Temperature anomaly identification method and device, electronic equipment, chip and storage medium

Abstract

The invention provides a temperature anomaly identification method and device, electronic equipment, a chip and a storage medium, and the method comprises the steps: determining a first temperature and a second temperature, the first temperature being a predicted temperature of a first point location of a first module at a first time point, and the second temperature being an actual temperature of the first point location of the first module at the first time point; determining a state identifier of the first module at the first time point according to the first temperature and the second temperature; and when the state identifier of the first module at the first time point is abnormal, determining whether the temperature of the first module is abnormal according to the state identifier of the first module at the at least one second time point. The temperature of the charging module can be monitored, temperature abnormity of the charging module occurs before the module breaks down, and the situation that the charging module cannot work normally or even is damaged due to the temperature abnormity is avoided.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing, and in particular to a method, device, electronic device, chip and storage medium for identifying temperature anomaly. Background Art

[0002] In the field of new energy vehicle charging, the charging module in the charging pile working in a high temperature environment for a long time or the module itself having abnormal temperature for a long time may cause damage to the module, thus affecting the charging experience. Summary of the invention

[0003] The present disclosure provides a temperature anomaly identification method, device, electronic device, chip and storage medium to solve the problems in the related art.

[0004] A first aspect embodiment of the present disclosure proposes a temperature anomaly identification method, the method comprising: determining a first temperature and a second temperature, the first temperature being a predicted temperature of a first point of a first module at a first time point, and the second temperature being an actual temperature of the first point of the first module at the first time point; determining a state identifier of the first module at the first time point based on the first temperature and the second temperature; when the state identifier of the first module at the first time point is abnormal, determining whether the temperature of the first module is abnormal based on the state identifier of the first module at at least one second time point.

[0005] In some embodiments of the present disclosure, the method also includes: determining the first temperature and the second temperature includes: obtaining message data of the first point of the first module at the first time point; performing feature processing on the message data to obtain data features of the first point of the first module at the first time point; inputting the data features into the target temperature prediction model to obtain the first temperature; and determining the second temperature based on the message data of the first point of the first module at the first time point.

[0006] In some embodiments of the present disclosure, the method also includes: the method also includes: collecting message data of at least one second module at at least one historical time point; performing data cleaning on the message data of at least one second module at at least one historical time point to obtain target message data; performing feature processing on the target message data to obtain a training data set and a test data set; using the training data set to train a polynomial regression model, and using the test data set to test it to obtain a target temperature prediction model.

[0007] In some embodiments of the present disclosure, the method also includes: performing data cleaning on message data of at least one second module at at least one historical time point, and obtaining target message data includes: collecting maintenance data of at least one second module; from the message data of at least one second module at at least one historical time point, eliminating the message data of the second module whose maintenance data meets a first preset condition, to obtain intermediate message data; determining the charging time data of at least one second module based on the intermediate message data; and from the intermediate message data, eliminating the message data of the second module whose charging time data is less than the preset time, to obtain the target message data.

[0008] In some embodiments of the present disclosure, the method also includes: training the polynomial regression model using a training data set, and testing it using a test data set, and obtaining the target temperature prediction model includes: fitting the polynomial regression model using the training data set to obtain a trained temperature prediction model; testing the trained temperature prediction model using the test data set to determine the error value of the trained temperature prediction model; when the error value meets a second preset condition, determining that the trained temperature prediction model is the target temperature prediction model.

[0009] In some embodiments of the present disclosure, the method also includes: determining the state identification of the first module at the first time point based on the first temperature and the second temperature, including: determining the difference between the first temperature and the second temperature; when the difference satisfies a third preset condition, determining that the state identification of the first module at the first time point is abnormal; when the difference does not satisfy the third preset condition, determining that the state identification of the first module at the first time point is normal.

[0010] In some embodiments of the present disclosure, the method also includes: when the status of the first module at a first time point is identified as abnormal, determining whether the temperature of the first module is abnormal based on the status identification of the first module at at least one second time point includes: determining the number of second time points at which the status of the first module is identified as abnormal; when the number meets a fourth preset condition, determining that the temperature of the first module is abnormal.

[0011] A second aspect of the present disclosure provides a temperature anomaly identification device, which includes: a first processing unit, used to determine a first temperature and a second temperature, the first temperature being a predicted temperature of a first point of a first module at a first time point, and the second temperature being an actual temperature of the first point of the first module at the first time point; a second processing unit, used to determine a state identifier of the first module at the first time point based on the first temperature and the second temperature; and a third processing unit, used to determine whether the temperature of the first module is abnormal based on the state identifier of the first module at at least one second time point when the state identifier of the first module at the first time point is abnormal.

[0012] The third aspect embodiment of the present disclosure proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in the first aspect embodiment of the present disclosure.

[0013] The fourth aspect embodiment of the present disclosure proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the method described in the first aspect embodiment of the present disclosure.

[0014] The fifth aspect embodiment of the present disclosure proposes a chip, characterized in that it includes at least one processor and a communication interface; the communication interface is used to receive signals input into the chip or signals output from the chip, and the processor communicates with the communication interface and implements the method described in the first aspect embodiment of the present disclosure through logic circuits or execution code instructions.

[0015] A sixth aspect of an embodiment of the present disclosure provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the method in any one of the implementation methods of the first aspect above.

[0016] In summary, the temperature anomaly identification method proposed in the present invention can monitor the temperature of the first module and determine whether there is an abnormality in the temperature of the first module. It can identify the temperature anomaly of the first module before the first module fails, and can avoid shutdown or damage caused by the temperature anomaly of the first module.

