Commodity monitoring systems, cable assemblies, cable sensor nodes, and related methods and systems

Abstract

A method of monitoring a commodity within a container. The method includes receiving uppermost sensor data from an uppermost sensor node of a cable of a cable assembly within the container, receiving lower sensor data from a lower sensor node of the cable, analyzing the uppermost sensor data and the lower sensor data via at least one machine learning model, and based at least partially on the analysis of the uppermost sensor data and the lower sensor data, determining whether the lower sensor node of the cable is in a commodity within the container or out of the commodity within the container.

Description

COMMODITY MONITORING SYSTEMS, CABLE ASSEMBLIES, CABLE SENSOR NODES, AND RELATED METHODS AND SYSTEMSFIELD

[0001] Embodiments generally relate to grain monitoring. In particular, embodiments relate to sensor nodes secured to cables used in the monitoring of stored commodities (e.g., grain).BACKGROUND

[0002] In the monitoring of commodities within storage bins, it is important to monitor certain parameters to keep the stored commodities cool and dry. Based on the monitored parameters, determinations that the stored commodities need aeration, heating, and / or by churning may be made. In cable-based monitoring, parameters are typically monitored via sensor nodes suspended by cables. Furthermore, knowing the moisture content and temperature of the commodities is important in determining that the stored commodities need aeration, heating, and / or by churning.BRIEF SUMMARY

[0003] Some embodiments include a method of monitoring a commodity within a container. The method may include receiving uppermost sensor data from an uppermost sensor node of a cable of a cable assembly within the container, receiving lower sensor data from a lower sensor node of the cable, analyzing the uppermost sensor data and the lower sensor data via at least one machine learning model, and based at least partially on the analysis of the uppermost sensor data and the lower sensor data, determining whether the lower sensor node of the cable is in a commodity within the container or out of the commodity within the container.

[0004] Analyzing the uppermost sensor data and the lower sensor data via at least one machine learning model may include analyzing the uppermost sensor data and the lower sensor data via at least one of a quadratic regression analysis, a logistic regression analysis, a support vector machine, a Gaussian process regression, or an ensemble model.

[0005] Analyzing the uppermost sensor data and the lower sensor data via at least one machine learning model may include analyzing the uppermost sensor data and the lower sensor data via at least one of a decision tree learning, regression trees, boosted trees, gradient boosted tree, multilayer perceptron, one-vs-rest, Naive Bayes, k-nearest neighbor, association rule learning, a neural network, deep learning, or pattern recognition.

[0006] Analyzing the uppermost sensor data and the lower sensor data via at least one machine learning model may include analyzing the uppermost sensor data and the lower sensor data based on learned correlations between sensor node states and conditions within the container and conditions at the uppermost sensor node.

[0007] The method may also include receiving external condition data representing at least one of plenum conditions of a commodity management device or outside weather conditions.

[0008] The method may also include, responsive to determining that the sensor node is out of commodity receiving additional lower sensor data from a lower sensor node of the cable, analyzing the uppermost sensor data and the additional lower sensor data via at least one machine learning model, and based at least partially on the analysis of the uppermost sensor data and the additional lower sensor data, determining whether the lower sensor node of the cable is in a commodity within the container or out of the commodity within the container.

[0009] The method may also include, responsive to a determination as to whether the lower sensor node is in commodity or out of commodity, adjusting operation of one or more commodity treatment devices of the container.

[0010] The uppermost sensor data may include at least one of first temperature measurements or first relative humidity measurements captured over a period of time, and the lower sensor data may include at least one of second temperature measurements or second relative humidity measurements captured over the period of time.

[0011] The uppermost sensor data may include a first temperature profile over a period time, and the lower sensor data may include a second temperature profile over the period of time.

[0012] The measured conditions within the container of the learned correlations may include at least one of temperature or relative humidity.

[0013] The measured conditions within the container of the learned correlations may also include at least one of moisture levels and carbon dioxide levels.

[0014] The measured conditions at the uppermost sensor node of the learned correlations may include at least one of temperature or relative humidity.

[0015] The method may also include analyzing the uppermost sensor data and the lower sensor data in conjunction with the received external condition data via at least one machine learning model.

[0016] The external condition data may include at least one of temperature data, pressure data, relative humidity data, or weather forecasts.

[0017] Adjusting operation of the one or more commodity treatment devices of the container may include at least one of turning on or off fans, blowers, or heaters, increasing or decreasing air flow through the commodity via fans, blowers, or heaters, turning on or off churners, or opening or closing vents of the container.

[0018] One or more embodiments include a system including a container and a cable assembly disposed within the container and including at least one cable including a plurality of sensor nodes operably coupled to the at least one cable. The system also includes a commodity monitoring system in communication with the cable assembly and including at least one processor and at least one non-transitory computer-readable storage medium storing instructions thereon that, when executed by the at least one processor, cause the commodity monitoring system to receive uppermost sensor data from an uppermost sensor node of the plurality of sensor nodes, receive lower sensor data from a lower sensor node of the plurality of sensor nodes of the cable, analyze the uppermost sensor data and the lower sensor data via at least one machine learning model, and based at least partially on the analysis of the uppermost sensor data and the lower sensor data, determine whether the lower sensor node of the plurality of sensor nodes of the cable is in a commodity within the container or out of the commodity within the container.

[0019] The system may also include instructions that, when executed by the at least one processor, cause the commodity monitoring system to: receive external condition data representing at least one of plenum conditions of a commodity management device or outside weather conditions.

[0020] The system may also include instructions that, when executed by the at least one processor, cause the commodity monitoring system to analyze the uppermost sensor data and the lower sensor data in conjunction with the received external condition data via at least one machine learning model.

