Battery ntc abnormality detection method and device, vehicle, electronic device and storage medium

Abstract

The present disclosure discloses a battery NTC abnormality detection method and device, a vehicle, an electronic device and a storage medium, NTC temperature data of a power battery pack is obtained, the NTC temperature data includes a temperature sequence of each NTC in a target sampling period; a temperature change rate set of each NTC in the target sampling period is calculated by using the NTC temperature data; uncertainty statistics is carried out based on each temperature change rate set, and statistical data corresponding to the temperature change rate set is obtained; if there is target statistical data greater than an abnormal threshold value in a plurality of statistical data, the NTC corresponding to the target statistical data is determined as an abnormal NTC. After calculating the temperature change rate set of a single NTC according to the NTC temperature data, the statistical data of the uncertainty statistics corresponding to the temperature change rate set is calculated, without grouping processing of the NTC temperature value, the abnormal identification result of the statistical data of the uncertainty statistics of the NTC is used to represent the detection result of the NTC abnormality, and the accuracy of the battery NTC abnormality detection is improved.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle technology, and in particular to a method and apparatus for detecting battery NTC anomalies, a vehicle, electronic equipment, and a storage medium. Background Technology

[0002] In vehicle batteries, negative temperature coefficient (NTC) thermistors are a type of sensor resistor whose resistance decreases as temperature increases. They are typically placed inside the battery to monitor its operating status. Because the resistance of an NTC is negatively correlated with temperature, when an NTC in the battery pack has a loose connection, it will exhibit increased internal resistance and decreased temperature. Conversely, when an NTC has an abnormal resistance value, it will exhibit an abnormally high temperature compared to other normal NTCs in the battery pack. An abnormal temperature in any NTC within the battery pack can cause an abnormal overall battery pack temperature, leading to reduced battery pack performance and potentially even safety hazards.

[0003] To address the aforementioned issue, the NTC anomaly detection method employed is as follows: The temperature values ​​of all NTCs in the battery pack are reported in real-time. Based on the temperature variations of each NTC under different operating conditions, all NTCs are divided into several groups. The temperature differences between different groups are relatively large, while the temperature differences between the highest and lowest temperatures within the same group are relatively small. Anomalies are detected by comparing the highest and lowest temperatures within each group with the temperatures of other NTCs within that group. While this method can detect anomalies to some extent, it relies heavily on accurate NTC grouping, leading to a high rate of missed or false alarms and consequently, low accuracy in NTC anomaly detection. Summary of the Invention

[0004] This disclosure provides a battery NTC anomaly detection method and apparatus, vehicle, electronic device, and storage medium. Its main objective is to address the problem that existing NTC anomaly detection methods rely on accurate NTC grouping, resulting in numerous false negatives or missed positives and consequently low accuracy in NTC anomaly detection.

[0005] According to a first aspect of this disclosure, a battery NTC anomaly detection method is provided, comprising:

[0006] Acquire NTC temperature data of the power battery pack, wherein the NTC temperature data includes the temperature sequence of each NTC within the target sampling period;

[0007] The set of temperature change rates for each NTC during the target sampling period is calculated using the NTC temperature data;

[0008] Uncertainty statistics are performed on each set of temperature change rates to obtain statistical data corresponding to the set of temperature change rates.

[0009] If there is a target statistical data point among the multiple statistical data points that is greater than the abnormal threshold, then the NTC corresponding to the target statistical data point is determined as an abnormal NTC.

[0010] In some embodiments, the step of performing uncertainty statistics based on each set of temperature change rates to obtain statistical data corresponding to the set of temperature change rates includes:

[0011] Calculate the temperature information entropy corresponding to each set of temperature change rates;

[0012] The abnormal NTC is a dummy NTC.

[0013] In some embodiments, the step of performing uncertainty statistics based on each set of temperature change rates to obtain statistical data corresponding to the set of temperature change rates includes:

[0014] For each set of temperature change rates, determine the frequency of the target temperature change rate in the set; the target temperature change rate is the temperature change rate with the same value in the set of temperature change rates.

[0015] For each target temperature change rate, the information content of the frequency of the target temperature change rate is calculated to obtain the target information content corresponding to the target temperature change rate;

[0016] The target information quantities corresponding to each set of temperature change rates are accumulated and calculated to obtain the sub-temperature information entropy corresponding to each set of temperature change rates.

[0017] The temperature information entropy is obtained by combining the sub-temperature information entropy corresponding to all sets of temperature change rates.

[0018] In some embodiments, the step of calculating the information content of the frequency of the target temperature change rate to obtain the target information content corresponding to the target temperature change rate includes:

[0019] The logarithm of the frequency of the target temperature change rate is calculated to obtain the logarithm of the frequency of the target temperature change rate.

[0020] The target information quantity corresponding to the target temperature change rate is obtained by multiplying the negative number of the frequency of the target temperature change rate with the logarithmic value.

[0021] In some embodiments, calculating the set of temperature change rates for each NTC within the target sampling period using the NTC temperature data includes:

[0022] Calculate the first temperature difference and time difference between any two adjacent temperatures in the temperature sequence;

[0023] Calculate the ratio of the first temperature difference to the time difference for each pair of adjacent temperatures in each group to obtain the set of temperature change rates for each NTC within the target sampling period.

[0024] In some embodiments, the step of determining the NTC corresponding to the target statistical data as an abnormal NTC if there is a target statistical data value greater than an abnormal threshold among the plurality of statistical data includes:

[0025] If an outlier statistical data point exists among the multiple statistical data points, and the target statistical data point exists among the outlier statistical data points, then the NTC corresponding to the target statistical data point is determined to be an abnormal NTC.

