WO2020210083A1

WO2020210083A1 - Method and system for managing refrigerated air usage

Info

Publication number: WO2020210083A1
Application number: PCT/US2020/025910
Authority: WO
Inventors: Kirk Erich Mellits
Original assignee: Kps Global Llc
Priority date: 2019-04-09
Filing date: 2020-03-31
Publication date: 2020-10-15

Abstract

Techniques for monitoring refrigerated air usage in a refrigerated enclosure are provided. Training data for a refrigerated enclosure machine learning model may be generated based on historical sensor data associated with one or more refrigerated enclosures. The refrigerated enclosure machine learning model may be trained using the training data, and the trained refrigerated enclosure machine learning model may be applied to current sensor data, captured by one or more sensors associated with a particular refrigerated enclosure, to identify/predict an anomalous condition associated with the particular refrigerated enclosure. For example, the anomalous condition may indicate a performance failure, safety concern, security situation, etc. Based on the identified anomalous condition, an action associated with the particular refrigerated enclosure may be triggered.

Description

METHOD AND SYSTEM FOR MANAGING REFRIGERATED AIR USAGE

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to and the benefit of U.S. Provisional Application No. 62/831 ,503, filed April 9, 2019, the disclosure of which is hereby incorporated by reference in its entirety.

FIELD OF THE DISCLOSURE

[0002] The present disclosure generally relates to refrigerated enclosures and, more particularly, to monitoring refrigerated air usage in a refrigerated enclosure.

BACKGROUND

[0003] The background description provided herein is for the purpose of generally presenting the context of the disclosure. Work of the presently named inventors, to the extent it is described in the background section, as well as aspects of the description that may not otherwise qualify as prior art at the time of filing, are neither expressly nor impliedly admitted as prior art against the present disclosure.

[0004] Currently, operators of refrigerated enclosures monitor the temperature of a refrigerated enclosure and its associated refrigeration equipment (and sometimes pressure) to ensure that the contents of the refrigerated enclosure are being kept cold. However, merely measuring the temperature of a refrigerated enclosure or its associated refrigeration equipment provides limited information to an operator. In particular, a measurement of the current temperature of a refrigerated enclosure alone does not typically provide an operator with enough information to predict future issues or conditions in the refrigerated enclosure. For example, by the time the temperature of a refrigerated enclosure or its associated refrigeration equipment exceeds a given temperature threshold, the refrigerated enclosure may have been heating or otherwise leaking cold air for hours due to equipment failures, open doors, or other problems. Moreover, diagnosing and rectifying the problem can take an operator additional hours or days, during which time food or other products contained within the refrigerated enclosure may become unusable. Consequently, due to this limited information, operators currently must rely on costly and time consuming corrective maintenance rather than less costly preventative maintenance when addressing conditions arising in a refrigerated enclosure. Additionally, measuring only the temperature of a refrigerated enclosure or its associated refrigeration equipment typically cannot provide an operator with any insight as to potential performance, safety, or security issues within the refrigerated enclosure. SUMMARY

[0005] Generally speaking, the present disclosure provides techniques for monitoring refrigerated air usage in a refrigerated enclosure.

[0006] In one aspect, a computer-implemented method for monitoring refrigerated air usage is provided. The method comprises generating, by a processor, training data based on historical sensor data associated with one or more refrigerated enclosures; training, by the processor, a refrigerated enclosure machine learning model using the training data; applying, by the processor, the trained refrigerated enclosure machine learning model to current sensor data captured by one or more sensors associated with a particular refrigerated enclosure to identify and/or predict an anomalous condition associated with the particular refrigerated enclosure; and triggering, by the processor, an action associated with the particular refrigerated enclosure based on the identified anomalous condition

[0007] In another aspect, a system for monitoring refrigerated air usage is provided. The system comprises one or more sensors associated with a particular refrigerated enclosure; one or more processors; and one or more memories storing instructions. The instructions, when executed by the one or more processors, cause the one or more processors to: generate training data based on historical sensor data associated with one or more refrigerated enclosures; train a refrigerated enclosure machine learning model using the training data; apply the trained refrigerated enclosure machine learning model to current sensor data captured by the one or more sensors associated with the particular refrigerated enclosure to identify and/or predict an anomalous condition associated with the particular refrigerated enclosure; and trigger an action associated with the particular refrigerated enclosure based on the identified anomalous condition.

[0008] In still another aspect, a tangible, non-transitory computer-readable medium storing executable instructions for monitoring refrigerated air usage is provided. The instructions, when executed by at least one processor of a computing device, causes the computing device to: generate training data based on historical sensor data associated with one or more refrigerated enclosures; train a refrigerated enclosure machine learning model using the training data; apply the trained refrigerated enclosure machine learning model to current sensor data captured by the one or more sensors associated with the particular refrigerated enclosure to identify and/or predict an anomalous condition associated with the particular refrigerated enclosure; and trigger an action associated with the particular refrigerated enclosure based on the identified anomalous condition. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] FIG. 1 illustrates an exemplary computer system in which techniques for monitoring refrigerated air usage in a refrigerated enclosure may be implemented, in accordance with some embodiments;

[0010] FIGs. 2A-2B illustrate a block diagram of an example machine learning model which the system of FIG. 1 can use to identify anomalous conditions associated with the refrigerated enclosure, in accordance with some embodiments;

[0011] FIGs. 3A and 3B illustrate example user interface screens which a computing device may generate in order to notify a user of an anomalous condition associated with a refrigerated enclosure, in accordance with some embodiments; and

[0012] FIG. 4 illustrates a flow diagram of an exemplary computer-implemented method of monitoring refrigerated air usage in a refrigerated enclosure, in accordance with some embodiments.

DETAILED DESCRIPTION

[0013] The present disclosure provides techniques for monitoring refrigerated air usage in a refrigerated enclosure by using a machine learning model trained using historical sensor data to identify or predict anomalous conditions in the refrigerated enclosure based on current sensor data captured by a variety of different sensors in the refrigerated enclosure. Upon identification or prediction of an anomalous condition, which may be a performance failure, a safety condition, a security issue, etc., an action may be triggered to alert a user, a maintenance service, or appropriate authorities of the condition or potential condition. Additionally, in some examples, upon identification or prediction of an anomalous condition, a computing device may transmit instructions to a controller, causing the controller to automatically activate refrigeration equipment and/or modify settings in the refrigerated controller to remedy the anomalous condition (e.g., by using actuators to physically adjust mechanisms that change settings or set conditions).

