Vehicle-mounted power battery abnormal degradation identification model construction and abnormal degradation identification method

Abstract

The present application relates to the technical field of power battery evaluation, and discloses a vehicle-mounted power battery abnormal degradation identification model construction and an abnormal degradation identification method.The vehicle-mounted power battery abnormal degradation identification model construction method provided by the present application uses the associated data set between the capacity retention rate data sequence of a plurality of target vehicles and the corresponding degradation type information to train a preset model, so that the preset model learns the association between the capacity retention rate data sequence of the target vehicle and the degradation type information, and subsequently inputs the capacity retention rate data sequence of the target vehicle into the vehicle-mounted power battery abnormal degradation identification model obtained after training, which can identify the degradation type information of the target vehicle, thereby solving the problem that the degradation type of the vehicle-mounted power battery cannot be detected in the related art.

Description

Technical Field

[0001] This invention relates to the field of power battery evaluation technology, specifically to the construction of an abnormal degradation identification model and a method for identifying abnormal degradation in vehicle-mounted power batteries. Background Technology

[0002] Electric vehicles suffer from high maintenance costs, partly due to the use of new technologies and partly due to their inherent structure. The onboard battery module accounts for approximately 25% to 40% of the total vehicle cost, making it the most valuable and frequently involved component in car insurance claims.

[0003] Traditional methods for detecting battery degradation in new energy vehicles are offline inspections, requiring significant manpower and equipment investment. Furthermore, these methods can only detect the presence of battery degradation before testing, but cannot distinguish between normal and abnormal degradation. Abnormal degradation refers to a rapid and significant decline in battery health, indicating damage caused by external forces such as collisions. Normal degradation, on the other hand, occurs due to normal battery use. Capitalizing on the loopholes in offline inspections of new energy vehicles, some car owners exploit this inability to identify when battery degradation is evident to fabricate accidents and commit insurance fraud. Therefore, finding a way to detect the type of degradation in vehicle batteries is a pressing issue that needs to be addressed. Summary of the Invention

[0004] In view of this, the present invention provides a model for identifying abnormal degradation of vehicle power batteries and a method for identifying abnormal degradation, so as to solve the problem that the degradation type of vehicle power batteries cannot be detected in related technologies.

[0005] In a first aspect, the present invention provides a method for constructing an abnormal degradation identification model for vehicle-mounted power batteries. The method includes: acquiring capacity retention rate data sequences of multiple target vehicles, wherein the multiple target vehicles are of the same model, and the capacity retention rate data sequences of the multiple target vehicles are used to characterize the change in capacity retention rate over time when the on-board power battery of the corresponding target vehicle experiences degradation; analyzing the capacity retention rate data sequences of the multiple target vehicles to determine the degradation type information of the on-board power battery corresponding to each target vehicle; associating the capacity retention rate data sequences of the multiple target vehicles with the corresponding degradation type information to obtain an associated dataset; and training a preset model using the associated dataset until preset conditions are met to obtain an abnormal degradation identification model for vehicle-mounted power batteries.

[0006] The present invention provides a method for constructing an abnormal degradation identification model for vehicle-mounted power batteries. This method analyzes the capacity retention rate sequence data of multiple target vehicles' power batteries at the time of degradation, determines the degradation type information corresponding to the capacity retention rate data sequence of each target vehicle, and associates the capacity retention rate data sequences of multiple target vehicles with the corresponding degradation type information to obtain an associated dataset. This associated dataset is then used to train a pre-set model to obtain the abnormal degradation identification model for vehicle-mounted power batteries. The method provided by this invention uses the associated dataset between the capacity retention rate data sequences of multiple target vehicles and the corresponding degradation type information to train the pre-set model, enabling the model to learn the correlation between the capacity retention rate data sequences and degradation type information of the target vehicles. Subsequently, the capacity retention rate data sequences of the target vehicles are input into the trained abnormal degradation identification model for vehicle-mounted power batteries. This model can identify the degradation type information of the target vehicles, solving the problem in related technologies that cannot detect the degradation type of vehicle-mounted power batteries.

[0007] In one optional implementation, the step of obtaining capacity retention rate data sequences of multiple target vehicles includes: obtaining historical capacity retention rate data sequences of multiple vehicles, wherein the multiple vehicles are of the same model; analyzing the historical capacity retention rate data sequences of multiple vehicles to identify multiple target vehicles among the multiple vehicles; and using the historical capacity retention rate data sequences corresponding to each target vehicle as the corresponding capacity retention rate data sequences of the target vehicles.