[0017] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0019] Figure 1 A schematic diagram of a flow chart of a method for identifying temperature anomalies provided in an embodiment of the present disclosure; Figure 2 A schematic diagram of a flow chart of a method for identifying temperature anomalies provided in an embodiment of the present disclosure; Figure 3 A schematic diagram of a flow chart of a method for identifying temperature anomalies provided in an embodiment of the present disclosure; Figure 4A schematic diagram of the structure of a temperature anomaly identification device provided in an embodiment of the present disclosure; Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure; Figure 6 A schematic diagram of the chip structure provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0020] Embodiments of the present disclosure are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0021] In the field of new energy vehicle charging, the charging module, as the core component of the charging pile, is of great importance. Specifically, the charging module directly determines the charging efficiency. The charging module is responsible for converting the AC power in the power grid into DC power suitable for charging electric vehicle batteries. The level of its conversion efficiency directly determines the speed of charging, which affects the user's charging experience. During the charging process, the charging module needs to maintain a stable output voltage and current to ensure that the battery can be charged safely and reliably. If the performance of the charging module is unstable, it may cause abnormalities in the charging process, such as voltage fluctuations, excessive current, etc., which may damage the battery life and even cause safety accidents.

[0022] Long-term operation in a high-temperature environment or long-term abnormal temperature of the module itself may cause damage to the module, thus affecting the charging experience. In related technologies, maintenance is usually carried out only after the charging module fails, and potential abnormalities cannot be discovered in advance. In addition, current technologies only stay at the pile dimension and do not go deep into the module, so the abnormal location cannot be discovered in time.

[0023] Therefore, in order to solve the above problems, the present disclosure proposes a temperature anomaly identification method, which can accurately identify the temperature status of each component inside the module, including key components such as DCDC, rectifier, diode, etc. By real-time monitoring of the temperature changes of these components, potential abnormal conditions such as overheating, overcooling or excessive temperature fluctuations can be discovered in time, thereby avoiding equipment damage or safety accidents caused by temperature anomalies.

[0024] The specific contents of this method are as follows.

[0025] Figure 1 The following is a flow chart of a method for identifying temperature anomalies provided by an embodiment of the present disclosure. Figure 1 As shown, the method may include the following steps.

[0026] Step 101, determining a first temperature and a second temperature.

[0027] In some embodiments, the first temperature is a predicted temperature of a first point of the first module at a first time point, and the second temperature is an actual temperature of the first point of the first module at the first time point.

[0028] Optionally, the first module may be a charging module, for example, the first module may be a charging module in a charging pile. In the field of new energy vehicles, the charging module may be responsible for converting the AC power in the power grid into DC power suitable for charging the battery of an electric vehicle. The charging module needs to maintain a stable output voltage and current to ensure that the battery can be charged safely and reliably. If the performance of the charging module is unstable, it may cause abnormalities during the charging process, such as voltage fluctuations, excessive current, etc., thereby damaging the battery life and even causing safety accidents.

[0029] Optionally, the first temperature may be determined using a target temperature prediction model. In other words, the target temperature prediction model may be used to predict the temperature of a first point of the first module at a first time point.

[0030] Optionally, the second temperature may be determined according to the message data reported by the first module, that is, the first module may report the actual temperature of the first point at the first time point.

[0031] In some embodiments, the first point may be a point of a component included in the first module, for example, the first point may be the position of three live wires of a power factor correction (PFC) module, or the first point may be the position of a positive MOS tube of a direct current-direct current (DCDC) module, or the first point may be the position of a negative MOS tube of a DCDC module, or the first point may be the position of an output diode of a DCDC module, or the first point may be the position of a rectifier diode, and therefore, optionally, the temperature of the first point may be any one of a module PFC temperature (U), a module PFC temperature (V), a module PFC temperature (W), a module DCDC positive MOS tube temperature, a module DCDC negative MOS tube temperature, a module DCDC output diode temperature, and a module rectifier diode temperature.

[0032] In some embodiments, optionally, the number of first points is at least one, in other words, the temperature of the first point can be determined as the temperature of the first module, or the temperatures of multiple points at the first time point can be determined simultaneously based on the data of each frame message.

[0033] In some embodiments, optionally, the first module may periodically report message data, for example, the first module may report a frame of message data every 60 seconds. Optionally, the message data may include at least one of module output current, module output voltage, module PFC temperature (U), module PFC temperature (V), module PFC temperature (W), module ambient temperature, module DCDC positive MOS tube temperature, module DCDC negative MOS tube temperature, module DCDC output diode temperature, module rectifier diode temperature, DC output capacitance percentage, and fan speed.

[0034] In some embodiments, the first module may optionally report other parameter information in addition to the message data. For example, when the first module is started, the basic module information may be reported, wherein the basic module information may include at least one of the number of modules, the module code (Serial Number, SN), the module software version, the module hardware version, the module rated power, the module rated voltage, the module rated current, and the total capacitance of the DC output side. The startup of the first module may be the first time the first module is used for charging.

[0035] Optionally, the first module may also report equipment maintenance information, wherein the equipment maintenance information may include equipment identification (eg, charging pile identification or first module identification or first point identification, etc.), fault type, fault time, and maintenance time.

[0036] Step 102: Determine a state identifier of a first module at a first time point according to a first temperature and a second temperature.

[0037] In some embodiments, the status identifier of the first module can be used to indicate whether the temperature status of the first module is normal. For example, when the status identifier of the first module at the first time point is normal, it means that according to the message data reported at the first time point, it can be determined that the temperature of the first module at the first time point is normal temperature; when the status identifier of the first module at the first time point is abnormal, it means that according to the message data reported at the first time point, it can be determined that the temperature of the first module at the first time point is abnormal.

