Battery pack detection method, device, equipment and medium

Abstract

The embodiment of the invention provides a battery pack detection method, device and equipment and a medium, and the method comprises the steps: obtaining the insulation fault data of a battery pack, carrying out the time series decomposition of the insulation fault data, obtaining the component sequence data, carrying out the insulation fault prediction through employing the component sequence data, and obtaining the insulation fault prediction result. According to the method, the insulation fault prediction value of the insulation fault data is obtained, and the insulation fault prediction result of the battery pack is determined according to the insulation fault prediction value, so that prediction and evaluation of the insulation fault of the battery pack are completed according to the time sequence decomposition result of the insulation fault data. The accuracy and reliability of battery pack insulation fault prediction are improved, so that the insulation fault of the battery pack can be recognized in advance, potential safety hazards such as electric leakage and short circuit are prevented, and the driving safety of the electric vehicle is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric vehicles, and in particular to a method, device, equipment and medium for detecting a battery pack. Background Art

[0002] New energy battery packs play a crucial role in modern electric vehicles, with their safety and reliability directly impacting vehicle performance and passenger safety. Battery pack insulation failure warrants particular attention, as it can pose a serious safety hazard. Since modern battery pack voltages typically range from 400 to 500V, or even as high as 800V, insulation failures can pose a significant risk to the driver and passengers of electric vehicles.

[0003] However, in the prior art, the accuracy of battery pack insulation fault prediction is not high enough, which results in significant limitations in battery pack insulation fault prediction and evaluation. Summary of the Invention

[0004] In view of the above problems, a method, apparatus, device and medium for battery pack detection are proposed to overcome or at least partially solve the above problems, including: A method for detecting a battery pack, the method comprising: Obtain insulation fault data of the battery pack; Performing time series decomposition on the insulation fault data to obtain component series data; Performing insulation fault prediction using the component sequence data to obtain an insulation fault prediction value of the insulation fault data; An insulation fault prediction result of the battery pack is determined according to the insulation fault prediction value.

[0005] Optionally, performing time series decomposition on the insulation fault data to obtain component series data includes: determining a target period of the insulation fault data; Based on the target period, the insulation fault data is decomposed into a time series to obtain component sequence data corresponding to the insulation fault data.

[0006] Optionally, determining a target period of the insulation fault component data includes: Performing frequency domain conversion on the insulation fault data to obtain corresponding frequency domain data; determining a plurality of candidate cycles of the insulation fault data based on the frequency domain data; A target cycle of the insulation fault data is determined from the plurality of candidate cycles.

[0007] Optionally, the component sequence data includes any one or more of the following: Trend series data, periodic series data, residual series data.

[0008] Optionally, the using the component sequence data to perform insulation fault prediction to obtain an insulation fault prediction value of the insulation fault data includes: In a case where the insulation fault data includes insulation fault component data, performing insulation fault prediction using component sequence data corresponding to the insulation fault component data to obtain an insulation fault prediction value corresponding to the insulation fault component data, and determining the insulation fault prediction value corresponding to the insulation fault component data as the insulation fault prediction value of the insulation fault data; In the case where the insulation fault data includes multiple insulation fault component data, insulation fault prediction is performed using component sequence data corresponding to each insulation fault component data to obtain an insulation fault prediction value corresponding to each insulation fault component data, and the insulation fault prediction values ​​corresponding to each insulation fault component data are superimposed according to preset weights to obtain the insulation fault prediction value of the insulation fault data.

[0009] Optionally, determining the insulation fault prediction result of the battery pack according to the insulation fault prediction value includes: Comparing the insulation fault prediction value with a preset fault threshold to obtain a comparison result; An insulation fault prediction result of the battery pack is determined according to the comparison result.

[0010] Optionally, after performing time series decomposition on the insulation fault component data to obtain component series data, the method further includes: The component sequence data are standardized.

[0011] A battery pack detection device, comprising: A data acquisition module is used to obtain insulation fault data of the battery pack; A sequence decomposition module, configured to perform time series decomposition on the insulation fault data to obtain component sequence data; A prediction value acquisition module, configured to use the component sequence data to perform insulation fault prediction and obtain an insulation fault prediction value; A prediction result determination module is used to determine the insulation fault prediction result of the battery pack according to the insulation fault prediction value.

[0012] An electronic device includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the battery pack detection method described above when executed by the processor.