[0014] Turning now to the drawings, FIG. 1 illustrates an exemplary computer system 100 in which techniques for monitoring refrigerated air usage in a refrigerated enclosure may be implemented, in accordance with some embodiments. The example computer system 100 may include a data acquisition device 104 and a controller 106 associated with a refrigerated enclosure 102, as well as a server 108 and a computing device 1 10. The data acquisition device 104 and the controller 106 may communicate with the server 108 and the computing device 1 10 via a network 1 12. The network 1 12 may be, for example, a local area network (LAN) or a wide area network (WAN) such as the Internet, and/or a cloud-based network.

[0015] The data acquisition device 104 may interface with sensors 1 14 positioned within or otherwise associated with the refrigerated enclosure 102 to collect data captured by the sensors 1 14 and transmit this sensor data to the server 108, e.g., via the network 1 12. Although FIG. 1 illustrates five sensors 1 14, there may be any number of sensors 1 14 in various embodiments. The sensors may include, for example, lighting status sensors, door status sensors, occupancy sensors, inventory level sensors, humidity sensors, temperature sensors, power status sensors, refrigeration performance sensors, defrost sensors, fan status sensors, air flow sensors, heater status sensors, alarm sensors, carbon monoxide sensors, heat flux sensors, video-computer vision, etc.

[0016] Generally speaking, the lighting status sensors may detect whether various lights associated with the refrigerated enclosure 102 are on or off. The lighting status sensors may include, e.g., light sensors configured to detect the presence or absence of light and/or voltage logic inputs configured to detect whether power is being provided to lighting within the refrigerated enclosure.

[0017] The door status sensors may detect whether various doors associated with the refrigerated enclosure 102 are open, closed, or latched. For example, the door status sensors may include a magnetic switch that can be used to identify whether a door is open or closed and/or whether a latch associated with the door is open or closed.

[0018] The occupancy sensors may detect whether a person is inside the refrigerated enclosure 102. These sensors may include, e.g., video-computer vision, proximity sensors, and/or motion sensors configured to capture data indicative of human presence in various areas of the interior of the refrigerated enclosure 102.

[0019] The inventory level sensors may capture data associated with the quantity of product stored within the refrigerated enclosure 102. These inventory level sensors may include, e.g., a scale sensor configured to determine the quantity of product stored within the refrigeration enclosure 102 based on weight (e.g., on each level or shelf within the refrigerated enclosure 102). Additionally or alternatively, these inventory level sensors may include proximity sensors located in various locations or various shelves of the refrigerated enclosure 102.

[0020] The humidity sensors may capture data indicating the humidity level within the refrigerated enclosure 102, e.g., by monitoring dew points at various locations within the refrigerated enclosure 102.

[0021] The temperature sensors may include thermocouples or digital thermometers configured to capture temperature data in various locations within the refrigerated enclosure 102.

[0022] The power status sensors may monitor current draw and/or voltage availability input for the refrigerated enclosure as a whole or for various refrigeration equipment associated with the refrigerated enclosure 102.

[0023] The refrigeration performance sensors may capture performance metric data for refrigeration equipment such as compressors, evaporators, etc., associated with the refrigerated enclosure 102.

[0024] The defrost sensors may include voltage logic inputs configured to detect whether power is being provided to various defrosters associated with the refrigerated enclosure 102.

[0025] The fan status sensors may include voltage logic inputs configured to detect whether power is being provided to various fans associated with the refrigerated enclosure 102.

[0026] The airflow sensors may monitor air circulation within the refrigerated enclosure 102. These sensors may include flapper and/or damper switch inputs configured to detect whether flappers and/or dampers associated with the refrigerated enclosure 102 are open or closed.

[0027] The heater status sensors may include voltage logic inputs configured to detect whether power is being provided to various anti-icing heaters associated with the refrigerated enclosure 102.

[0028] The alarm sensors may include mechanical switch inputs and/or may include voltage logic inputs configured to detect whether various emergency alarms associated with the refrigerated enclosure 102 are on or off.

[0029] The carbon monoxide sensors may detect the presence of carbon monoxide in the air associated with the refrigerated enclosure 102. [0030] The heat flux sensors may detect heat rate traveling through panels in order to determine localized heat transfer issues and/or heat infiltration associated with the refrigerated enclosure 102.

[0031] In some embodiments, the video-computer vision may be used to supplement or replace some of these sensors. For example, the video-computer vision may be used to detect that a door associated with the refrigerated enclosure 102 is opened or closed, or whether lights associated with the refrigerated enclosure 102 are on or off.

[0032] Generally speaking, the controller 106 may include control circuitry 1 16 for controlling refrigeration equipment positioned within or otherwise associated with the refrigerated enclosure 102. The refrigeration equipment may include, e.g., one or more compressors 1 18, one or more condensers 120, one or more evaporators 122, one or more fans 124, one or more defrosters 126, one or more de-icing heaters 128, one or more doors 130, one or more alarms 132, one or more lights 133, etc. Of course, in some embodiments the controller circuitry 1 16 may control additional or alternative refrigeration equipment. Generally speaking, the control circuitry 1 16 may control the activation and/or deactivation of the refrigeration equipment. For example, the control circuitry may power up or power down a fan 124 or lights 133 at various times. As another example, the control circuitry 1 16 may cause a door 130 to open or close, and/or to latch or unlatch. Additionally, the control circuitry 1 16 may modify settings associated with the refrigeration equipment. For instance, the control circuitry 1 16 may modify the temperature settings associated with a de-icing heater 128 to raise or lower the temperature of the heat being provided by the de-icing heater 128.

[0033] The controller 106 may transmit data associated with the control of the refrigeration equipment to the server 108, e.g., via the network 1 12. This data may include indications of refrigeration equipment that is activated or deactivated (e.g., including timestamps), as well as indications of controlled settings and indications of instances in which controlled settings are modified (e.g., including timestamps).

[0034] The server 108 may include one or more general-purpose (e.g., microcontrollers and/or microprocessors) or special-purpose processors 134 and a memory 136. The memory 136 may be a non-transitory memory and can include one or several suitable memory modules, such as random access memory (RAM), read-only memory (ROM), flash memory, other types of persistent memory, etc. The memory 136 may include a refrigerated enclosure application 138 and a refrigerated enclosure machine learning model 140. Generally speaking, the refrigerated enclosure application 138 may obtain sensor data transmitted to the server 108 by the data acquisition device 104, as well as data associated with the control of the refrigeration equipment transmitted to the server 108 by the controller 106 and/or historical sensor data from a historical database 142, and use this data to train and operate the refrigerated enclosure machine learning model 140 in accordance with the scheme illustrated in FIGs. 2A-2B. As discussed in greater detail with respect to FIGs. 2A-2B, the refrigerated enclosure machine learning model 140 may predict or identify anomalous conditions associated with the

refrigerated enclosure 102, and/or settings or other refrigeration equipment controls predicted to preemptively correct for such anomalous conditions.