[0008] In one optional implementation, the step of analyzing the historical capacity retention rate data sequence of multiple vehicles and identifying multiple target vehicles includes: calculating multiple incremental values ​​for each vehicle based on the historical capacity retention rate data sequence of each vehicle, wherein the incremental values ​​are calculated from the historical capacity retention rate data of the corresponding vehicle at a first time and the historical capacity retention rate data at a second time, the second time being the time immediately preceding the first time; calculating the average and standard deviation of the multiple incremental values ​​corresponding to each of the multiple vehicles; determining an abnormal decay threshold based on the average and standard deviation of the multiple incremental values ​​corresponding to each of the multiple vehicles; comparing the multiple incremental values ​​of each vehicle with the abnormal decay threshold to obtain a comparison result; and, based on the comparison result, identifying vehicles with incremental values ​​greater than the abnormal decay threshold as target vehicles.

[0009] The method provided in this optional implementation can filter out the capacity retention rate data sequence of multiple target vehicles from the historical data sequence of capacity retention rate of multiple vehicles.

[0010] In one optional implementation, the step of obtaining a sequence of historical capacity retention rate data for multiple vehicles includes: obtaining historical capacity retention rate data for multiple vehicles, wherein the historical capacity retention rate data includes capacity retention rate data and corresponding timestamps; cleaning the measured historical capacity retention rate data using a preset data cleaning method to obtain cleaned historical capacity retention rate data for each vehicle; imputing missing values ​​in the cleaned historical capacity retention rate data for each vehicle to obtain imputed historical capacity retention rate data for the corresponding vehicle; and sorting the imputed historical capacity retention rate data for each vehicle according to the timestamps to obtain a sequence of historical capacity retention rate data for multiple vehicles.

[0011] In one optional implementation, the step of associating the capacity retention rate data sequences of multiple target vehicles with the corresponding degradation type information to obtain an associated dataset includes: determining the degradation type identifier corresponding to each target vehicle, wherein the degradation type identifier is used to correspond to the degradation type information of the target vehicle; and associating the capacity retention rate data sequences of each target vehicle with the corresponding degradation type identifier to obtain an associated dataset.

[0012] Secondly, the present invention provides a method for identifying abnormal degradation of vehicle-mounted power batteries. The method includes: acquiring a capacity retention rate data sequence of a target vehicle to be identified; inputting the capacity retention rate data sequence of the target vehicle to be identified into a vehicle-mounted power battery abnormal degradation identification model, so that the vehicle-mounted power battery abnormal degradation identification model outputs vehicle-mounted power battery degradation type information corresponding to the target vehicle to be identified, the vehicle-mounted power battery abnormal degradation identification model being constructed by the vehicle-mounted power battery abnormal degradation identification model construction method of the first aspect or any corresponding embodiment thereof; and determining the vehicle-mounted power battery abnormal degradation identification result based on the vehicle-mounted power battery degradation type information corresponding to the target vehicle to be identified.

[0013] The present invention provides a method for identifying abnormal degradation of vehicle power batteries. The method inputs the capacity retention rate data sequence of the target vehicle into the vehicle power battery abnormal degradation identification model. The model can identify the degradation type information of the target vehicle, thus solving the problem that related technologies cannot detect the degradation type of vehicle power batteries.

[0014] In one optional implementation, the step of obtaining the capacity retention rate data sequence of the target vehicle to be identified includes: obtaining the capacity retention rate data sequence of the target vehicle; calculating multiple incremental values ​​of the target vehicle based on the capacity retention rate data sequence of the target vehicle; if the number of multiple incremental values ​​is greater than a preset threshold, and there is an incremental value among the multiple incremental values ​​that is greater than an abnormal decay threshold, then the capacity retention rate data of the target vehicle to be identified is used as the capacity retention rate data sequence of the target vehicle to be identified.

