Method, device, computer equipment and storage medium for identifying abnormal temperature control equipment

Abstract

The present application provides a method, device, computer device and storage medium for identifying abnormalities in a temperature control device, including: obtaining at least one operating data of a temperature control device and at least one temperature control data of at least one temperature control object corresponding to the temperature control device, and integrating the at least one operating data and the at least one temperature control data of the temperature control device to obtain device data; performing a clustering operation on the device data of at least one of the temperature control devices to obtain a first data cluster set and a second data cluster set; if it is determined that a target temperature control device is defined as a second temperature control device in at least one data cluster in the first data cluster set and is defined as a second temperature control device in at least one data cluster in the second data cluster set, then it is determined that the target temperature control device is an abnormal device. The present application achieves the technical effect of identifying abnormal temperature control devices from the general level dimension and the discrete degree dimension, ensuring the accuracy of identifying abnormal devices.

Description

Technical Field

[0001] This application relates to the technical field of temperature control, and particularly to a method, device, computer device, and storage medium for identifying anomalies in temperature control equipment. Background Art

[0002] Temperature has a great impact on the capacity, charge and discharge power, and safety of batteries. There are more batteries integrated in energy storage containers, and the battery capacity is also larger. Moreover, the arrangement of battery clusters composed of multiple batteries is relatively compact, with small gaps, and the energy density of the battery clusters is high, and the operating conditions are complex and changeable, and there are often frequent switches between high and low charge and discharge rates. This easily causes heat accumulation between battery clusters, uneven heat generation inside the system, uneven temperature distribution, and large temperature differences between battery clusters. Therefore, temperature control equipment (such as fans, air conditioning equipment, etc.), as a key link in the thermal management system of battery clusters in energy storage containers, its safe and stable operation plays an important role in ensuring that the temperature and humidity of the energy storage system are maintained within a reasonable range throughout the life cycle.

[0003] Currently, it is usually adopted to collect the fan speed frequency, fan motor speed value or current peak value of the temperature control equipment, and identify whether the temperature control equipment has anomalies by setting thresholds. However, the inventor found that if the temperature control equipment fails to rotate, has abnormal power wiring, or the fan ventilation port is blocked, the fan speed frequency, fan motor speed value or current peak value collected by the current method still indicates that the temperature control equipment is in a normal working state. However, the temperature control object (such as a battery cluster) will be overheated or have uneven temperature distribution due to the above situation, resulting in a low reliability of the energy storage container. Summary of the Invention

[0004] This application provides a method, device, computer device, and storage medium for identifying anomalies in temperature control equipment, so as to solve the problem that the current method of collecting the fan speed frequency, fan motor speed value or current peak value cannot identify the situations such as failure to rotate, abnormal power wiring, or blocked fan ventilation port of the temperature control equipment, and thus it is easy to cause the temperature control object to be overheated or have uneven temperature distribution due to this situation, resulting in a low reliability of the energy storage container.

[0005] In a first aspect, this application provides a method for identifying anomalies in temperature control equipment, where the temperature control equipment is used to perform temperature control operations on at least one temperature control object, and the method includes:

[0006] Obtain at least one operating data of a temperature control device and at least one temperature control data of at least one temperature control object corresponding to the temperature control device, and integrate the at least one operating data and the at least one temperature control data of the temperature control device to obtain device data; wherein, the operating data records a collection time and status data obtained from the temperature control device at the collection time; the status data reflects the temperature control method of the temperature control device for the temperature control object; the temperature control data records the collection time and temperature information of at least one of the temperature control objects at the collection time; the device data reflects the temperature control method of the temperature control device at each collection time and the temperature control effect on at least one of the temperature control objects.

[0007] Perform a clustering operation on the device data of at least one of the temperature control devices to obtain a first data cluster set and a second data cluster set; wherein, the first data cluster set includes at least one data cluster, and the data clusters in the first data cluster set are obtained by performing a clustering operation on the central tendency of the temperature control effects in the device data of each temperature control device; the second data cluster set includes at least one data cluster, and the data clusters in the second data cluster set are obtained by performing a clustering operation on the degree of dispersion of the temperature control effects in the temperature control data of each temperature control device; the data cluster is a data point representing at least one temperature control device; the temperature control device corresponding to the data point belonging to the data cluster is defined as the first temperature control device; the temperature control device corresponding to the data point not belonging to the data cluster is defined as the second temperature control device.

[0008] If it is determined that the target temperature control device is defined as the second temperature control device in at least one data cluster in the first data cluster set and is defined as the second temperature control device in at least one data cluster in the second data cluster set, then determine that the target temperature control device is an abnormal device.

[0009] In the above solution, the integration of the at least one operating data and the at least one temperature control data of the temperature control device to obtain device data includes:

[0010] Perform data cleaning processing on at least one of the operating data to obtain at least one first data;

[0011] Perform data cleaning processing on at least one of the temperature control data to obtain at least one second data;

[0012] Summarize the first data and the second data corresponding to one collection time into one initial data;

[0013] If it is determined that the number of at least one of the initial data reaches a preset calculation threshold, then set at least one of the initial data as device data.

[0014] In the above solution, the process of performing data cleaning on at least one of the operation data to obtain at least one first data includes:

[0015] If a null value is identified in one of the operation data, then determine that one operation data as invalid data; and / or

[0016] If an invalid value is identified in one of the operation data, then determine that one operation data as invalid data;

[0017] Delete the invalid data in at least one of the operation data to obtain at least one of the first data.

[0018] In the above solution, the process of performing data cleaning on at least one of the temperature control data to obtain at least one second data includes:

[0019] If a null value is identified in one of the temperature control data, then determine that one temperature control data as invalid data; and / or

[0020] If an invalid value is identified in one of the temperature control data, then determine that one temperature control data as invalid data; and / or

[0021] If it is identified that one of the temperature control data does not belong to a preset threshold range, then determine that one temperature control data as invalid data;

[0022] Delete the invalid data in at least one of the temperature control data to obtain at least one of the second data.

[0023] In the above solution, the process of performing clustering operation on the device data of at least one of the temperature control devices to obtain a first data cluster set and a second data cluster set includes:

[0024] Calculate the central tendency of at least one of the device data of one temperature control device to obtain a first statistical value, and perform a clustering operation on the first statistical values of at least one temperature control device to obtain the first data cluster set; wherein, the central tendency reflected by the first statistical value describes the general level of the temperature control method and temperature control effect of the temperature control device at each acquisition time;

[0025] Calculate the degree of dispersion of at least one of the device data of one temperature control device to obtain a second statistical value, and perform a clustering operation on the second statistical values of at least one temperature control device to obtain the second data cluster set; wherein, the degree of dispersion reflected by the second statistical value describes the degree of difference in the temperature control method and temperature control effect of the temperature control device at each acquisition time.

[0026] In the above solution, the temperature control methods include cooling temperature control and heating temperature control;

[0027] Calculating the central tendency of at least one piece of the device data of one of the temperature control devices to obtain a first statistical value includes:

[0028] Identifying, according to the status data in the operation data, the device data of at least one of the device data where the temperature control method of the temperature control device is refrigeration temperature control, and summarizing to obtain a first refrigeration set;

[0029] Calculating the central tendency of the temperature control data of each piece of device data in the first refrigeration set to obtain a first refrigeration value; wherein, the central tendency reflected by the first refrigeration value describes the general level of the temperature control data of each piece of device data under refrigeration temperature control;

[0030] Identifying, according to the status data in the operation data, the device data of at least one of the device data where the temperature control method of the temperature control device is heating temperature control, and summarizing to obtain a first heating set;

[0031] Calculating the central tendency of the temperature control data of each piece of device data in the first heating set to obtain a first heating value; wherein, the central tendency reflected by the first heating value describes the general level of the temperature control data of each piece of device data in the heating state;

[0032] Summarizing the first refrigeration value and the first heating value to obtain the first statistical value.

[0033] In the above solution, the temperature control methods include refrigeration temperature control and heating temperature control;

[0034] Calculating the degree of dispersion of at least one piece of the device data of one of the temperature control devices to obtain a second statistical value includes:

[0035] Identifying, according to the status data in the operation data, the device data of at least one of the device data where the temperature control method of the temperature control device is refrigeration temperature control, and summarizing to obtain a second refrigeration set;

[0036] Calculating the degree of dispersion of the temperature control data of each piece of device data in the second refrigeration set to obtain a second refrigeration value; wherein, the degree of dispersion reflected by the second refrigeration value describes the degree of difference between the temperature control data of each piece of device data under refrigeration temperature control;

[0037] Identifying, according to the status data in the operation data, the device data of at least one of the device data where the temperature control method of the temperature control device is heating temperature control, and summarizing to obtain a second heating set;

[0038] Calculating the degree of dispersion of the temperature control data of each piece of device data in the second heating set to obtain a second heating value; wherein, the degree of dispersion reflected by the second heating value describes the degree of difference between the temperature control data of each piece of device data in the heating state;

[0039] Summarize the second cooling value and the second heating value to obtain the second statistical value.

