a window controller receiving output from (e.g., transmittance and / or external) sensors. In some other embodiments, a colorable window in a second partition may remain at the hue level it was at when a manual overwrite was received for the first partition. The first zone can remain in manual command mode for a period of time, after which both the first and second zones can be restored to control by a window controller receiving output from (e.g., transmittance and / or external) sensors. The windows can be divided into multiple zones (e.g., at least in part based on the orientation, facade, floor, ownership, utilization rate, any other assignment measure, random assignment, or any combination thereof of the enclosure (e.g., room) where the windows are located). The allocation of windows to zones can be static or dynamic (e.g., based on a heuristic approach). Each zone can contain at least about 2, 5, 10, 12, 15, 30, 40, or 46 windows.

[0136] In some embodiments, at least one device operates in coordination with at least one other device, which are coupled to a network. The device may be a colorable window. Control of at least one device may be via an Ethernet network. For example, the hue level of the colorable window may be adjusted in parallel. When the device is in use, partitions of the device may have at least one identical characteristic. For example, when the colorable window is in a partition, the partition of the colorable window may have its hue level (automatically) changed (e.g., darkened or brightened) to the same level. The device may be a sensor. For example, when a sound sensor is in a partition, it may sample sound at the same frequency and / or within the same time window. A partition of the device may contain (e.g., of the same type) a plurality of devices. A partition may include (i) devices (e.g., tinted windows) facing a specific direction of an enclosure (e.g., a facility), (ii) multiple devices mounted on a specific face (e.g., a facade) of an enclosure, (iii) devices on a specific floor of the facility, (iv) devices in a specific type of room and / or activity (e.g., open space, office, meeting room, lecture hall, corridor, reception hall, or cafeteria), (v) devices mounted on the same fixture (e.g., an inner or outer wall), and / or (vi) users. Defined devices (e.g., a group of tintable windows in a room or on a facade, which is a subset of a larger group of tintable windows). (Automatic) adjustments to devices can be made automatically and / or by the user. Automatic changes to device attributes and / or states within a zone can be overwritten by the user (e.g., by manually adjusting hue levels). The user can overwrite the automatic adjustments to devices within a zone using mobile circuitry (e.g., remote controllers, virtual reality controllers, cellular phones, electronic notebooks, laptops, and / or similar mobile devices).

[0137] In some embodiments, various devices (e.g., IGUs) are grouped into target partitions (e.g., EC windows). At least one partition (e.g., each of these partitions) may include a subset of devices. For example, at least one partition (e.g., each) of devices may be controlled by one or more corresponding floor controllers and one or more corresponding local controllers (e.g., window controllers) controlled by such floor controllers. In some instances, at least one partition (e.g., each) may be controlled by a single floor controller and two or more local (e.g., window) controllers controlled by the single floor controller. For example, a partition may represent a logical grouping of devices. Each partition may correspond to a set of devices (e.g., of the same type) in a specific location or area of ​​a facility that is driven together at least partially based on its orientation. For example, a facility (e.g., a building) may have four faces or sides (north, south, east, and west) and ten floors. In such teaching examples, each partition may correspond to a set of smart windows (e.g., tinted windows) on a specific floor and on a specific one of the four faces. At least one (e.g., each) partition may correspond to a set of devices that share one or more physical characteristics (e.g., device parameters, such as size or service life). In some embodiments, the partitions of devices are grouped at least in part based on one or more non-physical characteristics such as security designation or business hierarchy (e.g., IGUs in demarcated managerial offices may be grouped into one or more partitions, while IGUs in demarcated non-manager offices may be grouped into one or more different partitions).

[0138] In some embodiments, at least one (e.g., each) floor controller is capable of addressing all devices (e.g., of the same or different types) in at least one (e.g., each) of one or more corresponding partitions. For example, a master controller may issue a primary hue command to the floor controller controlling the target partition. The primary hue command may include an (e.g., abstract) identifier of the target partition (also referred to hereinafter as a "partition ID"). For example, the partition ID may be a first protocol ID such as the one just described in the example above. In such cases, the floor controller receives a primary hue command including a hue value and a partition ID, and maps the partition ID to a second protocol ID associated with the local controller within the partition. In some embodiments, the partition ID is a higher-level abstraction than the first protocol ID. In such cases, the floor controller may first map the partition ID to one or more first protocol IDs, and then map the first protocol ID to the second protocol ID.

[0139] In some embodiments, a facility may be divided into one or more zones. Zones may be defined at least partially by the customer or by the facility manager. Zones may be defined at least partially automatically. For example, a zone for an installation (e.g., including a color-sensitive window, sensor, or transmitter) may be associated with (i) the facade of the building it faces, (ii) the floor in which it is located, (iii) the building within the facility, (iv) the functionality of the enclosure within it (e.g., a meeting room, gymnasium, office, or cafeteria), (iv) the prescribed and / or actual occupancy of the enclosure within it (e.g., organizational function), (v) the prescribed and / or actual activities within the enclosure, (vi) the tenants, owners, and / or managers of the facility's enclosure (e.g., for facilities with various tenants, owners, and / or managers), and / or (vii) its geographical location. Zones may be, for example, visually modifiable (e.g., using a software application). The status of a partition (e.g., in conjunction with the status of the devices within it) can be displayed by an application (e.g., updated in real-time or substantially in real-time). One or more partitions can be grouped. For example, all partitions on a floor can be grouped. There can be partition hierarchies using any of the partition associations (i) to (vii). Partitions can be created by providers of devices, control systems, and / or networks. Partitions can be generated by users (e.g., customers, tenants, or facility owners). Partitions can be created at the level of a digital model of the facility (e.g., a Revit file). Digital models and / or other similar files can be associated with facilities and devices. For example, a Building Information Modeling (BIM) can be a Revit file, a Microdesk (e.g., ModelStream), IMAGINIT, ATG USA, or similar facility-related digital file. In some embodiments, BIM is a computer-aided design (CAD) paradigm that allows for intelligent, 3D, and / or parametric object-based design.

[0140] Regardless of whether the window controller is a standalone window controller, part of a control system, or interfaces with (e.g., part of the control system itself) a building network, any of the methods described herein can be used to control the tint of a tintable window.

[0141] In some embodiments, the window controller described herein includes components for wired and / or wireless communication between the window controller, sensors, and / or individual communication nodes. Wireless and / or wired communication may be implemented via a communication interface that directly interfaces with the window controller. Such an interface may be microprocessor-native. Such an interface may be provided via additional circuitry that implements these functions.

[0142] The separate communication node for wireless communication can be, for example, another wireless window controller, the local end (e.g., the end), an intermediate or main window controller, a remote control device, or a BMS. Wireless communication can be used in the window controller for at least one of the following operations: programming and / or operating the colorable window, collecting data from the colorable window from (e.g., as described herein) various sensors and / or protocols, and / or using the colorable (e.g., electrochromic) window as a relay point for wireless communication. Data collected from the colorable window may include counting data, such as the number of times the EC device has been activated, the efficiency of the EC device over time, and the like.

[0143] In one embodiment, wireless communication is used to operate the associated colorable window, for example, via infrared (IR) and / or radio frequency (RF) signals. In some embodiments, the controller will include a wireless protocol chip, such as Bluetooth, EnOcean, WiFi, ZigBee, Global Positioning System (GPS), Ultra Wideband (UWB), or the like. The window controller may have wireless communication via a network. Input to the window controller may be entered manually by the end user (e.g., at a wall switch) either directly or via wireless communication. Input to the window controller may originate from the building's BMS, and the colorable window is a component of the building.

[0144] In some embodiments, when the window controller is part of a distributed network of controllers (e.g., a control system), wireless communication is used to transmit at least a portion of data to each of a plurality of colorable windows and to transmit at least a portion of data from each of the plurality of colorable windows via the distributed network of the controllers. At least one (e.g., each) controller in the controller network may have a wireless communication component. For example, referring again to FIG4, master controller 403 may wirelessly communicate with each of intermediate network controllers 405a and 405b, which in turn may wirelessly communicate with end controllers 410, each associated with an electrochromic window. Master controller 403 may wirelessly communicate with BMS 400. In one embodiment, communication at least one level of the window controller is performed wirelessly. In one embodiment, communication at least one level of the window controller is performed using wires.

[0145] In some embodiments, more than one mode of wireless communication protocol is used in a distributed network for window controllers. For example, the main window controller may communicate with the intermediate controller wirelessly via WiFi or Wi-Fi, while the intermediate controller communicates with the end controller via Bluetooth, Wi-Fi, EnOcea, or other protocols. In another instance, the window controller has a redundant wireless communication system with the flexibility of end-user selection for wireless communication.

[0146] In some embodiments, wireless communication between the main window controller and / or intermediate window controller and the end window controller provides the advantage of avoiding the installation of hard communication cables. For example, wireless communication between the window controller and the BMS. In some embodiments, this wireless communication is used to transmit data to and from tinted windows for operating those windows and to provide data to, for example, the BMS, thereby optimizing the building's environment and energy efficiency. Window orientation data and feedback from sensors can be used in conjunction for such optimization. For example, granular-level (window-by-window) microclimate information can be fed to the BMS to optimize one or more environments within the building.

[0147] In some embodiments, the sensor is operatively coupled to at least one controller and / or processor. Sensor readings may be obtained by one or more processors and / or controllers. The controller may include a processing unit (e.g., a CPU or GPU). The controller may receive input (e.g., from at least one sensor). The controller may include circuitry, electrical wiring, optical wiring, sockets, and / or receptacles. The controller may deliver outputs. The controller may include multiple (e.g., sub) controllers. The controller may be part of a control system. The control system may include a set of main controllers, floor controllers (e.g., including network controllers), and a set of local controllers. The set of local controllers may include window controllers (e.g., controlling optically switchable windows), enclosure controllers, and / or component controllers. For example, the controller may be part of a hierarchical control system (e.g., including a main controller that directs one or more controllers, such as floor controllers, local controllers (e.g., window controllers), enclosure controllers, and / or component controllers).