[0038] In some embodiments, based on the first temperature and the second temperature, determining the state identification of the first module at the first time point includes: determining the difference between the first temperature and the second temperature; when the difference meets a third preset condition, determining that the state identification of the first module at the first time point is abnormal; when the difference does not meet the third preset condition, determining that the state identification of the first module at the first time point is normal.

[0039] Optionally, the third preset condition may be that the difference is greater than or equal to a preset threshold. For example, the third preset condition may be that the difference between the first temperature and the second temperature is greater than or equal to 5 degrees. At this time, when the difference between the first temperature and the second temperature is greater than or equal to 5 degrees, it can be determined that the state of the first module at the first time point is identified as abnormal, that is, at the first time point, the actual temperature of the first point is higher than the predicted temperature. At this time, it can be preliminarily judged that there is an abnormality at the first point at the first time point.

[0040] Optionally, when the temperature of the first point at the first time point is abnormal, it can be determined that the first module is also abnormal at the first time point, that is, the temperature abnormality of a point can be equivalent to the abnormality of the first module, and the state of the first module at the first time point is marked as abnormal. In other words, when the temperature of a point at the first time point is abnormal, it can be determined that the state of the first module at the first time point is marked as abnormal. Optionally, the first temperature and the second temperature of multiple points in the first module can be determined based on a frame of message data, and when the actual temperature of any point among the multiple points is abnormal, it is determined that the state of the first module at the first time point is marked as abnormal.

[0041] Optionally, the state identification of the first module can be determined based on the state identification of multiple points, that is, the temperature anomalies of multiple points can be equivalent to the anomalies of the first module. For example, when the number or proportion of abnormal points exceeds a preset threshold, the state identification of the first module can be determined as abnormal. For example, the second temperature of 7 points in the first module can be determined based on the message data at the first time point, and the first temperature of the 7 points can be determined using the target temperature prediction model respectively. For each point, the difference between the first temperature and the second temperature is determined, and according to the third preset condition, it is determined whether the seven points are abnormal points. Optionally, when the difference between the first temperature and the second temperature meets the third preset condition, the corresponding point can be an abnormal point. Optionally, when the number of abnormal points is large, the state identification of the first module can be determined as abnormal.

[0042] Step 103 , when the state identification of the first module at a first time point is abnormal, determine whether the temperature of the first module is abnormal according to the state identification of the first module at at least one second time point.

[0043] In some embodiments, the second time point may be a time point adjacent to or close to the first time point. Optionally, the second time point may be before the first time point. For example, if the t-th frame message data can be reported at the first time point, then the t-1-th frame message data can be reported at the second time point. When there are multiple second time points, the t-2, t-3 or t+1 frame data can be reported at different second time points, and so on.

[0044] In other words, when the status of the first module at a first time point is identified as abnormal, it is possible to determine whether the first module is abnormal based on the status identifications at adjacent or similar time points. Optionally, when the points in the first module return to normal temperature within a period of time, it can be determined that the temperature of the first module is normal, which can improve the fault tolerance rate and avoid affecting the judgment of the abnormal temperature of the first module due to short-term emergencies at a single point.

[0045] In some embodiments, when the status of the first module at a first time point is identified as abnormal, determining whether the temperature of the first module is abnormal based on the status identification of the first module at at least one second time point includes: determining the number of second time points at which the status of the first module is identified as abnormal; and determining that the temperature of the first module is abnormal when the number meets a fourth preset condition.

[0046] In other words, the number of time points at which the status is marked as abnormal can be determined. For example, the status marks of the current frame and the previous two frames can be counted. If all three frames are marked as abnormal, the status mark of the first module is identified as abnormal. If not all three frames are marked as abnormal, the status mark of the first module is identified as normal.

[0047] In some embodiments, optionally, when the status identification of the first point at the first time point is abnormal, it can be determined that the status identification of the entire first module at the first time point is abnormal. At this time, at the second time point, the status identification of the first module can be determined according to the status identification of other points, and according to the status identification of the modules determined at different points, it is determined whether the temperature of the first module is abnormal. For example, the first module includes point 1, point 2, and point 3. According to the first frame message data, the status identification of point 1 is determined to be abnormal, and the other points are normal. According to the second frame message data, the status identification of point 2 is determined to be abnormal, and the other points are normal. According to the third frame message data, the status identification of point 3 is determined to be abnormal, and the other points are normal. At this time, it can be determined according to the 3 frames of message data that at the three time points, the status identification of the first module is abnormal. At this time, it can be determined that the temperature of the first module is abnormal.

[0048] In summary, the above-mentioned embodiments of the present disclosure can determine the status identifier of the first module according to the actual temperature and predicted temperature of the point in the first module, and determine whether the temperature of the first module is abnormal according to the status identifier of the first module at the first time point and the second time point, which can improve the accuracy of temperature anomaly identification, and can detect the temperature anomaly of the first module before the first module fails, thereby avoiding the failure of the first module caused by the temperature anomaly.

[0049] Figure 2 The following is a flow chart of a method for identifying temperature anomalies provided by an embodiment of the present disclosure. Figure 2 As shown, based on Figure 1In the illustrated embodiment, the method comprises the following steps.

[0050] Step 201, obtaining message data of a first point of a first module at a first time point.

[0051] In some embodiments, message data of the first module at a first time point may be acquired, wherein the message data may include data of multiple points in the first module, that is, the number of the first points may be multiple.