[0015] Thirdly, the present invention provides a device for constructing an abnormal degradation identification model for vehicle-mounted power batteries. The device includes: a first acquisition module for acquiring capacity retention rate data sequences of multiple target vehicles, wherein the multiple target vehicles are of the same model, and the capacity retention rate data sequences of the multiple target vehicles are used to characterize the change in capacity retention rate over time when the on-board power battery of the corresponding target vehicle experiences degradation; an analysis module for analyzing the capacity retention rate data sequences of the multiple target vehicles to determine the degradation type information of the on-board power battery corresponding to each target vehicle; an association module for associating the capacity retention rate data sequences of the multiple target vehicles with the corresponding degradation type information to obtain an association dataset; and a training module for training a preset model using the association dataset until preset conditions are met to obtain an abnormal degradation identification model for vehicle-mounted power batteries.

[0016] Fourthly, the present invention provides a device for identifying abnormal degradation of an on-board power battery. The device includes: a second acquisition module for acquiring a capacity retention rate data sequence of a target vehicle to be identified; an identification module for inputting the capacity retention rate data sequence of the target vehicle to be identified into an on-board power battery abnormal degradation identification model, such that the on-board power battery abnormal degradation identification model outputs on-board power battery degradation type information corresponding to the target vehicle to be identified, the on-board power battery abnormal degradation identification model being constructed by the on-board power battery abnormal degradation identification model construction method of the first aspect or any corresponding embodiment; and a determination module for determining the on-board power battery abnormal degradation identification result based on the on-board power battery degradation type information corresponding to the target vehicle to be identified.

[0017] Fifthly, the present invention provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the vehicle power battery abnormal degradation identification model construction method of the first aspect or any corresponding embodiment described above, or to perform the vehicle power battery abnormal degradation identification method of the second aspect or a corresponding embodiment described above.

[0018] In a sixth aspect, the present invention provides a computer-readable storage medium storing computer instructions, which are used to cause a computer to execute the method for constructing an abnormal degradation identification model for an on-board power battery according to the first aspect or any of the corresponding embodiments described above, or to execute the method for identifying abnormalities in an on-board power battery according to the second aspect or the corresponding embodiments described above. Attached Figure Description

[0019] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the method for constructing an abnormal degradation identification model for vehicle-mounted power batteries according to an embodiment of the present invention.

[0021] Figure 2 This is a flowchart illustrating another method for constructing an abnormal degradation identification model for vehicle-mounted power batteries according to an embodiment of the present invention.

[0022] Figure 3 This is a flowchart illustrating the method for identifying abnormal degradation of vehicle-mounted power batteries according to an embodiment of the present invention.

[0023] Figure 4 This is a structural block diagram of an on-board power battery abnormal degradation identification model construction device according to an embodiment of the present invention;

[0024] Figure 5 This is a structural block diagram of an on-board power battery abnormal degradation identification device according to an embodiment of the present invention;

[0025] Figure 6 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] The battery degradation detection method for new energy vehicles is an offline test, requiring manpower and equipment investment. Furthermore, it can only detect whether battery degradation existed before the test, but cannot distinguish whether the degradation of the vehicle's power battery is normal or abnormal. Taking advantage of these loopholes in offline testing of new energy vehicles, some car owners exploit the fact that offline testing cannot identify when obvious battery degradation occurs to fabricate accidents and commit insurance fraud.

[0028] In view of this, the present invention provides a method for constructing an abnormal degradation identification model for vehicle-mounted power batteries, which can be applied to a server to construct such a model. The method provides by training a preset model using a dataset relating capacity retention rate data sequences of multiple target vehicles to their corresponding degradation type information. This allows the preset model to learn the correlation between the capacity retention rate data sequences and degradation type information of the target vehicles. Subsequently, the capacity retention rate data sequences of the target vehicles are input into the trained abnormal degradation identification model, which can then identify the degradation type information of the target vehicles, thus solving the problem in related technologies where the degradation type of vehicle-mounted power batteries cannot be detected.

[0029] According to an embodiment of the present invention, an embodiment of a method for constructing an abnormal degradation identification model for vehicle power batteries is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0030] This embodiment provides a method for constructing an abnormal degradation identification model for vehicle-mounted power batteries, which can be used in the aforementioned server. Figure 1 This is a flowchart of a method for constructing an abnormal degradation identification model for vehicle-mounted power batteries according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0031] Step S101: Obtain capacity retention rate data sequences of multiple target vehicles. The multiple target vehicles are of the same model. The capacity retention rate data sequences of multiple target vehicles are used to characterize the change in capacity retention rate over time when the on-board power battery of the corresponding target vehicle degrades.