[0026] In some embodiments, after performing uncertainty statistics based on each set of temperature change rates to obtain statistical data corresponding to the set of temperature change rates, the method further includes:

[0027] The anomaly threshold is determined based on the box plots corresponding to the various statistical data, and the anomaly entropy threshold is related to the upper quartile and lower quartile of the box plot;

[0028] Analysis is performed based on the box plots corresponding to each statistical data point to determine whether any outlier statistical data exists among the multiple statistical data points.

[0029] According to a second aspect of this disclosure, an apparatus for detecting battery NTC anomalies is provided, comprising:

[0030] The acquisition unit is used to acquire NTC temperature data of the power battery pack, wherein the NTC temperature data includes the temperature sequence of each NTC within the target sampling period;

[0031] The first calculation unit is used to calculate the set of temperature change rates of each NTC within the target sampling period using the NTC temperature data;

[0032] The second calculation unit is used to perform uncertainty statistics based on each set of temperature change rates to obtain statistical data corresponding to the set of temperature change rates.

[0033] The first determining unit is configured to determine the NTC corresponding to the target statistical data as an abnormal NTC if there is a target statistical data that is greater than an abnormal threshold among the multiple statistical data.

[0034] In some embodiments, the second calculation unit is further configured to calculate the temperature information entropy corresponding to each set of temperature change rates;

[0035] The abnormal NTC is a dummy NTC.

[0036] In some embodiments, the second computing unit includes:

[0037] The determining module is used to determine the frequency of a target temperature change rate in each set of temperature change rates; the target temperature change rate is the temperature change rate with the same value in the set of temperature change rates.

[0038] The first calculation module is used to calculate the information content of the frequency of the target temperature change rate for each target temperature change rate, and obtain the target information content corresponding to the target temperature change rate.

[0039] The second calculation module is used to accumulate and calculate all target information quantities corresponding to each set of temperature change rates to obtain the sub-temperature information entropy corresponding to each set of temperature change rates.

[0040] The combination module is used to combine the sub-temperature information entropy corresponding to all temperature change rate sets to obtain the temperature information entropy.

[0041] In some embodiments, the first computing module is further configured to:

[0042] The logarithm of the frequency of the target temperature change rate is calculated to obtain the logarithm of the frequency of the target temperature change rate.

[0043] The target information quantity corresponding to the target temperature change rate is obtained by multiplying the negative number of the frequency of the target temperature change rate with the logarithmic value.

[0044] In some embodiments, the first computing unit includes:

[0045] The first calculation module is used to calculate the first temperature difference and time difference between any two adjacent temperatures in the temperature sequence;

[0046] The second calculation module is used to calculate the ratio of the first temperature difference to the time difference corresponding to each pair of adjacent temperatures in each group, so as to obtain the set of temperature change rates of each NTC in the target sampling period.

[0047] In some embodiments, the first determining unit is further configured to, if the target statistical data exists among the outlier statistical data, determine the NTC corresponding to the target statistical data as an anomalous NTC when outlier statistical data exists among the multiple statistical data.

[0048] In some embodiments, the apparatus further includes:

[0049] The second determining unit is used to determine the anomaly threshold based on the box plot corresponding to each set of temperature change rates after the second calculation unit performs uncertainty statistics based on each set of temperature change rates to obtain statistical data. The anomaly entropy threshold is related to the upper quartile and lower quartile of the box plot.

[0050] The analysis unit is used to perform analysis based on the box plots corresponding to each statistical data point to determine whether the outlier statistical data exists among the multiple statistical data points.

[0051] According to a third aspect of this disclosure, a vehicle is provided, the vehicle comprising:

[0052] At least one battery pack, wherein at least two thermistors are configured in the battery pack;

[0053] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the battery NTC anomaly detection method described in any one aspect.

[0054] According to a fourth aspect of this disclosure, an electronic device is provided, comprising:

[0055] At least one processor; and

[0056] A memory communicatively connected to the at least one processor; wherein,

[0057] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0058] According to a fifth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect above.

[0059] According to a sixth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0060] This disclosure provides a battery NTC anomaly detection method, apparatus, vehicle, electronic device, and storage medium. It acquires NTC temperature data of a power battery pack, including temperature sequences of each NTC within a target sampling period. The method calculates a set of temperature change rates for each NTC within the target sampling period using the NTC temperature data. Uncertainty statistics are performed on each set of temperature change rates to obtain statistical data corresponding to the set of temperature change rates. If a target statistical data point exceeding an anomaly threshold exists among the multiple statistical data points, the NTC corresponding to the target statistical data point is identified as an anomalous NTC. This NTC anomaly detection method calculates the temperature change rate set of a single NTC based on the NTC temperature data and then calculates the statistical data of the uncertainty statistics corresponding to the set of temperature change rates. This eliminates the need for grouping NTC temperature values ​​and uses the anomaly identification results of the uncertainty statistics to characterize the NTC anomaly detection results, thus improving the accuracy of battery NTC anomaly detection.

