Machine learning based event occurrence time model for optimizing asset health and prediction

Abstract

A system for determining a cleaning schedule for an asset is provided. In some aspects, the system may include: a plurality of sensors arranged to monitor an asset; and a computing system including at least one data processor and a memory storing instructions that, when executed by the at least one data processor, cause the at least one data processor to perform operations. In some aspects, the operations performed by the processor may include: receiving the data characterizing the operational efficiency of the asset from the plurality of sensors; determining an operation efficiency of the asset; determining an operating efficiency threshold that characterizes the undesired operating efficiency; determining a cleaning schedule for the asset using an optimization algorithm based on the operational efficiency of the asset and the operational efficiency threshold; and providing the cleaning schedule.

Description

[0001] Related applications

[0002] This application is based on 35 USC 119(e) claims priority to U.S. Provisional Application No. 63 / 459,684, filed April 16, 2023, the entire contents of which are expressly incorporated herein by reference. Background Technology

[0003] During the operation of industrial assets, such as heat exchangers and compressors, unwanted deposits or contaminants may accumulate on their surfaces. This accumulation is called scaling. Scaling within industrial assets can affect operational efficiency, increase operating costs, and damage the assets. For example, scaling can impede heat transfer efficiency in heat exchangers and can constrict flow channels within heat exchangers and compressors, leading to reduced flow rates, increased pressure drops, and potential operational problems such as cavitation. Summary of the Invention

[0004] In one aspect, a method for determining a cleaning schedule for an asset is provided. In some aspects, the method may include: acquiring data characterizing the operational efficiency of the asset over time from a plurality of sensors arranged to monitor the asset; receiving the data characterizing the operational efficiency of the asset via a computing system including at least one data processor and a memory storing instructions; determining the operational efficiency of the asset and an operational efficiency threshold characterizing undesirable operational efficiency by the at least one data processor; determining a cleaning schedule for the asset by the at least one data processor based on the operational efficiency of the asset and the operational efficiency threshold; and providing the cleaning schedule.

[0005] In some aspects, the cleaning schedule includes one or more light cleanings using non-invasive methods for the asset. In other aspects, the cleaning schedule includes one or more comprehensive cleanings using mechanical methods for the asset.

[0006] In some aspects, the method may further include: determining, by the at least one data processor, the predicted time of an event corresponding to the time when the operational efficiency threshold will be reached; and providing the time of the event.

[0007] In some aspects, the method may further include: receiving data representing one or more operational states of the asset from the asset via the computing system; and using an optimization algorithm, the at least one data processor determines the cleaning schedule based on the asset's operational efficiency, the operational efficiency threshold, and the data representing the one or more operational states of the asset.

[0008] In some aspects, the method may further include: the at least one data processor using an optimization algorithm to determine an optimized operation schedule for the operation of the asset in one or more operational states. In some aspects, the predicted event occurrence time may be determined based on the cleaning schedule and the optimized operation schedule.

[0009] In some aspects, the method may also include: determining the amount of scale that has formed in the asset by the at least one data processor.

[0010] In some respects, the asset may be a heat exchanger or a compressor, and the multiple sensors include at least one of a temperature sensor and a pressure sensor.

[0011] In some respects, the operational efficiency threshold can be determined based on at least one of the asset’s historical operational data, customer preferences, predetermined efficiency requirements, and predetermined energy consumption thresholds.

[0012] In another aspect, a system for determining a cleaning schedule for an asset is provided. In some aspects, the system may include: a plurality of sensors arranged to monitor the asset; and a computing system including at least one data processor and a memory storing instructions that, when executed by the at least one data processor, cause the at least one data processor to perform operations. In some aspects, the operations performed by the processor may include: receiving data characterizing the operational efficiency of the asset from the plurality of sensors; determining the operational efficiency of the asset; determining an operational efficiency threshold characterizing undesirable operational efficiency; determining a cleaning schedule for the asset using an optimization algorithm based on the operational efficiency of the asset and the operational efficiency threshold; and providing the cleaning schedule.

[0013] In some aspects, the cleaning schedule includes one or more light cleanings using non-invasive methods for the asset. In other aspects, the cleaning schedule includes one or more comprehensive cleanings using mechanical methods for the asset.

[0014] In some aspects, the operation performed by the processor may further include: determining the predicted time of an event that corresponds to the time when the operational efficiency threshold will be reached; and providing the time of the event.

[0015] In some aspects, the operation performed by the processor may also include: receiving data characterizing one or more operational states of the asset; and using an optimization algorithm to determine the cleaning schedule based on the asset's operational efficiency, the operational efficiency threshold, and the data characterizing the one or more operational states of the asset.