[0040] In the above solution, performing a clustering operation on the first statistical value of at least one of the temperature control devices to obtain the first data cluster set includes:

[0041] Construct at least one first cooling data point according to the first cooling value in the first statistical value of at least one of the temperature control devices;

[0042] Construct at least one first heating data point according to the first heating value in the first statistical value of at least one of the temperature control devices;

[0043] Perform a clustering operation on at least one of the first cooling data points according to a preset first neighborhood parameter and a first metric parameter to obtain the first cooling data cluster, and perform a clustering operation on at least one of the first heating data points to obtain the first heating data cluster. Summarize the first cooling data cluster and the first heating data cluster to obtain the first data cluster set; wherein, the first neighborhood parameter defines the diameter length of the data clusters in the first data cluster set; the first metric parameter defines the method for calculating the distance between two of the first cooling data points and two of the first heating data points;

[0044] If it is determined that the first cooling data point of a temperature control device belongs to the first cooling data cluster and the first heating data point of the temperature control device belongs to the first heating data cluster, then define the temperature control device as a first temperature control device;

[0045] If it is determined that the first cooling data point of a temperature control device does not belong to the first cooling data cluster and / or the first heating data point of the temperature control device does not belong to the first heating data cluster, then define the temperature control device as a second temperature control device.

[0046] In the above solution, the first cooling value includes a first cooling mean value and a first cooling quantile;

[0047] The constructing at least one first cooling data point according to the first cooling value in the first statistical value of at least one of the temperature control devices includes:

[0048] Construct the first cooling data point of the temperature control device with the first cooling mean value of one of the temperature control devices as the abscissa and the first cooling quantile of the temperature control device as the ordinate;

[0049] The first heating value includes a first heating mean value and a first heating quantile;

[0050] Constructing at least one first heating data point based on the first heating value in the first statistical value of at least one of the temperature control devices, includes:

[0051] Using the first heating average value of one of the temperature control devices as the abscissa and the first heating quantile of the temperature control device as the ordinate to construct the first heating data point of the temperature control device.

[0052] In the above solution, performing a clustering operation on the second statistical values of at least one of the temperature control devices to obtain the second data cluster set, includes:

[0053] Constructing at least one first cooling data point based on the first cooling value in the first statistical value of at least one of the temperature control devices;

[0054] Constructing at least one second cooling data point based on the second cooling value in the second statistical value of at least one of the temperature control devices;

[0055] Constructing at least one second heating data point based on the second heating value in the second statistical value of at least one of the temperature control devices;

[0056] Performing a clustering operation on at least one of the second cooling data points according to the preset second neighborhood parameter and the second metric parameter to obtain the second cooling data cluster, and performing a clustering operation on at least one of the second heating data points to obtain the second heating data cluster, and summarizing the second cooling data cluster and the second heating data cluster to obtain the second data cluster set; wherein, the second neighborhood parameter defines the diameter length of the data clusters in the second data cluster set; the second metric parameter defines the method for calculating the distance between two of the second cooling data points and two of the second heating data points;

[0057] If it is determined that the second cooling data point of a temperature control device belongs to the second cooling data cluster and the second heating data point of the temperature control device belongs to the second heating data cluster, then define the temperature control device as the first temperature control device;

[0058] If it is determined that the second cooling data point of a temperature control device does not belong to the second cooling data cluster, and / or the second heating data point of the temperature control device does not belong to the second heating data cluster, then define the temperature control device as the second temperature control device.

[0059] In the above solution, the second cooling value includes the second cooling standard deviation and the second cooling coefficient of variation;

[0060] Constructing at least one second cooling data point based on the second cooling value in the second statistical value of at least one of the temperature control devices, includes:

[0061] Taking the second refrigeration standard deviation of one of the temperature control devices as the abscissa and the second refrigeration coefficient of variation of the temperature control device as the ordinate, construct the second refrigeration data point of the temperature control device;

[0062] The second heating value includes a second heating standard deviation and a second heating coefficient of variation;

[0063] Constructing at least one second heating data point according to the second heating value in the second statistical values of at least one of the temperature control devices includes:

[0064] Taking the second heating standard deviation of one of the temperature control devices as the abscissa and the second heating coefficient of variation of the temperature control device as the ordinate, construct the second heating data point of the temperature control device.

[0065] In the above solution, after performing a clustering operation on the device data of at least one of the temperature control devices to obtain a first data cluster set and a second data cluster set, the method further includes:

[0066] If it is determined that the target temperature control device is defined as a first temperature control device in at least one data cluster in the first data cluster set and is defined as a first temperature control device in at least one data cluster in the second data cluster set, then determine that the target temperature control device is a normal device; or

[0067] If it is determined that the target temperature control device is defined as a second temperature control device in at least one data cluster in the first data cluster set and is defined as a first temperature control device in at least one data cluster in the second data cluster set, then determine that the target temperature control device is a key device; or

[0068] If it is determined that the target temperature control device is defined as a first temperature control device in at least one data cluster in the first data cluster set and is defined as a second temperature control device in at least one data cluster in the second data cluster set, then determine that the target temperature control device is a key device.

[0069] In a second aspect, the present application provides a temperature control device anomaly recognition device, where the temperature control device is used to perform temperature control operations on at least one temperature control object, and the device includes:

[0070] An input module is configured to obtain at least one operating data of a temperature control device and at least one temperature control data of at least one temperature control object corresponding to the temperature control device, and integrate the at least one operating data and the at least one temperature control data of the temperature control device to obtain device data; wherein, the operating data records a collection time and status data obtained from the temperature control device at the collection time; the status data reflects the temperature control mode of the temperature control device for the temperature control object; the temperature control data records the collection time and temperature information of at least one of the temperature control objects at the collection time; the device data reflects the temperature control mode of the temperature control device at each collection time and the temperature control effect on at least one of the temperature control objects.

[0071] A processing module is configured to perform a clustering operation on the device data of at least one of the temperature control devices to obtain a first data cluster set and a second data cluster set; wherein, the first data cluster set includes at least one data cluster, and the data clusters in the first data cluster set are obtained by performing a clustering operation on the general level of the temperature control effect in the device data of each temperature control device; the second data cluster set includes at least one data cluster, and the data clusters in the second data cluster set are obtained by performing a clustering operation on the dispersion degree of the temperature control effect in the temperature control data of each temperature control device; the data cluster is a data point representing at least one temperature control device; the temperature control device corresponding to the data point belonging to the data cluster is defined as the first temperature control device; the temperature control device corresponding to the data point not belonging to the data cluster is defined as the second temperature control device.

[0072] An exception module is configured to determine that the target temperature control device is an abnormal device if it is determined that the target temperature control device is defined as the second temperature control device in at least one data cluster in the first data cluster set and is defined as the second temperature control device in at least one data cluster in the second data cluster set.

[0073] In a third aspect, the present application provides a computer device, including: a processor and a memory communicatively connected to the processor;

[0074] The memory stores computer-executable instructions;

[0075] The processor executes the computer-executable instructions stored in the memory to implement the temperature control device anomaly recognition method as described above in the claims.

[0076] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, they are used to implement the temperature control device anomaly recognition method as described above.

[0077] Fifth aspect, the present application provides a computer program product, including a computer program, which when executed by a processor implements the above-mentioned method for identifying anomalies in temperature control devices.

[0078] A method, device, computer device, and storage medium for identifying anomalies in temperature control devices provided by the present application obtain at least one operating data of a temperature control device and at least one temperature control data of at least one temperature control object corresponding to the temperature control device, and integrate the at least one operating data and the at least one temperature control data of the temperature control device to obtain device data; realizing the collection of temperature control devices and temperature control objects, and collecting the characteristics of temperature control operations in two dimensions of temperature control methods and temperature control effects, so as to facilitate subsequent identification of abnormal temperature control devices based on these characteristics.

[0079] By performing clustering operations on the device data of at least one of the temperature control devices to obtain a first data cluster set and a second data cluster set; and if it is determined that a target temperature control device is defined as a second temperature control device in at least one data cluster in the first data cluster set and is defined as a second temperature control device in at least one data cluster in the second data cluster set, then determining that the target temperature control device is an abnormal device, achieving the technical effect of identifying temperature control devices with abnormal temperature control effects from the dimensions of central tendency and dispersion degree, ensuring the accuracy of abnormal device identification, and effectively identifying temperature control devices that have failed to rotate, have abnormal power wiring, or have blocked fan vents, etc., effectively avoiding problems such as overheating of temperature control objects and uneven temperature distribution caused by the failure of temperature control devices to rotate, abnormal fan wiring, or blocked fan vents, etc., and improving the operating reliability of energy storage containers. Description of the Drawings

[0080] The drawings here are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0081] Figure 1 It is a schematic diagram of an application scenario provided by an embodiment of the present application;

[0082] Figure 2 It is a flowchart of Embodiment 1 of a method for identifying anomalies in temperature control devices provided by an embodiment of the present application;

[0083] Figure 3 It is a flowchart of Embodiment 2 of a method for identifying anomalies in temperature control devices provided by an embodiment of the present application;

[0084] Figure 4 It is a schematic diagram of program modules of a device for identifying anomalies in temperature control devices provided by the present invention;

[0085] Figure 5This is a schematic diagram of the hardware structure of the computer device in the computer device of the present invention.

[0086] Through the above-mentioned drawings, specific embodiments of the present application have been shown, and there will be more detailed descriptions hereinafter. These drawings and textual descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. Detailed implementation manners

[0087] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0088] Please refer to Figure 1 , the specific application scenario of the present application is:

[0089] A server 2 for the method of identifying abnormalities in temperature control devices, the server 2 is installed in the control device 31 of the energy storage container 3, the energy storage container 3 further includes at least one temperature control device 32, and at least one temperature control object 33 corresponding to each temperature control device 32, and the temperature control device 32 is used to perform temperature control operations on at least one temperature control object 33.