[0013] A readable storage medium stores a computer program, and when the computer program is executed by a processor, the battery pack detection method described above is implemented.

[0014] The embodiments of the present invention have the following advantages: In an embodiment of the present invention, insulation fault data of a battery pack is acquired, time series decomposition of the insulation fault data is performed to obtain component sequence data, and then insulation fault prediction is performed using the component sequence data to obtain an insulation fault prediction value of the insulation fault data. Based on the insulation fault prediction value, an insulation fault prediction result of the battery pack is determined, thereby achieving prediction and evaluation of battery pack insulation faults based on the time series decomposition result of the insulation fault data, improving the accuracy and reliability of battery pack insulation fault prediction, and thus being able to identify battery pack insulation faults in advance to prevent safety hazards such as leakage and short circuit, thereby improving the safety of electric vehicle driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the description of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 is a flowchart of the steps of a battery pack detection method provided by some embodiments of the present invention; Figure 2 is a structural block diagram of a battery pack detection device provided by some embodiments of the present invention; Figure 3 is a block diagram of an electronic device provided in an embodiment of the present invention; Figure 4 is a schematic diagram of a computer-readable medium provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments described are only a portion of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are also within the scope of protection of the present invention.

[0018] In existing technologies, the Battery Management System (BMS) plays a crucial role in preventing and monitoring insulation failure in battery packs. The BMS monitors the insulation status of the battery pack system in real time. Using an insulation detection device, the BMS measures the resistance between the battery pack and the vehicle body to determine whether the insulation is in good condition. Specifically, the BMS prevents leakage by measuring the insulation resistance between the positive and negative electrodes of the battery pack and the vehicle body, thereby avoiding safety accidents.

[0019] This method ensures good insulation between the battery pack and the vehicle body, preventing safety hazards such as leakage and short circuits. However, it often relies solely on a single piece of insulation resistance data, making estimates without considering the influence of other related data. This results in low insulation resistance prediction accuracy, which in turn significantly limits insulation fault prediction and assessment.

[0020] In one embodiment of the present invention, insulation fault data of an electric vehicle is obtained, which may include a variety of insulation fault component data. The insulation fault data is decomposed into a time series, and the obtained component sequence data is then used as the input of a prediction model, thereby obtaining an insulation fault prediction value corresponding to the insulation fault data. Furthermore, a highly accurate insulation fault prediction result can be obtained based on the insulation fault prediction value.

[0021] Reference Figure 1 , shows a flowchart of a method for detecting a battery pack provided by some embodiments of the present invention, which may specifically include the following steps: Step 101: Obtain insulation fault data of the battery pack.

[0022] In order to detect the insulation fault of the battery pack in the electric vehicle, the insulation fault data of the battery pack in the electric vehicle can be obtained first. The insulation fault data is data associated with the insulation fault of the battery pack, such as abnormal voltage data, abnormal current data, abnormal resistance data, and abnormal temperature data associated with the insulation fault of the battery pack, etc.

[0023] Specifically, insulation fault data about the battery pack in the electric vehicle can be obtained. The insulation fault data may include one or more of abnormal voltage data, abnormal current data, abnormal resistance data, and abnormal temperature data. Each type of data can be called component data of the insulation fault data, that is, insulation fault component data.

[0024] In practical applications, electric vehicles can also obtain historical insulation fault data backed up in a cloud database and combine it with the current insulation fault data in the electric vehicle, making the final insulation fault data richer and more complete.

[0025] Step 102: performing time series decomposition on the insulation fault data to obtain component series data.

[0026] Since the insulation fault data is time series data, after obtaining the insulation fault data, the insulation fault data can be decomposed into time series to obtain corresponding component series data.

[0027] In some embodiments of the present invention, the component sequence data includes any one or more of the following: Trend series data, periodic series data, residual series data.

[0028] For example, in some examples, time series data can have three characteristics, corresponding to three components: a trend component, a periodic component, and an irregular fluctuation component. Therefore, by decomposing the insulation fault data into a time series, we can obtain corresponding trend series data, periodic series data, and residual series data.

[0029] In practical applications, time series decomposition can be performed using empirical mode decomposition, which extracts the intrinsic mode function components of time series data. Alternatively, the STL (Season and Trend decomposition using Loess) decomposition method can be used. In some examples, the multiplication model of classical time series decomposition can be used for calculations. The expression for the multiplication model is: Yt = Tt×St×It Here, Tt represents the trend component, St represents the cyclical component, and It represents the irregular fluctuation component (residual component). The time series decomposition method is not limited here and can be flexibly selected.