[0148] In a hierarchical control system, the physical orientation of controller types can change over time. For example, at the first time point, the first processor can act as the main controller, the second processor as the floor controller, and the third processor as the local controller. At the second time point, the second processor can act as the main controller, the first processor as the floor controller, and the third processor can maintain its local controller function. At the third time point, the third processor can act as the main controller, the second processor as the floor controller, and the first processor as the local controller.

[0149] The controller can control one or more devices (e.g., and is directly coupled to the devices). The controller can be located in proximity to one or more devices it controls. For example, the controller can control optically switchable devices (e.g., IGUs), antennas, sensors, and / or output devices (e.g., light sources, sound sources, odor sources, gas sources, HVAC outlets, or heaters). The output device can be a transmitter.

[0150] In one embodiment, a floor controller may direct one or more lower-level controllers (e.g., local controllers). Lower-level controllers may include one or more window controllers, one or more enclosure controllers, one or more component controllers, or any combination thereof. For example, a floor (e.g., including a network) controller may control a plurality of local (e.g., including window) controllers. The plurality of local controllers may be located in a portion of a facility (e.g., a portion of a building). A portion of the facility may be a floor of the facility. For example, a floor controller may be assigned to a floor. In some embodiments, a floor may include a plurality of floor controllers, for example, depending on the floor size and / or the number of local controllers coupled to the floor controllers. For example, a floor controller may be assigned to a portion of a floor. For example, a floor controller may be assigned to a portion of local controllers located in the facility. For example, a floor controller may be assigned to a portion of a floor of the facility.

[0151] The main controller may be coupled to one or more lower-level (e.g., floor) controllers. Floor controllers may be located within the facility. The main controller may be located within or outside the facility. The main controller may be located in the cloud. The controller may be part of or operationally coupled to a building management system. The controller may receive one or more inputs. The controller may generate one or more outputs. The controller may be a single-input single-output (SISO) controller or a multiple-input multiple-output (MIMO) controller. The controller may interpret the received input signals. The controller may acquire data from one or more components (e.g., sensors). Acquisition may include receiving or extracting. Data may include measurements, estimates, decisions, generation, or any combination thereof. The controller may include feedback control.

[0152] The controller may include feedforward control. Control may include on-off control, proportional control, proportional-integral (PI) control, or proportional-integral-derivative (PID) control. Control may include open-loop control or closed-loop control. The controller may include closed-loop control. The controller may include open-loop control. The controller may include a user interface. The user interface may include (or be operatively coupled to) a keyboard, keypad, mouse, touchscreen, microphone, voice recognition package, camera, imaging system, or any combination thereof. Outputs may include a display (e.g., a screen), speaker, or printer.

[0153] Figure 5 illustrates an example of a control system architecture 500 that includes a hierarchical controller structure. The controller hierarchy includes a main controller 508 that controls floor controllers 506. Floor controllers 506, in turn, control local controllers 504. In some embodiments, local controllers 504 control one or more IGUs, one or more sensors, one or more output devices (e.g., one or more transmitters), or any combination thereof. In the illustrative configuration of Figure 5, the main controller 508 is operatively coupled (e.g., wirelessly and / or wired) to a building management system (BMS) 524 and a database 520. Arrows in Figure 5 indicate communication paths. Controllers are operatively coupled (e.g., directly / indirectly and / or wired and / or wirelessly) to an external source 510. External source 510 may include a network. External source 510 may include one or more sensors or output devices. External source 510 may include cloud-based applications and / or databases. Communication may be wired and / or wireless. External source 510 may be located outside the facility. For example, external source 510 may include one or more sensors and / or antennas mounted, for example, on a wall or the ceiling of a facility. Communication may be unidirectional or bidirectional. In the example shown in Figure 5, all communication arrows may be bidirectional.

[0154] The controller can monitor and / or guide changes in the operating conditions (e.g., physical) of the devices, software, and / or methods described herein. Control may include regulation, manipulation, limitation, guidance, monitoring, adjustment, modulation, alteration, modification, constraint, inspection, guidance, or management. (E.g., via the controller) Control may include attenuation, modulation, alteration, management, suppression, discipline, regulation, constraint, supervision, manipulation, and / or guidance. Control may include controlling control variables (e.g., temperature, power, voltage, and / or distribution). Control may include real-time or offline control. Computations utilized by the controller may be performed real-time and / or offline. The controller may be a manual or non-manual controller. The controller may be an automatic controller. The controller may operate on request. The controller may be a programmable controller. The controller may be programmable. The controller may include a processing unit (e.g., CPU or GPU). The controller may receive input (e.g., from at least one sensor). The controller may deliver outputs. The controller may include multiple (e.g., sub-)controllers. The controller may be part of a control system. The control system may include a main controller, floor controllers, and local controllers (e.g., enclosure controllers or window controllers). A controller may receive one or more inputs. A controller may generate one or more outputs. A controller may be a single-input single-output (SISO) controller or a multiple-input multiple-output (MIMO) controller. The controller may interpret the received input signals.

[0155] The controller may acquire data from one or more sensors. Acquisition may include receiving or extracting. Data may include measurement, estimation, determination, generation, or any combination thereof. The controller may include feedback control. The controller may include feedforward control. Control may include on-off control, proportional control, proportional-integral (PI) control, or proportional-integral-derivative (PID) control. Control may include open-loop control or closed-loop control. The controller may include closed-loop control. The controller may include open-loop control. The controller may include a user interface. The user interface may include (or be operatively coupled to) a keyboard, keypad, mouse, touchscreen, microphone, voice recognition package, camera, imaging system, or any combination thereof. Output may include a display (e.g., screen), speaker, or printer.

[0156] The methods, systems, software, and / or devices described herein may include and / or utilize a control system. The control system may communicate with any of the devices (e.g., sensors) described herein. At least two of the sensors may be of the same or different types, for example, as described herein. For instance, the control system may communicate with a first sensor and / or a second sensor. The control system may control (e.g., guide) one or more sensors. The control system may control one or more components of a building management system (e.g., lighting, security, and / or air conditioning systems). The controller may regulate at least one (e.g., environmental) characteristic of an enclosure. The control system may use any component of the building management system to regulate the enclosure environment. For instance, the control system may regulate energy supplied by heating elements and / or cooling elements. For instance, the control system may regulate the speed of air flowing into and / or from the enclosure through vents.

[0157] The control system may include a processor. The processor may be a processing unit. The controller may include a processing unit. The processing unit may be central. The processing unit may include a central processing unit (hereinafter referred to as "CPU"). The processing unit may be a graphics processing unit (hereinafter referred to as "GPU"). The controller or control mechanism (e.g., including a computer system) may be programmed to implement one or more methods of the present invention. The processor may be programmed to implement the methods of the present invention. The controller may control at least one component of the system and / or device disclosed herein.

[0158] In some embodiments, the building network infrastructure has a vertical data plane (between building floors) and a horizontal data plane (within a single floor or multiple consecutive floors). In some cases, the horizontal and vertical data planes have the same or similar data carrying capacity and components. In other cases, the two data planes have different data carrying capacities. For example, the vertical data plane may contain components for faster data transmission rates and / or bandwidth. In one instance, the vertical data plane contains components supporting at least about 10, 20, or 50 gigabits / second or faster Ethernet transmission (e.g., using UTP wires and / or fiber optic cables), while the horizontal data plane contains components supporting up to about 1, 3, 5, or 8 gigabits / second Ethernet transmission, for example, via coaxial cable. In some cases, the horizontal data plane supports data transmission via multimedia via the MoCA 2.5 standard or the MoCA 3.0 standard. In some embodiments, the connection between floors on the vertical data plane uses a control panel with a high-speed Ethernet switch. These control panels can communicate with nodes on a given floor, for example, via a MoCA interface on a horizontal data plane and an associated coaxial cable.

[0159] Data transmission and (in some embodiments) voice services may be provided within a facility (e.g., a building) via wireless communication to and / or from building occupants. In the United States, current third-generation (3G), fourth-generation (4G), and fifth-generation (5G) cellular communication standards are deployed using spectral allocations in the 600 MHz to 850 MHz and 1700 to 2300 MHz frequency ranges. These deployments may experience problems, for example, due to radio frequency (RF) attenuation caused by some common building materials used in walls, floors, ceilings, and windows. While 5G systems currently operate within the 600 MHz and 850 MHz bands, the Federal Communications Commission (FCC) has allocated several additional bands for 5G, including the 24 GHz and 39 GHz millimeter-wave (mmW) bands. At millimeter-wave frequencies, building attenuation can be significantly more severe compared to the 600 to 2300 MHz bands.

[0160] In some embodiments (e.g., to address the challenge of RF attenuation), buildings may be equipped with components that act as gateways or ports for cellular signals. Such gateways may be coupled to infrastructure within the building that provides wireless services via internal antennas and other infrastructure implementing Wi-Fi, small cell services (e.g., via micro or microcell devices), CBRS, etc. Gateways (e.g., access points) for such services may include high-speed fiber optic cables (e.g., underground) from the operator’s headquarters, point-to-point microwave links between the headquarters and the facility, and / or wireless signals received at antennas located outside the building (e.g., donor antennas or sky sensors on the building’s roof). This high-speed fiber optic cable or point-to-point microwave link is sometimes referred to as a “backload.”

[0161] In some embodiments, one or more sensors are included within an enclosure. For example, the enclosure may include at least 1, 2, 4, 5, 8, 10, 20, 50, or 500 sensors. The enclosure may include a plurality of sensors in the range of any of the foregoing values ​​(e.g., about 1 to about 1000, about 1 to about 500, or about 500 to about 1000). The sensors may be of any type. For example, the sensors may be configured (e.g., and / or designed) to measure the concentration of gases (e.g., carbon monoxide, carbon dioxide, hydrogen sulfide, volatile organic compounds, or radon). For example, the sensors may be configured to measure current. For example, the sensors may be configured to measure voltage. For example, the sensors may be configured to measure current. For example, the sensors may be configured (e.g., and / or designed) to measure environmental noise. For example, sensors can be configured (e.g., and / or designed) to measure electromagnetic radiation (e.g., RF, microwave, infrared, visible light, and / or ultraviolet radiation). For example, sensors can be configured (e.g., and / or designed) to measure safety-related parameters, such as (e.g., glass) breakage and / or the unauthorized presence of personnel in a confined area. Sensors can cooperate with one or more (e.g., active) devices such as radar or lidar. Devices can be used to detect the physical size of an enclosure, personnel present within the enclosure, stationary objects within the enclosure, and / or moving objects within the enclosure.