[0090] The server 2 obtains at least one operating data of a temperature control device 32 and at least one temperature control data of at least one temperature control object 33 corresponding to the temperature control device 32, and integrates the at least one operating data and at least one temperature control data of the temperature control device 32 to obtain device data; the server 2 performs clustering operations on the device data of at least one temperature control device 32 to obtain a first data cluster set and a second data cluster set;

[0091] If the server 2 determines that the target temperature control device is defined as a second temperature control device in at least one data cluster in the first data cluster set and is defined as a second temperature control device in at least one data cluster in the second data cluster set, then it is determined that the target temperature control device is an abnormal device.

[0092] Therefore, the technical effect of identifying the temperature control device with abnormal temperature control effect from the dimensions of central tendency and dispersion degree is achieved, ensuring the accuracy of identifying abnormal devices, and then effectively identifying the temperature control device 32 that has failed to rotate, has abnormal power wiring, has a blocked fan vent, etc., effectively avoiding problems such as overheating of the temperature control object and uneven temperature distribution caused by the failure of the temperature control device to rotate, abnormal fan wiring, blocked fan vent, etc., and improving the operation reliability of the energy storage container 3.

[0093] The following uses specific embodiments to elaborate in detail on the technical solution of this application and how the technical solution of this application solves the problems in the prior art. The following several specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0094] Embodiment 1:

[0095] Please refer to Figure 2 , this application provides a method for identifying abnormal temperature control equipment. The temperature control equipment is used for temperature control operations on at least one temperature control object. The method for identifying abnormal temperature control equipment runs in the control equipment of the energy storage container. The energy storage container includes at least one temperature control equipment and at least one temperature control object corresponding to each temperature control equipment. The method includes:

[0096] S101: Obtain at least one operating data of a temperature control equipment and at least one temperature control data of at least one temperature control object corresponding to the temperature control equipment, and integrate the at least one operating data and the at least one temperature control data of the temperature control equipment to obtain equipment data; wherein, the operating data records a collection time and status data obtained from the temperature control equipment at the collection time; the status data reflects the temperature control method of the temperature control equipment for the temperature control object; the temperature control data records the collection time and the temperature information of at least one temperature control object at the collection time; the equipment data reflects the temperature control method of the temperature control equipment at each collection time and the temperature control effect on at least one temperature control object.

[0097] In this step, within a fixed period (for example: within one day), multiple collection times are obtained according to a specific collection frequency (for example: once per minute); within one day, the operating data of the temperature control equipment (recording the temperature control method of the temperature control equipment for the temperature control object) and the temperature control data of the temperature control object (such as: temperature) are collected every minute.

[0098] By integrating at least one operating data and at least one temperature control data of the temperature control equipment to obtain equipment data, it is possible to periodically obtain the temperature control method of the temperature control operation of the temperature control equipment and the temperature control effect of the temperature control equipment on the temperature control object.

[0099] The characteristics of the temperature control operation are collected in two dimensions of the temperature control method and the temperature control effect for the temperature control equipment and the temperature control object, so as to facilitate subsequent identification of abnormal temperature control equipment based on these characteristics.

[0100] Exemplarily, the temperature control equipment is an air conditioning equipment with a fan;

[0101] The temperature control object is an energy storage system integrated battery, also known as a battery cluster;

[0102] The operation data includes: the acquisition time, and the status of the air conditioner compressor, the electric heating status of the air conditioner, and the electric fan relay status of the temperature control device at the acquisition time;

[0103] The temperature control data includes: the internal cell temperature of the battery cluster.

[0104] In a preferred embodiment, at least one operation data and at least one temperature control data of the temperature control device are integrated to obtain device data, including:

[0105] Performing data cleaning processing on at least one operation data to obtain at least one first data;

[0106] Performing data cleaning processing on at least one temperature control data to obtain at least one second data;

[0107] Summarizing the first data and the second data corresponding to one acquisition time into one initial data;

[0108] If it is determined that the quantity of at least one initial data reaches a preset calculation threshold, then set at least one initial data as device data.

[0109] In this example, by performing data cleaning on the operation data and by performing data cleaning on the temperature control data, the invalid data in the operation data and the temperature control data are cleaned, and the first data and the second data with all valid data will be obtained to ensure the accuracy of subsequent anomaly identification; the initial data obtained by summarizing the first data and the second data belonging to the same acquisition time enables the temperature control method and the temperature control effect at the same time to correspond to each other;

[0110] The calculation threshold is the quantity of the initial data set according to requirements. Only when the quantity of the data reaches a certain level can the accuracy of anomaly identification of the temperature control device be ensured. In this embodiment, the calculation threshold can be set to 900. Then, if the data volume of the obtained initial data reaches 900, the obtained initial data can be set as device data for subsequent clustering operations; if it does not reach 900, it is necessary to continue to collect operation data and temperature control data until the finally obtained initial data reaches 900.

[0111] Specifically, performing data cleaning processing on at least one operation data to obtain at least one first data includes:

[0112] If a null value is identified in an operation data, then determine an operation data as invalid data; and / or

[0113] If an invalid value is identified in an operation data, then determine an operation data as invalid data;

[0114] Delete invalid data in at least one piece of operation data to obtain at least one first data.

[0115] In this example, a null value refers to a situation where the content is empty, and an invalid value refers to a situation where the content is garbled or meaningless. If a piece of operation data has a null value and / or an invalid value, it means that the operation data cannot describe the temperature control method of the temperature control device, so it is set as invalid data. By deleting the invalid data, at least one first data that can describe the temperature control method of the temperature control device at each acquisition time will be obtained.

[0116] Furthermore, perform data cleaning on at least one piece of temperature control data to obtain at least one second data, including:

[0117] If it is recognized that a null value exists in the key indicators of a piece of temperature control data, determine the piece of temperature control data as invalid data; and / or

[0118] If it is recognized that an invalid value exists in the key indicators of a piece of temperature control data, determine the piece of temperature control data as invalid data; and / or

[0119] If it is recognized that a piece of temperature control data does not belong to the preset threshold range, determine the piece of temperature control data as invalid data;

[0120] Delete invalid data in at least one piece of temperature control data to obtain at least one second data.

[0121] In this example, a null value refers to a situation where the content is empty, an invalid value refers to a situation where the content is garbled or meaningless, and the threshold range is the temperature range in which the temperature control object (i.e., the battery cluster) normally appears (for example: the temperature range is defined as [-35°C to 65°C]). Once the temperature control data exceeds the threshold range, it is considered that an error has occurred in the temperature control data.

[0122] If a piece of temperature control data has a null value and / or an invalid value and / or does not belong to the threshold range, it means that the temperature control data cannot correctly describe the temperature control effect of the temperature control device, so it is set as invalid data. By deleting the invalid data, at least one second data that can describe the temperature control effect of the temperature control device at each acquisition time will be obtained.

[0123] S102: Perform clustering operations on the device data of at least one temperature control device to obtain a first data cluster set and a second data cluster set. Among them, the first data cluster set includes at least one data cluster, and the data clusters in the first data cluster set are obtained by performing clustering operations on the central tendency of the temperature control effects in the device data of each temperature control device. The second data cluster set includes at least one data cluster, and the data clusters in the second data cluster set are obtained by performing clustering operations on the degree of dispersion of the temperature control effects in the temperature control data of each temperature control device. A data cluster is a representation of at least one data point of at least one temperature control device. The temperature control device corresponding to the data point belonging to the data cluster is defined as the first temperature control device. The temperature control device corresponding to the data point not belonging to the data cluster is defined as the second temperature control device.

[0124] In this step, clustering operations are respectively performed on the device data of at least one temperature control device through the first model and the second model to obtain at least one data cluster corresponding to the first model and the first data cluster set and the second data cluster set corresponding to the second model. A data cluster is a representation of at least one data point of at least one temperature control device. Therefore, at least one data cluster of the first model and at least one data cluster of the second model are obtained. By defining the temperature control device corresponding to the data point belonging to the data cluster as the first temperature control device and the temperature control device corresponding to the data point not belonging to the data cluster as the second temperature control device, the abnormal conditions of each temperature control device are identified respectively according to the temperature control method and the temperature control effect by using the first model and the second model, and the accuracy of abnormal identification of the temperature control device is improved.

[0125] In a preferred embodiment, performing clustering operations on the device data of at least one temperature control device to obtain a first data cluster set and a second data cluster set includes:

[0126] Calculate the central tendency of at least one device data of a temperature control device to obtain a first statistical value, and perform clustering operations on the first statistical values of at least one temperature control device to obtain a first data cluster set. Among them, the central tendency reflected by the first statistical value describes the general level of the temperature control method and the temperature control effect of the temperature control device at each acquisition time.

[0127] Calculate the degree of dispersion of at least one device data of a temperature control device to obtain a second statistical value, and perform clustering operations on the second statistical values of at least one temperature control device to obtain a second data cluster set. Among them, the degree of dispersion reflected by the second statistical value describes the degree of difference in the temperature control method and the temperature control effect of the temperature control device at each acquisition time.

[0128] In this example, at least one device data of a temperature control device is calculated through a first data model, and a first statistical value reflecting the central tendency (e.g., average or quantile) of the temperature control method and temperature control effect of the temperature control device is obtained. The first statistical value is subjected to a clustering operation (e.g., density clustering operation) through the first model to cluster the temperature control device from the dimensions of the operating condition of the temperature control device and the central tendency of the temperature control effect, identify data points with similar general levels of the temperature control effect at each acquisition time under the same temperature control method, and set at least one similar data point as a data cluster.