[0052] In some embodiments, the message data of the first module can be periodically received. For example, the first module can report a frame of message data every 60 seconds, wherein the reported message data is real-time data at the reporting time point. Optionally, the message data may include at least one of the module output current, the module output voltage, the module PFC temperature (U), the module PFC temperature (V), the module PFC temperature (W), the module ambient temperature, the module DCDC positive MOS tube temperature, the module DCDC negative MOS tube temperature, the module DCDC output diode temperature, the module rectifier diode temperature, the DC output capacitance percentage, and the fan speed.

[0053] Step 202 , feature processing is performed on the message data to obtain data features of the first point of the first module at the first time point.

[0054] In some embodiments, the data features of the first module may include at least one of the module number, the current charging time, the charging time from the previous frame, the output current, the output voltage, the module PFC temperature (U), the module PFC temperature (V), the module PFC temperature (W), the module ambient temperature, the module DCDC positive MOS tube temperature, the module DCDC negative MOS tube temperature, the module DCDC output diode temperature, the module rectifier diode temperature, the DC output capacitance percentage, the fan speed, the module ambient temperature of the previous frame, the module PFC temperature (U) of the previous frame, the module PFC temperature (V) of the previous frame, the module PFC temperature (W) of the previous frame, the module DCDC positive MOS tube temperature of the previous frame, the module DCDC negative MOS tube temperature of the previous frame, the module DCDC output diode temperature of the previous frame, and the module rectifier diode temperature of the previous frame.

[0055] Optionally, when the message data reported at the first time point is the first frame data of the current charging, the module ambient temperature of the previous frame, the module PFC temperature (U) of the previous frame, the module PFC temperature (V) of the previous frame, the module PFC temperature (W) of the previous frame, the DCDC positive MOS tube temperature of the previous frame, the DCDC negative MOS tube temperature of the previous frame, the DCDC output diode temperature of the previous frame, and the rectifier diode temperature of the previous frame module do not need to be reported, that is, the message data of the previous frame can be blank or the default value 0, etc.

[0056] In some embodiments, feature processing of the message data may be performed by acquiring corresponding data from the message data according to different points to obtain data features. For example, when the first point is the module DCDC positive MOS tube, the data features of the first point of the first module at the first time point may include the module number, the current charging time, the charging time from the previous frame, the output current, the output voltage, the module ambient temperature, the module DCDC positive MOS tube temperature, the module DCDC positive MOS tube temperature of the previous frame, the module ambient temperature of the previous frame, and the like.

[0057] In some embodiments, feature processing of message data may further include determining data features based on the message data. For example, the current charging duration and the duration from the last charging frame may be determined based on time point information reported in the message data.

[0058] In some embodiments, optionally, the charging duration of this time can be the duration from the start of charging to the reporting of the frame message data, and the charging duration from the previous frame can be the charging duration from the time point when the previous frame message data is reported to the time point when the current frame is reported. For example, when one frame message data is reported every 60s, and two adjacent frames of message data are in the same charging process, the charging duration from the previous frame can be 60s. When the first reported frame is in a charging state, but the second frame is in an uncharged state, the charging duration from the previous frame is less than 60s. In other words, the message data can record the charging duration in the reporting interval.

[0059] In some embodiments, the message data reported by the first module can be sorted in order according to the reporting time point. Optionally, the first module can report the message data only during the charging process, and not report the message data when the first module is in an idle state. At this time, when the interval between the reporting time points of two adjacent frames exceeds 5 minutes, it can be considered that the previous frame belongs to the data of the previous charging process, that is, the end frame of the previous charging, and the next frame belongs to the data of this charging process, that is, the start frame of a charging.

[0060] Optionally, feature processing may also include other contents, such as data cleaning, data conversion, etc. Feature processing can be used to process message data into input data of a target temperature prediction model, that is, feature processing can be used to convert message data into input data suitable for a target temperature prediction model.

[0061] Step 203: input the data features into a target temperature prediction model to obtain a first temperature.

[0062] In some embodiments, the data features may be used as input data of a target temperature prediction model. Optionally, the target temperature prediction model may be used to predict the temperature of a first point according to the data features of each point to obtain a first temperature.

[0063] Optionally, when there are multiple first points, data features may be determined for each point, and a target temperature prediction model may be used to determine a predicted temperature of each point at the first time point.

[0064] Step 204: determine the second temperature according to the message data of the first point of the first module at the first time point.

[0065] In some embodiments, optionally, the actual temperature of each point at the first time point, i.e., the second temperature, can be determined based on the message data of the first point of the first module at the first time point. In other words, the first module can report the real-time temperature of at least one point in the first module at the first time point as the actual temperature of the first point at the first time point.

[0066] In summary, the above-mentioned embodiments of the present application can use the target temperature prediction model to predict the temperature of the point in the first module, and determine the actual temperature of the point in the first module according to the message data reported by the first module. It can be used to determine whether the temperature of the first module is abnormal based on the predicted temperature and the actual temperature. The temperature anomaly of the first module can be identified in time to avoid problems such as failures caused by the temperature anomaly of the first module.

[0067] Figure 3 The following is a flow chart of a method for identifying temperature anomalies provided by an embodiment of the present disclosure. Figure 3 As shown, based on Figure 1 In the illustrated embodiment, the method comprises the following steps.

[0068] Step 301: Collect message data of at least one second module at at least one historical time point.

[0069] In some embodiments, message data of at least one second module can be collected. Optionally, data of the second module at multiple historical time points can be collected. Optionally, the first module can be the second module, that is, historical message data of the second module including the first module can be collected, wherein the collected message data at the historical time points can be used to train the target temperature prediction model.