[0162] In some embodiments, sensors can help control the environment of an enclosed space, providing inhabitants with an environment that is more comfortable, desirable, aesthetically pleasing, healthy, productive (e.g., in terms of resident performance), easier to live in (e.g., work), or any combination thereof. Sensors can be configured as low- or high-resolution sensors. Sensors can provide on / off indications of the occurrence and / or presence of specific environmental events (e.g., a single-pixel sensor). In some embodiments, the accuracy and / or resolution of sensors can be improved through artificial intelligence analysis of sensor measurements. Examples of artificial intelligence techniques that can be used include reactivity, limited memory, theory of mind, and / or self-sensing techniques known to those skilled in the art. Sensors can be configured to process, measure, analyze, detect, and / or respond to one or more of the following: data, temperature, humidity, sound, force, pressure, electromagnetic waves, position, distance, movement, flow, acceleration, velocity, vibration, dust, light, glare, color, gas, and / or other states (e.g., characteristics) of the environment (e.g., the enclosed space). The gas may include volatile organic compounds (VOCs). The gas may include carbon monoxide, carbon dioxide, water vapor (e.g., moisture), oxygen, radon, and / or hydrogen sulfide. One or more sensors may be calibrated in a factory setting. The sensors may be optimized to perform accurate measurements of one or more environmental characteristics present in the factory setting.

[0163] In some cases, factory-calibrated sensors may not be well-suited for operation in the target environment. For example, the factory setup may include an environment different from the target environment. The target environment may be the environment where the sensor is deployed. The target environment may be the environment in which the sensor is expected and / or intended to operate. The target environment may differ from the factory environment. The factory environment corresponds to the location where the sensor is assembled and / or built. The target environment may include a factory in which the sensor is not assembled and / or built. In some cases, the factory setup may differ from the target environment in terms of erroneous sensor readings captured in the target environment (e.g., within the measurable range). In this context, "erroneous" may refer to sensor readings that deviate from a specified accuracy (e.g., specified by the sensor manufacturer). In some cases, when operating in the target environment, a factory-calibrated sensor may provide readings that do not meet accuracy specifications (e.g., provided by the manufacturer).

[0164] In some embodiments, the sensor is operatively coupled to at least one controller. The coupling may include a communication link. The communication link may include any suitable communication medium (e.g., wired and / or wireless). The communication link may include wires, such as one or more conductors configured in twisted-pair, coaxial, and / or optical fibers. The communication link may include a wireless communication link, such as Wi-Fi, Bluetooth, cellular, or optical communication links. One or more segments of the communication link may include conductive (e.g., wired) media, while one or more other segments of the communication link may include a wireless link.

[0165] In some embodiments, an enclosure is a facility (e.g., a building). An enclosure may include walls, doors, or windows. In some embodiments, at least two of a plurality of enclosures are located within a facility. In some embodiments, at least two of a plurality of enclosures house different facilities. The different facilities may be a campus (e.g., belonging to the same entity). At least two of a plurality of enclosures may reside on the same floor of a facility. At least two of a plurality of enclosures may reside on different floors of a facility.

[0166] In some embodiments, after the first sensor is installed, the sensor performs self-calibration to establish an operating baseline. The self-calibration operation can be initiated by an individual sensor, a nearby second sensor, or by one or more controllers. For example, sensors deployed in an enclosure can perform a self-calibration procedure after installation and / or afterward. The baseline may correspond to a lower threshold value, from which the collected sensor readings are expected to include values ​​higher than the lower threshold value. The baseline may correspond to an upper threshold value, from which the collected sensor readings are expected to include values ​​lower than the upper threshold value. The self-calibration procedure may continue starting with a sensor search time window during which fluctuations or disturbances in relevant parameters are nominal. In some embodiments, the time window is sufficient to collect sensed data (e.g., sensor readings) that allows for the separation and / or identification of signals and noise from the sensed data. The time window may be predetermined. The time window may be undefined. The time window may remain open (e.g., continuously) until a calibration value is obtained.

[0167] In some embodiments, the sensor may search for the optimal time to measure a baseline (e.g., within a time window). The optimal time (e.g., within a time window) may be a time span during which (i) the measured signal is most stable and / or (ii) the signal-to-noise ratio is highest. The measured signal may contain noise at a certain level. The complete absence of noise may indicate sensor failure or insufficient environmental conditions. The sensed signal (e.g., sensor data) may include the timestamps of the measured data values. The sensor may be assigned a time window during which it can sense the environment. The time window may be predetermined (e.g., using third-party information and / or historical data about the attributes measured by the sensor). The signal can be analyzed during that time window, and the optimal time span within that time window can be identified where the measured signal is most stable and / or the signal-to-noise ratio is highest. The time span may be equal to or shorter than the time window. The time span may occur throughout the entire time window or a portion of the time window.

[0168] In some embodiments, a sensor set includes at least two sensors of the same type. A sensor set may refer to a series of different sensors. In some embodiments, at least two of the sensors in the set cooperate to determine environmental parameters, for example, of an enclosure in which the sensors are disposed. For example, a sensor set may include a carbon dioxide sensor, a carbon monoxide sensor, a volatile organic chemical sensor, an environmental noise sensor, a visible light sensor, a temperature sensor, and / or a humidity sensor. A sensor set may include other types of sensors, and the claimed subject matter is not limited in this respect. An enclosure may include one or more sensors that are not part of a sensor set. An enclosure may include multiple sets. At least two of the multiple sets may differ in at least one of their sensors. At least two of the multiple sets may have at least one of their similar (e.g., same type) sensors. For example, a set may have two motion sensors and one temperature sensor. For example, a set may have a carbon dioxide sensor and an IR sensor. The set may include one or more devices that are not sensors. One or more other devices that are not sensors may include sound emitters (e.g., buzzers) and / or electromagnetic radiation emitters (e.g., light-emitting diodes). In some embodiments, a single sensor (e.g., not concentrated) may be placed adjacent to (e.g., close to, such as in contact with) another device that is not a sensor.

[0169] In some embodiments, a plurality of sensors are assembled into a sensor kit (e.g., a sensor set). At least two of the plurality of sensors may be of different types (e.g., configured to measure different properties). Various sensor types may be assembled together (e.g., bundled together) to form a sensor kit. The plurality of sensors may be coupled to an electronic board. The electrical connection of at least two of the plurality of sensors in the sensor kit may be controlled (e.g., manually and / or automatically). For example, the sensor kit may be operatively coupled to or contain a controller (e.g., a microcontroller). The controller may control the on / off connection of the sensors to power. The controller may thus control the time (e.g., a period of time) during which the sensors will be operational.

[0170] In certain embodiments, one or more sensors in a sensor set provide readings. In some embodiments, the sensors are configured to sense parameters. Parameters may include temperature, particulate matter, volatile organic compounds, electromagnetic energy, pressure, acceleration, time, radar, lidar, glass breakage, movement, or gas. Gases may include inert gases. Gases may be inert. Gases may be gases harmful to ordinary people. Gases may be gases present in the ambient atmosphere (e.g., oxygen, carbon dioxide, ozone, chlorinated carbon compounds, or nitrogen). Gases may include radon, carbon monoxide, hydrogen sulfide, hydrogen, oxygen, and water (e.g., moisture). Electromagnetic sensors may include infrared, visible light, and ultraviolet sensors. Infrared radiation may be passive infrared radiation (e.g., blackbody radiation). Electromagnetic sensors may sense radio waves. Radio waves may include narrowband, wideband, or ultrawideband radio signals. Radio waves may include pulsed radio waves. Radio waves may include radio waves used for communication. Gas sensors can sense gas type, flow rate (e.g., velocity and / or acceleration), pressure, and / or concentration. Readings can have an amplitude range. Readings can also have a parameter range. For example, a parameter can be an electromagnetic wavelength, and the range can be the range of detected wavelengths.

[0171] In some embodiments, sensor data responds to the environment within the enclosure and / or to any inducement of change in that environment (e.g., any environmental disturbance). Sensor data may respond to transmitters (e.g., occupants, appliances (e.g., heaters, coolers, ventilation equipment, and / or vacuum cleaners), or openings) operatively coupled to the enclosure (e.g., within the enclosure). For example, sensor data may respond to air conditioning ducts or open windows. Sensor data may respond to activities occurring in the room. Activities may include human and / or non-human activities. Activities may include electronic, gaseous, and / or chemical activities. Activities may include sensory activities (e.g., visual, tactile, olfactory, auditory, and / or gustatory). Activities may include electronic and / or magnetic activities. Activities may be perceptible to a person. Activities may be imperceptible to a person. Sensor data may respond to occupants within the enclosure, the flow rate of a substance (e.g., gas), the pressure of a substance (e.g., gas), and / or temperature.

[0172] In some embodiments, data is collected and / or processed (e.g., analyzed) from sensors within an enclosure (e.g., and a sensor set). Data processing may be performed by a sensor processor, a processor within a sensor set, by another sensor, by another set, in the cloud, by a controller processor, by a processor within the enclosure, by a processor outside the enclosure, by a remote processor (e.g., in different facilities), or by the manufacturer (e.g., for sensors, windows, and / or building networks). Sensor data may have a time indicator (e.g., may be timestamped). Sensor data may have a sensor location identifier (e.g., may be location-stamped). Sensors may be identifiably coupled to one or more controllers.

[0173] In some embodiments, processing data derived from sensors includes applying one or more models. The models may include mathematical models. Processing may include fitting the models (e.g., curve fitting). The models may be multidimensional (e.g., two-dimensional or three-dimensional). The models may be represented as graphs (e.g., 2D or 3D graphs). For example, the models may be represented as contour plots. Modeling may include one or more matrices. The models may include topological models. The models may be related to the topology of the sensed parameters within the enclosure. The models may involve the time variation of the topology of the sensed parameters within the enclosure. The models may be environment- and / or enclosure-specific. The models may consider one or more properties of the enclosure (e.g., size, openings, and / or environmental disturbances (e.g., emitters)). Processing of sensor data may utilize historical sensor data and / or current (e.g., real-time) sensor data. Data processing (e.g., using models) may be used to predict environmental changes within the enclosure and / or recommend mitigation, adjustment, or other responses to changes.