[0021] Analyzing the uppermost sensor data and the lower sensor data via at least one machine learning model may include analyzing the uppermost sensor data and the lower sensor data based on learned correlations between sensor node states and conditions within the container and conditions at the uppermost sensor node.

[0022] Some embodiments include a method of monitoring a commodity within a container. The method may include, based on a machine learning analysis of measured conditions at an uppermost sensor node of a cable of a cable assembly within the container and measured conditions at lower sensor nodes of the cable, determining which lower sensor nodes of the cable are in commodity and which lower sensor nodes of the cable are out of commodity.

[0023] Other technical features may be readily apparent to one skilled in the art from the following figures, descriptions, and claims.

[0024] Within the scope of this application it should be understood that the various aspects, embodiments, examples and alternatives set out herein, and individual features thereof may be taken independently or in any possible and compatible combination. Where features are described with reference to a single aspect or embodiment, it should be understood that such features are applicable to all aspects and embodiments unless otherwise stated or where such features are incompatible.BRIEF DESCRIPTION OF THE DRAWINGS

[0025] While the specification concludes with claims particularly pointing out and distinctly claiming what are regarded as embodiments of the present disclosure, various features and advantages may be more readily ascertained from the following description of example embodiments when read in conjunction with the accompanying drawings, in which:

[0026] FIG. 1 shows a schematic representation of a commodity monitoring system having a cable assembly and sensor nodes according to one or more embodiments of the present disclosure;

[0027] FIG. 2 shows a flowchart of a method of monitoring a commodity within a container according to one or more embodiments of the disclosure; and

[0028] FIG. 3 is a schematic view of a computer device according to embodiments of the disclosure.DETAILED DESCRIPTION

[0029] Illustrations presented herein are not meant to be actual views of any particular storage container, cable assembly, cable, sensor node, component, or system, but are merely idealized representations that are employed to describe embodiments of the disclosure. Additionally, elements common between figures may retain the same numerical designation for convenience and clarity.

[0030] The following description provides specific details of embodiments. However, a person of ordinary skill in the art will understand that the embodiments of the disclosure may be practiced without employing many such specific details. Indeed, the embodiments of the disclosure may be practiced in conjunction with conventional techniques employed in the industry. In addition, the description provided below does not include all the elements that form a complete structure or assembly. Only those process acts and structures necessary to understand the embodiments of the disclosure are described in detail below. Additional conventional acts and structures may be used. The drawings accompanying the application are for illustrative purposes only, and are thus not drawn to scale.

[0031] As used herein, the terms "comprising," "including," "containing," "characterized by," and grammatical equivalents thereof are inclusive or open-ended terms that do not exclude additional, unrecited elements or method steps, but also include the more restrictive terms "consisting of" and "consisting essentially of" and grammatical equivalents thereof.

[0032] As used herein, the singular forms following "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0033] As used herein, the term "may" with respect to a material, structure, feature, or method act indicates that such is contemplated for use in implementation of an embodiment of the disclosure, and such term is used in preference to the more restrictive term "is" so as to avoid any implication that other compatible materials, structures, features, and methods usable in combination therewith should or must be excluded.

[0034] As used herein, the term "configured" refers to a size, shape, material composition, and arrangement of one or more of at least one structure and at least one apparatus facilitating operation of one or more of the structure and the apparatus in a predetermined way.

[0035] As used herein, any relational term, such as "first," "second," "top," "bottom," "upper," "lower," "above," "beneath," "side," "outer," "inner," etc., is used for clarity and convenience in understanding the disclosure and accompanying drawings, and does not connote or depend on any specific preference or order, except where the context clearly indicates otherwise. For example, these terms may refer to an orientation of elements of a sensor node, a cable, and / or a cable assembly as illustrated in the drawings. Additionally, these terms may refer to an orientation of elements of a sensor node, a cable, and / or a cable assembly when utilized in a conventional manners.

[0036] As used herein, any relational term, such as "first," "second," "top," "bottom," "upper," "lower," "above," "beneath," "side," etc., is used for clarity and convenience in understanding the disclosure and accompanying drawings, and does not connote or depend on any specific preference or order, except where the context clearly indicates otherwise. For example, these terms may refer to an orientation of elements of a cable assembly, cable,and / or sensor node when utilized in a conventional manner. Furthermore, these terms may refer to an orientation of elements of a cable assembly, cable, and / or sensor node when as illustrated in the drawings.

[0037] As used herein, the term "substantially" in reference to a given parameter, property, or condition means and includes to a degree that one skilled in the art would understand that the given parameter, property, or condition is met with a small degree of variance, such as within acceptable manufacturing tolerances. By way of example, depending on the particular parameter, property, or condition that is substantially met, the parameter, property, or condition may be at least 90.0% met, at least 95.0% met, at least 99.0% met, or even at least 99.9% met.

[0038] As used herein, the term "about" used in reference to a given parameter is inclusive of the stated value and has the meaning dictated by the context (e.g., it includes the degree of error associated with measurement of the given parameter, as well as variations resulting from manufacturing tolerances, etc.).

[0039] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0040] Embodiments of the disclosure include a cable assembly for monitoring a commodity (e.g., a grain) within a container (e.g., a storage bin). The cable assembly may include cables suspended within the container and a plurality of sensor nodes secured to each of the cables. The plurality of sensor nodes of each cable may include an uppermost sensor node and one or more lower sensor nodes. The uppermost sensor nodes are assumed to be out of commodity. Embodiments further include analyzing data acquired from the uppermost sensor nodes of the cables and data acquired from the lower sensor nodes of the cables via one or more machine learning models to determine which lower sensor nodes are within the commodity within the container and which lower sensor nodes are out of the commodity. Furthermore, based on the determination of which lower sensor nodes are within the commodity, operation of one or more commodity management devices may be adjusted based on data from the lower sensor nodes that are within the commodity.