[0032] For example, the target vehicle can be any vehicle that needs to be identified for abnormal degradation of its on-board power battery, and different target vehicles may have the same model. In this embodiment, the capacity retention rate data sequence of multiple target vehicles is used to characterize the change in capacity retention rate over time when the on-board power battery of the corresponding target vehicle degrades, including normal use degradation and abnormal degradation.

[0033] Step S102: Analyze the capacity retention rate data sequence of multiple target vehicles to determine the degradation type information of the on-board power battery corresponding to each target vehicle.

[0034] For example, the degradation type may include, but is not limited to, normal degradation and abnormal degradation. In this embodiment, when the on-board power battery degrades abnormally, its health status will drop significantly. The degradation type can be determined by comparing the change pattern of the capacity retention rate data of the target vehicle with the normal change pattern. If abnormal data is identified in the capacity retention rate data sequence of the target vehicle, the degradation type of the capacity retention rate data sequence is determined to be abnormal degradation. If no abnormal data is identified, the degradation type of the capacity retention rate data sequence is determined to be normal degradation.

[0035] Step S103: Associate the capacity retention rate data sequences of multiple target vehicles with the corresponding decay type information to obtain an associated dataset.

[0036] For example, the capacity retention rate data sequences of multiple target vehicles are associated with the corresponding degradation type information to determine the one-to-one correspondence between the capacity retention rate data sequence and the degradation type of each target vehicle. In this embodiment, the association method is not limited, and those skilled in the art can determine it according to their needs.

[0037] Step S104: Train the preset model using the associated dataset until the preset conditions are met to obtain the vehicle power battery abnormal degradation identification model.

[0038] For example, the preset model may include, but is not limited to, a machine learning model. In this embodiment, tsfresh is used to extract field features from the vehicle capacity retention rate data sequence. Features include statistical features, frequency domain features, autocorrelation features, etc. The tsfresh.select_features function is called to select features. Finally, the lightgbm algorithm package of Python is used to train the LGBM classification model. The samples are the capacity retention rate data of 20 models from each of the top 10 brands in terms of vehicle numbers for one year. The training set and test set are split in a ratio of 20% and 80%, respectively. The model parameters (params) are defined as follows:

[0039]

[0040]

[0041] The method for constructing an abnormal degradation identification model for vehicle-mounted power batteries provided in this embodiment uses a dataset of correlations between capacity retention rate data sequences of multiple target vehicles and corresponding degradation type information to train a preset model. This allows the preset model to learn the correlation between the capacity retention rate data sequences of the target vehicles and the degradation type information. Subsequently, the capacity retention rate data sequences of the target vehicles are input into the abnormal degradation identification model of the vehicle-mounted power batteries obtained after training. This model can identify the degradation type information of the target vehicles, solving the problem in related technologies that cannot detect the degradation type of vehicle-mounted power batteries.

[0042] This embodiment provides a method for constructing an abnormal degradation identification model for vehicle-mounted power batteries, which can be used in the aforementioned server. Figure 2 This is a flowchart of a method for constructing an abnormal degradation identification model for vehicle-mounted power batteries according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0043] Step S201: Obtain capacity retention rate data sequences for multiple target vehicles. These target vehicles are of the same model. The capacity retention rate data sequences are used to characterize the change in capacity retention rate over time when the on-board power battery of the corresponding target vehicle experiences degradation. For details, please refer to [link to relevant documentation]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0044] Specifically, step S201 includes:

[0045] Step S2011: Obtain historical data sequences of capacity retention rates for multiple vehicles, where the vehicles are of the same model.

[0046] In some optional implementations, step S2011 above includes:

[0047] Step a1: Obtain historical capacity retention rate data for multiple vehicles. The historical capacity retention rate data includes the capacity retention rate data and the corresponding timestamp.

[0048] For example, in this embodiment of the application, multiple vehicles have the same model. The historical data of capacity retention rate of multiple vehicles under one model is extracted. The data fields include vehicle unique identifier code, timestamp, and capacity retention rate.

[0049] Step a2: Clean the historical data of capacity retention rate of each measurement using a preset data cleaning method to obtain the cleaned historical data of capacity retention rate of each vehicle.