[0174] The position and / or stationary characteristics of an enclosure (e.g., the placement of walls and / or windows) can be used to measure the characteristics of a given environment. The position and / or stationary characteristics of an enclosure can be derived independently (e.g., from third-party data and / or from non-sensor data). The position and / or stationary characteristics of an enclosure can be derived using data from one or more sensors placed in the environment. When the environment is minimally disturbed relative to the measured environmental characteristics (e.g., when no one is present in the environment, and / or when the environment is quiet), some sensor data can be used to sense the position of (e.g., stationary and / or non-stationary) objects to determine the environment. Determining the position of objects includes determining occupancy (e.g., human presence) in the environment. Distance and / or orientation-related measurements can utilize sensors such as radar and / or ultrasonic sensors. Distance and orientation-related measurements can originate from sensors that are not traditionally associated with orientation and / or distance.

[0175] The sensors in a sensor set can be organized into a sensor module. The sensor set may include a circuit board, such as a printed circuit board, to which several sensors are glued or attached. Sensors can be removed from the sensor module. For example, sensors can be inserted into and / or removed from the circuit board. Sensors can be individually activated and / or deactivated (e.g., using a switch). The circuit board may contain a polymer. The circuit board may be transparent or opaque. The circuit board may contain a metal (e.g., an elemental metal and / or a metal alloy). The circuit board may contain a conductor. The circuit board may contain an insulator. The circuit board may contain any geometry (e.g., rectangular or elliptical). The circuit board may be configured (e.g., may have a shape) to allow the set to be placed in a vertical frame (e.g., a window frame). The circuit board may be configured (e.g., may have a shape) to allow the set to be placed in a frame (e.g., a door frame and / or window frame). The vertical frame and / or frame may include one or more holes to allow the sensors to obtain (e.g., accurate) readings. The circuit board may include electrical connection ports (e.g., sockets). The circuit board can be connected to a power source (e.g., electricity). The power source can be renewable or non-renewable.

[0176] Figure 6 illustrates an example of a system 600 including a sensor set organized into a sensor module. Sensors 610A, 610B, 610C, and 610D are shown as included in a sensor set 605. The sensor set organized into a sensor module (including sensor set 605) may include at least 1, 2, 4, 5, 8, 10, 20, 50, or 500 sensors. A sensor module may include a number of sensors in the range of any of the aforementioned values ​​(e.g., about 1 to about 1000, about 1 to about 500, or about 500 to about 1000). The sensors in the sensor module may include sensors configured or designed to sense parameters including: temperature, humidity, carbon dioxide, particulate matter (e.g., between 2.5 µm and 10 µm), total volatile organic compounds (e.g., via changes in voltage potential caused by surface adsorption of volatile organic compounds), ambient light, audio noise level, pressure (e.g., gas and / or liquid), acceleration, time, radar, lidar, radio signals (e.g., ultra-wideband radio signals), passive infrared, glass breakage, or motion detectors. The sensor set (e.g., 605) may include non-sensor devices such as buzzers and light-emitting diodes. Examples of sensor sets and their uses can be found in U.S. Patent Application No. 16 / 447,169, filed June 20, 2019, entitled "Sensing and Communication Unit for Optically Switchable Wind Systems," which is incorporated herein by reference in its entirety.

[0177] In some embodiments, increasing the number and / or type of sensors can be used to increase the probability that one or more measured attributes are accurate and / or that a specific event measured by one or more sensors has occurred. In some embodiments, sensors in a sensor set can cooperate with each other. In one example, radar sensors in a sensor set can determine that several individuals are present in an enclosure. A processor (e.g., processor 615) can determine that the detection of several individuals in an enclosure is positively correlated with an increase in carbon dioxide concentration. In one example, the processor can access memory to determine that an increase in detected infrared energy is positively correlated with an increase in temperature, such as that detected by a temperature sensor. In some embodiments, a network interface (e.g., 650) can communicate with other sensor sets similar to the sensor set. The network interface can also communicate with a controller.

[0178] Individual sensors in the sensor set (e.g., sensor 610A, sensor 610D, etc.) may include and / or utilize at least one dedicated processor. The sensor set may utilize a remote processor (e.g., 654) using wireless and / or wired communication links. The sensor set may utilize at least one processor (e.g., processor 652), which may represent a cloud-based processor coupled to the sensor set via a cloud (e.g., 651). The processors (e.g., 652 and / or 654) may be located in the same building, in different buildings, in buildings owned by the same or different entities, in facilities owned by the manufacturer of the window / controller / sensor set, or in any other location. In various embodiments, as indicated by the dashed lines in FIG6, the sensor set 605 does not need to include a separate processor and network interface. These entities may be separate entities and operatively coupled to the set 605. The dashed lines in FIG6 indicate features selected as appropriate. In some embodiments, the onboard processing and / or memory of one or more sensor sets can be used to support other functions (e.g., by allocating set memory and / or processing power to the building’s network infrastructure).

[0179] In some embodiments, a plurality of sensors of the same type may be distributed within an enclosure. At least one of the plurality of sensors of the same type may be part of a set. For example, at least two of the plurality of sensors of the same type may be part of at least two sets. The sensor sets may be distributed within the enclosure. The enclosure may contain a conference room. For example, a plurality of sensors of the same type may measure environmental parameters in the conference room. In response to the measurement of the environmental parameters of the enclosure, a parametric topology of the enclosure may be generated. The parametric topology may be generated using output signals from sensors of any type, such as those disclosed herein. The parametric topology may be generated for any enclosure of a facility such as a conference room, corridor, restroom, cafeteria, garage, auditorium, storeroom, storage room, machine room, and / or elevator.

[0180] In some embodiments, the sensor set is distributed throughout the enclosure. Sensors of the same type may be distributed throughout the enclosure, for example, to allow measurement of environmental parameters at various orientations within the enclosure. Sensors of the same type may measure gradients along one or more dimensions of the enclosure. Gradients may include temperature gradients, environmental noise gradients, or any other variation (e.g., increase or decrease) of the measured parameter that varies with the orientation of the point. Gradients can be used to determine if the sensor is providing an erroneous measurement (e.g., the sensor is faulty). Figure 8 illustrates an example of a configuration of sensor sets in an enclosure, diagram 890. In the example of Figure 8, set 892A is located at a distance D1 from vent 896. Sensor set 892B is located at a distance D2 from vent 896. Sensor set 892C is located at a distance D3 from vent 896. Vent 896 may correspond to an air conditioning vent, representing a relatively constant source of cooling air and a relatively constant source of white noise. Therefore, temperature and noise measurements can be performed by the sensor set 892A.

[0181] Alternatively or additionally, sensor set 892A can perform current and / or voltage measurements for one or more IGUs. These current and / or voltage measurements can be correlated with color shifts in one or more IGUs. These current and / or voltage measurements can be compared with fault signatures of one or more IGUs to identify existing IGU faults and / or predict future IGU faults. Current and voltage measurements performed by sensor 892A are displayed by output readout distribution 894A. Output readout distribution 894A indicates relatively low current and relatively medium voltage. Current and voltage measurements performed by sensor set 892B are displayed by output readout distribution 894B. Output readout distribution 894B indicates slightly higher current and slightly lower voltage. Current and voltage measurements performed by sensor set 892C are displayed by output readout distribution 894C. Output readout distribution 894C indicates a current slightly higher than the current measured by sensors 892B and 892A. The voltage measured by sensor set 892C indicates a lower level than the voltage measured by sensor sets 892A and 892B. In one example, if the current measured by sensor set 892C indicates a significantly higher current than the current measured by sensor set 892A, one or more processors and / or controllers may interpret the current measured by sensor set 892C as an indication of a current or future IGU failure.

[0182] In some embodiments, the control system is configured to change the hue of a colorable window to a plurality of dissimilar hue states, for example, at least 2, 3, 4, 5, 6, or 10 hue states. In some embodiments, the control system is configured to continuously change the hue of the colorable window. In some instances, dissimilar hue states include a desaturated state (hue 1), a darker hue state (hue 2), an even darker hue state (hue 3), and the darkest hue state (hue 4). For a given hue transition of IGI size, (i) the number of charges required to complete the transition and (ii) the voltage required to transfer the charges should remain constant over time. When a larger (or increasingly larger) voltage difference and / or charge transfer is required to achieve the hue transition, an IGI failure may be imminent or occur.

[0183] Figure 9A shows an example of a graph depicting the charge and time for an IGI transitioning from its decolorized state (T1) to its darkest hue (T4). This IGI began to deviate from normal operation on May 22, 2020, due to less change in migration when the same applied voltage difference was applied, and therefore received a fault prediction. Figure 9B shows an example of a graph depicting the leakage current and time for an IGI transitioning from T1 to T4. This IGI shows a skewed increase in current at time 900 and thereafter, and received a fault prediction. The hue transition from T1 to T4 may (but does not need to) involve one or more intermediate hues between T1 and T4. For example, such intermediate hues may include a second hue T2 and a third hue T3. In Figure 9A, charge is shown in coulombs (C). In Figure 9B, leakage current is shown in milliamperes (mA). The horizontal axis representing time in Figures 9A and 9B is scaled and automatically generated based on available data from the window controller (WC) coupled to the colorable window. Each colorable window has a unique identifier (e.g., window identifier (ID)), and each window controller has a unique identifier. Each point on the graph represents a full tone transition of a specified type, which in this example is the tone transition from T1 to T4. For the window controller-colorable window coupling, a full transition from T1 to T4 exists in the database for approximately one and a half years (from December 1, 2018 to June 10, 2020) depicted in the graphs of Figures 9A and 9B. Depending on the IGU, one or more full transitions of a given type (such as T1 to T4) may exist daily. Transitions that do not progress as expected can be described as 'non-characteristic'. Non-characteristic tone transitions are deviations of the colorable window in question from normal switching parameters (within the error range of normal).