[0041] FIG. 1 shows a schematic diagram of an environment 100 in which a sensor node (e.g., a cable sensor node) and commodity monitoring system may be implemented and operated according to one or more embodiments of the present disclosure. The environment 100 may include a cable assembly 102 having a plurality of cables 104 suspended within a container 106, at least one client device 108, at least one server 122 including the commodity monitoring system 120, and a network 110. The commodity monitoring system 120, the at least one client device 108, and the cable assembly 102 may communicate via the network 110. Although FIG. 1 illustrates a particular arrangement of the at least one client device 108, the at least one server 122, the cable assembly 102, and the network 110, various additional arrangements are possible. For example, the at least one server 122 and, accordingly, the commodity monitoring system 120, can communicate directly with the at least one client device 108, and / or the cable assembly 102, thereby bypassing the network 110.

[0042] The container 106 may include a grain storage bin. Furthermore, while a particular geometry is depicted in FIG. 1, it understood that the container 106 may include one or more containers of other geometries, for the same contents (e.g., grain) or other contents, with a different arrangement and / or quantity of inlet, outlet, and / or side ports.

[0043] The cable assembly 102 may include a plurality of cables 104 coupled to and suspended from one or more top structures of a container 106. In some embodiments, one or more of the plurality of cables 104 may be coupled to a floor of the container 106 via, for instance, a floor anchor. In some embodiments, the plurality of cables 104 may each be operably coupled to and hanging from a respective cable hub 112. Each cable hub 112 may include one or more hub sensors 124 and may be in communication (e.g., via wired and / or wireless communication) with a communications gateway 114, which in turn may be in communication with the network 110, and as a result, the at least one client device 108 and / or the commodity monitoring system 120 of the at least one server 122. The one or more hub sensors 124 may include one or more of humidity sensors, relative humidity sensors, temperature sensors, moisture sensors, and / or carbon dioxide (CO2) sensors.

[0044] The cable assembly 102 may be utilized to monitor contents (e.g., a commodity) within the container 106. For example, each cable 104 of the cable assembly 102 may include a plurality of sensor nodes 116 coupled (e.g., secured) to the cable 104. The plurality of sensor nodes 116 of each cable 104 may include include an uppermost sensor node 126 (i.e., a highest sensor node vertically) and one or more lower sensor nodes 128 (i.e., sensor nodes below the uppermost sensor node 126 on the cable 104). In some embodiments, the plurality of sensor nodes 116 of each cable 104 may be spaced apart from each along a longitudinal length of the given cable 104. As a result, when a commodity (e.g., a grain) is stored within the container 106, the plurality of sensor nodes 116 of each cable 104 may be vertically distributed throughout the commodity.

[0045] The plurality of sensor nodes 116 may include one or more of humidity sensors, relative humidity sensors, temperature sensors, moisture sensors, and / or carbon dioxide (CO2) sensors. Spacing between sensor nodes 116 of the plurality of sensor nodes 116 may be selected based on the type of sensors and / or type of commodity. Additionally, a quantity of cables 104 may be selected based at least partially on one or more of a region (e.g., climate) in which the container 106 is located, a type of commodity stored, a size of the container 106, air flow conditions within the container 106, and the types of sensors of the sensor nodes 116.

[0046] Additionally, in some embodiments, the commodity monitoring system 120 may include one or more of a commodity management sensor 132 mounted to or within the commodity management device 118 or one or more external sensors 134. In one or more embodiments, the commodity management sensor 132 may include a pressure sensor and / or airflow sensor for measuring a status and / or load of the commodity management device 118. For instance, the commodity management sensor 132 may include a plenum pressure sensor (e.g., a pressure sensor located within supply plenum of a fan and / or heater) for measuring and determining a fan status and / or load. In one or more embodiments, the one or more external sensors 134 may be exposed to conditions outside of the container 106. Additionally, the external sensors 134 may include one or more of humidity sensors, relative humidity sensors, temperature sensors, moisture sensors, and / or carbon dioxide(CO2) sensors. As is described in greater detail below, the commodity monitoring system 120 may utilize the one or more external sensors 134 to measure and determine conditions (e.g., weather conditions) external to the container 106 and the commodity management sensor 132 to measure and determine conditions (e.g., a status and / or load) of the commodity management device 118. In additional embodiments, the commodity monitoring system 120 may be in communication with one or more weather monitoring systems (e.g., weather services, weather.com, etc.) and may receive data regarding weather around the container from the one or more weather monitoring systems.

[0047] As is described in great detail below, the commodity monitoring system 120 may utilize measurements from the uppermost sensor nodes 126 of the cables 104, measurements from the lower sensor nodes 128 of the cables 104, measurements from the commodity management sensor 132, and / or the external sensors 134 or weather monitoring systems to determine statuses of the lower sensor nodes 128 of each cable 104. As used herein, the terms "status" or "state" when referring to the lower sensor nodes 128 of the cables 104, may refer to whether a given lower sensor node 128 is "in commodity" (e.g., in contact with the commodity (e.g., the contents) within the container 106) or "out of commodity" (e.g., not in contact with the commodity within the container 106). Furthermore, based at least partially on a determination of which lower sensor nodes 128 of the cable assembly 102 are in commodity or out of commodity, the commodity monitoring system 120 may adjust operation of commodity management devices 118 of the container 106 to affect conditions of the commodity. In some embodiments, the commodity management devices 118 may include one or more of heaters, fans, blowers, churners, vents, etc. Furthermore, based at least partially on a determination of which lower sensor nodes 128 of the cable assembly 102 are in commodity or out of commodity, the commodity monitoring system 120 may determine (e.g., estimate) one or more upper surface profiles of the commodity within the container 106.