[0030] In one example, for irregular fluctuation components (i.e., residual components), the components with severe fluctuations can be stabilized, such as some simple deletion or normalization operations.

[0031] It should be noted that, since the insulation fault data may contain one or more of abnormal voltage data, abnormal current data, abnormal resistance data and abnormal temperature data, when performing time series decomposition on the insulation fault data, if the insulation fault data only contains one type of insulation fault component data, then the insulation fault component data can be directly decomposed into time series to obtain the corresponding trend series data, periodic series data and residual series data. If the insulation fault data contains multiple types of insulation fault component data, then each type of insulation fault component data in the insulation fault data will be decomposed into time series separately, and then the component series data corresponding to each insulation fault component data will be obtained, that is, the trend series data, periodic series data and residual series data corresponding to each insulation fault component data will be obtained.

[0032] In some embodiments of the present invention, after performing time series decomposition on the insulation fault component data to obtain component series data, the method further includes: The component sequence data are standardized.

[0033] Specifically, after obtaining component sequence data corresponding to one or more insulation fault component data included in the insulation fault data, standardization processing may be performed on the trend sequence data, period sequence data, and residual sequence data corresponding to each insulation fault component data.

[0034] After standardization, the trend series data, period series data, and residual series data corresponding to each insulation fault component data can be made to have a unified scale or distribution characteristics. In other words, it can be understood as making the data on the same order of magnitude, thereby eliminating dimensional differences between the data and making different components comparable, making the data more standardized, stable, and representative. At the same time, it can provide more stable input for subsequent insulation fault prediction, improving accuracy and reliability.

[0035] In practical applications, the standardization processing method can be normalization, Z-score standardization (Z score standardization) or Min-Max standardization (minimum-maximum standardization) and other methods. No specific restrictions are made here, and you can flexibly choose.

[0036] In some embodiments of the present invention, performing time series decomposition on the insulation fault data to obtain component series data includes: Sub-step 11: determining a target period of the insulation fault data.

[0037] For insulation fault data, a target period of the insulation fault data in time sequence may be determined first.

[0038] Specifically, if the insulation fault data only contains one type of insulation fault component data, then the target period of the insulation fault component data in the time series can be determined, that is, the target period of the insulation fault data in the time series. If the insulation fault data contains multiple types of insulation fault component data, then the target period of each type of insulation fault component data in the time series needs to be determined separately, that is, multiple target periods corresponding to multiple types of insulation fault component data in the time series are determined. The multiple target periods corresponding to multiple types of data are the target periods of the insulation fault data.

[0039] Sub-step 12: performing time series decomposition on the insulation fault data based on the target period to obtain component series data corresponding to the insulation fault data.

[0040] After obtaining the target period of the insulation fault, the insulation fault data may be decomposed into time series based on the target period, thereby obtaining component series data corresponding to the insulation fault data.

[0041] Specifically, if the insulation fault data contains only one type of insulation fault component data, then the insulation fault component data can be time-series decomposed based on the target period of the insulation fault component data to obtain component sequence data corresponding to the insulation fault component data, namely, trend sequence data, period sequence data, and residual sequence data. If the insulation fault data contains multiple types of insulation fault component data, then the insulation fault component data can be time-series decomposed based on the target period of each type of insulation fault component data to obtain component sequence data corresponding to each type of insulation fault component data, namely, component sequence data corresponding to the insulation fault data.

[0042] In practical applications, insulation faults can be decomposed into time series based on the target period of the insulation fault data. For example, STL decomposition, empirical mode decomposition, or classic time series decomposition can be performed based on the target period of the insulation fault data. The period is a key parameter in STL decomposition. For empirical mode decomposition, based on the target period of the insulation fault data, the periodic characteristics of the signal can be understood in advance, which can help better decompose the insulation fault data and improve the efficiency of empirical mode decomposition. Overall, after determining the target period of the insulation fault data, performing time series decomposition based on the target period can improve the accuracy and reliability of the time series decomposition.

[0043] In some embodiments of the present invention, determining a target period of the insulation fault component data includes: Sub-step 21 : performing frequency domain conversion on the insulation fault data to obtain corresponding frequency domain data.