[0016] In some aspects, the operation performed by the processor may further include: the at least one data processor using an optimization algorithm to determine an optimized operation schedule for the operation of the asset in the one or more operational states. In some aspects, the predicted event occurrence time may be determined based on the cleaning schedule and the optimized operation schedule.

[0017] In some respects, the operation performed by the processor may also include: determining the amount of scale that has formed in the asset.

[0018] In some respects, the asset may be a heat exchanger or a compressor, and the multiple sensors include at least one of a temperature sensor and a pressure sensor.

[0019] In some respects, the operational efficiency threshold can be determined based on at least one of the asset’s historical operational data, customer preferences, predetermined efficiency requirements, and predetermined energy consumption thresholds. Attached Figure Description

[0020] Figure 1 This is a block diagram of an exemplary asset monitoring system as described herein, which is configured to monitor the operational efficiency of an asset and determine various non-intrusive and intrusive cleaning schedules for the asset;

[0021] Figure 2 Examples are given by Figure 1 Multiple graphs of exemplary non-invasive and invasive cleaning plans for assets identified by the asset monitoring system;

[0022] Figure 3 This is an exemplary graph illustrating the operational efficiency of an asset over time, wherein the asset operates in multiple operating modes, and predictive analysis is performed by the asset monitoring system described herein to predict the future operational efficiency of the asset.

[0023] Figure 4 This is an example of the asset monitoring system described in this article. Figure 3 The operational efficiency data execution specification analysis provides an exemplary curve chart to specify an operation plan table for multiple operating modes of the asset to optimize asset performance; and

[0024] Figure 5 This is a flowchart illustrating an exemplary method for determining prescribed non-invasive and invasive cleaning plans for assets according to the systems and methods described herein.

[0025] It should be noted that the accompanying drawings are not necessarily drawn to scale. The drawings are intended only to depict typical aspects of the subject matter disclosed herein and should not be considered as limiting the scope of this disclosure. Detailed Implementation

[0026] During the operation of industrial assets such as heat exchangers and compressors, operational degradation known as scaling can occur, leading to the accumulation of unwanted deposits or contaminants on their surfaces. Scaling within industrial assets can affect operational efficiency, increase operating costs, and damage the asset. For example, scaling can impede heat transfer efficiency in heat exchangers and can constrict flow channels within heat exchangers and compressors, resulting in reduced flow rates, increased pressure drops, and potential operational problems such as cavitation. Scaling can occur through impurities in the material being heated, or through biological processes (depending on whether it is affected by water) or other areas. Without appropriate measures to remove scaling from assets through non-invasive cleaning operations (e.g., decoking) or through robust mechanical cleaning of the asset, scaling can lead to operational inefficiencies and failures. Traditionally, scaling on assets is addressed retrospectively in response to assets operating at undesirable efficiency or in response to operational failures requiring attention. Therefore, it will be desirable to predict scaling within assets and provide information on when to proactively clean assets to extend asset life, improve efficiency, and reduce asset downtime.

[0027] The system and method described herein combine the use of sensors configured to monitor assets and a computing system arranged to receive data characterizing the operational efficiency of the assets from the sensors. Using the data characterizing the operational efficiency of the assets and operational efficiency thresholds characterizing undesirable operational efficiency, the computing system can determine various non-invasive and invasive cleaning schedules for the assets, as described in more detail below.

[0028] The systems and methods described herein advantageously combine the use of machine learning algorithms with descriptive data characterizing asset efficiency / health to provide a variety of non-invasive and invasive cleaning schedules for assets, extending asset life, improving efficiency, and reducing asset downtime. The systems and methods described herein can be applied to any industrial asset that undergoes performance degradation over time, resulting in reduced operational efficiency and / or vulnerability to anomalous behavior. The described asset monitoring systems and methods utilize proactive / predictive models to provide intervention schedules designed to manage fouling, improve efficiency, and extend asset life.

[0029] Figure 1 An exemplary asset monitoring system 100 is illustrated for determining various non-invasive and invasive cleaning schedules for asset 110 based on its operational efficiency over time. For example... Figure 1 As shown, system 100 may include multiple sensors 120a, 120b configured to monitor condition indicators (e.g., operational efficiency indicators) of asset 110 over time. In some aspects, asset 110 may be an industrial asset (e.g., a heat exchanger, a compressor). Figure 1As shown, multiple sensors 120a, 120b can be configured to detect multiple condition indicators of the asset during operation of asset 110. The condition indicators monitored by sensors 120a, 120b can be used by the system to determine changes in the operational efficiency of the asset over time as the asset degrades. For example, in some aspects, asset 100 may be a heat exchanger or compressor, and the multiple sensors 120a, 120b may include temperature sensors and / or pressure sensors configured to measure various temperatures and / or pressures (e.g., inlet temperature / pressure and outlet temperature / pressure) of asset 110. Based on the temperature and / or pressure measurements, system 100 can determine the operational efficiency of the asset and / or the degradation of asset 110 over time, as discussed in more detail below. In some aspects, the condition indicators monitored by sensors 120a, 120b can inform system 100 how much fouling has formed within asset 110, which can lead to reduced and degraded operational efficiency of the system.