[0129] At least one device data of a temperature control device is calculated through a second data model, and a second statistical value reflecting the central tendency (e.g., average or quantile) of the temperature control method and temperature control effect of the temperature control device is obtained. The second statistical value is subjected to a clustering operation (e.g., density clustering operation) through the second model to cluster the temperature control device from the dimension of the degree of dispersion of the operating condition of the temperature control device and the temperature control effect, identify data points with similar degrees of difference in the temperature control effect at each acquisition time under the same temperature control method, and set at least one similar data point as a data cluster; wherein, the degree of difference characterizes the degree of difference in the temperature control effect at each acquisition time.

[0130] Specifically, the temperature control methods include refrigeration temperature control and heating temperature control;

[0131] Obtaining a first statistical value by calculating the central tendency of at least one device data of a temperature control device includes:

[0132] Identifying the device data of the temperature control device with the temperature control method of refrigeration temperature control in at least one device data according to the status data in the operation data, and summarizing to obtain a first refrigeration set;

[0133] Calculating the central tendency of the temperature control data of each device data in the first refrigeration set to obtain a first refrigeration value; wherein, the central tendency reflected by the first refrigeration value describes the general level of the temperature control data of each device data under refrigeration temperature control;

[0134] Identifying the device data of the temperature control device with the temperature control method of heating temperature control in at least one device data according to the status data in the operation data, and summarizing to obtain a first heating set;

[0135] Calculating the central tendency of the temperature control data of each device data in the first heating set to obtain a first heating value; wherein, the central tendency reflected by the first heating value describes the general level of the temperature control data of each device data in the heating state;

[0136] Summarizing the first refrigeration value and the first heating value to obtain the first statistical value.

[0137] Further, calculating the degree of dispersion of at least one device data of a temperature control device to obtain a second statistical value includes:

[0138] Identifying, according to the status data in the operation data, the device data of the temperature control device with the temperature control mode of refrigeration temperature control among at least one device data, and summarizing to obtain a second refrigeration set;

[0139] Calculating the degree of dispersion of the temperature control data of each device data in the second refrigeration set to obtain a second refrigeration value; wherein, the degree of dispersion reflected by the second refrigeration value describes the degree of difference between the temperature control data of each device data under refrigeration temperature control;

[0140] Identifying, according to the status data in the operation data, the device data of the temperature control device with the temperature control mode of heating temperature control among at least one device data, and summarizing to obtain a second heating set;

[0141] Calculating the degree of dispersion of the temperature control data of each device data in the second heating set to obtain a second heating value; wherein, the degree of dispersion reflected by the second heating value describes the degree of difference between the temperature control data of each device data in the heating state;

[0142] Summarizing the second refrigeration value and the second heating value to obtain the second statistical value.

[0143] In this example, the temperature control modes include refrigeration temperature control and heating temperature control.

[0144] If the status data of a device data includes: the air conditioner compressor status is on, the air conditioner electric heating status is off, and the air conditioner fan relay status is on; then it is determined that the temperature control mode of the temperature control device is refrigeration temperature control, and this device data is entered into the first refrigeration set; calculating the average value or quantile of the temperature control data of each device data in the first refrigeration set to obtain a first refrigeration value, where the average value is the mean of each temperature control data, and the quantile (Quantile), also known as the quantile point, refers to the numerical point that divides the probability distribution range of a random variable into several equal parts. Commonly used ones include the median (i.e., the second quantile), quartiles, percentiles, etc. The quantile refers to a point in the continuous distribution function, and this point corresponds to the probability p. If the probability 0 < p < 1, the quantile Za of the random variable X or its probability distribution is the real number that satisfies the condition p(X ≤ Za) = α. In this embodiment, the average value and the quantile will characterize the central tendency of the temperature control data of each device data, that is: it describes the general level of the temperature control data of each device data under refrigeration temperature control.

[0145] If the status data of a device's data includes: the compressor status of the air-conditioning device is off, the electric heating status of the air-conditioning device is on, and the electric fan relay status of the air-conditioning device is on; then determine that the temperature control method of the temperature control device is heating temperature control, and enter the device data into the first heating set; calculate the average value or quantile of the temperature control data of each device data in the first heating set to obtain the first heating value. Among them, the average value is the mean of each temperature control data, and the quantile (Quantile), also known as the quantile point, is the numerical point that divides the probability distribution range of a random variable into several equal parts. Commonly used ones include the median (i.e., the bisecting quantile), quartiles, percentiles, etc. The quantile refers to a point in the continuous distribution function, and this point corresponds to the probability p. If the probability 0 < p < 1, the quantile Za of the random variable X or its probability distribution is the real number that satisfies the condition p(X ≤ Za) = α. In this embodiment, the average value and the quantile will characterize the central tendency of the temperature control data of each device data, that is: it describes the general level of the temperature control data of each device data under heating temperature control.

[0146] Summarize the first cooling value and the first heating value to obtain the first statistical value; in this embodiment, by summarizing the first cooling value and the first heating value into the first statistical value, the general level of the temperature control data of each device data of the temperature control device under the cooling state and the heating state is obtained respectively.

[0147] Based on the above example, determine that the temperature control method of the temperature control device is cooling temperature control, and enter the device data into the second cooling set; calculate the standard deviation or coefficient of variation of the temperature control data of each device data in the second cooling set to obtain the second cooling value. Among them, the standard deviation is the arithmetic square root of the variance of each temperature control data, and the standard deviation can reflect the dispersion degree of a data set; the coefficient of variation, also known as the "coefficient of dispersion" (English: coefficient of variation), is a normalized measure of the dispersion degree of the probability distribution. Its definition is the ratio of the standard deviation to the average value. The coefficient of variation (coefficient of variation) is only defined when the average value is not zero, and generally applies to the case where the average value is greater than zero. The coefficient of variation is also known as the standard deviation rate or unit risk. In this embodiment, the standard deviation and the coefficient of dispersion will characterize the dispersion degree of the temperature control data of each device data, that is: it describes the degree of difference of the temperature control data of each device data under cooling temperature control.

[0148] Based on the above distance, determine that the temperature control method of the temperature control device is heating temperature control, and enter the device data into the second heating set; calculate the standard deviation or coefficient of variation of the temperature control data of each device data in the second heating set to obtain the second heating value. In this embodiment, the standard deviation and the coefficient of variation will characterize the central tendency of the temperature control data of each device data, that is: it describes the degree of difference of the temperature control data of each device data under heating temperature control.

[0149] Summarize the second refrigeration value and the second heating value to obtain a second statistical value; in this embodiment, by summarizing the second refrigeration value and the second heating value into a second statistical value, the difference degree of the temperature control data of each device data of the temperature control device in the refrigeration state and the heating state is obtained respectively.

[0150] Specifically, perform a clustering operation on the first statistical values of at least one temperature control device to obtain a first data cluster set, including:

[0151] Construct at least one first refrigeration data point according to the first refrigeration value in the first statistical values of at least one temperature control device;

[0152] Construct at least one first heating data point according to the first heating value in the first statistical values of at least one temperature control device;

[0153] Perform a clustering operation on at least one first refrigeration data point according to a preset first neighborhood parameter and a first metric parameter to obtain a first refrigeration data cluster, and perform a clustering operation on at least one first heating data point to obtain a first heating data cluster, and summarize the first refrigeration data cluster and the first heating data cluster to obtain a first data cluster set; wherein, the first neighborhood parameter defines the diameter length of the data clusters in the first data cluster set; the first metric parameter defines the method for calculating the distance between two first refrigeration data points and two first heating data points;

[0154] If it is determined that the first refrigeration data point of a temperature control device belongs to the first refrigeration data cluster, and the first heating data point of the temperature control device belongs to the first heating data cluster, then define the temperature control device as a first temperature control device;

[0155] If it is determined that the first refrigeration data point of a temperature control device does not belong to the first refrigeration data cluster, and / or the first heating data point of the temperature control device does not belong to the first heating data cluster, then define the temperature control device as a second temperature control device.

[0156] Further, the first refrigeration value includes a first refrigeration mean value and a first refrigeration quantile;

[0157] Constructing at least one first refrigeration data point according to the first refrigeration value in the first statistical values of at least one temperature control device includes:

[0158] Construct a first refrigeration data point of the temperature control device with the first refrigeration mean value of a temperature control device as the abscissa and the first refrigeration quantile of the temperature control device as the ordinate;

[0159] The first heating value includes a first heating mean value and a first heating quantile;

[0160] Constructing at least one first heating data point according to the first heating value in the first statistical values of at least one temperature control device includes:

[0161] Construct a first heating data point of the temperature control device with the first heating mean value of the temperature control device as the abscissa and the first heating quantile of the temperature control device as the ordinate.

[0162] Specifically, perform a clustering operation on the second statistical values of at least one temperature control device to obtain a second data cluster set, including:

[0163] Construct at least one first cooling data point according to the first cooling value in the first statistical values of at least one temperature control device;

[0164] Construct at least one second cooling data point according to the second cooling value in the second statistical values of at least one temperature control device;

[0165] Construct at least one second heating data point according to the second heating value in the second statistical values of at least one temperature control device;

[0166] Perform a clustering operation on at least one second cooling data point according to the preset second neighborhood parameter and second metric parameter to obtain a second cooling data cluster, and perform a clustering operation on at least one second heating data point to obtain a second heating data cluster, and summarize the second cooling data cluster and the second heating data cluster to obtain a second data cluster set; wherein, the second neighborhood parameter defines the diameter length of the data clusters in the second data cluster set; the second metric parameter defines the method of calculating the distance between two second cooling data points and two second heating data points;

[0167] If it is determined that the second cooling data point of a temperature control device belongs to the second cooling data cluster and the second heating data point of the temperature control device belongs to the second heating data cluster, then define the temperature control device as a first temperature control device;

[0168] If it is determined that the second cooling data point of a temperature control device does not belong to the second cooling data cluster and / or the second heating data point of the temperature control device does not belong to the second heating data cluster, then define the temperature control device as a second temperature control device.