[0044] In order to determine the target period of the insulation fault data, one or more insulation fault component data that may be contained in the insulation fault data may be frequency-domain converted to obtain frequency domain data corresponding to the one or more insulation fault component data that may be contained in the insulation fault data.

[0045] Specifically, if the insulation fault data contains one type of insulation fault component data, a fast Fourier transform can be used to perform frequency domain conversion on the insulation fault component data to obtain corresponding frequency domain data. If the insulation fault data contains multiple types of insulation fault component data, a fast Fourier transform can be used to perform frequency domain conversion on each type of insulation fault component data to obtain frequency domain data corresponding to each type of insulation fault component data.

[0046] Sub-step 22: determining a plurality of candidate cycles of the insulation fault data based on the frequency domain data.

[0047] After obtaining the frequency domain data corresponding to the insulation fault data, the main frequency components can be identified through frequency domain analysis, and multiple frequencies can be determined therefrom as multiple candidate frequencies, and then the multiple candidate frequencies can be converted into multiple candidate cycles.

[0048] In practical applications, for the frequency domain data corresponding to one or more insulation fault component data in the insulation fault data, the frequency domain data corresponding to each insulation fault component data can be analyzed to identify the main frequency components, and then the first few frequencies with the largest amplitudes can be selected as candidate frequencies, and these candidate frequencies can be converted into periods, thereby determining multiple candidate periods for each insulation fault component data, that is, determining multiple candidate periods for the insulation fault data.

[0049] Sub-step 23: determining a target cycle of the insulation fault data from the multiple candidate cycles.

[0050] After obtaining a plurality of candidate cycles of insulation fault data, a target cycle of insulation fault data may be determined from the plurality of candidate cycles.

[0051] Specifically, the rationality analysis of multiple candidate periods of the insulation fault data may be performed using an autocorrelation function, thereby determining a target period of the insulation fault data.

[0052] In practical applications, for frequency domain data corresponding to one or more insulation fault component data in the insulation fault data, a time domain analysis can be performed on multiple candidate cycles corresponding to each insulation fault component data using an autocorrelation function. This allows the optimal cycle to be determined as the target cycle from among the multiple candidate cycles corresponding to each insulation fault component data. The target cycles corresponding to each of the one or more insulation fault component data in the insulation fault data are then the target cycles of the insulation fault data.

[0053] Step 103: Use the component sequence data to perform insulation fault prediction to obtain an insulation fault prediction value of the insulation fault data.

[0054] After obtaining component sequence data obtained by time series decomposition of the insulation fault data, the component sequence data may be used to perform insulation fault prediction to obtain an insulation fault prediction value of the insulation fault data.

[0055] Specifically, if the insulation fault data contains only one type of insulation fault component data, the component sequence data corresponding to the insulation fault component data, i.e., the trend sequence data, the periodic sequence data, and the memory residual sequence data, can be used to perform insulation fault prediction and obtain an insulation fault prediction value for the insulation fault data. If the insulation fault data contains multiple types of insulation fault component data, the component sequence data corresponding to each type of insulation fault component data, i.e., the trend sequence data, the periodic sequence data, and the memory residual sequence data, can be used to perform insulation fault prediction and obtain an insulation fault prediction value for the insulation fault data.

[0056] In practical applications, insulation fault prediction can be performed using a trained prediction model, that is, the component sequence data corresponding to one or more insulation fault component data contained in the insulation fault data are all used as the input of the prediction model, and the output of the prediction model is the insulation fault prediction value of the insulation fault data.

[0057] As an example, the prediction model may be a model built based on an LSTM model (Long Short-Term Memory, long short-term memory network model), and may include multiple LSTM models.

[0058] The LSTM model has four layers: the input layer, the LSIM structure layer, the fully connected layer, and the output layer. Dropout can be embedded in any of these layers. Dropout, which means "dropout," refers to a strategy proposed during neural network training to prevent overfitting. This strategy aims to randomly remove neurons from the network with a certain probability during training, thereby avoiding overfitting.

[0059] For the training of the prediction model, an adaptive enhancement algorithm can be used to optimize the training of the prediction model. The specific training steps are as follows: S1. Obtain training samples.

[0060] A large amount of insulation failure data of real vehicles can be obtained from the cloud database, and this data can be used as a training set for the prediction model, that is, training samples are obtained.

[0061] S2. Calculate the sampling weights for the training samples.

[0062] The insulation fault data in the training samples may contain a variety of insulation fault component data. Sampling weight calculation can be performed on the training samples, and the weights of different types of data may be different.