[0035] Based on anomalous conditions in the refrigerated enclosure 102 predicted and/or identified by the refrigerated enclosure machine learning model 140 and/or the settings or other refrigeration equipment controls predicted to preemptively correct for such anomalous conditions, the refrigerated enclosure application 138 may generate and/or transmit notifications or alerts to the computing device 1 10.

[0036] Generally speaking, the computing device 1 10 may be, for example, a personal computer, a portable device such as a tablet computer or smartphone, a wearable computing device, etc. As illustrated in FIG. 1 , the computing device 1 10 may include processing hardware such one or more processors 146 (which may be, e.g., microcontrollers and/or microprocessors) and a memory 148. The computing device 1 10 also can include a user interface 152. The memory 148 of the computing device 1 10 may be a non-transitory memory and may include one or several suitable memory modules, such as random access memory (RAM), read-only memory (ROM), flash memory, other types of persistent memory, etc. The memory 148 may further include a refrigerated enclosure monitoring application 150. The refrigeration enclosure monitoring application 150 may be configured to receive notifications and/or alerts transmitted by the server 108 to the computing device 1 10 and display these notifications and/or alerts to a user, e.g. via the user interface 152, as discussed in greater detail with respect to FIG. 3.

[0037] Additionally, in some embodiments, the refrigerated enclosure application 138 may automatically send instructions to the controller 106 for modifying settings or other refrigeration equipment controls based on the predictions of the refrigerated enclosure machine learning model 140. For example, the refrigerated enclosure application 138 may transmit the corrective settings generated by the refrigerated enclosure machine learning model 140 as instructions to the controller 106 (e.g., via the network 1 12), and the control circuitry 1 16 may in turn control the refrigeration equipment according to the instructions. [0038] Now referring to FIGs. 2A-2B, as discussed above, the refrigerated enclosure application 138 may train and operate the refrigerated enclosure machine learning model 140 in accordance with the scheme 200.

[0039] The refrigerated enclosure application 138 can receive various input signals, including historical data 202, current performance failure event data 204, current safety event data 206, current security event data, current sensor data 208 from sensors associated with the refrigerated enclosure, inventory status data 210, default settings 212, initial settings 214, energy use restrictions 216, safety restrictions 218, the size and/or dimensions 220 of the refrigerated enclosure 102. Generally speaking, the feature extraction functions 225 can operate on at least some of these input signals to generate feature vectors, or logical groupings of parameters associated with a refrigerated enclosure conditions at various dates and/or times. For example, the feature extraction functions 225 may generate a feature vector that indicates that, for a particular temperature level and for a particular humidity level, the result corresponds to a particular historical performance failure. As another example, the feature extraction functions 225 may generate a feature vector that indicates that, for a particular defrost level and a particular heater status, the result corresponds to an increased temperature in the refrigerated enclosure. As still another example, the feature extraction functions 225 may generate a feature vector that indicates that, for a particular door status, lighting status, and occupancy level, the result corresponds to a historical safety event (e.g., a person trapped in the refrigerated enclosure 102). As an additional example, the feature extraction functions 225 may generate a feature vector that indicate, for a particular occupancy status, lighting status, and date/time, the result corresponds to a historical security event (e.g., theft, burglary, trespassing, etc.). The results can be used as a set of labels for the feature vector.

[0040] For example, the historical data 202 may include historical performance failure event data 232, historical safety event data 234, historical security event data 235, historical setting data 236, historical sensor data 238, etc. The historical data 202 may include data associated with various refrigerated enclosures over time, and may be stored in the historical database 142 as shown in FIG. 1.

[0041] To process historical performance failure event data 232, the feature extraction functions 225 may identify dates and times of historical performance failures (e.g., based on stored operator indications of historical performance failures, or based on stored indications of corrective measures taken in response to performance failures, etc.) and may categorize these performance failures using various metrics, such as, e.g., severity, type of failure, refrigeration equipment involved in the failure, steps taken to resolve the failure, etc. The current performance failure data 204 may include updated indications of instances of performance failure events associated with the refrigerated enclosure 102, and may be processed similarly by the feature extraction functions 225.

[0042] Similarly, to process historical safety event data 234, the feature extraction functions 225 may identify dates and times of historical safety events (e.g., based on stored operator indications of historical safety events, or based on stored indications of corrective measures taken in response to historical safety events, etc.) and may categorize these safety events using various metrics, such as, e.g., severity, type of safety concern, refrigeration equipment involved in the safety event, steps taken to resolve the safety concern, etc. The current performance failure data 206 may include updated indications of instances of safety events associated with the refrigerated enclosure 102, and may be processed similarly by the feature extraction functions 225.

[0043] To process historical security event data 235, the feature extraction functions 225 may identify dates and times of historical security events, e.g., based on stored operator indications of historical security events (e.g., theft, burglary, trespassing, employee disputes, etc.), or based on stored indications of corrective measures taken in response to historical security events (such as locking doors, contacting police or other authorities, identifying an employee or customer involved in the security event, etc.), and may categorize these security events using various metrics such as, e.g., severity, type of security concern, steps taken to resolve the security concern, etc. The current security event data 207 may include updated indications of instances of security events associated with the refrigerated enclosure 102, and may be processed similarly by the feature extraction functions 225.

[0044] To process historical setting data 236, the feature extraction functions 225 may identify dates and times of instances in which control settings for refrigeration equipment exceeded default settings and/or average settings, and/or dates and times of instances in which control settings for refrigeration equipment exceeded setting thresholds (e.g., setting overrides).

[0045] To process historical sensor data 238, the feature extraction functions 225 may compare historical sensor data 238 for various refrigerated enclosures to threshold sensor data or average sensor data for various sensors, and may determine instances in which the sensor data was outside of threshold ranges or significantly above or below average. Moreover, the feature extraction functions 225 may identify spikes in numerical sensor data (such as, e.g., rapid increases or decreases in temperature, humidity, inventory, etc.) Additionally, the feature extraction functions 225 may identify dates and/or times associated with these instances.

Moreover, the feature extraction functions 225 may identify instances in which the historical sensor data 238 indicates abnormal sensor readings for certain dates and/or times, e.g., instances in which occupancy and/or lighting is detected at dates or times in which a business associated with a refrigerated enclosure is closed, instances in which the temperature inside a refrigerated enclosure is higher than outside the refrigerated enclosure, instances in which a door is opened, closed, or latched for a prolonged period of time (e.g., greater than a threshold period of time), instances in which various refrigeration equipment is powered on or powered off for a prolonged period of time (e.g., greater than a threshold period of time), etc.