[0048] In some embodiments, a user can interface with the at least one client device 108, for example, to communicate with the at least one server 122 and to utilize the commodity monitoring system 120 to monitor contents of the container 106. The user mayinclude one or more operators of the container 106 and / or commodity monitoring system 120. Although FIG. 1 shows a single client device 108, the environment 100 can include any number of client devices 108, in communication with the network 110, the at least one server 122, and / or the cable assembly 102.

[0049] In some embodiments, the client device 108 may include a client application installed thereon. In one or more embodiments, the client application can be associated with the commodity monitoring system 120. For example, the client application may allow the client device 108 to directly or indirectly interface with other elements the commodity monitoring system 120 and the cable assembly 102. The client application also enables a user (e.g., an operator) to initiate measurements via the commodity monitoring system 120 and observe any results of the measurements (e.g., measured humidity, measured temperatures, measured moisture levels, etc.).

[0050] Both the at least one client device 108 and the at least one server 122 (and the commodity monitoring system 120) can represent various types of computing devices with which operators can interact. For example, the at least one client device 108 and / or the at least one server 122 may include a mobile device (e.g., a cell phone, a smartphone, a PDA, a tablet, a laptop, a watch, a wearable device, etc.). In some embodiments, however, the at least one client device 108, and / or at least one server 122 can be a non-mobile device (e.g., a desktop or server). In some embodiments, the at least one server 122 may include a cloud computing platform and may be configured to perform processing required to implement the commodity monitoring system 120. In one or more embodiments, the at least one server 122 may include a web server that provides a web site that can be used by operators monitoring the contents of the container 106 via a remote client device 108. Additional details with respect to the client device 108 and the server 122 are discussed below with respect to FIG. 3.

[0051] Referring still to FIG. 1, while the commodity monitoring system 120 is depicted as being a portion of (e.g., implemented by) the server 122, the disclosure is not so limited. Rather, in some embodiments, the commodity monitoring system 120 may be implemented at one or more of the client device 108, the cable assembly 102, cable hubs112, or the server 122. In some embodiments, the commodity monitoring system 120 may be implemented at a computing device that is local to the container 106 (e.g., edge computing). In some embodiments, the commodity monitoring system 120 may be implemented at different devices of the environment 100 operating according to a primarysecondary configuration or peer-to-peer configuration. For purposes of illustration and convenience, implementation of the commodity monitoring system 120 is described herein as being implemented by the server 122, with the understanding that functionality may be implemented in other and / or additional devices.

[0052] The network 110 may include one or more networks, such as the Internet, and can use one or more communications platforms or technologies suitable for transmitting data and / or communication signals. As a non-limiting example, the network 110 may utilize one or more of near field communication (NFC), BLUETOOTH ©, wireless / cellular networks, wide area networks (WAN), LoRa, wired communications, or any other conventional network for transmitting data and / or communication signals between the cable assembly 102, the client device 108, and the server 122.

[0053] Referring still to FIG. 1, in some embodiments, one or more of the at least one client device 108, the cable assembly 102, or the at least one server 122 may include a display for displaying data regarding measurements obtained via the cable assembly 102. In some embodiments, the data may include one or more parameters of commodity within the container 106. The parameters may include one or more of temperature, humidity, relative humidity, moisture, or carbon dioxide. In some embodiments, the commodity monitoring system 120 may utilize the parameters to determine when to actuate commodity management devices 118 of the container 106 to affect conditions of the commodity. As noted above, the commodity management devices 118 may include one or more of heaters, fans, blowers, churners, vents, etc.

[0054] FIG. 2 shows a flowchart of a method 200 for monitoring the contents (e.g., grain) within a container 106 according to one or more embodiments of the present disclosure. The method 200 may include receiving uppermost sensor data from an uppermost sensor node 126 of the cable assembly 102 to which a cable 104 is coupled, as isshown in act 202 of FIG. 2. In some embodiments, the commodity monitoring system 120 may receive the uppermost sensor data from the uppermost sensor node 126. In one or more embodiments, the commodity monitoring system 120 may receive the uppermost sensor data from the uppermost sensor node 126 via the gateway 114 and the network 110.

[0055] In one or more embodiments, the uppermost sensor data may have been captured via the uppermost sensor node 126. Furthermore, in some embodiments, the commodity monitoring system 120 may initiate (e.g., may have previously initiated) capturing the uppermost sensor data. In other words, the commodity monitoring system may have caused the uppermost sensor node 126 to capture the uppermost sensor data.

[0056] In some embodiments, the uppermost sensor data may include at least one of first temperature measurements (e.g., a first temperature profile) captured over a period of time or first relative humidity measurements (e.g., a first relative humidity profile) captured over the period of time. In one or more embodiments, the first temperature measurements and / or the first relative humidity measurements may be captured at least substantially continuously over the period of time. In additional embodiments, the first temperature measurements and / or the first relative humidity measurements may be captured at regular intervals (e.g., every minute, every second, every 10 milliseconds, etc.) over the period of time. As noted above, the uppermost sensor node 126 is assumed to be out of commodity.

[0057] The method 200 may further include receiving lower sensor data from a lower sensor node 128 of the cable 104, as shown in act 204 of FIG. 2. In some embodiments, the commodity monitoring system 120 may receive the lower sensor data from the lower sensor node 128. In some embodiments, the sensor node 116 may include a second-uppermost sensor node (e.g., a second highest sensor node) of the cable 104. In one or more embodiments, the commodity monitoring system 120 may receive the lower sensor data from the sensor node 116 via the gateway 114 and the network 110.

[0058] In one or more embodiments, the lower sensor data may have been captured via the lower sensor node 128. Furthermore, in some embodiments, the commodity monitoring system 120 may initiate (e.g., may have previously initiated) capturing the lowersensor data. In other words, the commodity monitoring system may have caused the lower sensor node 128 to capture the lower sensor data.