[0061] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0062] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0063] Figure 1 This is a schematic flowchart of a battery NTC anomaly detection method provided in an embodiment of this disclosure;

[0064] Figure 2 A line graph of the temperature information entropy of an abnormal NTC provided in this embodiment of the disclosure;

[0065] Figure 3 This is a flowchart illustrating another battery NTC anomaly detection method provided in an embodiment of this disclosure;

[0066] Figure 4 This is a flowchart illustrating another battery NTC anomaly detection method provided in an embodiment of this disclosure;

[0067] Figure 5 This is a flowchart illustrating another battery NTC anomaly detection method provided in an embodiment of this disclosure;

[0068] Figure 6 A line graph illustrating the temperature distribution of an abnormal NTC as provided in an embodiment of this disclosure;

[0069] Figure 7 A schematic diagram of a housing provided for an embodiment of this disclosure;

[0070] Figure 8 This is a schematic diagram of the structure of a battery NTC anomaly detection device provided in an embodiment of this disclosure;

[0071] Figure 9 A schematic diagram of another battery NTC anomaly detection device provided in this embodiment of the present disclosure;

[0072] Figure 10 A schematic block diagram of an example electronic device 600 provided for embodiments of this disclosure. Detailed Implementation

[0073] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0074] The following description, with reference to the accompanying drawings, outlines a battery NTC anomaly detection method, apparatus, electronic device, and storage medium according to embodiments of the present disclosure.

[0075] Figure 1 This is a flowchart illustrating a battery NTC anomaly detection method provided in an embodiment of this disclosure. The method is applied in a vehicle, and the control method can be executed by an information-prompting control device or equipment. This device or equipment can be configured in a server, processor, or main control chip; for example, it can be deployed on the vehicle's infotainment system side, the power battery controller side, etc. The method includes the following steps:

[0076] Step 101: Obtain NTC temperature data of the power battery pack, wherein the NTC temperature data includes the temperature sequence of each NTC within the target sampling period.

[0077] In some embodiments provided in this disclosure, the power battery pack includes multiple battery cells or battery modules, each battery cell or battery module carrying one or more NTCs; therefore, the power battery pack includes multiple NTCs.

[0078] In one embodiment provided in this disclosure, the target sampling period is an empirical value that can be flexibly adjusted according to the actual situation. For example, in order to facilitate subsequent calculations, the target sampling period can be set to 1 second, or in order to reduce the occupation of computing resources, the target sampling period can be set to 1 minute or 2 minutes. The specific target sampling period is not limited in this embodiment of the disclosure.

[0079] In practical applications, the temperature of the NTCs in the power battery pack is measured at all operating times, including but not limited to power-on, charging, and driving. The temperature of all NTCs in the power battery pack changes continuously with the operating time. To calculate the temperature change rate of the NTCs, it is necessary to record the temperature changes of the NTCs within the target sampling period to obtain the temperature sequence. The target sampling period described in this application embodiment can be the sampling period under any scenario of power-on, charging, and driving; this application embodiment is not limited to this.

[0080] For example, assuming the target sampling period is 1 minute, the temperature sequence can be 25℃, 27℃, 28℃, 30℃, 31℃, and 33℃, with each temperature spaced 10 seconds apart.

[0081] Step 102: Calculate the set of temperature change rates of each NTC within the target sampling period using the NTC temperature data.

[0082] The rate of change of each NTC is recorded based on NTC temperature data, removing trend changes in NTC caused by the operating environment of the thermistor or battery thermal management strategies. In one embodiment provided in this disclosure, the set of temperature change rates is a collection of temperature changes for each NTC within each sampling period.

[0083] The temperature change rate can be the trend-like change in temperature within each NTC temperature data point caused by the operating environment of the corresponding thermistor or the battery thermal management strategy. This temperature change rate can be removed by statistically processing the NTC temperature data. Since the operating temperature of each thermistor at different times within a given period can vary by approximately the same amount due to the influence of the operating environment or battery thermal management strategy, the identical change in temperature between the two thermistor's NTC temperature data points can be removed. It is understood that the closer the two times of the difference are to the removed temperature change rate, the more accurate the result. Based on this, the removal of the temperature change rate can be achieved, including but not limited to, by determining the growth rate of the operating temperature data or by determining the difference between the operating temperature data and the median or average value.

[0084] In this embodiment of the invention, for the NTC temperature data of each thermistor, the NTC temperature data can be processed to remove the rate of temperature change, so as to eliminate the rate of temperature change in the NTC temperature data caused by the operating environment or battery thermal management strategy. This processing can be achieved by determining the rate of change of the NTC temperature data or by determining the difference between each temperature data in the NTC temperature data and the median value of the NTC temperature data. It is understood that the above-mentioned method of removing the rate of temperature change is only an example and is not limited. For example, the NTC temperature data can also be processed to remove the rate of temperature change by a pre-trained neural network model.

[0085] For example, after the power battery is powered on, NTC temperature data is collected. Assuming the power-on time for a certain NTC is 10 minutes and the target sampling period is set to 1 minute, then this NTC can be divided into 10 target sampling periods. If one temperature change rate is calculated for each target sampling period, then the set of temperature change rates for this NTC contains a total of 10 temperature change rates. It should be noted that the power-on time and target sampling period mentioned above are merely illustrative examples and not specific limitations on these parameters.

[0086] Step 103: Perform uncertainty statistics on each set of temperature change rates to obtain statistical data corresponding to the set of temperature change rates.

[0087] In some embodiments provided in this disclosure, the information entropy is an indicator used to measure uncertainty, that is, the probability of discrete random events occurring. Simply put, "the more chaotic the situation, the greater the information entropy, and vice versa." In embodiments of this disclosure, the statistical data corresponding to the set of temperature change rates in the uncertainty statistics are used to determine whether there are any anomalies in the set of temperature change rates, so as to determine whether the NTC is abnormal.