[0046] The current sensor data 208 may include updated data captured by the sensors 1 14 of the refrigerated enclosure 102, such as, e.g., lighting status data 240, door status data 242, occupancy data 244, inventory data 246, humidity data 248, temperature data 250, power status data 252, refrigeration performance data 254, defrost data 256, fan status data 258, air flow data 260, heater status data 262, alarm data 264, carbon monoxide sensor data 265, heat flux data 267, video-computer vision data 269, etc. The current sensor data 208 may be processed similarly by the feature extraction functions 225.

[0047] Accordingly, the feature extraction functions 225 can generate feature vectors 230 using the historical data 202, current performance failure event data 204, current safety event data 206, current security event data, and/or current sensor data 208 from sensors 1 14 associated with the refrigerated enclosure 102. The refrigerated enclosure application 138 may further receive input signals associated with inventory status data 210 (e.g., provided by an operator of the refrigerated enclosure 102 or a business associated with the refrigerated enclosure 102), default settings 212 associated with the refrigeration equipment of the refrigerated enclosure 102, initial settings 214 associated with the refrigeration equipment of the refrigerated enclosure 102 (e.g., initial temperature settings 266, initial heater settings 268, initial fan settings 270, initial door settings 272, etc.), energy use restrictions 216 for the refrigerated enclosure 102, safety restrictions 218 for the refrigerated enclosure 102, the size and/or dimensions 220 of the refrigerated enclosure 102, etc.

[0048] In general, the refrigerated enclosure application 138 can train the refrigerated enclosure machine learning model 140 using supervised learning, unsupervised learning, reinforcement learning, or any other suitable technique. Moreover, the refrigerated enclosure application 138 can train the refrigerated enclosure machine learning model 140 as a standard regression model. Specifically, the refrigerated enclosure application 138 can train the refrigerated enclosure machine learning model 140 using the generated feature vectors 230 and inventory status data 210, default settings 212, initial settings 214, energy use restrictions 216, safety restrictions 218, and the size and/or dimensions 220 of the refrigerated enclosure 102. Because the refrigerated enclosure application 138 does not modify these inputs during training, these inputs can be considered hyperparameters.

[0049] Over time, as the refrigerated enclosure application 138 trains the refrigerated enclosure machine learning model 140, the refrigerated enclosure machine learning model 140 can learn to predict current or future anomalous conditions 274 in the refrigerated enclosure based on current readings from the sensors 1 14. For example, the refrigerated enclosure machine learning model 140 may identify a leak in a wall of a refrigerated enclosure based on current defrost data, humidity data, and door data in a certain location of the refrigerated enclosure 102.

[0050] The refrigerated enclosure machine learning model 140 may further identify setting and/or control modifications predicted to preemptively correct for such anomalous conditions 276. For example, the refrigerated enclosure machine learning model 140 may predict that, based on the current temperature, humidity, and the initial fan settings 270, the fan 124 will likely experience a performance failure within the next week. Furthermore, the refrigerated enclosure machine learning model 140 may predict that modifying the initial fan setting 270 or modifying the initial temperature setting 266 may prolong the life of the fan 124 an additional week so that a replacement fan may be ordered. As another example, the refrigerated enclosure machine learning model 140 may predict that, based on the current occupancy detected, the current light detected, the current door status, and a localized increase in temperature, a person may be trapped in the refrigerated enclosure 102. Furthermore, the refrigerated enclosure machine learning model 140 may predict that opening or unlatching a door 130 may allow the person to exit the refrigerated enclosure 102. As still another example, the refrigerated enclosure machine learning model 140 may predict that, based on the current occupancy detected, the current light detected, and timestamps associated with times at which that the business associated with the refrigerated enclosure is closed, a person may be trespassing in the refrigerated enclosure 102 (e.g., indicating a security issue). Furthermore, the refrigerated enclosure machine learning model 140 may predict that contacting police or other authorities is a potential step for resolving the trespassing/security issue.

[0051] The refrigerated enclosure application 138 may send indications of predicted current or future anomalous conditions in the refrigerated enclosure to the computing device 1 10, where they can be displayed for a user (e.g., as shown in FIGs. 3A and 3B). Moreover, the refrigerated enclosure application 138 may send indications of settings predicted to correct anomalous conditions to the computing device 1 10, where they can be displayed for the user. For instance, in some embodiments, a user may select whether a particular setting should be modified or not. In other embodiments, the refrigerated enclosure application 138 may automatically modify settings based on the predictions of the refrigerated enclosure machine learning model 140. For example, the refrigerated enclosure application 138 may send the corrective settings (e.g., a corrective temperature setting 278, a corrective heater setting 280, a corrective fan setting 282, a corrective door setting 284, a corrective alarm setting 286, etc.) generated by the refrigerated enclosure machine learning model 140 as instructions to the controller 106. When the controller 106 modifies settings in the refrigerated enclosure in accordance with the generated settings predicted to correct an anomalous condition, new current sensor data 202 can be generated and used in subsequent training of the refrigerated enclosure machine learning model 140, i.e., for fine-tuning to improve the performance of the refrigerated enclosure machine learning model 140.

[0052] Turning to FIGs. 3A and 3B, example user interface screens which a computing device 1 10 may generate to notify a user of an anomalous condition associated with a refrigerated enclosure are illustrated in accordance with some embodiments. For example, as shown in FIG. 3A, an example screen displayed by a user interface 152 may notify a user of a safety condition, such as a person trapped in a refrigerated enclosure. In some examples, the user interface screen may display options for resolving the safety condition, which may be selected by the user. For instance, as shown in FIG. 3A, a user may select an option to unlatch or open the door of the refrigerated enclosure so that a person trapped in the refrigerated enclosure can escape.

[0053] As another example, as shown in FIG. 3B, a screen displayed by a user interface 152 may notify a user of a potential performance failure, such as a loss of cold air in the refrigerated enclosure. In some examples, the user interface screen may display options for resolving the potential performance failure, which may be selected by the user. For instance, as shown in FIG. 3B, a user may select an option to schedule a work order to replace a malfunctioning fan in order to restore cold air to the refrigerated enclosure.

[0054] Referring now to FIG. 4, a flow diagram of an exemplary computer-implemented method 400 of monitoring refrigerated air usage in a refrigerated enclosure is illustrated, in accordance with some embodiments. The method 400 can be implemented as a set of instructions stored on a computer-readable memory and executable on one or more processors.