[0030] System 100 may also include a computing system 130, which includes at least one data processor 140 and a memory 150 for storing instructions. In some aspects, the computing system 130 may also include a user interface display 160. The computing system may receive data characterizing the operational efficiency of the asset acquired by a plurality of sensors 120a, 120b. Using the data received from the plurality of sensors 120a, 120b, the processor 140 may be configured to determine the operational efficiency of the asset 110. For example, if the plurality of sensors 120a, 120b are temperature sensors, the operational efficiency may be determined based on the temperature ratios from the plurality of sensors 120a, 120b (e.g., using a logarithmic mean temperature difference (LMTD) method, etc.). In some aspects, the processor 140 may also determine an operational efficiency threshold characterizing undesirable operational efficiency of the asset 110. In some aspects, the operational efficiency threshold may be determined based on historical operational data of the asset, customer preferences, predetermined efficiency requirements, and predetermined energy consumption thresholds. For example, in some cases, a customer may want asset 110 to operate at a certain efficiency level to meet industry efficiency standards or to reduce operating / energy costs. In some aspects, the operating efficiency threshold can be determined by processor 140 using measurements received from multiple sensors 120a, 120b. For example, in some aspects, system 100 can be configured to determine the operating efficiency threshold based on a predetermined LMTD threshold corresponding to a predetermined undesirable efficiency set by system 100. The operating efficiency threshold can represent the operating efficiency that asset 110 would be undesirable when reached and would require maintenance to improve asset 110's performance.

[0031] Therefore, in some respects, based on the asset's operational efficiency and operational efficiency threshold, the processor 140 can determine a cleaning schedule for the asset 110 based on the asset's operational efficiency and operational efficiency threshold over time, and provide the cleaning schedule to the user, as discussed in more detail below.

[0032] Figure 2 Two graphs, 200 and 230, show the operational efficiency of assets over time. (Example) Figure 2 As shown, graphs 200 and 230 may each include those using the systems and methods described herein (e.g., Figure 1 The cleaning schedules 215 and 245, as determined by the asset monitoring system 100, will be referenced below. Figure 1 describe Figure 2 The exemplary curves 200 and 230 are shown.

[0033] As described above, in some aspects, the system described herein may include multiple sensors 120a, 120b configured to monitor asset 110 in response to condition indicators (e.g., indicators of operational efficiency). For example, in the case where asset 110 is a heat exchanger and the multiple sensors 120a, 120b are temperature sensors, temperature readings from the sensors may be received by computing system 130. As shown in graph 200, using the temperature readings from the sensors, processor 140 may determine the operational efficiency 205 of the asset over time. As described above, in some aspects, operational efficiency 205 may be determined based on the temperature ratios from the multiple sensors 120a, 120b (e.g., using a logarithmic mean temperature difference (LMTD) method, etc.). Processor 140 may also determine an operational efficiency threshold 210 characterizing undesirable operational efficiency of the asset. In some aspects, operational efficiency threshold 210 may be determined based on a predetermined LMTD threshold. In some aspects, the operational efficiency threshold can be determined based on historical operational data of the asset, customer preferences, predetermined efficiency requirements, and / or predetermined energy consumption thresholds. For example, system 100 may determine whether maintenance is required or a failure has occurred in asset 110 when it is operating above an operational efficiency threshold 210, based on historical operational data of asset 110 (stored in memory 150 of computing system 130 and / or in a remote database). In another example, if customer and / or industry standards require asset 110 to operate at a certain efficiency level (e.g., to ensure energy consumption costs are minimized), system 100 may determine the operational efficiency threshold 210 based on user input indicating customer preferences, predetermined efficiency requirements, and / or predetermined energy consumption thresholds, as described above. In some aspects, the operational efficiency threshold 210 may also include a predicted event occurrence time T1 corresponding to the time when the operational efficiency threshold 210 will be reached.