[0070] In some embodiments, historical message data of multiple second modules may be collected to improve the accuracy and generalization ability of the target prediction model. Optionally, basic information of multiple second modules and equipment maintenance data, etc. may also be collected.

[0071] Step 302: clean the message data of at least one second module at at least one historical time point to obtain target message data.

[0072] In some embodiments, data cleaning of message data of at least one second module at at least one historical time point can eliminate invalid data or erroneous data, thereby avoiding interference with model training.

[0073] In some embodiments, data cleaning is performed on message data of at least one second module at at least one historical time point to obtain target message data, including: collecting maintenance data of at least one second module; eliminating message data of the second module whose maintenance data meets a first preset condition from the message data of at least one second module at at least one historical time point to obtain intermediate message data; determining charging time data of at least one second module based on the intermediate message data; and eliminating message data of the second module whose charging time data is less than a preset time from the intermediate message data to obtain target message data.

[0074] In some embodiments, the first preset condition may be that the maintenance data is not empty, or the number of maintenance times is greater than 0, etc. In other words, after receiving the message data of the second module, the maintenance data of the second module may be collected. When the maintenance data of the second module is not empty, it indicates that the second module has been maintained. At this time, the data of the second module after maintenance may have deviations, which will affect the model. Therefore, when it is determined that there is a maintenance record for the second module, all the data of the second module may be eliminated, that is, the data of the second model will not be used.

[0075] In some embodiments, after receiving the message data from the second module, the charging time can be determined based on the message data. Optionally, data with shorter charging time can be eliminated. When the charging time is short, the working time of the second module is short and it cannot provide data support for long-term charging. Therefore, when the charging time is short, the message data of the second module can be eliminated, where the charging time data can be the total charging time data of the second module. For example, when the charging time is less than 5 minutes, the charging data will be eliminated; or the charging time can be the time from the start of charging to the reporting time point of the current frame. At this time, part of the data of the second module with a charging time of less than 5 minutes can be eliminated, and only data with longer charging time can be used for model training. When the charging time is short, the probability of temperature abnormality in the module is small. Therefore, only the target temperature prediction model can be used to predict the temperature of the point where the charging time exceeds the preset threshold, and the present disclosure is not limited to this.

[0076] Step 303: perform feature processing on the target message data to obtain a training data set and a test data set.

[0077] In some embodiments, feature processing may be performed on the target message data, wherein the feature processing method is similar to the feature processing method of step 202 and will not be repeated here. Optionally, when the number of first points is multiple, feature processing may be performed on the target message data of each point to obtain corresponding training data sets and test data sets. Optionally, the data features after feature processing may be used to train a polynomial regression model.

[0078] Optionally, the test data set and training data set obtained by feature processing of each point can be used to train a target temperature prediction model. In this case, the target temperature prediction model is used to predict the temperature of the corresponding point. That is, for each point, a target temperature prediction model can be trained, which is only used to predict the temperature of the point.

[0079] For example, when the first point is the position of the PFC module (U), the training data set and the test data set may include data features such as output current, output voltage, current charging time, charging time from the previous frame, module ambient temperature, module PFC temperature (U) of the previous frame, and ambient temperature of the previous frame.

[0080] Optionally, the solution of this solution can be used to determine the target temperature prediction model of seven points, including module PFC temperature (U), module PFC temperature (V), module PFC temperature (W), module DCDC positive MOS tube temperature, module DCDC negative MOS tube temperature, module DCDC output diode temperature, module rectifier diode temperature prediction model, etc.

[0081] Optionally, when determining whether the temperature of the first module is abnormal, the above seven prediction models can be used simultaneously to determine the predicted temperature of the point, and determine whether there is an abnormality in the first point based on the difference between the predicted temperature and the actual temperature. At this time, the number of first points is seven. Optionally, when there is an abnormality in at least one point, the status of the first module can be determined to be abnormal.

[0082] Step 304: Use the training data set to train the polynomial regression model, and use the test data set to test it, to obtain a target temperature prediction model.

[0083] In some embodiments, a polynomial regression model is trained using a training data set and tested using a test data set to obtain a target temperature prediction model, including: fitting and training the polynomial regression model using the training data set to obtain a trained temperature prediction model; testing the trained temperature prediction model using the test data set to determine an error value of the trained temperature prediction model; and when the error value meets a second preset condition, determining that the trained temperature prediction model is the target temperature prediction model.

[0084] In some embodiments, the second preset condition may be that the mean absolute error (MAE) or mean squared error (MSE) of the trained temperature prediction model is greater than a preset value and less than a preset threshold value, that is, the polynomial regression model can be iteratively trained using a training data set, and the error of the trained temperature prediction model can be tested using a test data set. When the error value of the trained temperature prediction model is small, the iterative training is completed to obtain the target temperature prediction model, wherein the smaller the error value, the better the effect of the model training.

[0085] In some embodiments, training a polynomial regression model using a training data set may be to fit the model using an automatic parameter search method to determine the optimal parameters of the polynomial regression model, wherein the parameters of the polynomial regression model may include polynomial coefficients, maximum order, 0th order term parameters, and whether only high-order terms are included, etc.

[0086] Optionally, the final target temperature prediction model can be expressed in a polynomial form, such as the following formula:

[0087] In multi-dimensional scenarios, it can be expressed as

[0088] In summary, the above-mentioned embodiments of the present disclosure can use historical message data to train the polynomial regression model to obtain a target temperature prediction model, which can improve the accuracy of the target temperature prediction model, realize the prediction of the temperature of the first point, and timely identify the temperature anomaly of the first module to avoid module failure caused by the temperature anomaly of the first module.