[0055] Training data may be generated (block 402) based on historical sensor data associated with one or more refrigerated enclosures. For example, the historical sensor data may include data captured by lighting status sensors, door status sensors, occupancy sensors, inventory level sensors, humidity sensors, temperature sensors, power status sensors, refrigeration performance sensors, defrost sensors, fan status sensors, air flow sensors, heater status sensors, alarm sensors, carbon monoxide sensors, heat flux sensors, video-computer vision, etc., associated with a plurality of refrigerated enclosures. A refrigerated enclosure machine learning model may be trained (block 404) using the training data.

[0056] The trained refrigerated enclosure machine learning model may be applied (block 406) to current sensor data captured by sensors associated with a particular refrigerated enclosure. For example, the current sensor data may include data captured by a lighting status sensor, a door status sensor, an occupancy sensor, an inventory level sensor, a humidity sensor, a temperature sensor, a power status sensor, a refrigeration performance sensor, a defrost sensor, a fan status sensor, an air flow sensor, a heater status sensor, an alarm sensor, a carbon monoxide sensor, a heat flux sensor, and/or video-computer vision associated with the refrigerated enclosure in various embodiments.

[0057] By applying the trained refrigerated enclosure machine learning model to the current sensor data captured by sensors in the refrigerated enclosure, an anomalous condition associated with the particular refrigerated enclosure may be identified or predicted (block 408). For example, the anomalous condition may indicate a performance failure (or potential performance failure) of a component of the refrigerated enclosure. As another example, the anomalous condition may indicate a safety concern or potential safety concern in the

refrigerated enclosure. As still another example, the anomalous condition may indicate a security concern or potential security concern in the refrigerated enclosure.

[0058] An action associated with the particular refrigerated enclosure may be triggered (block 410) based on the identified anomalous condition. In some examples, the action may include modifying one or more of a temperature setting, a fan setting, a heater setting, a defrost setting, a compressor setting, a condenser setting, an evaporator setting, and/or a pressure setting associated with the refrigerated enclosure. In another example, the action may include opening or unlatching a door associated with the particular refrigerated enclosure. In another example, the action may include turning on lights associated with the particular refrigerated enclosure. In another example, the action may include turning off and/or reducing refrigeration in the particular refrigerated enclosure. In still another example, the action may include generating an alert notifying a user of the identified anomalous condition. In still another example, the action may include generating an alert to police or other authorities based on the identified anomalous condition. In an additional example, the action may include generating an alert notifying a maintenance service of the identified anomalous condition.

[0059] In some examples, the method 400 may additionally include further training the refrigerated enclosure model using additional training data generated based on the current sensor data associated with the refrigerated enclosure.

[0060] Although the preceding text sets forth a detailed description of numerous different embodiments, it should be understood that the legal scope of the invention is defined by the words of the claims set forth at the end of this patent. The detailed description is to be construed as exemplary only and does not describe every possible embodiment, as describing every possible embodiment would be impractical, if not impossible. One could implement numerous alternate embodiments, using either current technology or technology developed after the filing date of this patent, which would still fall within the scope of the claims.

[0061] It should also be understood that, unless a term is expressly defined in this patent using the sentence“As used herein, the term‘ _ ’ is hereby defined to mean...” or a similar sentence, there is no intent to limit the meaning of that term, either expressly or by implication, beyond its plain or ordinary meaning, and such term should not be interpreted to be limited in scope based on any statement made in any section of this patent (other than the language of the claims). To the extent that any term recited in the claims at the end of this patent is referred to in this patent in a manner consistent with a single meaning, that is done for sake of clarity only so as to not confuse the reader, and it is not intended that such claim term be limited, by implication or otherwise, to that single meaning.

[0062] Throughout this specification, unless indicated otherwise, plural instances may implement components, operations, or structures described as a single instance. Although individual operations of one or more methods are illustrated and described as separate operations, one or more of the individual operations may be performed concurrently, and nothing requires that the operations be performed in the order illustrated. Structures and functionality presented as separate components in example configurations may likewise be implemented as a combined structure or component. Similarly, structures and functionality presented as a single component may be implemented as separate components. These and other variations, modifications, additions, and improvements fall within the scope of the subject matter herein.

[0063] Additionally, certain embodiments are described herein as including logic or a number of routines, subroutines, applications, or instructions. These may constitute either software (code embodied on a non-transitory, tangible machine-readable medium) or hardware. In hardware, the routines, etc., are tangible units capable of performing certain operations and may be configured or arranged in a certain manner. In example embodiments, one or more computer systems ( e.g ., a standalone, client or server computer system) or one or more hardware modules of a computer system (e.g., a processor or a group of processors) may be configured by software (e.g., an application or application portion) as a hardware module that operates to perform certain operations as described herein.

[0064] In various embodiments, a hardware module may be implemented mechanically or electronically. For example, a hardware module may comprise dedicated circuitry or logic that is permanently configured (e.g., as a special-purpose processor, such as a field programmable gate array (FPGA) or an application-specific integrated circuit (ASIC) to perform certain operations. A hardware module may also comprise programmable logic or circuitry (e.g., as encompassed within a general-purpose processor or other programmable processor) that is temporarily configured by software to perform certain operations. It will be appreciated that the decision to implement a hardware module mechanically, in dedicated and permanently configured circuitry, or in temporarily configured circuitry (e.g., configured by software) may be driven by cost and time considerations.

[0065] Hardware modules can provide information to, and receive information from, other hardware modules. Accordingly, the described hardware modules may be regarded as being communicatively coupled. Where multiple of such hardware modules exist contemporaneously, communications may be achieved through signal transmission (e.g., over appropriate circuits and buses) that connect the hardware modules. In embodiments in which multiple hardware modules are configured or instantiated at different times, communications between such hardware modules may be achieved, for example, through the storage and retrieval of information in memory structures to which the multiple hardware modules have access. For example, one hardware module may perform an operation and store the output of that operation in a memory device to which it is communicatively coupled. A further hardware module may then, at a later time, access the memory device to retrieve and process the stored output. Hardware modules may also initiate communications with input or output devices, and can operate on a resource ( e.g ., a collection of information).

[0066] The various operations of example methods described herein may be performed, at least partially, by one or more processors that are temporarily configured {e.g., by software) or permanently configured to perform the relevant operations. Whether temporarily or permanently configured, such processors may constitute processor-implemented modules that operate to perform one or more operations or functions. The modules referred to herein may, in some example embodiments, comprise processor-implemented modules.

[0067] Similarly, in some embodiments, the methods or routines described herein may be at least partially processor-implemented. For example, at least some of the operations of a method may be performed by one or more processors or processor-implemented hardware modules. The performance of certain of the operations may be distributed among the one or more processors, not only residing within a single machine, but deployed across a number of machines. In some example embodiments, the one or more processors or processor- implemented modules may be located in a single geographic location {e.g., within a home environment, an office environment, or a server farm). In other example embodiments, the one or more processors or processor-implemented modules may be distributed across a number of geographic locations.