[0059] In some embodiments, the lower sensor data may include at least one of second temperature measurements (e.g., a second temperature profile) captured over the period of time (e.g., at least substantially the same period of time over which the first temperatures measurements were captured) or second relative humidity measurements (e.g., a second relative humidity profile) captured over the period of time. In one or more embodiments, the second temperature measurements and / or the second relative humidity measurements may be captured at least substantially continuously over the period of time. In additional embodiments, the second temperature measurements and / or the second relative humidity measurements may be captured at regular intervals (e.g., every minute, every second, every 10 milliseconds, etc.) over the period of time. In one or more embodiments, the first temperature measurements and the second temperature measurements may be captured at the same intervals over the period of time. In some embodiments, the first relative humidity measurements and the second relative humidity measurements may be captured at the same intervals over the period of time.

[0060] The period of time may include a window of time, such as, for example, three hours, four hours, five hours, ten hours, twenty hours, thirty hours, forty hours, or more. As a non-limiting example, the period of time may include a window of time of at least nine hours. As another example, the period of time may include a window of time of at least twelve hours.

[0061] Referring generally to FIG. 2 and method 200, in some embodiments, other measurements may be captured via the uppermost sensor node 126 and lower sensor nodes 128 instead of or in addition to temperature measurements and relative humidity measurements. For example, moisture measurements and / or carbon dioxide (CO2) measurements may be captured via the uppermost sensor node 126 and lower sensor nodes 128 instead of or in addition to temperature measurements and relative humidity measurements. For ease of explanation, method 200 is described utilizing only temperature and / or relative humidity measurements; however, the disclosure is not so limited, and ineach instance where temperature and / or relative measurements are described or mentioned, moisture measurements and / or carbon dioxide (CO2) measurements may be utilized instead of or in addition to the temperature and / or relative humidity measurements.

[0062] In some embodiments, the method 200 may optionally include receiving external condition data representing at least one of plenum conditions of a commodity management device 118 or outdoor weather conditions, as shown in act 206 of FIG. 2. In one or more embodiments, the commodity monitoring system 120 may receive the external condition data representing at least one of plenum conditions or outdoor weather conditions. As a non-limiting example, the commodity monitoring system 120 may receive the external condition data from one or more of the commodity management sensor 132 or the external sensor 134. Additionally, in some embodiments, the commodity monitoring system 120 may receive the external condition data from an external weather monitoring system (e.g., weather.com).

[0063] In some embodiments, the external condition data may include one or more of temperature data, pressure data, relative humidity data, or weather forecasts (e.g., temperature forecasts, rain forecasts, humidity forecasts, etc.).

[0064] F urthermore, the method 200 may include analyzing at least the uppermost sensor data and the lower sensor data via one or more machine learning models, as shown in act 208 of FIG. 2. For example, the commodity monitoring system 120 may analyze at least the uppermost sensor data and the lower sensor data via one or more machine learning models. In some embodiments, analyzing at least the uppermost sensor data and the lower sensor data via one or more machine learning models may include analyzing at least the uppermost sensor data, the lower sensor data, and the external condition data.

[0065] In some embodiments, the commodity monitoring system 120 may analyze at least the uppermost sensor data and the lower sensor data and / or perform any of the analyses described herein via one of more of structured or unstructured machine-learning models. The machine-learning models may include a quadratic regression analysis, a logistic regression analysis, a support vector machine, a Gaussian process regression, ensemble models, or any other regression analysis. Furthermore, in yet further embodiments, themachine-learning models may include decision tree learning, regression trees, boosted trees, gradient boosted tree, multilayer perceptron, one-vs-rest, Naive Bayes, k-nearest neighbor, association rule learning, a neural network, deep learning, pattern recognition, or any other type of machine-learning.

[0066] The commodity monitoring system 120 may apply one or more of the abovedescribed machine learning techniques to at least the uppermost sensor data and the lower sensor data in conjunction with data representing measured conditions (e.g., temperature data, relative humidity data, pressure data, moisture data, and / or carbon dioxide (CO2) data) associated with known nodes statuses, relative uppermost sensor node 126 conditions associated with the known nodes statuses, and relative external environment conditions (referred to hereinafter as "external condition data) associated with the known nodes statuses. As a non-limiting example, the commodity monitoring system 120 may utilize measured condition data (e.g., conditions within container, at the uppermost sensor node 126, and / or outside of the container 106 (e.g., external)) associated with known nodes statuses to train the machine-learning models to develop / determine correlations (e.g., definitions of correlations) between node statuses (e.g., in or out of commodity) and condition data and correlate the condition data with node statuses. Furthermore, analyzing at least the uppermost sensor data and the lower sensor data via the one or more machinelearning models may include comparing the measured conditions represented in the uppermost sensor data (e.g., uppermost sensor node 126 conditions), which is known to be out of commodity, to the measured conditions represented in the lower sensor data (e.g., the sensor node 116 conditions).

[0067] In other words, via the machine learning model techniques, the commodity monitoring system 120 may learn trends and correlations between nodes statuses (e.g., in or out of commodity) and the measured conditions and relative uppermost sensor node 126 conditions and external environment conditions. Put another way, the commodity monitoring system 120 may learn relationships between node statuses and measured conditions and relative uppermost sensor node 126 conditions and external environment conditions. Put yet another way, the commodity monitoring system 120 may learnrelationships between node statuses and the lower sensor data (e.g., measured conditions at a lower sensor node 128), the uppermost sensor data (e.g., relative uppermost sensor node 126 conditions (e.g., relative to the measured conditions at a lower sensor node 128)), and the external condition data (e.g., relative external environment conditions (e.g., relative to the measured conditions at a sensor node 116). For example, as will be understood in the art, for a given set of input values (e.g., the uppermost sensor data, the lower sensor data, and the external condition data), the commodity monitoring system 120 is expected to produce the same output values (i.e., correct identification of the node statuses (e.g., in or out of commodity)). In particular, the machine learning models may be trained via supervised learning, as is known in the art. After a sufficient number of iterations, the machine learning models become trained machine-learning models. In some embodiments, the machine learning models may also be trained on historical data from previously- identified node statuses and measured conditions and relative uppermost sensor node 126 conditions and external environment conditions. In view of the foregoing, and as is described below, in some embodiments, the commodity monitoring system 120 may determine node statuses at least partially via any of the machine-learning techniques described herein.