[0088] Uncertainty statistics can be used to statistically process the uncertainty within a set of temperature change rates. Uncertainty statistics can generate uncertainty values ​​for the set of temperature change rates, which indicate the degree of uncertainty. A higher degree of uncertainty in the set of temperature change rates indicates a higher probability of anomalies. Uncertainty statistics can be achieved through methods such as standard deviation probability statistics, upper quartile probability statistics, and information entropy statistics. Statistical data can be uncertainty values ​​generated from the set of temperature change rates through uncertainty statistics. This statistical data can be generated based on uncertainty statistics of the set of temperature change rates and can include, but is not limited to, standard deviation, upper quartile probability values, and information entropy.

[0089] In this embodiment of the invention, uncertainty statistics can be performed on each set of temperature change rates. Probability distribution statistics or information entropy calculation can be performed on the data values ​​of the temperature change rate sets. The statistical results or information entropy results can be used as statistical data generated by uncertainty statistics to determine the conformity of each operating temperature data with the specified probability distribution or the value of the information entropy of the calculated temperature data. It is understood that uncertainty statistics can be performed on each set of temperature change rates by performing one or more statistical methods such as standard deviation probability statistics, upper quartile probability statistics, and information entropy statistics on each set of temperature change rates. For example, statistical results can be determined for each moving temperature data by comparing it with standard deviation probability statistics, upper quartile probability statistics, and information entropy statistics. The weighted sum of the statistical results can be used as the uncertainty of the moving temperature data.

[0090] Step 104: If there is a target statistical data point among the multiple statistical data points that is greater than the abnormal threshold, then the NTC corresponding to the target statistical data point is determined as an abnormal NTC.

[0091] In one embodiment provided in this disclosure, the abnormal threshold is the abnormal range or abnormal value of the statistical data. For example, if the normal range of the statistical data is 0 to 0.10, then the abnormal threshold is exceeding 0.10. For instance, if the value of a certain NTC statistical data is 0.72, then the NTC corresponding to the statistical data can be determined to be an NTC abnormal. Conversely, if the value of the NTC statistical data is 0.06, then the NTC is normal.

[0092] In the embodiments disclosed herein, the NTC anomaly mentioned in this application includes, but is not limited to, a loose NTC connection and an abnormal resistance value. A loose NTC connection refers to a poor physical connection between the NTC and the corresponding battery cell or battery module. An abnormal resistance value corresponds to a temperature that is continuously higher than a preset abnormal duration and the continuous temperature exceeds a preset abnormal temperature threshold.

[0093] Due to the differences in NTC connection issues and abnormal resistance values, the methods for setting abnormal thresholds also differ when determining whether an abnormality exists. It should be noted that the above-mentioned normal range of 0 to 0.10 is merely an illustrative example. This explanation is not intended to limit the normal range to only 0 to 0.10; it could also be 0 to 0.15, 0 to 0.09, etc., and can be adjusted according to the application scenario. Furthermore, there are no limitations on the preset temperature abnormality threshold or the preset abnormality duration.

[0094] As another implementation of this application, the abnormal entropy threshold is related to the standard deviation of the temperature information entropy. After calculating the temperature information entropy corresponding to each temperature change rate set, the standard deviation σ of all temperature information entropies is calculated. When setting the abnormal entropy threshold, the abnormal entropy threshold can be set to 3σ, etc. Specifically, this application does not limit the specific value of the abnormal entropy threshold.

[0095] To better understand the abnormal NTC in the above embodiments, this disclosure provides a line graph of the temperature information entropy of abnormal NTC, such as... Figure 2 As shown in the figure, the horizontal axis of the line graph represents the NTC number, and the vertical axis represents the entropy value of the NTC's temperature information entropy. In this figure, the normal entropy threshold is 0.1. The entropy value of NTC number 10 significantly exceeds the normal entropy threshold and meets the abnormal entropy threshold. Therefore, NTC number 10 can be identified as an abnormal NTC.

[0096] The battery NTC anomaly detection method disclosed herein acquires NTC temperature data of a power battery pack, wherein the NTC temperature data includes the temperature sequence of each NTC within a target sampling period; calculates a set of temperature change rates for each NTC within the target sampling period using the NTC temperature data; performs uncertainty statistics on each set of temperature change rates to obtain statistical data corresponding to the set of temperature change rates; if a target statistical data exceeding an anomaly threshold exists among multiple statistical data, the NTC corresponding to the target statistical data is identified as an abnormal NTC. This NTC anomaly detection method, after calculating the set of temperature change rates for a single NTC based on the NTC temperature data, calculates the statistical data of the uncertainty statistics corresponding to the set of temperature change rates, eliminating the need for grouping NTC temperature values. The anomaly identification result of the statistical data of the uncertainty statistics characterizes the NTC anomaly detection result, thus improving the accuracy of battery NTC anomaly detection.

[0097] The above embodiments illustrate that abnormal NTCs include loosely connected NTCs. Since loose connections exhibit disordered behavior, they are detected using uncertainty statistics. Therefore, when performing uncertainty statistics based on each set of temperature change rates to obtain the statistical data corresponding to that set, the following methods can be used, but are not limited to: calculating the temperature information entropy corresponding to each set of temperature change rates; and identifying the abnormal NTC as a loosely connected NTC. Accurately identifying loosely connected NTCs through temperature information entropy allows for accurate monitoring of the NTC status, early identification of anomalies, and prevention of potential safety hazards.

[0098] To better understand the calculation of the temperature information entropy corresponding to each set of temperature change rates described above, please refer to... Figure 3 , Figure 3This is a schematic diagram of another battery NTC anomaly detection process provided in an embodiment of this disclosure, as shown below. Figure 3 As shown, the method includes the following steps:

[0099] Step 201: For each set of temperature change rates, determine the frequency of the target temperature change rate in the set of temperature change rates; the target temperature change rate is the temperature change rate with the same value in the set of temperature change rates.