[0089] The technical solution of the present disclosure is further described in detail below in conjunction with specific application examples.

[0090] The following is a method for identifying abnormal temperature of a charging module based on a polynomial regression algorithm provided by an embodiment of the present disclosure. Since module charging always goes through the states of idle-starting charging-charging, and the temperature change trend is from gradually rising to gradually stabilizing, the trends are mostly consistent and can be fitted with a curve. This method analyzes the working temperature reported by a series of temperature sensors inside the module, and combines historical module maintenance data to fit a temperature change curve of a single module during a single charge through a polynomial regression algorithm. This is used to characterize the temperature change of a fault-free module during charging, and to identify whether the module has temperature abnormalities by comparing the actual temperature at multiple time points with the predicted temperature. The specific content of this method is as follows.

[0091] 1. Feature Engineering 1.1 Data Collection Data is collected through messages reported during the operation of the charging module, where the collected data is used to train the regression model: Basic module information (reported at startup): module quantity, module code SN, module software version, module hardware version, module rated power, module rated voltage, module rated current, and total capacitance on the DC output side.

[0092] Module operation data (one frame reported every 60 seconds): module output current, module output voltage, module PFC temperature (U), module PFC temperature (V), module PFC temperature (W), module ambient temperature, module DCDC positive MOS tube temperature, module DCDC negative MOS tube temperature, module DCDC output diode temperature, module rectifier diode temperature, DC output capacitance percentage, fan speed.

[0093] Equipment maintenance information: equipment ID, fault type, fault time, and repair time.

[0094] 1.2 Data Processing Construct a charging data: classify the charging module message data by module code and sort them in chronological order; if the time interval between adjacent messages AB exceeds 5 minutes, it is considered that A is the end of the previous charging and B is the beginning of a new charging.

[0095] Feature processing: Construct the following features for each frame (each message) of each charge: Module number; current charging time; charging time since the last frame; output current; output voltage; module PFC temperature (U); module PFC temperature (V); module PFC temperature (W); module ambient temperature; module DCDC positive MOS tube temperature; module DCDC negative MOS tube temperature; module DCDC output diode temperature; module rectifier diode temperature; DC output capacitance percentage; fan speed; module ambient temperature in the previous frame; module PFC temperature (U) in the previous frame. If the current time is the start time of charging and the time since the last charging is greater than 5 minutes, the module PFC temperature (U) in the previous frame is the current module ambient temperature. The following temperatures are the same as above; module PFC temperature (V) in the previous frame; module PFC temperature (W) in the previous frame; module DCDC positive MOS tube temperature in the previous frame; module DCDC negative MOS tube temperature in the previous frame; module DCDC output diode temperature in the previous frame; module rectifier diode temperature in the previous frame.

[0096] 1.3 Data cleaning: If the charging time is less than 5 minutes, it is considered invalid data; if there is a module failure record, the module data will be removed.

[0097] 1.4 Variable Selection Consider regression fitting for multiple temperature points, taking the module PFC temperature (U) scenario as an example.

[0098] Select independent variables: output current, output voltage, current charging time, charging time from the previous frame, module ambient temperature, module PFC temperature (U) of the previous frame, and ambient temperature of the previous frame.

[0099] Select the dependent variable: module PFC temperature (U).

[0100] 2. Polynomial Regression The Polynomial Features regression algorithm is used to fit each temperature scenario, and the final fitting equation can be expressed as:

[0101] In multi-dimensional scenarios, it can be expressed as

[0102] Determine the degree of a polynomial: A higher number may lead to overfitting. Consider verifying the MAE and MSE of the model on the test set to determine the most appropriate number. The selection standard is MAE. The smaller the MSE, the better the model fitting effect.

[0103] Determine feature dimensions: Automatic parameter search method is used to determine the optimal parameter selection.

[0104] Finally, the regression models for seven scenarios can be obtained: module PFC temperature (U), module PFC temperature (V), module PFC temperature (W), module DCDC positive MOS tube temperature, module DCDC negative MOS tube temperature, module DCDC output diode temperature, and module rectifier diode temperature.

[0105] 3. Temperature anomaly identification Taking the module PFC temperature (U) as an example, the rest of the scenarios are the same.

[0106] I. Record the module report messages in the current and previous period.

[0107] II. Process the current message data according to feature engineering to obtain corresponding features.

[0108] III. Input the features into the pre-trained regression model to obtain the model predicted temperature.

[0109] i. If the current actual temperature minus the predicted temperature < 5, it is considered normal; ii. If the current actual temperature - predicted temperature >= 5, it is marked as a potential anomaly.

[0110] IV. Count the abnormal marks of the current frame and the previous two frames.

[0111] i. If all three frames are marked as potential anomalies, identify them as anomalies; ii. If not all three frames are marked as potential anomalies, they are identified as normal.

[0112] V. Output anomaly identification conclusion.

[0113] 4. Rule diagnosis application Data monitoring: The module operation and maintenance interface provides real-time monitoring of the module working status. Each module displays two temperature curves, one for the actual temperature change curve and the other for the predicted temperature curve. Points where the actual temperature and the predicted temperature are greater than the threshold are highlighted.

[0114] Provides site-level temperature anomaly monitoring, showing how many modules in the site have temperature anomalies.

[0115] Provides temperature anomaly monitoring in pile dimension, showing how many modules in the pile have temperature anomalies.