[0034] As shown in graph 200, system 100 can also determine a cleaning schedule 215 for the asset based on the asset's operational efficiency 205 and operational efficiency threshold 210. Cleaning schedule 215 may represent a prescribed schedule for cleaning the asset 110 throughout its operation until the asset's operational efficiency reaches operational efficiency threshold 210. In some aspects, cleaning schedule 215 may include one or more light cleanings 220a to 220d and / or one or more full cleanings 220e. In some aspects, one or more light cleanings 220a to 220d and / or one or more full cleanings 220e in cleaning schedule 215 may be determined by processor 140 at fixed intervals. However, in some aspects, the cleaning schedule may be determined by processor 140 using an optimization algorithm, as described in more detail below. One or more light cleanings 220a to 220d within cleaning schedule 215 may indicate to the user that non-invasive cleaning of asset 110 is required. In some aspects, the non-invasive cleaning operations to be performed during one or more specified minor cleanings 220a to 220d may include, but are not limited to, chemical descaling, steam-air descaling, or internal stripping descaling. In some aspects, the systems and methods described herein may be configured to command asset 110 to undergo one or more specified minor cleanings 220a to 220d at their scheduled times as defined by cleaning schedule 215 when a human operator is unavailable to clean asset 110. In some aspects, one or more comprehensive cleanings 220e within cleaning schedule 215 may indicate to the user that a more robust / invasive cleaning of asset 110 is required (e.g., due to excessive material fouling within asset 110). In some aspects, the invasive cleaning operations to be performed during one or more specified comprehensive cleanings 220e may include, but are not limited to, mechanical and / or manual cleaning of the asset by an operator. In some aspects, graph 200 and / or cleaning schedule 215 may be provided to the user interface display 160 of system 100 for customer / user viewing. For example, in some cases, cleaning schedule 215 may be provided as one or more future times, which correspond to the specified times for performing one or more light / comprehensive cleanings.

[0035] As mentioned above, in some aspects, the cleaning schedule can be determined by the processor 140 using an optimization algorithm. Graph 230 illustrates this optimization process. As shown in Graph 230, the processor 140 can determine the asset's operational efficiency 235 over time and an operational efficiency threshold 240 characterizing the asset's undesirable operational efficiency. In some aspects, the operational efficiency 235 and the operational efficiency threshold 240 can be determined in a manner similar to that described above with reference to Graph 200. In the case of Graph 230, the system 100 can also determine an optimized cleaning schedule 245 for the asset based on the asset's operational efficiency 205 and operational efficiency threshold 210. Similar to cleaning schedule 215, the optimized cleaning schedule 245 may include one or more light cleanings 250a to 250d and / or one or more full cleanings 250e. In some aspects, the operational efficiency threshold 210 may also include a predicted event occurrence time T2, which corresponds to the time when the operational efficiency threshold 210 will be reached under the given optimized cleaning schedule 245. The optimized cleaning schedule 245 can be determined by processor 140 using one or more optimization algorithms. In some aspects, operational efficiency data stored in memory 150 can be used to train the optimization algorithm. For example, in some aspects, the systems and methods described herein can use machine learning algorithms to perform simulations to optimize the total operational duration using intervention intervals (e.g., one or more light cleanings 250a to 250d and / or one or more full cleanings 250e) as optimization variables. In some aspects, the machine learning / optimization algorithm may include Monte Carlo algorithms, which indicate the optimal time to intervene with light or full cleaning operations to extend the operational duration of the asset. By using machine learning / optimization algorithms as described herein, system 100 can advantageously increase the operational duration of asset 110. For example, as Figure 2 As shown, with cleaning schedule 215 specified, the predicted event occurrence time is T1, and with optimized cleaning schedule 225 specified, the predicted event occurrence time is T2. Therefore, with optimized cleaning schedule 245 specified, the predicted event occurrence time can be increased by ΔT(T2-T1).

[0036] In some respects, the monitored assets (e.g., Figure 1 The asset 110 can be configured to operate in multiple operating modes. For example, in some cases, the asset may be a heat exchanger that can operate in a first mode and a second mode. Therefore, in some aspects, the systems and methods described herein (e.g., computing system 130) can also be configured to receive data characterizing one or more operating states of the asset, which can be used to generate an optimized cleaning schedule, as described in more detail below. In some aspects, the data characterizing one or more operating states of the asset may be received directly from the asset.