[0169] Furthermore, the second cooling value includes a second cooling standard deviation and a second cooling coefficient of variation;

[0170] Construct at least one second cooling data point according to the second cooling value in the second statistical values of at least one temperature control device, including:

[0171] Construct a second cooling data point of the temperature control device with the second cooling standard deviation of the temperature control device as the abscissa and the second cooling coefficient of variation of the temperature control device as the ordinate;

[0172] The second heating value includes a second heating standard deviation and a second heating coefficient of variation;

[0173] Construct at least one second heating data point according to the second heating value in the second statistical value of at least one temperature control device, including:

[0174] Construct the second heating data point of the temperature control device with the second heating standard deviation of one temperature control device as the abscissa and the second heating coefficient of variation of the temperature control device as the ordinate.

[0175] In this example, enter the first cooling value in the first statistical value of at least one temperature control device into the first model to construct at least one first cooling data point; wherein, the first cooling value includes the first cooling mean value and the first cooling quantile; use the first cooling mean value of one temperature control device as the abscissa and the first cooling quantile of the temperature control device as the ordinate to construct the first cooling data point of the temperature control device;

[0176] Enter the first heating value in the first statistical value of at least one temperature control device into the first model to construct at least one first heating data point; wherein, the first heating value includes the first heating mean value and the first heating quantile; use the first heating mean value of one temperature control device as the abscissa and the first heating quantile of the temperature control device as the ordinate to construct the first heating data point of the temperature control device.

[0177] According to the first neighborhood parameter and the first metric parameter preset in the first model, perform clustering operations on at least one first cooling data point to obtain a first cooling data cluster, and perform clustering operations on at least one first heating data point to obtain a first heating data cluster, and summarize the first cooling data cluster and the first heating data cluster to obtain a first data cluster set; therefore, it realizes that the general level of the temperature control data of a temperature control device in the cooling state and the heating state can be respectively reflected by the first cooling data cluster and the first heating data cluster; configure the first neighborhood parameter in the first model to determine the diameter length of the data clusters in the first data cluster set; configure the first metric parameter in the first model to determine the way for the first model to calculate the distance between two first data points; realize the parameter configuration of the first model, so that the first model can perform clustering operations according to the needs of the user.

[0178] Specifically, perform clustering operations on the second statistical values of at least one temperature control device to obtain a second data cluster set, including:

[0179] Construct at least one first cooling data point according to the first cooling value in the first statistical value of at least one temperature control device;

[0180] Construct at least one second cooling data point according to the second cooling value in the second statistical value of at least one temperature control device;

[0181] Construct at least one second heating data point according to the second heating value in the second statistical value of at least one temperature control device;

[0182] According to the preset second neighborhood parameter and second metric parameter, perform clustering operations on at least one second cooling data point to obtain a second cooling data cluster, and perform clustering operations on at least one second heating data point to obtain a second heating data cluster, and summarize the second cooling data cluster and the second heating data cluster to obtain a second data cluster set; wherein, the second neighborhood parameter defines the diameter length of the data clusters in the second data cluster set; the second metric parameter defines the way to calculate the distance between two second cooling data points and two second heating data points.

[0183] If it is determined that the second cooling data point of a temperature control device belongs to the second cooling data cluster and the second heating data point of the temperature control device belongs to the second heating data cluster, then define the temperature control device as a first temperature control device.

[0184] If it is determined that the second cooling data point of a temperature control device does not belong to the second cooling data cluster, and / or the second heating data point of the temperature control device does not belong to the second heating data cluster, then define the temperature control device as a second temperature control device.

[0185] Furthermore, the second cooling value includes a second cooling standard deviation and a second cooling coefficient of variation.

[0186] Construct at least one second cooling data point according to the second cooling value in the second statistical value of at least one temperature control device, including:

[0187] Use the second cooling standard deviation of a temperature control device as the abscissa and the second cooling coefficient of variation of the temperature control device as the ordinate to construct the second cooling data point of the temperature control device.

[0188] The second heating value includes a second heating standard deviation and a second heating coefficient of variation.

[0189] Construct at least one second heating data point according to the second heating value in the second statistical value of at least one temperature control device, including:

[0190] Use the second heating standard deviation of a temperature control device as the abscissa and the second heating coefficient of variation of the temperature control device as the ordinate to construct the second heating data point of the temperature control device.

[0191] In this example, input the second cooling value in the second statistical value of at least one temperature control device into the second model to construct at least one second cooling data point; wherein, the second cooling value includes a second cooling mean and a second cooling quantile; use the second cooling mean of a temperature control device as the abscissa and the second cooling quantile of the temperature control device as the ordinate to construct the second cooling data point of the temperature control device.

[0192] The second heating value in the second statistical value of at least one temperature control device is input into the second model to construct at least one second heating data point; wherein, the second heating value includes a second heating mean value and a second heating quantile; taking the second heating mean value of one temperature control device as the abscissa and the second heating quantile of the temperature control device as the ordinate, a second heating data point of the temperature control device is constructed.

[0193] According to the second neighborhood parameter and the second metric parameter preset in the second model, clustering operations are performed on at least one second cooling data point to obtain a second cooling data cluster, and clustering operations are performed on at least one second heating data point to obtain a second heating data cluster. The second cooling data cluster and the second heating data cluster are summarized to obtain a second data cluster set; therefore, it is realized that the temperature control data dispersion degree of a temperature control device in the cooling state and the heating state can be respectively reflected by the second cooling data cluster and the second heating data cluster; the second neighborhood parameter is configured in the second model to determine the diameter length of the data clusters in the second data cluster set; the second metric parameter is configured in the second model to determine the way for the second model to calculate the distance between two second data points; the parameter configuration of the second model is realized, enabling the second model to perform clustering operations according to the needs of users.

[0194] In this embodiment, the first model and the second model can be DBSCAN density clustering models. DBSCAN density clustering is a set of samples that are maximally density-connected derived from the density reachability relationship, which is a category for our final clustering, or a cluster. There can be one or more core objects in this DBSCAN cluster. If there is only one core object, then all other non-core object samples in the cluster are in the ∈-neighborhood of this core object; if there are multiple core objects, then there must be another core object in the ∈-neighborhood of any one core object in the cluster, otherwise these two core objects cannot be density-reachable. The set of all samples in the ∈-neighborhood of these core objects forms a DBSCAN clustering cluster. The method used by DBSCAN is very simple. It arbitrarily selects a core object without a category as a seed, and then finds all the sample sets that this core object can be density-reachable, which is a data cluster.

[0195] Exemplarily, based on DBSCAN density clustering, outlier analysis is performed on the temperature statistical values (such as mean value and quantile) within each cluster to identify outlier battery clusters. The specific process is as follows. The quantile refers to a point in the continuous distribution function, and this point corresponds to the probability p. If the probability 0 < p < 1, the quantile Za of the random variable X or its probability distribution is a real number that satisfies the condition p(X ≤ Za) = α.

[0196] Input: Sample set D = {x1, x2,......, xm}, where x1 represents the in-cluster temperature statistical value of Battery Cluster No. 1 within a day, neighborhood parameters (ε, MinPts), and the sample distance metric is taken as (e.g., Euclidean distance);

[0197] Output: Cluster partition C.

[0198] A: Initialize the set of core objects Initialize the number of clustering clusters k = 0, initialize the set of unvisited samples Γ = D, and the cluster partition

[0199] B: For j = 1, 2,......, m, find the clustering core objects according to the following steps:

[0200] C: If the current cluster core object Then the current clustering cluster Ck is generated, update the cluster partition C = {C1, C2,......, Ck}, update the set of core objects Ω = Ω - Ck, and go to step B. Otherwise, update the set of core objects Ω = Ω - Ck;

[0201] D: Take out a core object o' from the current cluster core object queue Ωcur, find all ε-neighborhood subset samples Nε(o') through the neighborhood distance, let Δ = Nε(o') ∩ Γ, update the current cluster sample set Ck = Ck ∪ Δ, update the set of unvisited samples Γ = Γ - Δ, update Ωcur = Ωcur ∪ (Δ ∩ Ω) - o', and go to C.

[0202] E: The output result is: cluster partition C = {C1, C2,......, Ck}. For the data points not recognized as data clusters, that is, the data points discrete from this data cluster are defined as outliers. Therefore, set the temperature control device corresponding to the data points belonging to the data cluster as the first temperature control device, and set the temperature control device corresponding to this outlier as the second temperature control device.

[0203] S103: If it is determined that the target temperature control device is defined as the second temperature control device in at least one data cluster of the first model and is defined as the second temperature control device in at least one data cluster of the second model, then determine that the target temperature control device is an abnormal device.

[0204] This step is based on the above example: The first model performs clustering operations based on the general level of the temperature control effect of each temperature control device to obtain data clusters; the second model performs clustering operations based on the degree of difference in the temperature control effect of each temperature control device and obtains data clusters; therefore, it realizes the technical effect of identifying the temperature control devices with abnormal temperature control effects from the dimensions of the general level and the degree of dispersion, ensuring the accuracy of identifying abnormal devices.