[0100] In some embodiments provided in this disclosure, the same temperature change rate may exist in each NTC's temperature change rate set. For example, the temperature change rate set of a certain NTC is {0.5, 0.3, 0.5, 0.4, 0.3, 0.2, 0.5, 0.6, 0.4, 0.2}, where 0.5 appears 3 times, so the frequency of 0.5 is 0.3; 0.3 appears 2 times, so the frequency is 0.2; 0.4 appears 2 times, so the frequency is 0.2; 0.6 appears 1 time, so the frequency is 0.1; and 0.2 appears 2 times, so the frequency is 0.2. The examples within the above temperature change rate sets are only for ease of understanding and are not intended to limit specific values. The embodiments of this application do not limit the values ​​of the temperature change rate set or the frequency of each value.

[0101] Step 202: For each target temperature change rate, calculate the information content of the frequency of the target temperature change rate to obtain the target information content corresponding to the target temperature change rate.

[0102] In one embodiment provided in this disclosure, when performing information content calculation, the frequency of the target temperature change rate can be calculated by, but is not limited to, calling an information content calculation algorithm. The information content calculation algorithm includes: first, taking the logarithm of the frequency of the target temperature change rate to obtain the logarithmic value of the frequency of the target temperature change rate; then, multiplying the negative of the frequency of the target temperature change rate by the logarithmic value to obtain the information content corresponding to the target temperature change rate. For a better understanding of the information content calculation algorithm, please refer to formula (1).

[0103] Information content = -plog2p formula (1)

[0104] Where p is the frequency of the target temperature change rate.

[0105] Step 203: Accumulate and calculate all target information quantities corresponding to each set of temperature change rates to obtain the sub-temperature information entropy corresponding to each set of temperature change rates.

[0106] Using the calculation method described in step 202, at least one target information quantity is calculated sequentially for each temperature change rate set. In this step, at least one target information quantity corresponding to each temperature change rate set needs to be summed to obtain the sub-temperature information entropy corresponding to each temperature change rate set.

[0107] Step 204: Combine the sub-temperature information entropies corresponding to all temperature change rate sets to obtain the temperature information entropy.

[0108] By calculating the temperature entropy of each NTC, abnormal NTCs can be identified, and the state of NTCs in the power battery pack can be accurately monitored, thus improving the accuracy of battery NTC anomaly detection.

[0109] To better understand step 102 above, which involves calculating the set of temperature change rates for each NTC within the target sampling period using the NTC temperature data, please refer to... Figure 4 , Figure 4 This is a schematic diagram of another battery NTC anomaly detection process provided in an embodiment of this disclosure, as shown below. Figure 4 As shown, the method includes the following steps:

[0110] Step 301: Calculate the first temperature difference and time difference between any two adjacent temperatures in the temperature sequence.

[0111] To better understand the calculation process of the first temperature difference, taking the temperature sequence {25℃, 27℃, 28℃, 30℃, 31℃, 33℃, 35℃} as an example, the first temperature difference between any two adjacent temperatures in this sequence is {2℃, 1℃, 2℃, 1℃, 3℃, 2℃}. This method is not intended to limit the specific values ​​of the temperature sequence.

[0112] To better understand the sequential determination of the time corresponding to each temperature in the temperature sequence, please continue to refer to the temperature sequence {25℃, 27℃, 28℃, 30℃, 31℃, 33℃, 35℃} provided in the above embodiment. The sampling period corresponding to this temperature sequence has a period length of 1 minute, and the temperature is recorded once every 10 seconds. That is, the temperature at second 0 is 25℃, the temperature at second 10 is 27℃, the temperature at second 20 is 28℃, the temperature at second 30 is 30℃, the temperature at second 40 is 31℃, the temperature at second 50 is 33℃, and the temperature at second 60 is 35℃.

[0113] To better understand the time difference, please continue to refer to the above embodiments. The time difference between any two adjacent times is 10 seconds. The above description of the first temperature difference and time difference between any two adjacent temperatures is only an illustrative example, and the specific values ​​are not limited in this application embodiment.

[0114] Step 302: Calculate the ratio of the first temperature difference to the time difference corresponding to each pair of adjacent temperatures in each group, and obtain the set of temperature change rates of each NTC in the target sampling period.

[0115] To better understand the calculation process of the temperature change rate, please continue to refer to the embodiment of step 301 above. In this temperature sequence, the first temperature difference from second 0 to second 10 is 2℃, and the time difference is 10 seconds. Therefore, the corresponding temperature change rate is 0.2℃ / second. Combining all temperature change rates in chronological order yields the set of temperature change rates.

[0116] By calculating the temperature change rate set of each NTC using temperature data from all NTCs in the power battery pack, the impact of vehicle thermal management strategies on NTC temperature changes is significantly reduced, thereby improving the accuracy of NTC anomaly detection.

[0117] To better understand the battery NTC anomaly detection method provided in this disclosure, please refer to... Figure 5 , Figure 5 This is a flowchart illustrating another battery NTC anomaly detection method provided in this disclosure embodiment, as shown below. Figure 5 As shown, the method includes the following steps:

[0118] Step 401: Determine whether the static time of the power battery pack is greater than the preset static time.