[0037] Figure 3 Another exemplary graph 300 is shown, illustrating the operational efficiency of an asset over time when it operates in multiple operating modes. Reference will be made below. Figures 1 to 2 describe Figure 3 The exemplary graph 300 is shown below. Figure 3 As shown, graph 300 includes a first operating efficiency 305a of the asset when operating in a first mode and a second operating efficiency 305b of the asset when operating in a second mode. In some aspects, operating efficiency (shown on the Y-axis) can be measured in units of temperature, or it can be a unitless measure of operating efficiency. For example, when the sensor monitoring the asset is a temperature sensor and the operating efficiency is determined using LMTD, the operating efficiency can be measured in units of temperature, as described above. In some aspects, when the temperature sensor and operating efficiency are determined using the LMTD ratio, the operating efficiency can be a unitless measure of efficiency. In another example, when the asset is a compressor or pump, and the sensor monitoring the asset is a pressure sensor, the operating efficiency can be a unitless measure of efficiency, for example, determined by comparing the actual pressure output of the asset with a reference or desired output. In some aspects, when the sensor is a pressure sensor, the operating efficiency can also be a pressure difference measured in units of pressure. In some aspects, processor 140 may receive operation indicators from multiple sensors 120a, 120b over a period of time (e.g., from day 0 to the current date T1) and determine the operational efficiency 305a, 305b of the asset over time and an operational efficiency threshold 310 characterizing undesirable operational efficiency of the asset, similar to the reference above. Figures 1 to 2 As described. In some aspects, such as Figure 3As shown, data received from sensors in system 100 can also indicate the time during which the asset is in standby operation (or has stopped operating). As shown in graph 300, the asset may have lower efficiency 305b when operating in the second mode and higher efficiency 305a when operating in the first mode. System 100 can also determine an optimized cleaning schedule 315 for the asset based on its operating efficiencies 305a, 305b and an operating efficiency threshold 310. Similar to what is described above, the optimized cleaning schedule 315 may include one or more cleaning sessions 320a to 320b. In some aspects, one or more cleaning sessions 320a to 320b may include both light cleaning and thorough cleaning as described above. In some aspects, the operating efficiency threshold 310 may also include a predicted event occurrence time T2, which corresponds to the time when the operating efficiency threshold 310 will be reached under the given optimized cleaning schedule 315. In some aspects, similar to what is described above, the optimized cleaning schedule 315 may be provided to a user interface for user viewing. In some aspects, the user can interact with display 160 to request information corresponding to a predicted event occurrence time fault (at T2) of the asset during its operating window. In other aspects, the user can also request via display 160 a prediction of the asset's degradation curve with and / or without intervention as specified in cleaning plan table 315. Based on the user-provided request, processor 140 can be configured to retrieve data stored in memory 150 of the computing system to provide predictive analysis regarding the predicted event occurrence time fault (at T2) and the evolution of the asset's operational efficiency with and / or without intervention.

[0038] In cases where a user wishes to operate the asset using previously completed first and second modes, the optimized cleaning schedule 315 can easily predict future operating modes, corresponding operational efficiencies 305a' and 305b' of the asset, and the optimized cleaning schedule 315 using the optimization algorithms described herein. However, in some aspects, the user can interact with the display 160 to request the system 100 to generate a specified operating schedule and cleaning schedule, thereby operating and cleaning the asset in a manner that optimally extends its operational lifespan. In this case, the system and method described herein can be configured to further determine the optimized operating schedule and the optimized cleaning schedule using operating indicators received from multiple sensors 120a, 120b over a period of time (e.g., from day 0 to the current date T1) and the optimization algorithms described herein, as described in more detail below.

[0039] Figure 4 Another exemplary graph 400 is shown, illustrating the operational efficiency of an asset over time when it operates in multiple operating modes, similar to... Figure 3 As shown. The following will refer to... Figures 1 to 3 describe Figure 4 The exemplary graph 400 is shown below. Figure 4 As shown, graph 400 includes a first operational efficiency 405a of the asset when operating in a first mode and a second operational efficiency 405b of the asset when operating in a second mode. In some aspects, processor 140 may receive operation indicators from multiple sensors 120a, 120b over a period of time (e.g., from day 0 to the current date T1) and determine the operational efficiency 405a, 405b of the asset over time and an operational efficiency threshold 410 characterizing undesirable operational efficiency of the asset, similar to that described above. Data received from the sensors of system 100 may also indicate the time during which the asset is in standby operation (or has stopped operating). As mentioned above, in some cases, the user of the system and method may interact with display 160 to request system 100 to generate a prescribed schedule including both an optimized operation schedule and an optimized cleaning schedule to operate and clean the asset in a manner that optimally extends the asset's operational life. In this context, the system and method described herein can be configured to further determine an optimized schedule 415 for the asset using operation indicators received from multiple sensors 120a, 120b over a period of time (e.g., from day 0 to the current date T1) and the optimization algorithm described herein. The optimized schedule 415 may include an optimized operation schedule that informs the user of the optimal way to combine the asset's operation in a first and second operation mode to extend the asset's lifespan. Additionally, the optimized schedule 415 includes one or more cleaning sessions 420a to 420b, which may include a mix of light cleaning and / or thorough cleaning, similar to those described above. For example, the optimized schedule may indicate multiple specified times 425 for operating the asset in the first operation mode and multiple specified times 430 for operating the asset in the second operation mode.