[0116] Abnormal reminder: After identifying the temperature abnormality, the merchant is reminded that the temperature of a certain pile module is abnormal and whether the module output power needs to be limited.

[0117] In summary, the above examples disclosed in the present invention can observe the temperature of each key component when the module is charging in real time, and compare it with the temperature predicted by the model. Combined with the corresponding abnormality identification strategy, it can promptly discover the temperature anomaly when the module is working, implement timely and effective disposal measures, and provide the temperature data monitoring and abnormal points to the merchant in a visual way, so that the merchant can have a more comprehensive understanding of the working condition of the equipment. The minimum recognition granularity of the present invention is a single module, so it is also possible to discover temperature anomalies in the pile dimension or the station dimension through statistical analysis of aggregated data, help operation and maintenance personnel to investigate the cause of temperature anomalies, and ensure that the charging module has a good working environment.

[0118] Figure 4 FIG. 4 is a schematic diagram of a temperature anomaly identification device 400 provided in an embodiment of the present disclosure. Figure 4 As shown, the device includes: a first processing unit 410, used to determine a first temperature and a second temperature, the first temperature being a predicted temperature of a first point of the first module at a first time point, and the second temperature being an actual temperature of the first point of the first module at the first time point; a second processing unit 420, used to determine a state identifier of the first module at the first time point based on the first temperature and the second temperature; a third processing unit 430, used to determine whether the temperature of the first module is abnormal based on a state identifier of the first module at at least one second time point when the state identifier of the first module at the first time point is abnormal.

[0119] In some embodiments, the first processing unit is also used to obtain message data of the first point of the first module at the first time point; perform feature processing on the message data to obtain data features of the first point of the first module at the first time point; input the data features into the target temperature prediction model to obtain the first temperature; and determine the second temperature based on the message data of the first point of the first module at the first time point.

[0120] In some embodiments, the temperature anomaly identification device also includes a fourth processing unit, which is used to collect message data of at least one second module at at least one historical time point; perform data cleaning on the message data of at least one second module at at least one historical time point to obtain target message data; perform feature processing on the target message data to obtain a training data set and a test data set; use the training data set to train the polynomial regression model, and use the test data set to test it to obtain a target temperature prediction model.

[0121] In some embodiments, the fourth processing unit is also used to collect maintenance data of at least one second module; from the message data of at least one second module at at least one historical time point, eliminate the message data of the second module whose maintenance data meets the first preset condition to obtain intermediate message data; determine the charging time data of at least one second module based on the intermediate message data; from the intermediate message data, eliminate the message data of the second module whose charging time data is less than the preset time to obtain the target message data.

[0122] In some embodiments, the fourth processing unit is also used to use the training data set to fit the polynomial regression model to obtain a trained temperature prediction model; use the test data set to test the trained temperature prediction model to determine the error value of the trained temperature prediction model; when the error value meets the second preset condition, determine that the trained temperature prediction model is the target temperature prediction model.

[0123] In some embodiments, the second processing unit is also used to determine the difference between the first temperature and the second temperature; when the difference meets the third preset condition, the state of the first module at the first time point is determined to be abnormal; when the difference does not meet the third preset condition, the state of the first module at the first time point is determined to be normal.

[0124] In some embodiments, the third processing unit is further used to determine the number of second time points at which the state of the first module is marked as abnormal; when the number meets a fourth preset condition, determine that the temperature of the first module is abnormal.

[0125] In summary, the temperature anomaly identification device 400 can monitor the temperature of the first module and determine whether there is an abnormality in the temperature of the first module. It can identify the temperature anomaly of the first module before the first module fails, and can avoid shutdown or damage caused by the temperature anomaly of the first module.

[0126] In the embodiments provided in the present application, the methods and devices provided in the embodiments of the present application are introduced. In order to implement the functions in the methods provided in the embodiments of the present application, the electronic device may include a hardware structure and a software module, and implement the functions in the form of a hardware structure, a software module, or a hardware structure plus a software module. A function of the functions may be executed in the form of a hardware structure, a software module, or a hardware structure plus a software module.

[0127] Figure 5 is a block diagram of an electronic device 500 for implementing the above method according to an exemplary embodiment. For example, the electronic device 500 may be a mobile phone, a computer, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0128] Reference Figure 5 , the electronic device 500 may include one or more of the following components: a processing component 502 , a memory 504 , a power component 506 , a multimedia component 508 , an audio component 510 , an input / output (I / O) interface 512 , a sensor component 514 , and a communication component 516 .

[0129] The processing component 502 generally controls the overall operation of the electronic device 500, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 502 may include one or more processors 520 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 502 may include one or more modules to facilitate the interaction between the processing component 502 and other components. For example, the processing component 502 may include a multimedia module to facilitate the interaction between the multimedia component 508 and the processing component 502.

[0130] The memory 504 is configured to store various types of data to support operations on the electronic device 500. Examples of such data include instructions for any application or method operating on the electronic device 500, contact data, phone book data, messages, pictures, videos, etc. The memory 504 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0131] The power supply component 506 provides power to the various components of the electronic device 500. The power supply component 506 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 500.

[0132] The multimedia component 508 includes a screen that provides an output interface between the electronic device 500 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 508 includes a front camera and / or a rear camera. When the electronic device 500 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0133] The audio component 510 is configured to output and / or input audio signals. For example, the audio component 510 includes a microphone (MIC), and when the electronic device 500 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 504 or sent via the communication component 516. In some embodiments, the audio component 510 also includes a speaker for outputting audio signals.