[0184] In some embodiments, the sensor system is used in conjunction with artificial intelligence (AI) to predict and detect malfunctions of colorable windows. Over time, a large amount of data can accumulate from the colorable window controller. This data may relate to current and / or voltage measurements applied to facilitate hue changes in one or more windows. Measurement values ​​may be stored in a database. In addition to the measured values, the measurements may also include: (i) timestamps, (ii) datestamps, (iii) controller IDs, (iv) colorable window IDs, and / or (v) measurement types. The architecture can be configured to retrieve window controller data from one or more databases, aggregate this data, and use the data to analyze and / or predictively maintain windows, for example, those displaying fault signatures. Statistical measurements of current and / or voltage can be used to identify fault signatures. The ID may contain a serial identifier for the device and may be alphanumeric. The ID may be (e.g., subsequently) hashed. For example, the ID may be converted using hexadecimal or a basic 64-character set.

[0185] Currently, static rules (e.g., excluding learning systems) are sometimes used for alarms of colorable window malfunctions (e.g., using threshold values ​​and / or functions) in an attempt to minimize false readings. Such static rules and threshold values ​​can provide a rigid framework that sometimes fails to adequately predict the malfunction of a colorable window before its failure becomes apparent.

[0186] In some embodiments, a method for alarming a tinted window malfunction is implemented using at least one controller and / or software. The tinted window may include an IGU, electrochromic glass, and / or mechanically controlled shading. Current, voltage, and / or sensor measurements may be acquired, and these measurements are related to changing the tinted window of the enclosure. The facility may include several buildings. A building may include one or more rooms. The enclosure may include the facility, a building, or a portion thereof (e.g., a corridor or room). Sensors may include acoustic, motion, vibration, temperature, and / or electromagnetic sensors (e.g., light sensors). Sensors may include transmittance sensors. Sensors may be sensitive to visible light, IR, and / or UV radiation. Tinted glass may act as a sensor. Sensors may include any sensors disclosed herein. Integration (e.g., integral) and / or derivation (e.g., derivative) of the measurements (e.g., voltage and / or current) may be utilized. Associated data may be accessed from various sensors placed in and / or on the facility. This data may be organized (e.g., assigned, categorized, and / or reorganized). The reliability of the data used (e.g., at least in part based on) associated data, measurements (e.g., current and / or voltage, and / or other sensor measurements) can be determined. Measurements may be accumulated in at least one database, for example, during normal operation of sensors and / or devices (e.g., colorable windows) in the facility. The determined reliability and the obtained current, voltage, and / or other sensor measurements can be adjusted. Adjusted sensor measurements may be used, for example, to assign and / or update reliability values ​​to one or more sensors.

[0187] In some embodiments, sensor measurements are processed by considering the enclosure (or any part thereof), historical readings, benchmarks, and / or modeling to produce results. Current, voltage, and / or other sensor measurements can be used as inputs (e.g., learning set inputs) to a learning module trained to recognize signatures in cases of faults within a colorizable window and / or signatures in cases of other faults. Inputs can be used to fine-tune the learning module's computational scheme. For example, inputs can be used to optimize parameters (e.g., function weights and / or function thresholds) of various functions used in the computational scheme.

[0188] Data analysis (e.g., analysis of sensor measurements) can be performed by a machine-based system (e.g., a circuit). The circuit may have a processor. Sensor data analysis may utilize artificial intelligence. Sensor data analysis may rely on one or more models (e.g., a mathematical model). In some embodiments, sensor data analysis includes linear regression, least squares fitting, Gaussian process regression, kernel regression, nonparametric multiplicative regression (NPMR), regression tree, local regression, semiparametric regression, isotonic regression, multivariate adaptive regression spline (MARS), logistic regression, robust regression, multinomial regression, stepwise regression, ridge regression, lasso regression, elastic network regression, principal component analysis (PCA), singular value decomposition, fuzzy measure theory, Borel measure, Han measure, risk-neutral measure, Lebesgue measure, data processing grouping method (GMDH), Naive Bayes classifier, k-nearest neighbor algorithm (k-NN), support vector machine (SVM), neural network, support vector machine, classification and regression tree (CART), random forest, gradient boosting, or generalized linear model (GLM) techniques.

[0189] In some embodiments, the learning module incorporates machine learning. The learning module may include a multi-layered neural network (e.g., a deep learning algorithm). The learning module may include an infinite number of layers of finite size, for example, progressively extracting higher-level features from raw (e.g., sensor) input measurements. The layers in the multi-layered neural network may be hierarchical (e.g., the output of each layer may be a higher-level abstraction from the input of previous layers). The learning module may utilize exploratory techniques (e.g., overall model and sensor data) that will thus accelerate the output of reliable predictions. The learning module may be optimized for prediction accuracy and / or computational speed. The learning module may take into account the neural network size (number of layers and number of units in each layer), learning rate, and / or initial weights (e.g., weights of artificial neurons and / or algorithms (when several algorithms are used to produce results)). The learning module may learn from measurements of faults in a colorable window using sensor measurements (e.g., real-time, historical, or synthetic sensor measurements).

[0190] In some embodiments, the learning module includes algorithms and / or computations. The learning model may include machine learning, artificial intelligence (AI), and / or statistical validation layers. The learning module may be trained to identify fault thresholds (e.g., values ​​or functions). Alternatively, the learning module may not be trained to identify fault thresholds.

[0191] In some embodiments, filters (e.g., convolutional filters) are applied to teach one or more failure modes of the colorizable window of the learning module. Filters can be applied in the temporal domain. Data loss can be minimized. Data loss can be attributed to misclassification and / or labeling errors (e.g., through data tracing). The learning module can be trained using historical, real-time, and / or synthetic data used as the training set. The time frame of the learning module can be adjusted using a near-time frame during which colorizable window failures are observable. A machine learning (ML) set can be used to implement the learning module. The ML set can include, for example, multiple models working together using a voting scheme (e.g., at least about 2, 3, 4, 5, 7, or 10 models). Different weights can be assigned to at least two of the multiple models. Equal weights can be assigned to at least two of the multiple models. The ML set can include at least one model. The use of the ML set can be automatic, scheduled, and / or controlled.

[0192] In some embodiments, the learning module also has a verification mechanism configured to perform data management. The learning module may utilize one or more models. A model (or combination of models) may be more suitable in one situation than in another. For example, rare cases may require the use of a specific model. The model may use adaptive synthetic oversampling. The model may use deep learning techniques (e.g., convolutional neural networks). The model may use AI techniques excluding deep learning algorithms and / or novel AI techniques including deep learning algorithms. The learning set may contain real data. The learning set may contain synthetic data. Synthetic data may be synthesized using real data. For example, synthetic data may use a real data backbone with different types of non-essential information (e.g., noise) added. Non-essential information (e.g., noise) may be characteristics of sensor measurements (e.g., faulty, malfunctioning, and / or properly functioning shadeable windows). The learning model may use temporal convolutional neural networks. The learning model may also have computational schemes for analyzing visual imaging. The learning model can use data related to the hue transition of a first window in a first enclosure (e.g., a first facility) or from another second enclosure (e.g., from the same first facility as another second facility). The second facility may be geographically separated from the first facility (e.g., remote), and the first tintable window is located within that first facility. The tintable window is oriented outwards in a first direction. Data related to the second window of the second enclosure may be oriented in the same first direction or in a different second direction. The learning model can use data from tintable windows of the same type (e.g., electrochromic glass with the same type of layering, the same surface area, and / or the same basic length scale). In this example, the data should have the same transition type (e.g., from a first hue T1 to a second hue T2). The basic length scale (abbreviated herein as "FLS") may include length, width, height, radius, or the radius of a delimiting circle.

[0193] In some embodiments, the results and / or reliability values ​​are used to predict subsequent colorable window failures. Colorable window failures can be predicted for a second set of colorable windows (including at least one colorable window). Outlier data can be detected. Future readings of sensor measurements can be predicted.

[0194] Figure 10 illustrates an example of flowchart 1000, which describes the acquisition of one instance of measurements related to the hue transition of one or more colorable windows, and the application of these measurements to a learning module to predict a near-time frame during which a coloring fault can be observed. In block 1002, current and / or voltage measurements related to the transition of the colorable window are acquired. In block 1004, the current and / or voltage measurements are applied as input to a learning module trained to recognize the signature of the coloring fault. The learning module may include a computational scheme (e.g., an algorithm). The learning model may include machine learning, artificial intelligence (AI), and / or statistical validation. Next, in block 1006, filters (e.g., mathematical filters) are applied in the time domain to teach the learning module one or more fault modes of the colorable windows. In block 1008, the learning module is trained using historical, real-time, and / or synthetic data. Next, in block 1010, the data is applied to the learning module to predict faults in a second set of colorable windows. In block 1012, the timeframe of the learning module is adjusted using a proximity timeframe during which shading faults can be observed.

[0195] In some embodiments, the acquired data is merged into a storage library and / or into multiple communication-coupled storage libraries. All data measurements may be maintained in one or more storage libraries. For example, analytical queries may be performed based on the Controller Area Network ID (hereinafter abbreviated as "CAN ID," which is a form of network ID), the colorizable window ID (e.g., window ID), the IGU and / or colorizable glass size (e.g., FLS), the transition type, and the time frame. Analytical queries may be performed within the same facility or across facilities (e.g., across locations). Scheduling may be executed for automatic retrieval. Data retrieval may be performed according to a schedule or arbitrarily. Automatically generated reports on colorizable window performance may be performed per facility or across facilities. Learning modules may be applied to the data to generate fault alarms and / or reports, for example, using acquired current, voltage, and / or other sensor data. The learning module can learn specific fault signatures for the following: (i) facility, (ii) layer construction type of electrochromic glass, (iii) type of tinted window, (iv) surface area of ​​window, (v) FLS of window, (vi) hue change type, (vii) facade orientation of the tinted window, (viii) geographical location of facility, (ix) external weather conditions, and (x) temperature, pressure, and / or noise (internal or external) to which the window is exposed. Pressure includes, for example, pressure gradients experienced during explosions, earthquakes, and / or winds (e.g., tornadoes). Noise may include loud noise, such as thunder, gunshots, and / or explosions. The learning module can utilize historical and / or real-time measurements from other sites / to other sites. The learning module can add noise to the data.