[0068] Unless specifically stated otherwise, discussions herein using words such as “processing,”“computing,”“calculating,”“determining,”“presenting,”“displaying,” or the like may refer to actions or processes of a machine {e.g., a computer) that manipulates or transforms data represented as physical {e.g., electronic, magnetic, or optical) quantities within one or more memories {e.g., volatile memory, non-volatile memory, or a combination thereof), registers, or other machine components that receive, store, transmit, or display information.

[0069] As used herein any reference to“one embodiment” or“an embodiment” means that a particular element, feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. The appearances of the phrase“in one embodiment” or“in some embodiments” in various places in the specification are not necessarily all referring to the same embodiment or embodiments.

[0070] Some embodiments may be described using the terms“coupled,”“connected,” “communicatively connected,” or“communicatively coupled,” along with their derivatives. These terms may refer to a direct physical connection or to an indirect (physical or communication) connection. For example, some embodiments may be described using the term“coupled” to indicate that two or more elements are in direct physical or electrical contact. The term “coupled,” however, may also mean that two or more elements are not in direct contact with each other, but yet still co-operate or interact with each other. Unless expressly stated or required by the context of their use, the embodiments are not limited to direct connection.

[0071] As used herein, the terms“comprises,”“comprising,”“includes,”“including,”“has,” “having” or any other variation thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, article, or apparatus that comprises a list of elements is not necessarily limited to only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Further, unless expressly stated to the contrary,“or” refers to an inclusive or and not to an exclusive or. For example, a condition A or B is satisfied by any one of the following: A is true (or present) and B is false (or not present), A is false (or not present) and B is true (or present), and both A and B are true (or present).

[0072] In addition, use of the“a” or“an” are employed to describe elements and components of the embodiments herein. This is done merely for convenience and to give a general sense of the description. This description, and the claims that follow, should be read to include one or at least one and the singular also includes the plural unless the context clearly indicates otherwise.

[0073] Upon reading this disclosure, those of skill in the art will appreciate still additional alternative structural and functional designs for monitoring refrigerated air usage. Thus, while particular embodiments and applications have been illustrated and described, it is to be understood that the disclosed embodiments are not limited to the precise construction and components disclosed herein. Various modifications, changes and variations, which will be apparent to those skilled in the art, may be made in the arrangement, operation and details of the method and apparatus disclosed herein without departing from the spirit and scope defined in the appended claims.

[0074] The particular features, structures, or characteristics of any specific embodiment may be combined in any suitable manner and in any suitable combination with one or more other embodiments, including the use of selected features without corresponding use of other features. In addition, many modifications may be made to adapt a particular application, situation or material to the essential scope and spirit of the present invention. It is to be understood that other variations and modifications of the embodiments of the present invention described and illustrated herein are possible in light of the teachings herein and are to be considered part of the spirit and scope of the present invention. [0075] Finally, the patent claims at the end of this patent application are not intended to be construed under 35 U.S.C. § 1 12(f), unless traditional means-plus-function language is expressly recited, such as“means for” or“step for” language being explicitly recited in the claims.

ASPECTS

[0076] Embodiments of the techniques described in the present disclosure may include any number of the following aspects, either alone or combination:

[0077] 1 . A computer-implemented method for monitoring refrigerated air usage, the method comprising: generating, by a processor, training data based on historical sensor data associated with one or more refrigerated enclosures; training, by the processor, a refrigerated enclosure machine learning model using the training data; applying, by the processor, the trained refrigerated enclosure machine learning model to current sensor data captured by one or more sensors associated with a particular refrigerated enclosure to identify and/or predict an anomalous condition associated with the particular refrigerated enclosure; and triggering, by the processor, an action associated with the particular refrigerated enclosure based on the identified anomalous condition.

[0078] 2. The computer-implemented method of aspect 1 , wherein the one or more sensors include one or more of: a lighting status sensor, a door status sensor, an occupancy sensor, an inventory level sensor, a humidity sensor, a temperature sensor, a power status sensor, a refrigeration performance sensor, a defrost sensor, a fan status sensor, an air flow sensor, a heater status sensor, an alarm sensor, a carbon monoxide sensor, and/or a heat flux sensor.

[0079] 3. The computer-implemented method of any of aspects 1 or 2, wherein the identified anomalous condition indicates a performance failure and/or a potential performance failure of a component of the particular refrigerated enclosure.

[0080] 4. The computer-implemented method of any of aspects 1 -3, wherein the identified anomalous condition indicates a safety concern and/or a potential safety concern in the particular refrigerated enclosure.

[0081] 5. The computer-implemented method of any of aspects 1 -4, wherein the identified anomalous condition indicates a security concern and/or a potential security concern in the particular refrigerated enclosure. [0082] 6. The computer-implemented method of any of aspects 1 -5, wherein the triggered action includes opening or unlatching a door associated with the particular refrigerated enclosure.

[0083] 7. The computer-implemented method of any of aspects 1 -6, wherein the triggered action includes turning on lights associated with the particular refrigerated enclosure.

[0084] 8. The computer-implemented method of any of aspects 1 -7, wherein the triggered action includes turning off and/or reducing refrigeration the particular refrigerated enclosure.

[0085] 9. The computer-implemented method of any of aspects 1 -8, wherein the triggered action includes modifying one or more of a temperature setting, a fan setting, a heater setting, a defrost setting, a compressor setting, a condenser setting, an evaporator setting, and/or a pressure setting associated with the particular refrigerated enclosure.

[0086] 10. The computer-implemented method of any of aspects 1 -9, wherein the triggered action includes generating an alert notifying a user associated with the particular refrigerated enclosure of the identified anomalous condition.

[0087] 1 1 . The computer-implemented method of any of aspects 1 -10, wherein the triggered action includes generating an alert notifying police or other authorities of the identified anomalous condition.

[0088] 12. The computer-implemented method of any of aspects 1 -1 1 , wherein the triggered action includes generating an alert notifying a maintenance service of the identified anomalous condition.