[0119] In one embodiment provided in this disclosure, the settling time is an empirical value that can be flexibly adjusted according to the vehicle's operating conditions or ambient temperature. For example, in winter, due to the low ambient temperature, the battery pack temperature drops quickly after the vehicle is powered off. In this case, the settling time can be set to a shorter duration, such as 5 minutes or 10 minutes. Alternatively, when the vehicle is in heating mode, the NTC temperature is high when the vehicle is powered off and cannot recover to the ambient temperature in a short time. In this case, the settling time can be set to a longer duration, such as 30 minutes or 40 minutes. Specifically, this application does not limit the preset settling time in the embodiments.

[0120] The purpose of determining whether the static time of the power battery pack is greater than the preset static time is to allow the NTC temperature to return to the ambient temperature and reduce the impact of the residual heat of the NTC on the detection of battery NTC abnormalities.

[0121] If the settling time is less than or equal to the preset settling time, then step 405 is executed; if the settling time is greater than the preset settling time, then step 402 is executed.

[0122] Step 402: Obtain the initial temperature set corresponding to all NTCs in the power battery pack at the power-on time. The initial temperature set contains an initial temperature corresponding to each NTC.

[0123] Step 403: Calculate the average temperature of the initial temperature set and the second temperature difference between each initial temperature in the initial temperature set to obtain a temperature difference set.

[0124] Step 404: If there is a target temperature difference that meets the abnormal temperature difference threshold in the set of temperature difference values, then the NTC corresponding to the target temperature difference value is determined as an NTC with abnormal resistance.

[0125] In one embodiment provided in this disclosure, the abnormal temperature difference threshold is the abnormal temperature difference range of the difference. For example, if the normal NTC temperature difference range is 2°C to 5°C, then the temperature range exceeding this temperature range (2°C, 5°C) is the abnormal temperature difference threshold.

[0126] To better understand the abnormal NTC resistance in the above embodiments, this disclosure provides a line graph of the temperature distribution of the abnormal NTC resistance, as shown below. Figure 6 As shown in the graph, the horizontal axis represents the NTC number, and the vertical axis represents the NTC temperature. In this graph, the average temperature is 25°C, and the normal temperature range is 2 to 5°C. The NTC with NTC number 9 has a temperature of 35°C, which is 10°C different from the average temperature. This significantly exceeds the normal temperature range and meets the abnormal temperature difference threshold. Therefore, the NTC with NTC number 9 can be identified as an NTC with abnormal resistance.

[0127] Step 405: Obtain the first temperature data of all NTCs in the power battery pack.

[0128] If the settling time is less than or equal to the preset settling time, the influence of residual heat on NTC abnormality detection cannot be eliminated. In this case, there may be errors in detecting the resistance abnormality of the NTC. Therefore, the first temperature data of all NTCs in the power battery pack is directly obtained in order to detect the NTC loose connection abnormality. The detection of loose connection abnormality is not affected by residual heat.

[0129] In some embodiments, this application also provides another implementation method for determining abnormal NTC, including: after performing uncertainty statistics based on each set of temperature change rates to obtain statistical data corresponding to the set of temperature change rates, determining the abnormal threshold based on the box plot corresponding to each statistical data, wherein the abnormal entropy threshold is related to the upper quartile and lower quartile of the box plot, and analyzing based on the box plot corresponding to each statistical data to determine whether the outlier statistical data exists among the multiple statistical data.

[0130] If an outlier statistical data point exists among the multiple statistical data points, and the target statistical data point exists among the outlier statistical data points, then the NTC corresponding to the target statistical data point is determined to be an abnormal NTC.

[0131] For a better understanding of outlier entropy, please refer to [link / reference]. Figure 7 This method uses the interquartile range (IQR) of box plots to detect abnormal NTCs, based on Figure 7 The upper and lower bounds in the data can be used to identify outlier information entropy.

[0132] The interquartile range (IQR) is the difference between the upper quartile and the lower quartile. Using 1.5 times the IQR as a standard, the threshold for abnormal entropy value is defined: points that exceed the distance of the upper quartile + 1.5 times the IQR or the distance of the lower quartile - 1.5 times the IQR are considered abnormal NTCs.

[0133] Compared to the 3σ principle, box plots, based on actual data, realistically and intuitively represent the true distribution of temperature entropy, without imposing any restrictive requirements on temperature entropy (the 3σ principle requires data to follow a normal or approximately normal distribution). The criteria for determining constant values ​​are based on quartiles and interquartile ranges. Quartiles provide some indication of the center, dispersion, and shape of the temperature entropy distribution, exhibiting a certain robustness; that is, 25% of the temperature entropy can become arbitrarily far without significantly perturbing the quartiles. Therefore, anomalous NTCs generally do not affect this criterion. Given this, box plots provide a more objective result in identifying anomalous NTCs, thus possessing certain advantages in this area.

[0134] Box plots provide a standard for identifying anomalous NTCs, which are typically defined as values ​​less than QL - 1.5IQR or greater than QU + 1.5IQR. Here, QL is called the lower quartile, representing one-quarter of all temperature entropy values ​​smaller than it; QU is called the upper quartile, representing one-quarter of all temperature entropy values ​​larger than it; and IQR is the interquartile range, the difference between the upper quartile QU and the lower quartile QL, encompassing half of the total temperature entropy.

[0135] In addition to identifying outlier statistical data through box plots as described in the above embodiments, this can also be achieved in the following ways: Clustering can be performed on the statistical data, where the distance of each statistical data point from the cluster center is used as the clustering result. Statistical data points with a distance greater than the average distance or a threshold can be considered outlier statistical data. Clustering methods for statistical data can include, but are not limited to, k-means clustering, Gaussian mixture model clustering, etc. Alternatively, classification can be performed on the statistical data, where the classification results are compared, and statistical data points with different classification results are considered outlier statistical data. It is understood that this classification process can be implemented using logistic regression classification algorithms, ridge regression classification algorithms, etc.