[0040] Furthermore, in some aspects, the user can be given the option to specify any of the optimized operation schedules 425, 430 and one or more cleanings 420a to 420b. Therefore, if the user provides input to the user interface indicating that they want to specify one or more cleanings 420a to 420b instead of the optimized operation schedules 425, 430, the system can be configured to determine a first predicted event time T2, which corresponds to the time when the operational efficiency threshold 410 will be reached in the case where one or more cleanings 420a to 420b are specified, but the user wishes to operate the asset in the first and second modes as they have done in the past. In this case, the system can simply predict the future operation mode, the corresponding operational efficiencies 405a', 405b' of the asset, and one or more cleanings 420a to 420b using the optimization algorithm described above. Alternatively, if the user provides input to the user interface indicating that they wish to specify a complete optimized schedule 415 including one or more cleanings 420a to 420b and optimized operation schedules 425, 430, the system can be configured to determine a second predicted event occurrence time T3 corresponding to the time when the operational efficiency threshold 410 will be reached under the specified complete optimized schedule 415. In this case, the system can use condition indicator data received from sensors and historical operational data received from assets, as well as the optimization algorithm described above, to predict the optimized operation schedules 425, 430, the corresponding operational efficiencies 405a”, 405b” of the assets, and one or more cleanings 420a to 420b. In some aspects, the operational efficiency data described above can be used to train the optimization algorithm. Additionally, in some aspects, historical operation schedules of assets or other similar assets can be used to train the optimization algorithm. For example, in some aspects, the systems and methods described herein can use machine learning algorithms to perform simulations to optimize operational schedules and intervention intervals (e.g., one or more light / comprehensive cleanings 420a to 420b) as optimization variables. By specifying a complete optimized schedule 415, system 100 can advantageously increase the operational duration of asset 110. For example, as Figure 4 As shown, when one or more cleaning operations 420a to 420b are specified but no optimized operation schedule 425, 430 is specified, the predicted event occurrence time is T2. When a complete optimized schedule 415 is specified, the predicted event occurrence time is T3. Therefore, when a complete optimized schedule 415 is specified, the predicted event occurrence time can increase by ΔT(T3-T2). In some aspects, the prediction results based on only a portion of the optimized schedule 415 and the prediction results based on the complete optimized schedule 415 (including both predicted event occurrence times T2 and T3, and ΔT) can be provided to the user interface for the user to view.

[0041] As described above, the cleaning events described herein may include mechanical cleaning requiring a user, as well as alternative intervention methods, such as non-invasive light cleaning in the absence of an operator. For example, a user may request the asset monitoring system to include light cleaning requirements for an asset in the cleaning schedule described herein, such as descaling (e.g., internal stripping, steam-air descaling, or chemical descaling). Both light cleaning events and full cleaning events specified by the systems and methods described herein advantageously allow users to extend the operational window of their assets while maintaining operational efficiency below a defined operational efficiency threshold.

[0042] In some respects, the systems and methods described herein can also be configured to monitor platoons of assets, where each asset may have a different operational efficiency than another, depending on varying degrees of fouling. Traditionally, in such cases, users may find it difficult to determine the optimal cleaning schedule for each asset in the platoon. Therefore, by leveraging the machine learning and optimization capabilities of the systems and methods described herein, operational data from the asset platoon and operational efficiency data from sensors monitoring the platoon can be used to train the systems described herein to generate robust network systems capable of providing descriptive, predictive, and prescriptive analytical models to optimize asset health and performance.

[0043] Figure 5 This is a flowchart illustrating an exemplary method 500 for determining a prescribed light and full (e.g., non-invasive and invasive) cleaning schedule for an asset according to the systems and methods described herein. In some aspects, method 500 may include step 510 of acquiring data characterizing the operational efficiency of the asset over time from a plurality of sensors configured to monitor the asset. The plurality of sensors may include temperature sensors and / or pressure sensors; however, the use of other sensor types capable of monitoring operational efficiency is also implemented.

[0044] Method 500 may further include step 520 of receiving data characterizing the operational efficiency of an asset via a computing system including at least one data processor and a memory for storing instructions. In some aspects, the asset monitoring system may store data corresponding to the operational efficiency of the asset over a period of time during its operation.

[0045] Method 500 may further include method step 530, which involves at least one data processor determining the operational efficiency of an asset and an operational efficiency threshold characterizing undesirable operational efficiency, as referenced above. Figures 1 to 4 As described.

[0046] Method 500 may further include step 540 of determining a cleaning schedule for the asset based on operational efficiency and an operational efficiency threshold. In some aspects, the cleaning schedule may be determined using an optimization algorithm as described herein. In some aspects, the method may further include a step of determining the predicted time of occurrence of an event corresponding to the time when the operational efficiency threshold will be reached. Additionally, in some aspects, step 540 may further include determining multiple cleaning schedules with different intervention levels and / or different predicted failure times, which may be provided to a user interface for user viewing and selection. In some aspects, the asset may include multiple operating modes that may require specific cleaning methods or optimized approaches to clean the asset in order to extend its operating duration. In this case, the method may further include the steps of: receiving data characterizing one or more operating states of the asset from the asset; and determining a cleaning schedule using an optimization algorithm based on the asset's operational efficiency, an operational efficiency threshold, and the data characterizing one or more operating states of the asset.