[0063] In one example, at the beginning of model training, multiple insulation fault component data may be proportionally divided according to the importance of insulation fault determination to obtain an initial sampling weight, ie, a sample weight.

[0064] Specifically, the various insulation fault component data included in the insulation fault data have different initial weights, and the trend sequence data, period sequence data, and residual sequence data corresponding to each insulation fault component data may also have different initial weights.

[0065] S3. Sample the training samples using the sampling weights, and then calculate the training samples to obtain the prediction factors of the prediction model.

[0066] Sampling is performed according to the sample weight to generate a new training subset, and then calculation is performed based on this new training subset to obtain the prediction factor of the current prediction model, which can be considered as the intermediate insulation fault prediction value.

[0067] S4. Calculate the prediction error and overall weight of the prediction factors of the prediction model.

[0068] The prediction error and overall weight of the current prediction model are calculated using the obtained prediction factors.

[0069] S5. Update the sample weights of the training samples.

[0070] Adjust the sample weight of the training sample by using the prediction error and the overall weight.

[0071] S6. Repeat steps S3-S5 until all LSTM models that may be included in the prediction model are trained, thereby completing the training of the prediction model.

[0072] In one example, using the component sequence data to perform insulation fault prediction to obtain an insulation fault prediction value of the insulation fault data includes: In the case where the insulation fault data includes a type of insulation fault component data, insulation fault prediction is performed using component sequence data corresponding to the insulation fault component data to obtain an insulation fault prediction value corresponding to the insulation fault component data, and the insulation fault prediction value corresponding to the insulation fault component data is determined as the insulation fault prediction value of the insulation fault data.

[0073] Specifically, when the insulation fault data includes a type of insulation fault component data, the trend series data, periodic series data, and residual series data corresponding to the insulation fault component data can be used as inputs of the trained prediction model to perform insulation fault prediction. In the prediction model, an insulation fault prediction value corresponding to the insulation fault component data is obtained. Since the insulation fault data includes a type of insulation fault component data, it can be understood that the weight of the insulation fault component data in the prediction model is 100%. Therefore, the insulation fault prediction value corresponding to the insulation fault component data can be used as the output of the trained prediction model, that is, determined as the insulation fault prediction value of the insulation fault data.

[0074] In the case where the insulation fault data includes multiple insulation fault component data, insulation fault prediction is performed using component sequence data corresponding to each insulation fault component data to obtain an insulation fault prediction value corresponding to each insulation fault component data, and the insulation fault prediction values ​​corresponding to each insulation fault component data are superimposed according to preset weights to obtain the insulation fault prediction value of the insulation fault data.

[0075] Specifically, when the insulation fault data includes multiple insulation fault component data, the trend series data, periodic series data, and residual series data corresponding to the multiple insulation fault component data can be used as the input of the trained prediction model to perform insulation fault prediction. In the prediction model, an insulation fault prediction value corresponding to each insulation fault component data is obtained. Since the trained prediction model has corresponding weights for the multiple insulation fault component data, that is, preset weights, the insulation fault prediction values ​​corresponding to the multiple insulation fault component data can be superimposed according to the preset weights, and the superimposed value can be used as the output of the trained prediction model, that is, the insulation fault prediction value of the insulation fault data is obtained.

[0076] In one example, the trained prediction model can still be optimized based on the update of insulation performance-related data in the cloud database, that is, the update of a large amount of insulation failure data of actual vehicles, so as to further improve the performance of the prediction model, thereby enabling this solution to achieve big data early warning function.

[0077] Step 104 : Determine an insulation fault prediction result of the battery pack according to the insulation fault prediction value.

[0078] After the insulation fault prediction value is obtained, the insulation fault prediction result of the battery pack in the electric vehicle can be obtained through the fault prediction value.

[0079] In some embodiments of the present invention, determining the insulation fault prediction result of the battery pack according to the insulation fault prediction value includes: Sub-step 31 : comparing the insulation fault prediction value with a preset fault threshold to obtain a comparison result.

[0080] Specifically, for insulation fault prediction, an insulation fault threshold is preset, ie, a preset fault threshold. Therefore, after obtaining the insulation fault prediction value, the insulation fault prediction value can be compared with the preset fault threshold to obtain a corresponding comparison result.

[0081] Sub-step 32: determining an insulation fault prediction result of the battery pack according to the comparison result.