[0136] The specific numerical value of the abnormal entropy threshold is not limited in the embodiments of this application.

[0137] In summary, the embodiments disclosed herein achieve the following effects:

[0138] 1. By calculating the temperature entropy of each NTC, the system can identify NTCs with loose connections, accurately monitor the state of NTCs in the power battery pack, and improve the accuracy of NTC anomaly detection.

[0139] 2. By using the temperature data of all NTCs in the power battery pack, the set of temperature change rates for each NTC is calculated, which significantly reduces the impact of vehicle thermal management strategies on NTC temperature changes, thereby improving the accuracy of NTC anomaly detection.

[0140] Corresponding to the aforementioned battery NTC anomaly detection method, this invention also proposes a battery NTC anomaly detection device. Since the device embodiments of this invention correspond to the aforementioned method embodiments, details not disclosed in the device embodiments can be referred to the aforementioned method embodiments, and will not be repeated here.

[0141] Figure 8 This is a schematic diagram of the structure of a battery NTC anomaly detection device provided in an embodiment of this disclosure, as shown below. Figure 8 As shown, it includes:

[0142] The acquisition unit 51 is used to acquire NTC temperature data of the power battery pack, wherein the NTC temperature data includes the temperature sequence of each NTC within the target sampling period;

[0143] The first calculation unit 52 is used to calculate the set of temperature change rates of each NTC within the target sampling period using the NTC temperature data;

[0144] The second calculation unit 53 is used to perform uncertainty statistics based on each set of temperature change rates to obtain statistical data corresponding to the set of temperature change rates.

[0145] The first determining unit 54 is used to determine the NTC corresponding to the target statistical data as an abnormal NTC if there is a target statistical data that is greater than the abnormal threshold among the multiple statistical data.

[0146] Furthermore, in one possible implementation of this embodiment, such as Figure 9 As shown, the second calculation unit 53 is also used to calculate the temperature information entropy corresponding to each set of temperature change rates;

[0147] The abnormal NTC is a dummy NTC.

[0148] Furthermore, in one possible implementation of this embodiment, such as Figure 9 As shown, the second computing unit 53 includes:

[0149] The determining module 531 is used to determine the frequency of a target temperature change rate in each set of temperature change rates; the target temperature change rate is the temperature change rate with the same value in the set of temperature change rates.

[0150] The first calculation module 532 is used to calculate the information content of the frequency of the target temperature change rate for each target temperature change rate, and obtain the target information content corresponding to the target temperature change rate.

[0151] The second calculation module 533 is used to accumulate and calculate all target information quantities corresponding to each set of temperature change rates to obtain the sub-temperature information entropy corresponding to each set of temperature change rates.

[0152] The combination module 534 is used to combine the sub-temperature information entropy corresponding to all temperature change rate sets to obtain the temperature information entropy.

[0153] Furthermore, in one possible implementation of this embodiment, such as Figure 9 As shown, the first calculation module 532 is further configured to:

[0154] The logarithm of the frequency of the target temperature change rate is calculated to obtain the logarithm of the frequency of the target temperature change rate.

[0155] The target information quantity corresponding to the target temperature change rate is obtained by multiplying the negative number of the frequency of the target temperature change rate with the logarithmic value.

[0156] Furthermore, in one possible implementation of this embodiment, such as Figure 9As shown, the first computing unit 52 includes:

[0157] The first calculation module 521 is used to calculate the first temperature difference and time difference between each pair of adjacent temperatures in the temperature sequence;

[0158] The second calculation module 522 is used to calculate the ratio of the first temperature difference to the time difference corresponding to each pair of adjacent temperatures in each group, so as to obtain the set of temperature change rates of each NTC in the target sampling period.

[0159] Furthermore, in one possible implementation of this embodiment, such as Figure 9 As shown, the first determining unit 54 is further configured to, in the case where there are outlier statistical data among the multiple statistical data, if the target statistical data is among the outlier statistical data, determine the NTC corresponding to the target statistical data as an abnormal NTC.

[0160] Furthermore, in one possible implementation of this embodiment, such as Figure 9 As shown, the device further includes:

[0161] The second determining unit 55 is used to determine the anomaly threshold based on the box plot corresponding to each set of temperature change rates after the second calculation unit 53 performs uncertainty statistics based on each set of temperature change rates to obtain statistical data. The anomaly entropy threshold is related to the upper quartile and lower quartile of the box plot.

[0162] Analysis unit 56 is used to perform analysis based on the box plots corresponding to each statistical data to determine whether the outlier statistical data exists among the multiple statistical data.

[0163] The battery NTC anomaly detection device provided in this disclosure acquires NTC temperature data of a power battery pack, the NTC temperature data including the temperature sequence of each NTC within a target sampling period; calculates a set of temperature change rates for each NTC within the target sampling period using the NTC temperature data; performs uncertainty statistics on each set of temperature change rates to obtain statistical data corresponding to the set of temperature change rates; if a target statistical data exceeding an anomaly threshold exists among multiple statistical data, the NTC corresponding to the target statistical data is identified as an abnormal NTC. The NTC anomaly detection method of this disclosure, after calculating the set of temperature change rates for a single NTC based on the NTC temperature data, calculates the statistical data of the uncertainty statistics corresponding to the set of temperature change rates. This eliminates the need for grouping NTC temperature values ​​and uses the anomaly identification results of the uncertainty statistics to characterize the NTC anomaly detection results, thus improving the accuracy of battery NTC anomaly detection.