[0196] In some embodiments, the learning module goes through several stages. For example, a low-fidelity stage and a high-fidelity stage. Compared to the low-fidelity stage, the high-fidelity stage can enable better prediction of faults. Compared to the low-fidelity stage, the high-fidelity stage can have a larger, more diverse, and / or more accurate training set.

[0197] Figure 11 illustrates an example of flowchart 1100, which describes an example of a method for predicting faults and learning fault signatures for colorable window faults, with a lower fidelity stage 1130 and a higher fidelity stage 1140. In block 1110, voltage, current, and / or other sensor data are merged into at least one storage library. The data may be related to a colorable window (e.g., voltage and / or current used to achieve hue transitions in the colorable window). Next, in block 1112, the data measurements are maintained in the storage library. In block 1114, at least one learning module is applied to the data to predict faults and, if appropriate, generate one or more fault alarms and / or reports. In block 1116, a verification mechanism is incorporated into the learning module for data management. Then, in block 1118, historical, real-time, and / or synthetic measurements from this and / or other sites with colorable windows are used to learn fault signatures. These fault signatures may be specific (e.g., as disclosed herein, they may be site-specific). The ML module can search for specificities (e.g., FLS, location, and / or weather specificities). For example, in block 1120, which is selected as appropriate, the nature of specificities and fault signatures can be learned. In block 1122, which is selected as appropriate, noise is added to the data to generate synthetic data. In block 1124, the data is compared with the learned fault signatures to predict faults and, if appropriate, generate fault alarms and / or reports.

[0198] In some embodiments, event data is synthesized for a learning set to be used by the learning module. This synthesized data may cover rare, anomalous, and / or infrequently observed events, for example, to allow the ML module to accurately identify subsequent uncommon events when they occur. The synthesized data may use historical, real-time, and / or synthesized event data from this and / or other sites with colorable windows to learn fault signatures. The event data may be compared with the learned fault signatures to predict faults. The ML module may perform calculations real-time and / or during periods of low building activity (e.g., at night, and / or on holidays). For example, a baseline (e.g., a threshold value) may change over time, and therefore, the baseline (e.g., a threshold function) applied in the ML module may be dynamic over time.

[0199] In some embodiments, leakage current (e.g., open-circuit voltage Voc) can be used as an indicator of a problematic colorizable window (e.g., containing an electrochromic device). The voting set can be communicatively coupled to a statistical validation layer to perform current leakage degradation testing. In some embodiments, voting is a set method that can be used for classification. A first operation can be to create a multi-classification and / or regression model using a training dataset. At least one of several base models can be created using different splits of the same training dataset and the same computation scheme (e.g., algorithm) or using the same dataset with different computation schemes. In majority voting (sometimes referred to as multiple voting), each model makes a prediction (vote) for each test example. The final output prediction is the prediction that receives more than half the votes. If no prediction receives more than half the votes, the set method may not make a stable prediction for that example. In such cases, the prediction with the most votes (even if this prediction receives less than half the votes) can be used as the final prediction. Unlike majority voting, where each model has equal weight (e.g., equal weight in the overall scheme), the importance of one or more models can be increased (e.g., their relative weights increased). In weighted voting, the predictions of the better model are multiplied by its correspondingly higher weight (e.g., multiple counts) relative to the worse model.

[0200] In simple averaging, an average prediction is calculated for each example in the test dataset. This method can reduce overfitting and / or create a smoother regression model.

[0201] In some embodiments, changes in leakage current over time serve as an indicator of potential faults in a colorizable window. AI and / or statistical verification layers can look for leakage current degradation over time. These layers can also look for leakage current degradation and / or other fault characteristics (e.g., hue transition time and hue transition peak current may depend on the window size; leakage current may not depend on the window size).

[0202] In some embodiments, the controller selects a facility (or guides the selection of a facility) to extract metrics for a given time period (e.g., the most recent nine (9) months). The controller may maintain a work history (e.g., historical data) (or guides the maintenance of a work history). Controller data can be used to estimate the health of a colorable window. The controller may estimate the health of a colorable window or guide the estimation of the health of a colorable window. For example, by using a learning module to track failures to track unreplaced field failures (the percentage of all uniquely identifiable window IDs). For example, by tracking any problems identified by ML, AI, and / or statistical validation layers. The controller may identify one or more colorable windows at risk of failure (or guides the identification of one or more colorable windows at risk of failure). The controller estimates the severity of the risk (at the model set confidence level) (or guides the estimation of the severity of the risk). The controller may identify the predicted failure date and / or the predicted duration until the failure occurs (or guides the identification of the predicted failure date and / or the predicted duration). The controller can enable or guide the detection of any colorable window (e.g., an integrated glass unit - IGU) that exhibits a deteriorating current and / or voltage signature. When the ML module identifies a fault event, the controller can automatically generate an alarm and / or report (or guide the automatic generation of an alarm and / or report). If deployed in real-time at the edge, the controller can send alarm, report, and / or any other action messages (or guide the sending of alarm, report, and / or any other action messages). The controller can schedule the detection, maintenance, manufacturing, and / or storage of colorable windows of a risky type (or guide the scheduling of detection, maintenance, manufacturing, and / or storage) (e.g., for convenience after a risk occurs and / or when maintenance is scheduled). The controller may include a processor.

[0203] In some embodiments, the fault itself is represented on different time scales. The fault may be represented differently over time (e.g., gradually decreasing versus rapidly decreasing). Calibration control can be used to manage some faults (e.g., a window may require different (e.g., more) currents and / or voltages for the same hue level as previously required). The controller may tag and / or classify fault types and / or severity (e.g., estimate the risk of the fault). Examples of fault types are corrosive faults and irreversible shading. The controller may provide visualization over time of one or more (e.g., all) transition types for all window controllers of one or more (e.g., all) measures. Alarms and / or reports may be associated with fault events to automatically report problems for situation resolution. The controller may perform or direct the execution of the operations disclosed herein.

[0204] In some embodiments, one or more colorable window metrics are measured. Metrics may include transition time. Transition time may be the complete transition time (e.g., in minutes) required to implement a change from a first hue state to a second hue state (e.g., from T1 to T4). Hue state may be characterized by color, hue, transparency level, and / or absorption. The first hue state may be the least tinted state of the window. The second hue state may be the most tinted state of the window. The first hue state may be an intermediate state between the least tinted and most tinted states of the window, wherein the first hue state is less tinted than the second hue state. The second hue state may be an intermediate state between the least tinted and most tinted states of the window, wherein the first hue state is less tinted than the second hue state. In some instances, only data from complete transitions (e.g., uninterrupted transitions from the first hue state to the second hue state) may be considered.

[0205] Figure 12 is a flowchart illustrating an example of a method for generating alarms and / or reports in response to the identification of a colorable window at risk of failure. In block 1210, a learning module is used to simulate events related to rare conditions to aid in the subsequent identification of similar events at future times. In block 1220, calculations are performed using the learning module in real time and / or during periods of low activity within the enclosure. In block 1240, the learning module is used to identify leakage current, voltage, and / or current variations (e.g., to look for IPU leakage current degradation). In block 1250, selected as appropriate, a location (e.g., facility) is chosen for extracting measurements over a given time period. In block 1260, the health of at least one colorable window is estimated by tracking failures using the learning module. In block 1270, any colorable window at risk of failure is identified. The risk of failure, the timing of failure, and / or the severity of failure can be estimated. In block 1280, reports and / or alarms are generated in response to the identification of fault risks and / or the timing of faults. Reports and / or alarms can be sent by sending alarm or action messages, and / or by providing visualization of IGU metrics across time for the type of change. Next, in block 1290, reports and / or alarms are associated with fault events. This association can be used for the purposes of automating fault detection, rapid fault resolution, and / or preventing larger and / or more obvious faults in colorable windows. This association can alert colorable windows that are predicted to fail, similar to the storage of colorable windows. This association can help, for example, coordinate the replacement of windows that are predicted to fail before they completely and / or obviously fail.

[0206] Figure 13 illustrates an example of a flowchart illustrating a method for processing sensor readings (e.g., other than current, voltage, and / or Voc) to produce results. At block 1310, sensor readings are obtained from one or more sensors. These sensor readings may be obtained from one or more sensor sets or from one or more individual sensors. At block 1320, the sensor readings are processed (e.g., by considering enclosures, historical readings, benchmarks, and / or modeling) to produce results. In block 1330, the results are used to detect outlier data to predict subsequent tintable glass failures and / or to predict future readings from one or more sensors. Any of the sensor results (e.g., including current, voltage, and / or Voc) can be used to extract usable (e.g., characteristic) noise data, for example, to synthesize data for learning sets.

[0207] Figure 14 illustrates an example flowchart of a method for determining the reliability of sensor readings. At block 1455, sensor readings are obtained from one or more sensors (e.g., housed in an enclosure). Sensor readings can be obtained from a set of sensors and / or from individual sensors. At block 1460, correlation data from other sensors (e.g., housed in an enclosure) is accessed. At block 1465, the reliability of the obtained sensor readings is determined at least in part based on the accessed correlation data. At block 1470, the obtained sensor readings are adjusted at least in part based on the determined reliability of the obtained sensor readings. At block 1475, the reliability values ​​of one or more sensors are assigned or updated at least in part based on the adjusted obtained sensor readings. Next, at block 1477, the reliability values ​​are used to adjust predictions of subsequent colorizable window failures.

[0208] Examples of sensors, their calibration, operation, and control can be found in U.S. Provisional Patent Application No. 62 / 967,204, entitled "Sensor CALLIBRATION AND OPERATION," filed January 29, 2020, which is incorporated herein by reference in its entirety. Examples of sensors, their coexistence, operation, and control can be found in U.S. Provisional Patent Application No. 63 / 079,851, entitled "DEVICE ENSEMBLES AND COEXISTENCE MANAGEMENT OF DEVICES," filed September 17, 2020, which is incorporated herein by reference in its entirety.