[0134] I / O interface 512 provides an interface between processing component 502 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0135] The sensor assembly 514 includes one or more sensors for providing various aspects of status assessment for the electronic device 500. For example, the sensor assembly 514 can detect the open / closed state of the electronic device 500, the relative positioning of components, such as the display and keypad of the electronic device 500, and the sensor assembly 514 can also detect the position change of the electronic device 500 or a component of the electronic device 500, the presence or absence of user contact with the electronic device 500, the orientation or acceleration / deceleration of the electronic device 500, and the temperature change of the electronic device 500. The sensor assembly 514 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 514 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 514 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0136] The communication component 516 is configured to facilitate wired or wireless communication between the electronic device 500 and other devices. The electronic device 500 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, 4G LTE, 5G NR (NewRadio), or a combination thereof. In an exemplary embodiment, the communication component 516 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 516 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0137] In an exemplary embodiment, the electronic device 500 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0138] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 504 including instructions, and the above instructions can be executed by the processor 520 of the electronic device 500 to complete the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0139] The embodiments of the present disclosure further provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the method described in the above embodiments of the present disclosure.

[0140] The embodiments of the present disclosure further provide a computer program product, including a computer program, which executes the method described in the above embodiments of the present disclosure when a processor is used.

[0141] Figure 6 FIG. 6 is a schematic diagram showing a structure of a chip 600 for implementing the above method according to an exemplary embodiment. Figure 6 The chip 600 includes a communication interface 601 and at least one processor 602. The communication interface 601 is used to receive signals input to the chip 600 or signals output from the above chip 600. The processor 602 communicates with the communication interface 601 and implements the method described in the above embodiment of the present disclosure through logic circuits or executing code instructions.

[0142] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0143] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any at least one embodiment or example in a suitable manner.

[0144] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0145] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processing module, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection having at least one wiring (control method), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or otherwise processing in a suitable manner if necessary, and then stored in a computer memory.

[0146] It should be understood that the various parts of the embodiments of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0147] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0148] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. The above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0149] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for identifying temperature anomalies, characterized in that: The method comprises: Determine a first temperature and a second temperature, wherein the first temperature is a predicted temperature of a first point of a first module at a first time point, and the second temperature is an actual temperature of the first point of the first module at the first time point; Determining a state identifier of the first module at the first time point according to the first temperature and the second temperature; When the state of the first module at the first time point is identified as abnormal, it is determined whether the temperature of the first module is abnormal according to the state identification of the first module at at least one second time point.

2. The method according to claim 1, characterized in that Determining the first temperature and the second temperature includes: Acquire message data of the first point position of the first module at the first time point; Performing feature processing on the message data to obtain data features of the first point of the first module at the first time point; Inputting the data features into a target temperature prediction model to obtain the first temperature; The second temperature is determined according to message data of the first point of the first module at the first time point.

3. The method according to claim 2, characterized in that The method further comprises: Collecting message data of at least one second module at at least one historical time point; Cleaning the message data of the at least one second module at the at least one historical time point to obtain target message data; Performing feature processing on the target message data to obtain a training data set and a test data set; The polynomial regression model is trained using the training data set, and tested using the test data set to obtain the target temperature prediction model.

4. The method according to claim 3, characterized in that The performing data cleaning on the message data of the at least one second module at the at least one historical time point to obtain the target message data comprises: collecting maintenance data of the at least one second module; Eliminate the message data of the second module whose maintenance data meets the first preset condition from the message data of the at least one second module at the at least one historical time point, to obtain intermediate message data; Determining charging duration data of the at least one second module according to the intermediate message data; The message data of the second module whose charging duration data is less than the preset duration is eliminated from the intermediate message data to obtain the target message data.

5. The method according to claim 3, characterized in that: The polynomial regression model is trained using the training data set, and the target temperature prediction model is obtained using the test data set to perform testing, including: Using the training data set to perform fitting training on the polynomial regression model to obtain a trained temperature prediction model; Using the test data set to test the trained temperature prediction model, and determining an error value of the trained temperature prediction model; When the error value satisfies a second preset condition, the trained temperature prediction model is determined to be the target temperature prediction model.

6. The method according to claim 2, characterized in that The determining, according to the first temperature and the second temperature, a state identifier of the first module at the first time point includes: determining a difference between the first temperature and the second temperature; When the difference satisfies a third preset condition, determining that the state of the first module at the first time point is identified as abnormal; When the difference does not satisfy the third preset condition, it is determined that the state of the first module at the first time point is identified as normal.

7. The method according to claim 1, characterized in that In the case where the state identifier of the first module at the first time point is abnormal, determining whether the temperature of the first module is abnormal according to the state identifier of the first module at at least one second time point includes: Determine the number of second time points at which the state of the first module is marked as abnormal; When the number meets a fourth preset condition, it is determined that the temperature of the first module is abnormal.

8. A temperature anomaly identification device, comprising: A first processing unit, configured to determine a first temperature and a second temperature, wherein the first temperature is a predicted temperature of a first point of a first module at a first time point, and the second temperature is an actual temperature of the first point of the first module at the first time point; a second processing unit, configured to determine a state identifier of the first module at the first time point according to the first temperature and the second temperature; The third processing unit is configured to determine whether the temperature of the first module is abnormal according to the state identifier of the first module at at least one second time point when the state identifier of the first module at the first time point is abnormal.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-7.

11. A chip, characterized in that: It includes at least one processor and a communication interface; the communication interface is used to receive a signal input to the chip or a signal output from the chip, and the processor communicates with the communication interface and implements the method as described in any one of claims 1 to 7 through a logic circuit or executing code instructions.

12. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images