[0050] For example, in the embodiments of this application, the preset data cleaning method may include, but is not limited to, the principle of box plot processing outliers. The outliers of the capacity retention rate historical data are cleaned according to the box plot principle and filled with null values ​​to obtain the cleaned capacity retention rate historical data.

[0051] Step a3: Fill in the missing values ​​in the historical data of capacity retention rate after cleaning for each vehicle to obtain the corresponding historical data of capacity retention rate after filling.

[0052] For example, in this embodiment of the application, missing values ​​are filled with the previous non-empty value sorted in ascending time. The filled data is resampled, and the missing data after resampling is filled with the mean of historical data with a forward sliding window of 7. If the window cannot be 7, the maximum value that can be taken is used to obtain the filled historical data of capacity retention.

[0053] Step a4: Sort the historical capacity retention rate data of each vehicle after filling according to the timestamp to obtain a sequence of historical capacity retention rate data for multiple vehicles.

[0054] Step S2012: Analyze the historical data sequence of capacity retention rate of multiple vehicles to identify multiple target vehicles among the multiple vehicles.

[0055] For example, the historical data sequences of capacity retention rates of multiple vehicles are analyzed, and vehicles with anomalies in their historical data sequences of capacity retention rates are identified as target vehicles.

[0056] In some optional implementations, step S2012 above includes:

[0057] Step b1: Calculate multiple incremental values ​​for each vehicle based on the historical data sequence of capacity retention rate of each vehicle. The incremental values ​​are calculated from the historical data of capacity retention rate of the corresponding vehicle at the first time and the historical data of capacity retention rate at the second time. The second time is the time immediately preceding the first time.

[0058] For example, in the embodiments of this application, when calculating multiple incremental values ​​corresponding to the historical data sequence of capacity retention rate of each vehicle, the value of the current row is subtracted from the value of the previous row for the capacity retention rate of the vehicle, the row is used to represent different times, and then the negative operation (i.e., taking the opposite number) is performed to obtain the final incremental value of capacity retention rate.

[0059] Step b2: Calculate the average and standard deviation of the multiple incremental values ​​corresponding to multiple vehicles.

[0060] Step b3: Determine the abnormal degradation threshold based on the average and standard deviation of multiple incremental values ​​corresponding to multiple vehicles.

[0061] For example, in this embodiment of the application, the abnormal degradation threshold is calculated based on the number of data entries, average value, and standard deviation of incremental values ​​for multiple vehicles under a single vehicle model. Specifically, the calculation is performed on a monthly rolling basis. Let n be the number of data entries for the previous month, and m be the number of data entries for the current month. The average value for the previous month is... The average for this month is The standard deviation for last month was σ x The standard deviation for this month is σ. y New number of data points: m+n; New average value: The new standard deviation is calculated using the following formula (1):

[0062]

[0063] The new threshold for abnormal decline is the new mean + 3 × the new standard deviation.

[0064] Step b4: Compare the multiple incremental values ​​of each vehicle with the abnormal decay threshold to obtain the comparison results.

[0065] Step b5: Based on the comparison results, vehicles with incremental values ​​greater than the abnormal decay threshold are identified as target vehicles.

[0066] For example, in this application embodiment, when any vehicle has an incremental value greater than the abnormal degradation threshold, it indicates that the vehicle's on-board power battery has degraded, and that vehicle is designated as the target vehicle.

[0067] Step S2013: Use the historical data sequence of capacity retention rate corresponding to each target vehicle as the capacity retention rate data sequence of the corresponding target vehicle.

[0068] Step S202 involves analyzing the capacity retention rate data sequences of multiple target vehicles to determine the degradation type of the on-board power battery for each target vehicle. For details, please refer to [link to relevant documentation]. Figure 1 Step S102 of the illustrated embodiment will not be described again here.

[0069] Step S203: Associate the capacity retention rate data sequences of multiple target vehicles with the corresponding decay type information to obtain an associated dataset.

[0070] Specifically, step S203 includes:

[0071] Step S2031: Determine the corresponding degradation type identifier for each target vehicle. The degradation type identifier is used to identify the degradation type of the corresponding target vehicle.

[0072] For example, in the embodiments of this application, the decay type corresponding to each target vehicle is divided into two categories: 0 is used to represent non-abnormal decay, and 1 is used to represent abnormal decay.