[0209] Figure 15 illustrates an example of a controller 1505 for controlling one or more sensors. The controller 1505 includes a sensor correlator 1510, a model generator 1515, an event detector 1520, a processor 1525, and a network interface 1550. The sensor correlator 1510 is used to detect correlations between or among various sensor types. For example, an infrared radiation sensor measuring an increase in infrared energy may be positively correlated with an increase in temperature. The sensor correlator 1510 can establish correlation coefficients, such as coefficients for negatively correlated sensor readings (e.g., correlation coefficients between -1 and 0). For example, the sensor correlator 1510 can establish coefficients for positively correlated sensor readings (e.g., correlation coefficients between 0 and +1).

[0210] In some embodiments, multiple devices (e.g., sensors, transmitters, actuators, transmitters, and / or receivers) are integrated into a common assembly (such as onto a common circuit board). This assembly may have a single housing (e.g., a cover). One or more circuit boards may be housed within a single housing to form a device assembly. The circuit boards within the housing may be physically coupled or not physically coupled (e.g., using wiring). The boards within the housing may be communicatively coupled. The communicative coupling may be, for example, using a network, directly or indirectly, for example, wired or wireless communication. The common assembly may be referred to herein as a "set".

[0211] In some embodiments, multiple assemblies (e.g., clusters) containing such elements are deployed close to each other. Close proximity of at least two devices in the same or different clusters may result in one or more disadvantages in their operation. These one or more disadvantages may occur during their normal (e.g., designed and / or intended) operation. One or more disadvantages may result from (i) mutual interference between devices in the cluster (e.g., intra-assembly interference) and / or (ii) mutual interference between devices in different clusters (e.g., inter-assembly interference). The cluster may include or be operatively coupled to at least one controller. At least one controller may include a digital architecture system controller. At least one controller may be housed in an assembly housing (referred to herein as a “housing” or “enclosure”). The enclosure may be suitable for mounting to windows, walls, ceilings, or any other structure and / or fixtures in an enclosed space (e.g., a building, facility, or room) to perform various functions. These functions may include tinted window control, environmental monitoring, building management, video communication, audio communication, lighting (e.g., optical communication), and / or wireless networking. For example, interference may occur during simultaneous operation of the elements. Interference can cause sensor inaccuracy, false readings, sensor saturation, loss of consistency, signal transmission failure, power imbalance, and any combination thereof.

[0212] In some embodiments, a plurality of devices (e.g., modules) are integrated into a common housing, for example, to provide a useful suite of functions to be offered to a particular user. These functions may improve building efficiency (e.g., energy and / or finance), improve occupant health, improve occupant well-being, provide a networking platform, and / or provide a communication platform. Examples of various devices (e.g., modules) included in the integrated assembly include temperature sensors, humidity sensors, carbon dioxide sensors, particulate (e.g., dust) sensors, volatile organic compound sensors, ambient light sensors, glass breakage sensors, microphones, speakers / buzzers, digital amplifiers, cameras, video displays, LED indicators, Bluetooth transceivers, ultra-wideband transceivers, passive infrared motion sensors, radar sensors, accelerometers, and pressure sensors. The integrated assembly may include power conditioning components, processing units, memory, and / or network interfaces. In some embodiments, the assembly has a form factor suitable for installation in various orientations within an enclosure. For example, a corresponding mounting adapter may be provided for mounting the assembly to at least a portion of a fixture, such as a window frame, building wall, or roof.

[0213] The controller can monitor and / or guide changes in the operating conditions (e.g., physical) of the devices, software, and / or methods described herein. Control may include regulation, manipulation, limitation, guidance, monitoring, adjustment, modulation, alteration, modification, constraint, inspection, directing, or management. (E.g., via the controller) Control may include attenuation, modulation, alteration, management, suppression, discipline, regulation, constraint, supervision, manipulation, and / or guidance. Control may include controlling control variables (e.g., temperature, power, voltage, and / or distribution). The control may include real-time or offline control. Calculations utilized by the controller may be performed real-time and / or offline. The controller may be a manual or non-manual controller. The controller may be an automatic controller. The controller may operate on request. The controller may be a programmable controller. The controller may be programmable. The controller may include a processing unit (e.g., CPU or GPU). The controller may receive input (e.g., from at least one sensor). The controller may deliver outputs. The controller may include multiple (e.g., sub-)controllers. The controller may be part of a control system. The control system may include a main controller, floor controllers, and local controllers (e.g., enclosure controllers or window controllers). Controllers may receive one or more inputs. Controllers may generate one or more outputs. Controllers may be single-input single-output (SISO) controllers or multiple-input multiple-output (MIMO) controllers. Controllers may interpret the received input signals. Controllers may acquire data from one or more sensors. Acquisition may include receiving or extracting. Data may include measurement, estimation, determination, generation, or any combination thereof. Controllers may include feedback control. Controllers may include feedforward control. Control may include on-off control, proportional control, proportional-integral (PI) control, or proportional-integral-derivative (PID) control. Control may include open-loop control or closed-loop control. Controllers may include closed-loop control. Controllers may include open-loop control. Controllers may include a user interface. The user interface may include (or be operatively coupled to) a keyboard, keypad, mouse, touchscreen, microphone, voice recognition device, camera, imaging system, or any combination thereof. Outputs may include a display (e.g., a screen), a speaker, or a printer.

[0214] The methods, systems, and / or devices described herein may include a control system. The control system may communicate with any of the devices described herein (e.g., sensors). Sensors may be of the same or different types, for example, as described herein. For example, the control system may communicate with a first sensor and / or a second sensor. The control system may control one or more sensors. The control system may control one or more components of a building management system (e.g., lighting, security, and / or air conditioning systems). The controller may regulate at least one characteristic of the enclosure (e.g., environment). The control system may use any component of the building management system to regulate the enclosure environment. For example, the control system may regulate energy supplied by heating elements and / or cooling elements. For example, the control system may regulate the speed of air flowing into and / or out of the enclosure through vents. The control system may include a processor. The processor may be a processing unit. The controller may include a processing unit. The processing unit may be central. The processing unit may include a central processing unit (hereinafter referred to as a "CPU"). The processing unit may be a graphics processing unit (hereinafter referred to as a "GPU"). A controller or control mechanism (e.g., including a computer system) may be programmed to implement one or more methods of the present invention. A processor may be programmed to implement the methods of the present invention. The controller may control at least one component of the system and / or device disclosed herein. Outputs may include a display (e.g., a screen), a speaker, or a printer.

[0215] Figure 7 illustrates a schematic example of a computer system 700, which is programmed or otherwise configured to perform one or more operations of any of the methods provided herein. The computer system can control (e.g., guide, monitor, and / or regulate) various features of the methods, apparatus, and systems of the present invention, such as controlling heating, cooling, lighting, and / or ventilation of an enclosure, or any combination thereof. The computer system may be part of, or communicate with, any sensor or sensor set disclosed herein. The computer may be coupled to one or more mechanisms and / or any part thereof disclosed herein. For example, the computer may be coupled to one or more sensors, valves, switches, lights, windows (e.g., IGUs), motors, pumps, optical components, or any combination thereof.

[0216] A computer system may include a processing unit (e.g., 706) (also referred to herein as a "processor," "computer," and "computer processor"). The computer system may include memory or memory locations (e.g., 702) (e.g., random access memory, read-only memory, flash memory), electronic storage units (e.g., 704) (e.g., hard disk), communication interfaces for communicating with one or more other systems (e.g., 703) (e.g., network adapters), and peripheral devices (e.g., 705), such as caches, other memory, data storage, and / or electronic display adapters. In the example shown in Figure 7, memory 702, storage unit 704, interface 703, and peripheral device 705 communicate with processing unit 706 via a communication bus (solid line) such as a motherboard. The storage unit may be a data storage unit (or database) for storing data. The computer system may be operatively coupled to a computer network ("network") (e.g., 701) via the communication interface. The network may be the Internet, an inter-enterprise network, or an intranet and / or inter-enterprise network communicating with the Internet. In some cases, the network is a telecommunications and / or data network. The network may include one or more computer servers that enable distributed computing, such as cloud computing. In some cases, the network may be implemented as a peer-to-peer network using computer systems, which allows devices coupled to the computer systems to act as clients or servers.

[0217] The processing unit can execute a series of machine-readable instructions, which may be embodied in a program or software. These instructions may be stored in a memory location such as memory 702. These instructions may be directed to the processing unit, which may then be programmed or otherwise configured to implement the methods of the present invention. Examples of operations performed by the processing unit may include fetching, decoding, executing, and writing back. The processing unit may interpret and / or execute instructions. The processor may include a microprocessor, data processor, central processing unit (CPU), graphics processing unit (GPU), system-on-a-chip (SoC), coprocessor, network processor, application-specific integrated circuit (ASIC), application-specific instruction set processor (ASIP), controller, programmable logic device (PLD), chipset, field-programmable gate array (FPGA), or any combination thereof. The processing unit may be a part of a circuit, such as an integrated circuit. One or more other components of system 700 may be included in the circuit.

[0218] Storage units can store files, such as drives, libraries, and saved programs. Storage units can store user data (e.g., user preferences and user programs). In some cases, a computer system may include one or more additional data storage units located outside the computer system, such as on a remote server that communicates with the computer system via an intranet or the Internet.

[0219] A computer system can communicate with one or more remote computer systems via a network. For example, a computer system can communicate with a user's (e.g., an operator's) remote computer system. Examples of remote computer systems include personal computers (e.g., portable PCs), tablet PCs (e.g., Apple® iPad, Samsung® Galaxy Tab), telephones, smartphones (e.g., Apple® iPhone, Android-enabled devices, Blackberry®), or personal digital assistants. Users (e.g., client devices) can access the computer system via a network.

[0220] The method described herein can be implemented using machine-executable code (e.g., a computer processor) stored in electronic storage locations of the computer system, such as memory 702 or electronic storage unit 704. The machine-executable or machine-readable code can be provided in software form. During use, the processor 706 executes the code. In some cases, code can be retrieved from a storage unit and stored in memory for processor access. In other cases, electronic storage units can be omitted, and machine-executable instructions can be stored in memory.

[0221] The code may be pre-compiled and configured for use with a machine having a processor adapted to execute the code, or it may be compiled during runtime. The code may be supplied in a programming language, which may be selected so that the code can be executed in a pre-compiled or freshly compiled manner.