[0068] The method 200 may further include determining of a status of the lower sensor node 128 of the cable 104 , as shown in act 210 of FIG. 2. In some embodiments, the commodity monitoring system 120 may determine the status of the lower sensor node 128 of the cable 104 from which the lower sensor data was received. As mentioned above, the status of the sensor node 116 may refer to whether the lower sensor node 128 is "in commodity" (e.g., in contact with the commodity (e.g., the contents) within the container 106) or "out of commodity" (e.g., not in contact with the commodity within the container 106). The status of the lower sensor node 128 of the cable 104 may be determined based on the analysis performed on the uppermost sensor data and the lower sensor data via one or more machine learning models, as described above in act 208 of FIG. 2.

[0069] Responsive to a determination that the lower sensor node 128 is out of commodity, the method 200 may include repeating acts 204 through act 210 for a vertica I ly- adjacent lower sensor node 128 of the cable 104, as shown in act 212 of FIG. 2. For example,the method 200 may begin with a second-uppermost sensor node 116 (e.g., a second highest sensor node 116 overall or highest lower sensor node 128 in a vertical direction) of the cable 104, and responsive to a determination that the second-uppermost sensor node 116 is out of commodity, a status of a third-uppermost sensor node 116 may be analyzed via acts 202 through 236. Furthermore, the method 200 may include analyzing the status of each consecutive lower sensor node 128 of the cable 104 in a downward direction until a lower sensor node 128 of the cable 104 is determined to be in commodity or until a status of each lower sensor node 128 of the cable 104 is determined. Additionally, responsive to a determination that a given lower sensor node 128 is in commodity, each lower sensor node 128 of the cable 104 below the given lower sensor node 128 may be assumed and determined to be in commodity. In additional embodiments, a status of each and every lower sensor node 128 of the cable 104 is individually analyzed and determined.

[0070] Referring still to act 212, alternatively, each sensor node 116 of a given cable 104 will be analyzed at least substantially simultaneously via act 204 through act 210.

[0071] Referring still to FIG. 2, in some embodiments, each cable 104 of the cable assembly 102 may be analyzed independently via method 200. In additional embodiments, two or more of the cables of the cable assembly 102 may be analyzed at least substantially simultaneously via method 200.

[0072] In some embodiments, the method 200 may further optionally include adjusting operation of one or more commodity management devices 118, as shown in act 214 of FIG. 2. For example, the commodity monitoring system 120 may adjust operation of one or more commodity management devices 118. In one or more embodiments, the commodity monitoring system 120 may adjust operation of one or more commodity management devices 118 based at least partially on the determined statuses of the lower sensor nodes 128 of the cable assembly 102. For example, which lower sensor nodes 128 of the cable assembly 102 are determined to be in commodity and which lower sensor nodes 128 of the cable assembly 102 are determined to be out of commodity may influence operation of the one or more commodity management devices 118. As noted above, the oneor more commodity management devices 118 may include one or more of heaters, fans, blowers, churners, vents, etc.

[0073] Referring still to act 214 of FIG. 2, knowing which lower sensor nodes 128 of the cable assembly 102 are in commodity and which lower sensor nodes 128 of the cable assembly 102 are out of commodity may improve data (e.g., provide more accurate data) utilized to operate the one or more commodity management devices 118. For example, in drying operations, fans, blowers, and / or heaters draw and / or blow air from outside the container 106 into the container 106. The incoming air will have a certain humidity (e.g., moisture content) and temperature. When the commodity is exposed to the air, a moisture and a temperature of the commodity will eventually reach an equilibrium point approaching the moisture content and the temperature of the air. As a non-limiting example, the air may have an equilibrium moisture content of about 14%, and prolonged exposure to the air causes the commodity to approach a moisture content of about 14%. However, in typical operations, fans, blowers, and / or drier are set to dry (e.g., bring in air from out outside of the container 106) as long the incoming air is within a target range of temperatures and moisture contents for the commodity or as long as the incoming air is at a temperature and / or a moisture content that will cause the commodity to approach the target range of temperatures and moisture contents. Accordingly, accurate data from the commodity can be critical to know when fans, blowers, and / or heaters should be operating. In view of the foregoing, by knowing which lower sensor nodes 128 are in commodity, only data from those in-commodity sensor nodes 116 may be utilized in determining moisture contents and temperatures of the commodity, and the data from the lower sensor nodes 128 out of commodity can be disregarded or not captured. Accordingly, the commodity monitoring system 120 and methods of the present disclosure result in more accurate data than conventional commodity monitoring systems. Furthermore, having more accurate data can result in faster and more accurate commodity treatments (e.g., drying).

[0074] In some embodiments, adjusting operation of one or more commodity management devices 118 may include one or more of turning on or off fans, blowers, and / orheaters, increasing or decreasing air flow through the commodity via fans, blowers, and / or heaters, turning on or off churners, and / or opening or closing vents of the container 106.