[0205] Further, the first model generates data points representing the general level of the temperature control effect of each temperature control device based on the first statistical value representing the general level of the temperature control effect of each temperature control device, and generates a data cluster in which the general level of the temperature control effect belongs to a level category based on the data points; sets the data points whose general level of the temperature control effect does not belong to the data cluster as discrete points, and sets the temperature control device corresponding to the discrete point as the second temperature control device;

[0206] The second model generates data points representing the degree of difference in the temperature control effect of each temperature control device based on the second statistical value representing the degree of difference in the temperature control effect of each temperature control device, and generates a data cluster in which the degree of dispersion of the temperature control effect belongs to a degree category based on the data points; sets the data points whose degree of dispersion of the temperature control effect does not belong to the data cluster as discrete points, and sets the temperature control device corresponding to the discrete point as the second temperature control device.

[0207] If the temperature control device (such as: the compressor of the air conditioning system, and / or the electric heating device, and / or the fan) fails to rotate, has abnormal power wiring, or the fan vent is blocked, etc., resulting in abnormal function of the temperature control device, it will cause abnormal distribution of the temperature control data of the temperature control object (such as: the battery cluster), for example: the general level of the temperature control data increases or decreases, that is: the average temperature or quantile of the battery cells in the battery cluster is too high or too low; the degree of difference in the temperature control data increases, that is: the standard deviation or coefficient of variation of the battery cell temperatures in the battery cluster is too high.

[0208] Therefore, when it is recognized that the temperature control device whose general level of the temperature control effect and the degree of difference in the temperature control effect at each acquisition time are far from the data cluster, it means that the temperature control device must have experienced relatively serious failures such as failure to rotate, abnormal power wiring, or blocked fan vents, etc. Therefore, the temperature control device is set as an abnormal device, ensuring the accuracy of abnormal device identification, and then accurately identifying the early abnormality of the temperature control device corresponding to the temperature control object and achieving the technical effect of sending an abnormal warning, effectively avoiding problems such as overheating and uneven temperature distribution of the temperature control object caused by the failure of the temperature control device to rotate or abnormal fan wiring, etc., and improving the operation reliability of the energy storage container.

[0209] Embodiment 2:

[0210] Please refer to Figure 3 , this application provides a method for identifying abnormal temperature control devices. The temperature control device is used to perform temperature control operations on at least one temperature control object. The method for identifying abnormal temperature control devices runs in the control device of the energy storage container. The energy storage container includes at least one temperature control device and at least one temperature control object corresponding to each temperature control device. The method includes:

[0211] S201: Obtain at least one operating data of a temperature control device and at least one temperature control data of at least one temperature control object corresponding to the temperature control device, and integrate the at least one operating data and the at least one temperature control data of the temperature control device to obtain device data; wherein, the operating data records a collection time and status data obtained from the temperature control device at the collection time; the status data reflects the temperature control method of the temperature control device for the temperature control object; the temperature control data records the collection time and temperature information of at least one temperature control object at the collection time; the device data reflects the temperature control method of the temperature control device at each collection time and the temperature control effect on at least one temperature control object.

[0212] This step is the same as S101 in Embodiment 1, so it will not be elaborated here.

[0213] S202: Perform clustering operations on the device data of at least one temperature control device through a preset first model and second model respectively, and obtain at least one data cluster corresponding to the first model and the second model respectively; wherein, the first model is used to perform clustering operations on the general level of the temperature control effect in the device data of each temperature control device; the second model is used to perform clustering operations on the dispersion degree of the temperature control effect in the temperature control data of each temperature control device; the data cluster is a data point representing at least one temperature control device; the temperature control device corresponding to the data point belonging to the data cluster is defined as the first temperature control device; the temperature control device corresponding to the data point not belonging to the data cluster is defined as the second temperature control device.

[0214] This step is the same as S102 in Embodiment 1, so it will not be elaborated here.

[0215] S203: If it is determined that the target temperature control device is defined as the second temperature control device in at least one data cluster of the first model and is defined as the second temperature control device in at least one data cluster of the second model, then determine that the target temperature control device is an abnormal device.

[0216] This step is the same as S103 in Embodiment 1, so it will not be elaborated here.

[0217] S204: If it is determined that the target temperature control device is defined as the first temperature control device in at least one data cluster in the first data cluster set and is defined as the first temperature control device in at least one data cluster in the second data cluster set, then determine that the target temperature control device is a normal device; or

[0218] If it is determined that the target temperature control device is defined as the second temperature control device in at least one data cluster in the first data cluster set and is defined as the first temperature control device in at least one data cluster in the second data cluster set, then determine that the target temperature control device is a key device; or

[0219] If it is determined that the target temperature control device is defined as the first temperature control device in at least one data cluster of the first data cluster set and is defined as the second temperature control device in at least one data cluster of the second data cluster set, then the target temperature control device is determined to be a critical device.

[0220] This step is based on the above example: The first model performs clustering operations based on the general level of the temperature control effect of each temperature control device to obtain data clusters; the second model performs clustering operations based on the degree of difference in the temperature control effect of each temperature control device and obtains data clusters; therefore, identifying abnormal temperature control devices from the dimensions of the general level and the degree of difference ensures the accuracy of identifying abnormal devices and reduces...

[0221] Furthermore, the first model generates data points representing the general level of the temperature control effect of each temperature control device based on the first statistical value representing the general level of the temperature control effect of each temperature control device, and generates data clusters where the general level of the temperature control effect belongs to one level category based on each data point; sets the data points whose general level of the temperature control effect does not belong to this data cluster as discrete points, and sets the temperature control device corresponding to this discrete point as the second temperature control device;

[0222] The second model generates data points representing the degree of difference in the temperature control effect of each temperature control device based on the second statistical value representing the degree of difference in the temperature control effect of each temperature control device, and generates data clusters where the degree of dispersion of the temperature control effect belongs to one degree category based on each data point; sets the data points whose degree of dispersion of the temperature control effect does not belong to this data cluster as discrete points, and sets the temperature control device corresponding to this discrete point as the second temperature control device.

[0223] If a temperature control device (such as a compressor of an air conditioning system, and / or an electric heating device, and / or a fan) malfunctions and stops rotating, has abnormal power wiring, or has a blocked fan vent, etc., resulting in abnormal function of the temperature control device, it will cause the temperature control data of the temperature control object (such as a battery cluster) (such as the temperature distribution law of the battery cells in the battery cluster) to be abnormally distributed. For example, the general level of the temperature control data increases or decreases, that is, the average temperature or quantile of the battery cells in the battery cluster is too high or too low; the degree of difference in the temperature control data increases, that is, the standard deviation or coefficient of variation of the temperature of the battery cells in the battery cluster is too high.

[0224] Therefore, when a temperature control device with a general level of temperature control effect within each acquisition time or a degree of difference in temperature control effect within each acquisition time far from the data cluster is identified, it indicates that the temperature control device may have serious failures such as shutdown, abnormal power connection, or blocked fan vents. Therefore, the temperature control device is set as a device of concern, ensuring the accuracy of abnormal device identification. Furthermore, the early abnormality of the temperature control device corresponding to the temperature control object can be accurately identified, and the technical effect of issuing an abnormal warning can effectively avoid problems such as overheating of the temperature control object and uneven temperature distribution caused by the failure of the temperature control device to stop rotating or abnormal fan wiring, improving the operating reliability of the energy storage container. Among them, by setting the above temperature control device as a device of concern, different levels of classification settings for the temperature control device are realized based on the distribution of different temperature control data, so that operators can perform targeted processing and repair on each temperature control device according to different classification settings.

[0225] Embodiment 3:

[0226] Please refer to Figure 4 , this application provides an abnormal identification device 1 for a temperature control device. The temperature control device is used to perform temperature control operations on at least one temperature control object. The abnormal identification device for the temperature control device is installed in the control device of the energy storage container. The energy storage container includes at least one temperature control device and at least one temperature control object corresponding to each temperature control device. The device includes:

[0227] An input module 11, configured to obtain at least one operating data of a temperature control device and at least one temperature control data of at least one temperature control object corresponding to the temperature control device, and integrate at least one operating data and at least one temperature control data of the temperature control device to obtain device data; wherein, the operating data records an acquisition time and status data obtained from the temperature control device at the acquisition time; the status data reflects the temperature control method of the temperature control device for the temperature control object; the temperature control data records the acquisition time and temperature information of at least one temperature control object at the acquisition time; the device data reflects the temperature control method of the temperature control device at each acquisition time and the temperature control effect on at least one temperature control object.

[0228] A processing module 12, configured to perform clustering operations on the device data of at least one temperature control device through a preset first model and a second model respectively, and obtain at least one data cluster corresponding to the first model and the second model respectively; wherein, the first model is used to perform clustering operations on the general level of temperature control effect in the device data of each temperature control device; the second model is used to perform clustering operations on the discrete degree of temperature control effect in the temperature control data of each temperature control device; the data cluster is a data point representing at least one temperature control device; the temperature control device corresponding to the data point belonging to the data cluster is defined as the first temperature control device; the temperature control device corresponding to the data point not belonging to the data cluster is defined as the second temperature control device.

[0229] Anomaly recognition module 13, configured to determine that the target temperature control device is an abnormal device if it is determined that the target temperature control device is defined as a second temperature control device in at least one data cluster of the first model and is defined as a second temperature control device in at least one data cluster of the second model.