[0222] In some embodiments, the processor includes program code. The program code may be program instructions. The program instructions may cause at least one processor (e.g., a computer) to direct feedforward and / or feedback control loops. In some embodiments, the program instructions cause at least one processor to direct closed-loop and / or open-loop control schemes. Control may be based at least in part on one or more sensor readings (e.g., sensor data). A controller may direct a plurality of operations. At least two operations may be directed by different controllers. In some embodiments, different controllers may direct at least two of operations (a), (b), and (c). In some embodiments, different controllers may direct at least two of operations (a), (b), and (c). In some embodiments, a non-transitory computer-readable medium causes each different computer to direct at least two of operations (a), (b), and (c). In some embodiments, different non-transitory computer-readable media cause each different computer to direct at least two of operations (a), (b), and (c). Controllers and / or computer-readable media may direct any of the devices or components thereof disclosed herein. Controllers and / or computer-readable media may direct any operation of the methods disclosed herein.

[0223] In some embodiments, at least one sensor is operatively coupled to a control system (e.g., a computer control system). The sensor may include a light sensor, an acoustic sensor, a vibration sensor, a chemical sensor, an electrical sensor, a magnetic sensor, a flow sensor, a motion sensor, a speed sensor, a position sensor, a pressure sensor, a force sensor, a density sensor, a distance sensor, or a proximity sensor. The sensor may include a temperature sensor, a weight sensor, a material (e.g., powder) content sensor, a unit sensor, a gas sensor, or a humidity sensor. The unit sensor may include a measurement sensor (e.g., height, length, width, angle, and / or volume). The unit sensor may include a magnetic, acceleration, orientation, or optical sensor. The sensor may transmit and / or receive sound (e.g., echo), magnetic, electronic, or electromagnetic signals. Electromagnetic signals may include visible light, infrared, ultraviolet, ultrasonic, radio wave, or microwave signals. The gas sensor may sense any of the gases described herein. The distance sensor may be one type of unit sensor. Distance sensors may include optical sensors or capacitive sensors. Temperature sensors may include calorimeters, bimetallic strips, heat meters, exhaust thermometers, flame detectors, Gardon meters, Golay cells, heat flux sensors, infrared thermometers, microcalorimeters, microwave radiometers, net radiometers, quartz thermometers, resistance temperature detectors, resistance thermometers, silicon bandgap temperature sensors, special sensors (microwave / imagers), temperature gauges, thermistors, thermocouples, thermometers (e.g., resistance thermometers), or pyrometers. Temperature sensors may include optical sensors. Temperature sensors may include image processing. Temperature sensors may include cameras (e.g., IR cameras, CCD cameras). Pressure sensors may include barometers, barometers, booster gauges, Bourdon gauges, hot filament ionizers, ionizers, McLeod gauges, U-tube manometers, permanent downhole pressure gauges, pressure gauges, Pirani gauges, pressure sensors, pressure gauges, tactile sensors, or time-pressure gauges. Position sensors may include growth meters, capacitive displacement sensors, capacitive sensors, free-fall sensors, gravimeters, gyroscope sensors, collision sensors, inclinometers, integrated circuit piezoelectric sensors, laser rangefinders, laser surface velocimeters, LiDAR, linear encoders, linear variable differential transformers (LVDTs), liquid capacitive inclinometers, odometers, photoelectric sensors, piezoelectric accelerometers, rate sensors, rotary encoders, rotary variable differential transformers, synchros, impact detectors, impact data loggers, tilt sensors, tachometers, ultrasonic thickness gauges, variable magnetoresistive sensors, or speed receivers.Optical sensors may include charge-coupled devices, colorimeters, contact image sensors, electro-optic sensors, infrared sensors, dynamic inductive detectors, light-emitting diodes (e.g., light sensors), optically addressable potential sensors, Nichols radiometers, fiber optic sensors, optical position sensors, light detectors, photodiodes, photomultiplier tubes, photocrystals, photodetectors, photoionization detectors, photomultipliers, photoresistors, optical switches, phototubes, scintillation counters, Shack-Hartmann wavefront sensors, single-photon burst diodes, superconducting nanowire single-photon detectors, transition edge sensors, visible light photon counters, or wavefront sensors. One or more sensors may be connected to a control system (e.g., to a processor, to a computer).

[0224] While preferred embodiments of the invention have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. The invention is not intended to be limited to the specific examples provided in the specification. Although the invention has been described with reference to the foregoing specification, the description and illustration of the embodiments herein are not intended to be construed as limiting. Numerous variations, modifications, and substitutions will now occur to those skilled in the art without departing from the invention. Furthermore, it should be understood that all forms of the invention are not limited to the specific depictions, configurations, or relative proportions set forth herein, as this depends on various conditions and variables. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in the practice of the invention. Therefore, the invention is intended to cover any such alternatives, modifications, variations, or equivalents. The following claims are intended to define the scope of the invention and thereby cover methods and structures within the scope of such claims and their equivalents.

[0225] 100: Insulating glass unit 104: First Window 106: Second Window 108: Internal volume 118: Spacer 200: Electrochromic device 202:Substrate 204: Conductive layer 206: Tungsten oxide electrochromic layer 208: Ion-conducting layer 210: Nickel-tungsten oxide counter electrode layer 214: Conductive layer 216: Power Supply 220: Electrochromic Stacking 301: Peak Current 302: Line 303: Leakage Current 304: Voltage Curve 305: Voltage Distribution 306: Line 307: Negative Slope 308: Line 309: Negative Maintenance 311: Slope 313: Maintaining 400:BMS 401: Building 402: Control System 403: Main Controller 405a: Intermediate Network Controller 405b: Intermediate Network Controller 410: Controller 500: Control System Architecture 504: Local controller 506: Floor Controller 508: Main Controller 510: External Source 520: Database 524: Building Management System 600: System 605: Sensor Set 610A: Sensor 610B: Sensor 610C: Sensor 610D: Sensor 615: Processor 650: Network Interface 651: Cloud 652: Processor 654: Processor 700: Computer System 701: Network 702: Memory 703: Interface 704: Storage Unit 705: Peripheral Equipment 706: Processing Unit 890: Schematic 892A: Sensor Set 892B: Sensor Set 892C: Sensor Set 894A: Read Distribution 894B: Read Distribution 894C: Read Distribution 896: Ventilation opening 900: Time 1000: Flowchart 1002: Square 1004: Square 1006: Square 1008: Square 1010: Square 1012: Square 1100: Flowchart 1110: Square 1112: Square 1114: Square 1116: Square 1118: Square 1120: Square 1122: Square 1124: Square 1130: Lower Fidelity Stage 1140: Higher Fidelity Stage 1210: Square 1220: Square 1240: Square 1250: Square 1260: Square 1270: Square 1280: Square 1290: Square 1310: Square 1320: Square 1330: Square 1455: Square 1460: Square 1465: Square 1470: Square 1475: Square 1477: Square 1505: Controller 1510: Sensor Correlator 1515: Model Generator 1520: Event Detector 1525: Processor 1550: Network Interface D 1: Distance D 2: Distance D 3: Distance S1: First surface S2: Second surface S3: First surface S4: Second surface

Claims

1. A method for predicting a fault in a colorable window in a facility, the method comprising: acquiring one or more measurements relating to a leakage current of the colorable window disposed in the facility; analyzing the one or more measurements acquired by considering data (i) being related to a type of the one or more measurements and (ii) being related to the leakage current of the colorable window using a trained learning module; and the learning module using the analysis to predict a fault in the coloring of the colorable window.

2. The method of claim 1, wherein the one or more measurements include a plurality of current measurements obtained in real time.

3. The method of claim 1, wherein the one or more measurements comprise a plurality of open-circuit voltage measurements.

4. The method of claim 1, wherein the one or more measurements comprise a plurality of measurements from at least one sensor, and wherein the method further comprises using the analysis to determine a reliability value for one of the at least one sensors.

5. The method of claim 4, further comprising using the reliability value to adjust the plurality of measurements of the at least one sensor to form a plurality of adjusted sensor measurements.

6. The method of claim 5 further includes using the plurality of adjusted sensor measurements to update the reliability value.

7. The method of claim 5 further includes using the reliability value to generate a prediction of a subsequent colorable window failure of the facility.

8. The method of claim 1, wherein the relevant data is related to one or more measurements obtained from one or more different windows having the size of the colorable window or substantially having the size of the colorable window.

9. The method of claim 1, wherein the data comprises data acquired within at least about 10, 50, 100 or 1,000 occurrences of the leakage current and / or acquired within at least about 12, 25, 52, 104 or 156 weeks.

10. The method of claim 1, wherein the use of the analysis includes providing an alarm and / or a report of a fault of the colorizable window, and wherein providing the alarm and / or the report includes at least one of: predicting the time of a visible fault that is visible to an average person; or scheduling maintenance.

11. The method of claim 10, wherein the colorable window is a first colorable window, and wherein providing the alarm and / or the report includes: scheduling the inventory of another colorable window and / or scheduling the manufacture of another colorable window to replace the first colorable window.

12. The method of claim 1, wherein the method further comprises adjusting a control scheme to facilitate the leakage current via the colorable window.

13. A non-transitory computer-readable program instruction for predicting a fault in a colorable window in a facility, the non-transitory computer-readable program instruction, when executed by one or more processors, causes the one or more processors to perform the following operations: acquiring one or more measurements related to a leakage current of the colorable window located in the facility, or guiding the acquisition of the one or more measurements; analyzing the one or more measurements acquired by considering data, or guiding the analysis of the one or more measurements, using a trained learning module, the data (i) being related to a type of the one or more measurements and (ii) being related to the leakage current of the colorable window; and the learning module using the analysis or guiding the use of the analysis to predict a fault in the coloring of the colorable window.

14. An apparatus for predicting a fault in a colorable window in a facility, the apparatus comprising at least one controller configured to: acquire or guide the acquisition of one or more measurements relating to a leakage current of the colorable window disposed in the facility; analyze, using a trained learning module, the one or more measurements acquired by considering data, or the analysis of the one or more measurements, wherein the data (i) is related to a type of the one or more measurements and (ii) is related to the leakage current of the colorable window; and the learning module uses the analysis or guides the use of the analysis to predict a fault in the coloring of the colorable window.

Images