[0047] Method 500 may also include step 550 of providing one or more cleaning schedules to a user via a user interface display.

[0048] Certain exemplary embodiments are described to provide a comprehensive understanding of the principles of structure, function, manufacture, and use of the systems, apparatuses, and methods disclosed herein. One or more examples of these embodiments are illustrated in the accompanying drawings. It will be understood by those skilled in the art that the systems, apparatuses, and methods specifically described herein and illustrated in the accompanying drawings are non-limiting exemplary embodiments, and that the scope of the invention is defined only by the claims. Features illustrated or described in conjunction with one exemplary embodiment may be combined with features of other embodiments. Such modifications and variations are intended to be included within the scope of the invention. Furthermore, in this disclosure, similarly named components of embodiments generally have similar features, and therefore, within a specific embodiment, not every feature of every similarly named component is necessarily fully described.

[0049] The subject matter described herein may be implemented in analog electronic circuits, digital electronic circuits and / or computer software, firmware or hardware (including structural devices and their structural equivalents disclosed herein) or combinations thereof. The subject matter described herein may be implemented as one or more computer program products, such as those tangibly embodied in an information carrier (e.g., in a machine-readable storage device) or embodied in a propagated signal, for execution by or control of the operation of a data processing device (e.g., a programmable processor, a computer, or multiple computers). A computer program (also referred to as a program, software, software application, or code) may be written in any form of programming language (including compiled or interpreted languages) and may be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for a computing environment. A computer program does not necessarily correspond to a file. A program may be stored as a portion of a file containing other programs or data, in a single file dedicated to the program under consideration, or in multiple co-located files (e.g., a file storing portions of one or more modules, subroutines, or code). Computer programs can be deployed to run on one computer or on multiple computers located at one site or distributed across multiple sites and interconnected by a communication network.

[0050] The processes and logical flows described in this specification (including the method steps of the subject matter described herein) can be executed by one or more programmable processors that execute one or more computer programs to perform the functions of the subject matter described herein by manipulating input data and generating output. These processes and logical flows can also be executed by special-purpose logic circuitry (e.g., FPGAs (Field-Programmable Gate Arrays) or ASICs (Application-Specific Integrated Circuits)), and the devices of the subject matter described herein can be implemented as special-purpose logic circuitry (e.g., FPGAs or ASICs).

[0051] By way of example, processors suitable for executing computer programs include both general-purpose microprocessors and special-purpose microprocessors, as well as any one or more processors in any kind of digital computer. Generally, a processor receives instructions and data from read-only memory or random access memory, or both. The basic components of a computer are a processor for executing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include one or more mass storage devices (e.g., magnetic disks, magneto-optical disks, or optical disks) for storing data, or operatively coupled to receive data from or / and transfer data to one or more mass storage devices (e.g., magnetic disks, magneto-optical disks, or optical disks) for storing data. Information carriers suitable for embodying computer program instructions and data include all forms of non-volatile memory, including, for example, semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices); magnetic disks (e.g., internal hard disks or removable magnetic disks); magneto-optical disks; and optical disks (e.g., CDs and DVDs). The processor and memory may be supplemented by or incorporated into special-purpose logic circuitry.

[0052] To provide interaction with the user, the subjects described herein can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user, and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user. For example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback), and input from the user can be received in any form, including sound, speech, or tactile input.

[0053] The techniques described herein can be implemented using one or more modules. As used herein, the term "module" refers to computing software, firmware, hardware, and / or various combinations thereof. However, at a minimum, a module should not be construed as software not implemented on hardware, firmware, or documented on a non-transitory processor-readable storage medium (i.e., a module itself is not software). In practice, a "module" will be interpreted as always including at least some physical non-transitory hardware, such as a processor or part of a computer. Two different modules may share the same physical hardware (e.g., two different modules may use the same processor and network interface). The modules described herein can be combined, integrated, separated, and / or replicated to support a variety of applications. Additionally, instead of functions performed at a particular module, or functions described herein as performing at a particular module, functions may be performed at one or more other modules and / or by one or more other devices. Furthermore, modules may be implemented locally or remotely across multiple devices and / or other components relative to each other. Additionally, modules may be moved from one device and added to another device, and / or may be included in two devices.

[0054] The subject matter described herein can be implemented in a computing system that includes back-end components (e.g., a data server), middleware components (e.g., an application server), or front-end components (e.g., a client computer with a graphical user interface or web browser through which a user can interact with a specific implementation of the subject matter described herein), or any combination of such back-end, middleware, and front-end components. Components of the system can be interconnected via any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include local area networks (“LANs”) and wide area networks (“WANs”), such as the Internet.