[0089] 13. A system for monitoring refrigerated air usage, the system comprising: one or more sensors associated with a particular refrigerated enclosure; one or more processors; and one or more memories storing instructions that, when executed by the one or more processors, cause the one or more processors to: generate training data based on historical sensor data associated with one or more refrigerated enclosures; train a refrigerated enclosure machine learning model using the training data; apply the trained refrigerated enclosure machine learning model to current sensor data captured by the one or more sensors associated with the particular refrigerated enclosure to identify and/or predict an anomalous condition associated with the particular refrigerated enclosure; and trigger an action associated with the particular refrigerated enclosure based on the identified anomalous condition. [0090] 14. The system of aspect 13, wherein the one or more sensors include one or more of: a lighting status sensor, a door status sensor, an occupancy sensor, an inventory level sensor, a humidity sensor, a temperature sensor, a power status sensor, a refrigeration performance sensor, a defrost sensor, a fan status sensor, an air flow sensor, a heater status sensor, an alarm sensor, a carbon monoxide sensor, and/or a heat flux sensor.

[0091 ] 15. The system of any of aspects 13 or 14, wherein the identified anomalous condition indicates a performance failure and/or a potential performance failure of a component of the particular refrigerated enclosure.

[0092] 16. The system of any of aspects 13-15, wherein the identified anomalous condition indicates a safety concern and/or a potential safety concern in the particular refrigerated enclosure.

[0093] 17. The system of any of aspects 13-16, wherein the identified anomalous condition indicates a security concern and/or a potential security concern in the particular refrigerated enclosure.

[0094] 18. The system of any of aspects 13-17, wherein the triggered action includes opening or unlatching a door associated with the particular refrigerated enclosure.

[0095] 19. The system of any of aspects 13-18, wherein the triggered action includes turning on lights associated with the particular refrigerated enclosure.

[0096] 20. The system of any of aspects 13-19, wherein the triggered action includes turning off and/or reducing refrigeration the particular refrigerated enclosure.

[0097] 21 . The system of any of aspects 13-20, wherein the triggered action includes modifying one or more of a temperature setting, a fan setting, a heater setting, a defrost setting, a compressor setting, a condenser setting, an evaporator setting, and/or a pressure setting associated with the particular refrigerated enclosure.

[0098] 22. The system of any of aspects 13-21 , wherein the triggered action includes generating an alert notifying a user associated with the particular refrigerated enclosure of the identified anomalous condition.

[0099] 23. The system of any of aspects 13-22, wherein the triggered action includes generating an alert notifying police or other authorities of the identified anomalous condition.

[0100] 24. The system of any of aspects 13-23, wherein the triggered action includes generating an alert notifying a maintenance service of the identified anomalous condition. [0101] 25. A tangible, non-transitory computer-readable medium storing executable instructions for monitoring refrigerated air usage that, when executed by at least one processor of a computing device, causes the computing device to: generate training data based on historical sensor data associated with one or more refrigerated enclosures; train a refrigerated enclosure machine learning model using the training data; apply the trained refrigerated enclosure machine learning model to current sensor data captured by the one or more sensors associated with the particular refrigerated enclosure to identify and/or predict an anomaly associated with the current sensor data; and trigger an action associated with the particular refrigerated enclosure based on the identified anomalous condition associated with the current sensor data.

[0102] 26. The tangible, non-transitory computer-readable medium of aspect 25, wherein the one or more sensors include one or more of: a lighting status sensor, a door status sensor, an occupancy sensor, an inventory level sensor, a humidity sensor, a temperature sensor, a power status sensor, a refrigeration performance sensor, a defrost sensor, a fan status sensor, an air flow sensor, a heater status sensor, an alarm sensor, a carbon monoxide sensor, and/or a heat flux sensor.

[0103] 27. The tangible, non-transitory computer-readable medium of any of aspects 25 or

26, wherein the identified anomalous condition indicates a performance failure and/or a potential performance failure of a component of the particular refrigerated enclosure.

[0104] 28. The tangible, non-transitory computer-readable medium of any of aspects 25-27, wherein the identified anomalous condition indicates a safety concern and/or a potential safety concern in the particular refrigerated enclosure.

[0105] 29. The tangible, non-transitory computer-readable medium of any of aspects 25-28, wherein the identified anomalous condition indicates a security concern and/or a potential security concern in the particular refrigerated enclosure.

[0106] 30. The tangible, non-transitory computer-readable medium of any of aspects 25-29, wherein the triggered action includes turning off and/or reducing refrigeration the particular refrigerated enclosure.

[0107] 31. The tangible, non-transitory computer-readable medium of any of aspects 25-30, wherein the triggered action includes opening or unlatching a door associated with the particular refrigerated enclosure. [0108] 32. The tangible, non-transitory computer-readable medium of any of aspects 25-31 , wherein the triggered action includes turning on lights associated with the particular refrigerated enclosure.

[0109] 33. The tangible, non-transitory computer-readable medium of any of aspects 25-32, wherein the triggered action includes modifying one or more of a temperature setting, a fan setting, a heater setting, a defrost setting, a compressor setting, a condenser setting, an evaporator setting, and/or a pressure setting associated with the particular refrigerated enclosure.

[0110] 34. The tangible, non-transitory computer-readable medium of any of aspects 25-33, wherein the triggered action includes generating an alert notifying a user associated with the particular refrigerated enclosure of the identified anomalous condition.

[0111] 35. The tangible, non-transitory computer-readable medium of any of aspects 25-34, wherein the triggered action includes generating an alert notifying police or other authorities of the identified anomalous condition.

[0112] 36. The tangible, non-transitory computer-readable medium of any of aspects 25-35, wherein the triggered action includes generating an alert notifying a maintenance service of the identified anomalous condition.

Claims

What is Claimed is:

1. A computer-implemented method for monitoring refrigerated air usage, the method comprising:

generating, by a processor, training data based on historical sensor data associated with one or more refrigerated enclosures;

training, by the processor, a refrigerated enclosure machine learning model using the training data;

applying, by the processor, the trained refrigerated enclosure machine learning model to current sensor data captured by one or more sensors associated with a particular refrigerated enclosure to identify and/or predict an anomalous condition associated with the particular refrigerated enclosure; and

triggering, by the processor, an action associated with the particular refrigerated enclosure based on the identified anomalous condition.

2. The computer-implemented method of claim 1 , wherein the one or more sensors include one or more of: a lighting status sensor, a door status sensor, an occupancy sensor, an inventory level sensor, a humidity sensor, a temperature sensor, a power status sensor, a refrigeration performance sensor, a defrost sensor, a fan status sensor, an air flow sensor, a heater status sensor, an alarm sensor, a carbon monoxide sensor, and/or a heat flux sensor.

3. The computer-implemented method of any of claims 1 or 2, wherein the identified anomalous condition indicates a performance failure and/or a potential performance failure of a component of the particular refrigerated enclosure.

4. The computer-implemented method of any of claims 1 -3, wherein the identified anomalous condition indicates a safety concern and/or a potential safety concern in the particular refrigerated enclosure.

5. The computer-implemented method of any of claims 1 -4, wherein the identified anomalous condition indicates a security concern and/or a potential security concern in the particular refrigerated enclosure.