[0230] Optionally, the temperature control device anomaly recognition apparatus 1 further includes:

[0231] Attention recognition module 14, configured to determine that the target temperature control device is a normal device if it is determined that the target temperature control device is defined as a first temperature control device in at least one data cluster of the first data cluster set and is defined as a first temperature control device in at least one data cluster of the second data cluster set; or determine that the target temperature control device is a critical device if it is determined that the target temperature control device is defined as a second temperature control device in at least one data cluster of the first data cluster set and is defined as a first temperature control device in at least one data cluster of the second data cluster set; or determine that the target temperature control device is a critical device if it is determined that the target temperature control device is defined as a first temperature control device in at least one data cluster of the first data cluster set and is defined as a second temperature control device in at least one data cluster of the second data cluster set.

[0232] Embodiment 4:

[0233] To achieve the above object, the present application further provides a computer device 4, including: a processor 42 and a memory 41 communicatively connected to the processor 42; the memory stores computer-executable instructions;

[0234] The processor executes the computer-executable instructions stored in the memory 41 to implement the above temperature control device anomaly recognition method, wherein the components of the temperature control device anomaly recognition apparatus may be dispersed in different computer devices, and the computer device 4 may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack server, a blade server, a tower server or a cabinet server (including an independent server, or a server cluster composed of multiple application servers) that executes the program, etc. The computer device of this embodiment at least includes but is not limited to: a memory 41 and a processor 42 that can communicate with each other through a system bus, as Figure 5 shown. It should be noted that, Figure 5Only a computer device with components - is shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. In this embodiment, the memory 41 (i.e., the readable storage medium) includes flash memory, hard disk, multimedia card, card - type memory (e.g., SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read - only memory (ROM), electrically erasable programmable read - only memory (EEPROM), programmable read - only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device, such as the hard disk or memory of the computer device. In other embodiments, the memory 41 can also be an external storage device of the computer device, such as a plug - in hard disk equipped on the computer device, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Of course, the memory 41 can also include both the internal storage unit and the external storage device of the computer device. In this embodiment, the memory 41 is generally used to store the operating system installed on the computer device and various application software, such as the program code of the temperature - control device anomaly recognition device in Embodiment 3. In addition, the memory 41 can also be used to temporarily store various data that have been output or will be output. The processor 42 can be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data - processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device. In this embodiment, the processor 42 is used to run the program code stored in the memory 41 or process data, such as running the temperature - control device anomaly recognition device to implement the temperature - control device anomaly recognition method of the above - mentioned embodiment.

[0235] The integrated modules implemented in the form of software function modules can be stored in a computer-readable storage medium. The above-mentioned software function modules are stored in a storage medium and include several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute some steps of the methods in various embodiments of the present application. It should be understood that the above-mentioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in combination with the application can be directly implemented by the execution of the hardware processor, or can be implemented by the combination of the hardware and software modules in the processor. The memory may include high-speed RAM memory, and may also include non-volatile storage NVM, such as at least one disk memory, and can also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk, or an optical disc, etc.

[0236] To achieve the above object, the present application also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disc, a server, an App application store, etc., on which computer-executable instructions are stored, and when the program is executed by the processor 42, the corresponding functions are realized. The computer-readable storage medium of this embodiment is used to store the computer-executable instructions for implementing the method for identifying the abnormality of the temperature control device, and when executed by the processor 42, the method for identifying the abnormality of the temperature control device in the above embodiment is realized.

[0237] The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk, or an optical disc. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0238] An exemplary storage medium is coupled to a processor, enabling the processor to read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an Application Specific Integrated Circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic device or a master device.

[0239] The present application provides a computer program product, including a computer program which, when executed by a processor, implements the above-mentioned method for identifying anomalies in a temperature control device.

[0240] It should be noted that, in this context, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, article or device comprising that element.

[0241] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common general knowledge or conventional technical means in the technical field not disclosed in the present application. The specification and the embodiments are only regarded as exemplary, and the true scope and spirit of the present application are pointed out by the following claims.

[0242] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present application is only limited by the appended claims.

Claims

1. A method for identifying anomalies in a temperature control device, characterized in that, The temperature control device is used for performing temperature control operations on at least one temperature control object, and the method includes: Obtaining at least one operation data of a temperature control device and at least one temperature control data of at least one temperature control object corresponding to the temperature control device, and integrating the at least one operation data and the at least one temperature control data of the temperature control device to obtain device data; wherein, the operation data records a collection time and status data obtained from the temperature control device at the collection time; the status data reflects the temperature control method of the temperature control device for the temperature control object; the temperature control data records the collection time and temperature information of at least one of the temperature control objects at the collection time; the device data reflects the temperature control method of the temperature control device at each collection time and the temperature control effect on at least one of the temperature control objects; Performing a clustering operation on the device data of at least one of the temperature control devices to obtain a first data cluster set and a second data cluster set; wherein, the first data cluster set includes at least one data cluster, and the data clusters in the first data cluster set are obtained by performing a clustering operation on the central tendency of the temperature control effect in the device data of each temperature control device; the second data cluster set includes at least one data cluster, and the data clusters in the second data cluster set are obtained by performing a clustering operation on the dispersion degree of the temperature control effect in the temperature control data of each temperature control device; the data cluster is a data point representing at least one temperature control device; the temperature control device corresponding to the data point belonging to the data cluster is defined as a first temperature control device; the temperature control device corresponding to the data point not belonging to the data cluster is defined as a second temperature control device; If it is determined that the target temperature control device is defined as a second temperature control device in at least one data cluster in the first data cluster set and is defined as a second temperature control device in at least one data cluster in the second data cluster set, then it is determined that the target temperature control device is an abnormal device; Among them, the first data cluster set is obtained by summarizing the first cooling data clusters and the first heating data clusters. The first cooling data clusters are obtained by performing clustering operations on at least one first cooling data point. The first heating data clusters are obtained by performing clustering operations on at least one first heating data point. The first cooling data point is constructed with the first cooling mean value of a temperature control device as the abscissa and the first cooling quantile of the temperature control device as the ordinate. The first heating data point is constructed with the first heating mean value of a temperature control device as the abscissa and the first heating quantile of the temperature control device as the ordinate. The second data cluster set is obtained by summarizing the second cooling data clusters and the second heating data clusters. The second cooling data clusters are obtained by performing clustering operations on at least one second cooling data point. The second heating data clusters are obtained by performing clustering operations on at least one second heating data point. The second cooling data point is constructed with the second cooling mean value of a temperature control device as the abscissa and the second cooling quantile of the temperature control device as the ordinate. The second heating data point is constructed with the second heating mean value of a temperature control device as the abscissa and the second heating quantile of the temperature control device as the ordinate.

2. The method for identifying anomalies in a temperature control device according to claim 1, wherein Integrating at least one piece of the operation data and at least one piece of the temperature control data of the temperature control device to obtain device data includes: Performing data cleaning processing on at least one piece of the operation data to obtain at least one first data; Performing data cleaning processing on at least one piece of the temperature control data to obtain at least one second data; Summarizing the first data and the second data corresponding to one acquisition time into one initial data; If it is determined that the quantity of at least one piece of the initial data reaches a preset calculation threshold, then setting at least one piece of the initial data as device data.

3. The method for identifying abnormalities of the temperature control device according to claim 2, wherein, Performing data cleaning processing on at least one piece of the operation data to obtain at least one first data includes: If it is recognized that there is a null value in one piece of the operation data, then determining that the one piece of operation data is invalid data; and / or If it is recognized that there is an invalid value in one piece of the operation data, then determining that the one piece of operation data is invalid data; Deleting the invalid data in at least one piece of the operation data to obtain at least one first data.

4. The method for identifying abnormal temperature control equipment according to claim 2, wherein Performing data cleaning processing on at least one piece of the temperature control data to obtain at least one second data includes: If it is recognized that there is a null value in one piece of the temperature control data, then determining that the one piece of temperature control data is invalid data; and / or If it is recognized that there is an invalid value in one piece of the temperature control data, then determining that the one piece of temperature control data is invalid data; and / or If it is recognized that one piece of the temperature control data does not belong to a preset threshold range, then determining that the one piece of temperature control data is invalid data; Deleting the invalid data in at least one piece of the temperature control data to obtain at least one second data.

5. The method for identifying abnormalities of a temperature control device according to claim 1, wherein Performing clustering operations on the device data of at least one temperature control device to obtain a first data cluster set and a second data cluster set includes: Calculating the central tendency of at least one piece of the device data of a temperature control device to obtain a first statistical value, and performing a clustering operation on the first statistical values of at least one temperature control device to obtain the first data cluster set; wherein, the central tendency reflected by the first statistical value describes the general level of the temperature control method and the temperature control effect of the temperature control device at each acquisition time; Calculating the degree of dispersion of at least one piece of the device data of a temperature control device to obtain a second statistical value, and performing a clustering operation on the second statistical values of at least one temperature control device to obtain the second data cluster set; wherein, the degree of dispersion reflected by the second statistical value describes the degree of difference in the temperature control method and the temperature control effect of the temperature control device at each acquisition time.

6. The method for identifying abnormalities in the temperature control device according to claim 5, characterized in that, The temperature control methods include cooling temperature control and heating temperature control; The calculating the central tendency of at least one piece of the device data of a temperature control device to obtain a first statistical value includes: Identifying, according to the status data in the operation data, the device data with the temperature control method of cooling temperature control in at least one piece of the device data, and summarizing to obtain a first cooling set; Calculating the central tendency of the temperature control data of each piece of device data in the first cooling set to obtain a first cooling value; wherein, the central tendency reflected by the first cooling value describes the general level of the temperature control data of each piece of device data under cooling temperature control; Identifying, according to the status data in the operation data, the device data with the temperature control method of heating temperature control in at least one piece of the device data, and summarizing to obtain a first heating set; Calculating the central tendency of the temperature control data of each piece of device data in the first heating set to obtain a first heating value; wherein, the central tendency reflected by the first heating value describes the general level of the temperature control data of each piece of device data in the heating state; Summarizing the first cooling value and the first heating value to obtain the first statistical value.