[0055] As used herein throughout the specification and claims, approximate language may be used to modify any quantitative expression that may vary but does not result in a change in the essential function associated with it. Therefore, a value modified by one or more terms such as “about,” “approximately,” and “substantially” should not be limited to the specified precise value. In at least some cases, approximate language may correspond to the precision of the instrument used to measure the value. Scope limitations may be combined and / or interchanged herein and throughout the specification and claims, and unless otherwise indicated by context or language, such scopes are identified and include all subscopes contained therein.

[0056] Based on the embodiments described above, those skilled in the art will understand other features and advantages of the present invention. Therefore, this application is not limited to what has been specifically shown and described, except as indicated in the appended claims. All publications and references cited herein are expressly incorporated in their entirety by reference.

Claims

1. A method, the method comprising: Data characterizing the operational efficiency of the asset over time is acquired from multiple sensors configured to monitor the asset. The data characterizing the operational efficiency of the asset is received via a computing system including at least one data processor and a memory for storing instructions; The at least one data processor determines the operational efficiency of the asset and an operational efficiency threshold representing undesirable operational efficiency. The cleaning schedule for the asset is determined by the at least one data processor based on the asset's operational efficiency and the operational efficiency threshold. as well as Provide the cleaning schedule.

2. The method of claim 1, wherein the cleaning schedule includes one or more light cleanings for non-invasive cleaning of the asset.

3. The method of claim 2, wherein the cleaning schedule includes one or more comprehensive cleanings for mechanical cleaning of the asset.

4. The method according to claim 1, further comprising: The at least one data processor determines the predicted time of an event that corresponds to the time when the operational efficiency threshold will be reached. as well as Provide the time when the event occurred.

5. The method according to claim 4, further comprising: The computing system receives data representing one or more operational states of the asset from the asset. as well as The cleaning schedule is determined by the at least one data processor using an optimization algorithm based on the operational efficiency of the asset, the operational efficiency threshold, and the data characterizing the one or more operational states of the asset.

6. The method according to claim 5, further comprising: The at least one data processor uses the optimization algorithm to determine an optimized operation schedule for the operation of the asset in the one or more operating states.

7. The method of claim 6, wherein the predicted event occurrence time is determined based on the cleaning schedule and the optimized operation schedule.

8. The method according to claim 1, further comprising: The amount of scale that has formed in the asset is determined by the at least one data processor.

9. The method of claim 1, wherein the asset is a heat exchanger or a compressor, and the plurality of sensors include at least one of a temperature sensor and a pressure sensor.

10. The method of claim 1, wherein the operational efficiency threshold is determined based on at least one of the asset's historical operational data, customer preferences, predetermined efficiency requirements, and predetermined energy consumption thresholds.

11. A system comprising: Multiple sensors, which are configured to monitor assets; and A computing system comprising at least one data processor and a memory storing instructions, the instructions, when executed by the at least one data processor, causing the at least one data processor to perform operations, the operations including: The data characterizing the operational efficiency of the asset are received from the plurality of sensors; Determine the operational efficiency of the asset; Determine the operational efficiency threshold that characterizes undesirable operational efficiency; Based on the operational efficiency and operational efficiency threshold of the asset, an optimization algorithm is used to determine the cleaning schedule for the asset; and Provide the cleaning schedule.

12. The system of claim 11, wherein the cleaning schedule includes one or more light cleanings for non-invasive cleaning of the asset.

13. The system of claim 12, wherein the cleaning schedule includes one or more comprehensive cleanings for mechanical cleaning of the asset.

14. The system of claim 11, wherein the operation performed by the at least one data processor further comprises: Determine the predicted event occurrence time corresponding to the time when the operational efficiency threshold will be reached; as well as Provide the time when the event occurred.

15. The system of claim 14, wherein the operation performed by the at least one data processor further comprises: Receive data representing one or more operational states of the asset from the asset; as well as The cleaning schedule is determined using the optimization algorithm based on the operational efficiency of the asset, the operational efficiency threshold, and the data characterizing one or more operational states of the asset.

16. The system of claim 15, wherein the operation performed by the at least one data processor further comprises: The at least one data processor uses the optimization algorithm to determine an optimized operation schedule for the operation of the asset in the one or more operating states.

17. The system of claim 16, wherein the predicted event occurrence time is determined based on the cleaning schedule and the optimized operation schedule.

18. The system of claim 11, wherein the operation performed by the at least one data processor further comprises: Determine the amount of scale that has formed in the asset.

19. The system of claim 11, wherein the asset is a heat exchanger or a compressor, and the plurality of sensors include at least one of a temperature sensor and a pressure sensor.

20. The system of claim 11, wherein the operational efficiency threshold is determined based on at least one of the following: historical operational data of the asset, customer preferences, predetermined efficiency requirements, and predetermined energy consumption threshold.

Images