[0082] After obtaining the comparison result between the insulation fault prediction value and the preset fault threshold, a judgment can be made based on the comparison result to determine the insulation fault prediction result of the battery pack.

[0083] Specifically, when the insulation fault prediction value is less than a preset fault threshold, it can be considered that the battery pack of the electric vehicle is in a normal state.

[0084] When the insulation fault prediction value is greater than the preset fault threshold, it can be considered that the battery pack of the electric vehicle may suffer from insulation failure, and the current battery pack may be at risk of a safety accident.

[0085] In an embodiment of the present invention, insulation fault data of a battery pack is obtained, time series decomposition of the insulation fault data is performed to obtain component sequence data, insulation fault prediction is performed using the component sequence data to obtain an insulation fault prediction value of the insulation fault data, and an insulation fault prediction result of the battery pack is determined based on the insulation fault prediction value. This achieves the prediction and evaluation of battery pack insulation faults based on the time series decomposition result of the insulation fault data, improves the accuracy and reliability of battery pack insulation fault prediction, and thus can identify battery pack insulation faults in advance to prevent safety hazards such as leakage and short circuit, thereby improving the safety of electric vehicle driving.

[0086] It should be noted that for the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0087] Reference Figure 2 , which shows a schematic structural diagram of a battery pack detection device provided by some embodiments of the present invention, which may specifically include the following modules: The data acquisition module 201 is used to obtain insulation fault data of the battery pack; A sequence decomposition module 202 is used to perform time series decomposition on the insulation fault data to obtain component sequence data; A prediction value acquisition module 203 is configured to use the component sequence data to perform insulation fault prediction and obtain an insulation fault prediction value; The prediction result determination module 204 is configured to determine an insulation fault prediction result of the battery pack according to the insulation fault prediction value.

[0088] In one embodiment of the present application, the sequence decomposition module 202 includes: a cycle determination submodule, configured to determine a target cycle of the insulation fault data; The sequence decomposition submodule is used to perform time series decomposition on the insulation fault data based on the target period to obtain component sequence data corresponding to the insulation fault data.

[0089] In one embodiment of the present application, the period determination submodule includes: A frequency domain conversion unit, configured to perform frequency domain conversion on the insulation fault data to obtain corresponding frequency domain data; a candidate cycle determining unit, configured to determine a plurality of candidate cycles of the insulation fault data based on the frequency domain data; The target cycle determining unit is configured to determine a target cycle of the insulation fault data from the plurality of candidate cycles.

[0090] In one embodiment of the present application, the component sequence data includes any one or more of the following: Trend series data, periodic series data, residual series data.

[0091] In one embodiment of the present application, the predicted value acquisition module 203 includes: a first prediction value acquisition submodule for, when the insulation fault data includes a type of insulation fault component data, using component sequence data corresponding to the insulation fault component data to perform insulation fault prediction, obtaining an insulation fault prediction value corresponding to the insulation fault component data, and determining the insulation fault prediction value corresponding to the insulation fault component data as the insulation fault prediction value of the insulation fault data; The second prediction value acquisition submodule is used to, when the insulation fault data includes multiple insulation fault component data, use the component sequence data corresponding to each insulation fault component data to perform insulation fault prediction, obtain the insulation fault prediction value corresponding to each insulation fault component data, and superimpose the insulation fault prediction values ​​corresponding to each insulation fault component data according to preset weights to obtain the insulation fault prediction value of the insulation fault data.

[0092] In one embodiment of the present application, the prediction result determination module 204 includes: A comparison result acquisition submodule, configured to compare the insulation fault prediction value with a preset fault threshold to obtain a comparison result; The result determination submodule is used to determine the insulation fault prediction result of the battery pack according to the comparison result.

[0093] In one embodiment of the present application, after performing time series decomposition on the insulation fault component data to obtain component series data, the method further includes: The standardization processing module performs standardization processing on the component sequence data.

[0094] In an embodiment of the present invention, insulation fault data of a battery pack is obtained, time series decomposition of the insulation fault data is performed to obtain component sequence data, insulation fault prediction is performed using the component sequence data to obtain an insulation fault prediction value of the insulation fault data, and an insulation fault prediction result of the battery pack is determined based on the insulation fault prediction value. This achieves the prediction and evaluation of battery pack insulation faults based on the time series decomposition result of the insulation fault data, improves the accuracy and reliability of battery pack insulation fault prediction, and thus can identify battery pack insulation faults in advance to prevent safety hazards such as leakage and short circuit, thereby improving the safety of electric vehicle driving.