[0075] Referring still to FIG. 2, in some embodiments, the method 200 may optionally include determining (e.g., estimating) one or more profiles of an upper surface of the commodity, as shown in act 216. For example, the commodity monitoring system 120 may determine (e.g., estimate) one or more profiles of an upper surface of the commodity, as shown in act 216. In some embodiments, by determining, for each lower sensor node 128 of each cable 104 of the cable assembly 102, whether the lower sensor node 128 is in commodity or out of commodity and based on known elevations (e.g., vertical locations) and known locations of the sensor nodes 116 of the cable assembly 102, the commodity monitoring system 120 may determine heights of the commodity at each of the cables 104 of the cable assembly 102.

[0076] In some embodiments, determining heights of the commodity at each of the cables 104 of the cable assembly 102 may include determining the heights of the commodity based at least partially on a known time period since a given lower sensor node 128 was determined to change from being in commodity to out of commodity. For example, determining heights of the commodity at each of the cables 104 of the cable assembly 102 may include estimating how much the height of the commodity has changed relative to an elevation of given lower sensor node 128, previously determined to be in commodity, based at least partially on one or more of 1) a known time period since the given lower sensor node 128 was determined to be in commodity, 2) a known amount of commodity (e.g., grain) added to the container 106, 3) a known amount of commodity (e.g., grain) removed from the container 106, and / or 4) a known rate at which the height of the contents has changed previously.

[0077] Determining heights of the commodity at each of the cables 104 of the cable assembly 102 may enable the commodity monitoring system 120 to determine (e.g., estimate) one or more profiles of an upper surface of the commodity. Furthermore, determining (e.g., estimating) one or more profiles of an upper surface of the commoditymay enable the commodity monitoring system 120 to determine a volume of the commodity within the container 106.

[0078] Additionally, the method 200 may include outputting determined heights, the determined upper surface profiles, and / or determined volumes of the commodity to the client device 108. For example, the commodity monitoring system 120 may cause the determined heights, the determined upper surface profiles, and / or the determined volumes of the commodity to be displayed on the client device 108. Additionally, the method 200 may include outputting the determined heights, the determined upper surface profiles, and / or the determined volumes of the commodity to one or more third party systems.

[0079] FIG. 3 is a schematic view of a computer device 314. In some embodiments, one or more of the commodity management device 118, the client device 108, and / or the server 122 may include a computer device such as the computer device 314 of FIG. 3. The computer device 314 may include a communication interface 302, a processor 304, a memory 306, a storage device 308, an input / output device 310, and a bus 312.

[0080] In some embodiments, the processor 304 includes hardware for executing instructions, such as those making up a computer program. As an example, and not by way of limitation, to execute instructions, the processor 304 may retrieve (or fetch) the instructions from an internal register, an internal cache, the memory 306, or the storage device 308 and decode and execute them. In some embodiments, the processor 304 may include one or more internal caches for data, instructions, or addresses. As an example, and not by way of limitation, the processor 304 may include one or more instruction caches, one or more data caches, and one or more translation look aside buffers (TLBs). Instructions in the instruction caches may be copies of instructions in the memory 306 or the storage device 308.

[0081] The memory 306 may be coupled to the processor 304. The memory 306 may be used for storing data, metadata, and programs for execution by the processor(s). The memory 306 may include one or more of volatile and non-volatile memories, such as Random-Access Memory ("RAM"), Read-Only Memory ("ROM"), a solid state disk ("SSD"),Flash, Phase Change Memory ("PCM"), or other types of data storage. The memory 306 may be internal or distributed memory.

[0082] The storage device 308 may include storage for storing data or instructions. As an example, and not by way of limitation, storage device 308 can comprise a non- transitory storage medium described above. The storage device 308 may include a hard disk drive (HDD), Flash memory, an optical disc, a magneto-optical disc, magnetic tape, or a Universal Serial Bus (USB) drive or a combination of two or more of these. The storage device 308 may include removable or non-removable (or fixed) media, where appropriate. The storage device 308 may be internal or external to the computing storage device 308. In one or more embodiments, the storage device 308 is non-volatile, solid-state memory. In other embodiments, the storage device 308 includes read-only memory (ROM). Where appropriate, this ROM may be mask programmed ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), electrically alterable ROM (EAROM), or Flash memory or a combination of two or more of these.

[0083] The input / output device 310 may allow an operator of the commodity monitoring system 120 to provide input to, receive output from, and otherwise transfer data to and receive data from computer device 314. The input / output device 310 may include a mouse, a keypad or a keyboard, a joystick, a touch screen, a camera, an optical scanner, network interface, modem, other known I / O devices, or a combination of such I / O interfaces. The input / output device 310 may include one or more devices for presenting output to an operator, including, but not limited to, a graphics engine, a display (e.g., a display screen), one or more output drivers (e.g., display drivers), one or more audio speakers, and one or more audio drivers. In certain embodiments, the input / output device 310 is configured to provide graphical data to a display for presentation to an operator. The graphical data may be representative of one or more graphical user interfaces and / or any other graphical content as may serve a particular implementation. As is described above, the computer device 314 and the input / output device 310 may be utilized to display data (e.g., images and / or video data) regarding the contents of the container 106. 1

[0084] The communication interface 302 can include hardware, software, or both. The communication interface 302 may provide one or more interfaces for communication (such as, for example, packet-based communication) between the computer device 314 and one or more other computing devices or networks (e.g., a server). As an example, and not by way of limitation, the communication interface 302 may include a network interface controller (NIC) or network adapter for communicating with an Ethernet or other wire-based network or a wireless NIC (WNIC) or wireless adapter for communicating with a wireless network, such as a WI-FI.

[0085] In some embodiments, the bus 312 (e.g., a Controller Area Network (CAN) bus) may include hardware, software, or both that couples components of computer device 314 to each other and to external components.

[0086] All references cited herein are incorporated herein in their entireties. If there is a conflict between definitions herein and in an incorporated reference, the definition herein shall control.