7. The method for identifying anomalies in a temperature control device according to claim 5, characterized in that, The temperature control methods include cooling temperature control and heating temperature control; The calculating the degree of dispersion of at least one piece of the device data of a temperature control device to obtain a second statistical value includes: Identifying, according to the status data in the operation data, the device data with the temperature control method of cooling temperature control in at least one piece of the device data, and summarizing to obtain a second cooling set; Calculating the degree of dispersion of the temperature control data of each piece of device data in the second cooling set to obtain a second cooling value; wherein, the degree of dispersion reflected by the second cooling value describes the degree of difference between the temperature control data of each piece of device data under cooling temperature control; Identifying, according to the status data in the operation data, the device data with the temperature control method of heating temperature control in at least one piece of the device data, and summarizing to obtain a second heating set; Calculating the degree of dispersion of the temperature control data of each piece of device data in the second heating set to obtain a second heating value; wherein, the degree of dispersion reflected by the second heating value describes the degree of difference between the temperature control data of each piece of device data in the heating state; Summarizing the second cooling value and the second heating value to obtain the second statistical value.

8. The method for identifying anomalies in a temperature control device according to claim 5, wherein, Performing clustering operations on the first statistical values of at least one of the temperature control devices to obtain the first data cluster set, including: Constructing at least one first cooling data point according to the first cooling value in the first statistical values of at least one of the temperature control devices; Constructing at least one first heating data point according to the first heating value in the first statistical values of at least one of the temperature control devices; Performing clustering operations on at least one of the first cooling data points according to a preset first neighborhood parameter and a first metric parameter to obtain the first cooling data cluster, and performing clustering operations on at least one of the first heating data points to obtain the first heating data cluster, and summarizing the first cooling data cluster and the first heating data cluster to obtain the first data cluster set; wherein, the first neighborhood parameter defines the diameter length of the data clusters in the first data cluster set; the first metric parameter defines the method for calculating the distance between two of the first cooling data points and two of the first heating data points; If it is determined that the first cooling data point of a temperature control device belongs to the first cooling data cluster and the first heating data point of the temperature control device belongs to the first heating data cluster, then define the temperature control device as a first temperature control device; If it is determined that the first cooling data point of a temperature control device does not belong to the first cooling data cluster, and / or the first heating data point of the temperature control device does not belong to the first heating data cluster, then define the temperature control device as a second temperature control device.

9. The method for identifying an abnormality of a temperature control device according to claim 8, characterized in that, The first cooling value includes a first cooling mean value and a first cooling quantile; The constructing at least one first cooling data point according to the first cooling value in the first statistical values of at least one of the temperature control devices includes: Constructing the first cooling data point of the temperature control device with the first cooling mean value of the temperature control device as the abscissa and the first cooling quantile of the temperature control device as the ordinate; The first heating value includes a first heating mean value and a first heating quantile; The constructing at least one first heating data point according to the first heating value in the first statistical values of at least one of the temperature control devices includes: Constructing the first heating data point of the temperature control device with the first heating mean value of the temperature control device as the abscissa and the first heating quantile of the temperature control device as the ordinate.

10. The method for identifying anomalies in a temperature control device according to claim 5, characterized in that, Performing clustering operations on the second statistical values of at least one of the temperature control devices to obtain the second data cluster set, including: Constructing at least one first cooling data point according to the first cooling value in the first statistical values of at least one of the temperature control devices for two of the second cooling data points and two of the second heating data points; Constructing at least one second cooling data point according to the second cooling value in the second statistical values of at least one of the temperature control devices; Constructing at least one second heating data point according to the second heating value in the second statistical values of at least one of the temperature control devices; Performing clustering operations on at least one of the second cooling data points according to preset second neighborhood parameters and second metric parameters to obtain the second cooling data clusters, and performing clustering operations on at least one of the second heating data points to obtain the second heating data clusters, and aggregating the second cooling data clusters and the second heating data clusters to obtain a second data cluster set; wherein, the second neighborhood parameters define the diameter lengths of the data clusters in the second data cluster set; the second metric parameters define the manner of calculating the distances between two of the second cooling data points and between two of the second heating data points. If it is determined that the second cooling data point of a temperature control device belongs to the second cooling data cluster and the second heating data point of the temperature control device belongs to the second heating data cluster, then define the temperature control device as a first temperature control device. If it is determined that the second cooling data point of a temperature control device does not belong to the second cooling data cluster, and / or the second heating data point of the temperature control device does not belong to the second heating data cluster, then define the temperature control device as a second temperature control device.

11. The method for identifying abnormalities of a temperature control device according to claim 10, characterized in that, The second cooling value includes a second cooling standard deviation and a second cooling coefficient of variation. The constructing of at least one second cooling data point according to the second cooling value in the second statistical value of at least one of the temperature control devices includes: Constructing the second cooling data point of the temperature control device with the second cooling standard deviation of the temperature control device as the abscissa and the second cooling coefficient of variation of the temperature control device as the ordinate. The second heating value includes a second heating standard deviation and a second heating coefficient of variation. The constructing of at least one second heating data point according to the second heating value in the second statistical value of at least one of the temperature control devices includes: Constructing the second heating data point of the temperature control device with the second heating standard deviation of the temperature control device as the abscissa and the second heating coefficient of variation of the temperature control device as the ordinate.

12. The method for identifying abnormal temperature control equipment according to any one of claims 1-11, characterized in that, After performing clustering operations on the device data of at least one of the temperature control devices to obtain a first data cluster set and a second data cluster set, the method further includes: If it is determined that the target temperature control device is defined as a first temperature control device in at least one data cluster in the first data cluster set and is defined as a first temperature control device in at least one data cluster in the second data cluster set, then determine that the target temperature control device is a normal device; or If it is determined that the target temperature control device is defined as a second temperature control device in at least one data cluster in the first data cluster set and is defined as a first temperature control device in at least one data cluster in the second data cluster set, then determine that the target temperature control device is a critical device; or If it is determined that the target temperature control device is defined as a first temperature control device in at least one data cluster in the first data cluster set and is defined as a second temperature control device in at least one data cluster in the second data cluster set, then determine that the target temperature control device is a critical device.

13. An abnormal recognition device for a temperature control device, characterized in that, The temperature control device is used for performing temperature control operations on at least one temperature control object, and the device includes: An input module, configured to obtain at least one operating data of a temperature control device and at least one temperature control data of at least one temperature control object corresponding to the temperature control device, and integrate the at least one operating data and the at least one temperature control data of the temperature control device to obtain device data; wherein, the operating data records a collection time and status data obtained from the temperature control device at the collection time; the status data reflects the temperature control method of the temperature control device for the temperature control object; the temperature control data records the collection time and temperature information of at least one of the temperature control objects at the collection time; the device data reflects the temperature control method of the temperature control device at each collection time and the temperature control effect on at least one of the temperature control objects. A processing module, configured to perform a clustering operation on the device data of at least one of the temperature control devices to obtain a first data cluster set and a second data cluster set; wherein, the first data cluster set includes at least one data cluster, and the data clusters in the first data cluster set are obtained by performing a clustering operation on the general level of the temperature control effect in the device data of each temperature control device; the second data cluster set includes at least one data cluster, and the data clusters in the second data cluster set are obtained by performing a clustering operation on the dispersion degree of the temperature control effect in the temperature control data of each temperature control device; the data cluster is a data point representing at least one temperature control device; the temperature control device corresponding to the data point belonging to the data cluster is defined as a first temperature control device; the temperature control device corresponding to the data point not belonging to the data cluster is defined as a second temperature control device. An abnormality module, configured to determine that the target temperature control device is an abnormal device if it is determined that the target temperature control device is defined as a second temperature control device in at least one data cluster in the first data cluster set and is defined as a second temperature control device in at least one data cluster in the second data cluster set. Among them, the first data cluster set is obtained by summarizing the first cooling data clusters and the first heating data clusters. The first cooling data clusters are obtained by performing clustering operations on at least one first cooling data point, and the first heating data clusters are obtained by performing clustering operations on at least one first heating data point. The first cooling data point is constructed with the first cooling mean value of one of the temperature control devices as the abscissa and the first cooling quantile of the temperature control device as the ordinate. The first heating data point is constructed with the first heating mean value of one of the temperature control devices as the abscissa and the first heating quantile of the temperature control device as the ordinate. The second data cluster set is obtained by summarizing the second cooling data clusters and the second heating data clusters. The second cooling data clusters are obtained by performing clustering operations on at least one second cooling data point, and the second heating data clusters are obtained by performing clustering operations on at least one second heating data point. The second cooling data point is constructed with the second cooling mean value of one of the temperature control devices as the abscissa and the second cooling quantile of the temperature control device as the ordinate. The second heating data point is constructed with the second heating mean value of one of the temperature control devices as the abscissa and the second heating quantile of the temperature control device as the ordinate.

14. A computer device, characterized in that, Comprising: a processor and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the temperature control device anomaly recognition method according to any one of claims 1 to 12.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the temperature control device anomaly recognition method according to any one of claims 1 to 12.

Images