[0095] Some embodiments of the present invention further provide an electronic device, such as Figure 3 As shown, it includes a processor 301, a communication interface 302, a memory 303 and a communication bus 304. The processor 301, the communication interface 302 and the memory 303 communicate with each other through the communication bus 304. Memory 303, for storing computer programs; The processor 301 is configured to execute the program stored in the memory 303, and implement the following steps: Obtain insulation fault data of the battery pack; Performing time series decomposition on the insulation fault data to obtain component series data; Performing insulation fault prediction using the component sequence data to obtain an insulation fault prediction value of the insulation fault data; An insulation fault prediction result of the battery pack is determined according to the insulation fault prediction value.

[0096] The communication bus mentioned in the terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0097] The communication interface is used for communication between the above terminal and other devices.

[0098] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0099] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0100] Some embodiments of the present invention further provide a computer-readable storage medium, such as Figure 4 As shown, a computer program is stored on a computer-readable storage medium, and the above method is implemented when the computer program is executed by a processor.

[0101] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0102] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0103] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0104] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, apparatus, or computer program products. Thus, embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0105] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0106] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0107] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0108] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they become aware of the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0109] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device that includes the above elements.

[0110] The above is a detailed introduction to the provided method, device, equipment and medium for battery pack detection. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for detecting a battery pack, characterized in that: The method comprises: Obtain insulation fault data of the battery pack; Performing time series decomposition on the insulation fault data to obtain component series data; Performing insulation fault prediction using the component sequence data to obtain an insulation fault prediction value of the insulation fault data; An insulation fault prediction result of the battery pack is determined according to the insulation fault prediction value.

2. The method according to claim 1, wherein The time series decomposition of the insulation fault data to obtain component series data includes: determining a target period of the insulation fault data; Based on the target period, the insulation fault data is decomposed into a time series to obtain component sequence data corresponding to the insulation fault data.

3. The method according to claim 2, characterized in that Determining a target period of the insulation fault component data includes: Performing frequency domain conversion on the insulation fault data to obtain corresponding frequency domain data; determining a plurality of candidate cycles of the insulation fault data based on the frequency domain data; A target cycle of the insulation fault data is determined from the plurality of candidate cycles.

4. The method according to claim 2, characterized in that The component sequence data includes any one or more of the following: Trend series data, periodic series data, residual series data.

5. The method according to any one of claims 1 to 4, characterized in that The step of using the component sequence data to perform insulation fault prediction to obtain an insulation fault prediction value of the insulation fault data includes: In a case where the insulation fault data includes insulation fault component data, performing insulation fault prediction using component sequence data corresponding to the insulation fault component data to obtain an insulation fault prediction value corresponding to the insulation fault component data, and determining the insulation fault prediction value corresponding to the insulation fault component data as the insulation fault prediction value of the insulation fault data; In the case where the insulation fault data includes multiple insulation fault component data, insulation fault prediction is performed using component sequence data corresponding to each insulation fault component data to obtain an insulation fault prediction value corresponding to each insulation fault component data, and the insulation fault prediction values ​​corresponding to each insulation fault component data are superimposed according to preset weights to obtain the insulation fault prediction value of the insulation fault data.

6. The method according to any one of claims 1 to 4, characterized in that The step of determining an insulation fault prediction result of the battery pack according to the insulation fault prediction value includes: Comparing the insulation fault prediction value with a preset fault threshold to obtain a comparison result; An insulation fault prediction result of the battery pack is determined according to the comparison result.

7. The method according to any one of claims 1 to 4, characterized in that After performing time series decomposition on the insulation fault component data to obtain component series data, it also includes: The component sequence data are standardized.

8. A battery pack detection device, characterized in that: The device comprises: A data acquisition module is used to obtain insulation fault data of the battery pack; A sequence decomposition module, configured to perform time series decomposition on the insulation fault data to obtain component sequence data; A prediction value acquisition module, configured to use the component sequence data to perform insulation fault prediction and obtain an insulation fault prediction value; A prediction result determination module is used to determine the insulation fault prediction result of the battery pack according to the insulation fault prediction value.

9. An electronic device, characterized in that: The invention comprises a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the method for detecting a battery pack according to any one of claims 1 to 7 is implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for detecting a battery pack according to any one of claims 1 to 7 is implemented.

Images