6. The computer-implemented method of any of claims 1 -5, wherein the triggered action includes opening or unlatching a door associated with the particular refrigerated enclosure.

7. The computer-implemented method of any of claims 1 -6, wherein the triggered action includes turning on lights associated with the particular refrigerated enclosure.

8. The computer-implemented method of any of claims 1 -7, wherein the triggered action includes turning off and/or reducing refrigeration the particular refrigerated enclosure.

9. The computer-implemented method of any of claims 1 -8, wherein the triggered action includes modifying one or more of a temperature setting, a fan setting, a heater setting, a defrost setting, a compressor setting, a condenser setting, an evaporator setting, and/or a pressure setting associated with the particular refrigerated enclosure.

10. The computer-implemented method of any of claims 1 -9, wherein the triggered action includes generating an alert notifying a user associated with the particular refrigerated enclosure of the identified anomalous condition.

1 1 . The computer-implemented method of any of claims 1 -10, wherein the triggered action includes generating an alert notifying police or other authorities of the identified anomalous condition.

12. The computer-implemented method of any of claims 1 -1 1 , wherein the triggered action includes generating an alert notifying a maintenance service of the identified anomalous condition.

13. A system for monitoring refrigerated air usage, the system comprising:

one or more sensors associated with a particular refrigerated enclosure;

one or more processors; and

one or more memories storing instructions that, when executed by the one or more processors, cause the one or more processors to:

generate training data based on historical sensor data associated with one or more refrigerated enclosures; train a refrigerated enclosure machine learning model using the training data; apply the trained refrigerated enclosure machine learning model to current sensor data captured by the one or more sensors associated with the particular refrigerated enclosure to identify and/or predict an anomalous condition associated with the particular refrigerated enclosure; and

trigger an action associated with the particular refrigerated enclosure based on the identified anomalous condition.

14. The system of claim 13, wherein the one or more sensors include one or more of: a lighting status sensor, a door status sensor, an occupancy sensor, an inventory level sensor, a humidity sensor, a temperature sensor, a power status sensor, a refrigeration performance sensor, a defrost sensor, a fan status sensor, an air flow sensor, a heater status sensor, an alarm sensor, a carbon monoxide sensor, and/or a heat flux sensor.

15. The system of claims 13 or 14, wherein the identified anomalous condition indicates a performance failure and/or a potential performance failure of a component of the particular refrigerated enclosure.

16. The system of any of claims 13-15, wherein the identified anomalous condition indicates a safety concern and/or a potential safety concern in the particular refrigerated enclosure.

17. The system of any of claims 13-16, wherein the identified anomalous condition indicates a security concern and/or a potential security concern in the particular refrigerated enclosure.

18. The system of any of claims 13-17, wherein the triggered action includes opening or unlatching a door associated with the particular refrigerated enclosure.

19. The system of any of claims 13-18, wherein the triggered action includes turning on lights associated with the particular refrigerated enclosure.

20. The system of any of claims 13-19, wherein the triggered action includes turning off and/or reducing refrigeration the particular refrigerated enclosure.

21 . The system of any of claims 13-20, wherein the triggered action includes modifying one or more of a temperature setting, a fan setting, a heater setting, a defrost setting, a compressor setting, a condenser setting, an evaporator setting, and/or a pressure setting associated with the particular refrigerated enclosure.

22. The system of any of claims 13-21 , wherein the triggered action includes generating an alert notifying a user associated with the particular refrigerated enclosure of the identified anomalous condition.

23. The system of any of claims 13-22, wherein the triggered action includes generating an alert notifying police or other authorities of the identified anomalous condition.

24. The system of any of claims 13-23, wherein the triggered action includes generating an alert notifying a maintenance service of the identified anomalous condition.

25. A tangible, non-transitory computer-readable medium storing executable instructions for monitoring refrigerated air usage that, when executed by at least one processor of a computing device, causes the computing device to:

generate training data based on historical sensor data associated with one or more refrigerated enclosures;

train a refrigerated enclosure machine learning model using the training data;

apply the trained refrigerated enclosure machine learning model to current sensor data captured by the one or more sensors associated with the particular refrigerated enclosure to identify and/or predict an anomaly associated with the current sensor data; and

trigger an action associated with the particular refrigerated enclosure based on the identified anomalous condition associated with the current sensor data.

26. The tangible, non-transitory computer-readable medium of claim 25, wherein the one or more sensors include one or more of: a lighting status sensor, a door status sensor, an occupancy sensor, an inventory level sensor, a humidity sensor, a temperature sensor, a power status sensor, a refrigeration performance sensor, a defrost sensor, a fan status sensor, an air flow sensor, a heater status sensor, an alarm sensor, a carbon monoxide sensor, and/or a heat flux sensor.

27. The tangible, non-transitory computer-readable medium of any of claims 25 or 26, wherein the identified anomalous condition indicates a performance failure and/or a potential performance failure of a component of the particular refrigerated enclosure.

28. The tangible, non-transitory computer-readable medium of any of claims 25-27, wherein the identified anomalous condition indicates a safety concern and/or a potential safety concern in the particular refrigerated enclosure.

29. The tangible, non-transitory computer-readable medium of any of claims 25-28, wherein the identified anomalous condition indicates a security concern and/or a potential security concern in the particular refrigerated enclosure.

30. The tangible, non-transitory computer-readable medium of any of claims 25-29, wherein the triggered action includes turning off and/or reducing refrigeration the particular refrigerated enclosure.

31 . The tangible, non-transitory computer-readable medium of any of claims 25-30, wherein the triggered action includes opening or unlatching a door associated with the particular refrigerated enclosure.

32. The tangible, non-transitory computer-readable medium of any of claims 25-31 , wherein the triggered action includes turning on lights associated with the particular refrigerated enclosure.

33. The tangible, non-transitory computer-readable medium of any of claims 25-32, wherein the triggered action includes modifying one or more of a temperature setting, a fan setting, a heater setting, a defrost setting, a compressor setting, a condenser setting, an evaporator setting, and/or a pressure setting associated with the particular refrigerated enclosure.

34. The tangible, non-transitory computer-readable medium of any of claims 25-33, wherein the triggered action includes generating an alert notifying a user associated with the particular refrigerated enclosure of the identified anomalous condition.

35. The tangible, non-transitory computer-readable medium of any of claims 25-34, wherein the triggered action includes generating an alert notifying police or other authorities of the identified anomalous condition.

36. The tangible, non-transitory computer-readable medium of any of claims 25-35, wherein the triggered action includes generating an alert notifying a maintenance service of the identified anomalous condition.