[0164] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of this embodiment, and the principle is the same, so it is not limited in this embodiment.

[0165] According to embodiments of this disclosure, this disclosure also provides an electronic device, a vehicle, a readable storage medium, and a computer program product.

[0166] This application provides a vehicle, including: at least one battery pack, wherein at least two thermistors are disposed in the battery pack;

[0167] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the battery NTC anomaly detection method described in any of the above embodiments.

[0168] Figure 10 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0169] like Figure 10 As shown, device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 602 or a computer program loaded from storage unit 608 into RAM (Random Access Memory) 603. RAM 603 may also store various programs and data required for the operation of device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. I / O (Input / Output) interface 605 is also connected to bus 604.

[0170] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of monitors, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0171] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as the battery NTC anomaly detection method. For example, in some embodiments, the battery NTC anomaly detection method can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the methods described above can be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the aforementioned battery NTC anomaly detection method by any other suitable means (e.g., by means of firmware).

[0172] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0173] The program code for implementing the methods of this disclosure is implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0174] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0175] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0176] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0177] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0178] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0179] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0180] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for detecting battery NTC anomalies, characterized in that, include: Acquire NTC temperature data of the power battery pack, wherein the NTC temperature data includes the temperature sequence of each NTC within the target sampling period; The set of temperature change rates for each NTC during the target sampling period is calculated using the NTC temperature data; Uncertainty statistics are performed on each set of temperature change rates to obtain statistical data corresponding to the set of temperature change rates. If there is a target statistical data point among the multiple statistical data points that is greater than the abnormal threshold, then the NTC corresponding to the target statistical data point is determined as an abnormal NTC. The step of performing uncertainty statistics on each set of temperature change rates to obtain the statistical data corresponding to the set of temperature change rates includes: Calculate the temperature information entropy corresponding to each set of temperature change rates; The abnormal NTC is a dummy NTC.

2. The method according to claim 1, characterized in that, The uncertainty statistics based on each set of temperature change rates are used to obtain statistical data corresponding to the set of temperature change rates, including: For each set of temperature change rates, determine the frequency of the target temperature change rate in the set; the target temperature change rate is the temperature change rate with the same value in the set of temperature change rates. For each target temperature change rate, the information content of the frequency of the target temperature change rate is calculated to obtain the target information content corresponding to the target temperature change rate; The target information quantities corresponding to each set of temperature change rates are accumulated and calculated to obtain the sub-temperature information entropy corresponding to each set of temperature change rates. The temperature information entropy is obtained by combining the sub-temperature information entropy corresponding to all sets of temperature change rates.

3. The method according to claim 2, characterized in that, The step of calculating the information content of the frequency of the target temperature change rate to obtain the target information content corresponding to the target temperature change rate includes: The logarithm of the frequency of the target temperature change rate is calculated to obtain the logarithm of the frequency of the target temperature change rate. The target information quantity corresponding to the target temperature change rate is obtained by multiplying the negative number of the frequency of the target temperature change rate with the logarithmic value.

4. The method according to claim 1, characterized in that, The calculation of the set of temperature change rates for each NTC within the target sampling period using the NTC temperature data includes: Calculate the first temperature difference and time difference between any two adjacent temperatures in the temperature sequence; Calculate the ratio of the first temperature difference to the time difference for each pair of adjacent temperatures in each group to obtain the set of temperature change rates for each NTC within the target sampling period.

5. The method according to claim 1, characterized in that, If, among the multiple statistical data, there exists a target statistical data point greater than an abnormal threshold, then the NTC corresponding to the target statistical data point is determined as an abnormal NTC, including: If an outlier statistical data point exists among the multiple statistical data points, and the target statistical data point exists among the outlier statistical data points, then the NTC corresponding to the target statistical data point is determined to be an abnormal NTC.

6. The method according to claim 5, characterized in that, After performing uncertainty statistics on each set of temperature change rates to obtain statistical data corresponding to the set of temperature change rates, the method further includes: The anomaly threshold is determined based on the box plots corresponding to each statistical data point, and the anomaly entropy threshold is related to the upper quartile and lower quartile of the box plot. Analysis is performed based on the box plots corresponding to each statistical data point to determine whether any outlier statistical data exists among the multiple statistical data points.

7. A device for detecting battery NTC anomalies, characterized in that, include: The acquisition unit is used to acquire NTC temperature data of the power battery pack, wherein the NTC temperature data includes the temperature sequence of each NTC within the target sampling period; The first calculation unit is used to calculate the set of temperature change rates of each NTC within the target sampling period using the NTC temperature data; The second calculation unit is used to perform uncertainty statistics based on each set of temperature change rates to obtain statistical data corresponding to the set of temperature change rates. The first determining unit is configured to determine the NTC corresponding to the target statistical data as an abnormal NTC if there is a target statistical data that is greater than an abnormal threshold among the multiple statistical data. The step of performing uncertainty statistics on each set of temperature change rates to obtain the statistical data corresponding to the set of temperature change rates includes: Calculate the temperature information entropy corresponding to each set of temperature change rates; The abnormal NTC is a dummy NTC.

8. A vehicle, characterized in that, The vehicles include: At least one battery pack, wherein at least two thermistors are configured in the battery pack; At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the battery NTC anomaly detection method according to any one of claims 1-6.

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 to enable the at least one processor to perform the method of any one of claims 1-6.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

11. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images