[0087] The embodiments of the disclosure described above and illustrated in the accompanying drawings do not limit the scope of the disclosure, which is encompassed by the scope of the appended claims and their legal equivalents. Any equivalent embodiments are within the scope of this disclosure. Indeed, various modifications of the disclosure, in addition to those shown and described herein, such as alternate useful combinations of the elements described, will become apparent to those skilled in the art from the description. Such modifications and embodiments also fall within the scope of the appended claims and equivalents.

Claims

CLAIMSWhat is claimed is:

1. A method of monitoring a commodity within a container, the method comprising: receiving uppermost sensor data from an uppermost sensor node of a cable of a cable assembly within the container; receiving lower sensor data from a lower sensor node of the cable; analyzing the uppermost sensor data and the lower sensor data via at least one machine learning model; and based at least partially on the analysis of the uppermost sensor data and the lower sensor data, determining whether the lower sensor node of the cable is in a commodity within the container or out of the commodity within the container.

2. The method of claim 1, wherein analyzing the uppermost sensor data and the lower sensor data via at least one machine learning model comprises analyzing the uppermost sensor data and the lower sensor data via at least one of a quadratic regression analysis, a logistic regression analysis, a support vector machine, a Gaussian process regression, or an ensemble model.

3. The method of claim 1, wherein analyzing the uppermost sensor data and the lower sensor data via at least one machine learning model comprises analyzing the uppermost sensor data and the lower sensor data via at least one of a decision tree learning, regression trees, boosted trees, gradient boosted tree, multilayer perceptron, one-vs-rest, Naive Bayes, k-nearest neighbor, association rule learning, a neural network, deep learning, or pattern recognition.

4. The method of any one of claims 1 to 3, wherein analyzing the uppermost sensor data and the lower sensor data via at least one machine learning model comprises analyzing the uppermost sensor data and the lower sensor data based on learnedcorrelations between sensor node states and conditions within the container and conditions at the uppermost sensor node.

5. The method of claim 4, wherein the conditions within the container of the learned correlations comprise at least one of temperature or relative humidity.

6. The method of claim 4 or 5, wherein the conditions within the container of the learned correlations further comprise at least one of moisture levels and carbon dioxide levels.

7. The method of any one of claims 4 to 6, wherein the conditions at the uppermost sensor node of the learned correlations comprise at least one of temperature or relative humidity.

8. The method of claim 1, further comprising: receiving external condition data representing at least one of plenum conditions of a commodity management device or outside weather conditions.

9. The method of claim 8, further comprising analyzing the uppermost sensor data and the lower sensor data in conjunction with the received external condition data via at least one machine learning model.

10. The method of claim 8, wherein the external condition data comprises at least one of temperature data, pressure data, relative humidity data, or weather forecasts.

11. The method of any one of claims 1 to 9, further comprising, responsive to determining that the sensor node is out of commodity: receiving additional lower sensor data from a lower sensor node of the cable; analyzing the uppermost sensor data and the additional lower sensor data via at least one machine learning model; and based at least partially on the analysis of the uppermost sensor data and the additional lower sensor data, determining whether the lower sensor node of the cable is in a commodity within the container or out of the commodity within the container.

12. The method of any one of claims 1 to 9, further comprising, responsive to a determination as to whether the lower sensor node is in commodity or out of commodity, adjusting operation of one or more commodity treatment devices of the container.

13. The method of claim 12, wherein adjusting operation of the one or more commodity treatment devices of the container comprises at least one of turning on or off fans, blowers, or heaters, increasing or decreasing air flow through the commodity via fans, blowers, or heaters, turning on or off ch urners, or opening or closing vents of the container.

14. The method of any one of claims 1-13, wherein the uppermost sensor data comprises at least one of first temperature measurements or first relative humidity measurements captured over a period of time, and wherein the lower sensor data comprises at least one of second temperature measurements or second relative humidity measurements captured over the period of time.

15. The method of any one of claims 1-13, wherein the uppermost sensor data comprises a first temperature profile over a period time, and wherein the lower sensor data comprises a second temperature profile over the period of time.

16. A system, comprising: a container; a cable assembly disposed within the container and comprising: at least one cable comprising a plurality of sensor nodes operably coupled to the at least one cable; and a commodity monitoring system in communication with the cable assembly and comprising: at least one processor; and at least one non-transitory computer-readable storage medium storing instructions thereon that, when executed by the at least one processor, cause the commodity monitoring system to: receive uppermost sensor data from an uppermost sensor node of the plurality of sensor nodes; receive lower sensor data from a lower sensor node of the plurality of sensor nodes of the cable; analyze the uppermost sensor data and the lower sensor data via at least one machine learning model; and based at least partially on the analysis of the uppermost sensor data and the lower sensor data, determine whether the lower sensor node of the plurality of sensor nodes of the cable is in a commodity within the container or out of the commodity within the container.

17. The system of claim 16, further comprising instructions that, when executed by the at least one processor, cause the commodity monitoring system to: receive external condition data representing at least one of plenum conditions of a commodity management device or outside weather conditions.

18. The system of claim 17, further comprising instructions that, when executed by the at least one processor, cause the commodity monitoring system to: analyze the uppermost sensor data and the lower sensor data in conjunction with the received external condition data via at least one machine learning model.

19. The system of claim 17, wherein analyzing the uppermost sensor data and the lower sensor data via at least one machine learning model comprises analyzing the uppermost sensor data and the lower sensor data based on learned correlations between sensor node states and conditions within the container and conditions at the uppermost sensor node.

20. A method of monitoring a commodity within a container, the method comprising, based on a machine learning analysis of measured conditions at an uppermost sensor node of a cable of a cable assembly within the container and measured conditions at lower sensor nodes of the cable, determining which lower sensor nodes of the cable are in commodity and which lower sensor nodes of the cable are out of commodity.

Images