[0073] Step S2032: Associate the data sequences of each target vehicle capacity retention rate with the corresponding decline type identifier to obtain the associated dataset.

[0074] Step S204: Train the preset model using the associated dataset until preset conditions are met, thus obtaining the vehicle power battery abnormal degradation identification model. For details, please refer to [link to relevant documentation]. Figure 1 Step S104 of the illustrated embodiment will not be described again here.

[0075] This embodiment provides a method for identifying abnormal degradation of vehicle-mounted power batteries, which can be used in the aforementioned server. Figure 3 This is a flowchart of a method for identifying abnormal degradation of vehicle-mounted power batteries according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps:

[0076] Step S301: Obtain the capacity retention rate data sequence of the target vehicle to be identified.

[0077] For example, the target vehicle to be identified can be any vehicle that needs to be identified for abnormal degradation of its on-board power battery.

[0078] Specifically, step S301 includes:

[0079] Step c1: Obtain the capacity retention rate data sequence of the vehicle to be identified.

[0080] For example, the vehicle to be identified can be any vehicle for which it is necessary to determine whether the on-board power battery has experienced abnormal degradation.

[0081] Step c2: Calculate multiple incremental values ​​for the vehicle to be identified based on the capacity retention rate data sequence of the vehicle to be identified.

[0082] Step c3: If the number of multiple incremental values ​​is greater than a preset threshold, and there is an incremental value among the multiple incremental values ​​that is greater than the abnormal decay threshold, then the capacity retention rate data of the vehicle to be identified is used as the capacity retention rate data sequence of the target vehicle to be identified.

[0083] For example, in this embodiment of the application, the preset threshold may include, but is not limited to, 50. When the number of multiple incremental values ​​is greater than 50, and there is an incremental value of the abnormal degradation threshold, the vehicle to be identified can be determined to be a suspected abnormal degradation vehicle, and the capacity retention rate data of the vehicle to be identified is used as the capacity retention rate data sequence of the target vehicle to be identified. If the number of multiple incremental values ​​is less than 50, or there is no incremental value greater than the abnormal degradation threshold among the multiple incremental values, the on-board power battery of the vehicle to be identified is determined to be in normal degradation.

[0084] Step S302: Input the capacity retention rate data sequence of the target vehicle to be identified into the vehicle power battery abnormal degradation identification model, so that the vehicle power battery abnormal degradation identification model outputs the vehicle power battery degradation type information corresponding to the target vehicle to be identified. The vehicle power battery abnormal degradation identification model is constructed by the vehicle power battery abnormal degradation identification model construction method of the above embodiment.

[0085] For example, the capacity retention rate data sequence of the target vehicle to be identified is input into the vehicle power battery abnormal degradation identification model, and the model will output the corresponding vehicle power battery degradation type information.

[0086] Step S303: Determine the abnormal degradation identification result of the on-board power battery based on the degradation type information of the on-board power battery corresponding to the target vehicle to be identified.

[0087] For example, in this embodiment of the application, when the output result of the model is 0, it is determined that the on-board power battery of the target vehicle to be identified is not abnormally degraded; when the output result of the model is 1, it can be determined that the on-board power battery of the target vehicle to be identified is abnormally degraded.

[0088] This embodiment also provides a device for constructing an abnormal degradation identification model for vehicle-mounted power batteries. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0089] This embodiment provides a device for constructing an abnormal degradation identification model for vehicle-mounted power batteries, such as... Figure 4 As shown, it includes:

[0090] The first acquisition module 401 is used to acquire the capacity retention rate data sequence of multiple target vehicles. The multiple target vehicles are of the same model. The capacity retention rate data sequence of multiple target vehicles is used to characterize the change in the capacity retention rate of the on-board power battery of the corresponding target vehicle over time when it degrades.

[0091] Analysis module 402 is used to analyze the capacity retention rate data sequence of multiple target vehicles to determine the degradation type information of the on-board power battery corresponding to each target vehicle.

[0092] The association module 403 is used to associate the capacity retention rate data sequences of multiple target vehicles with the corresponding decay type information to obtain an association dataset;

[0093] Training module 404 is used to train a preset model using an associated dataset until preset conditions are met, thereby obtaining an abnormal degradation identification model for vehicle power batteries.

[0094] In some optional implementations, the first acquisition module 401 includes:

[0095] The first acquisition submodule is used to acquire historical data sequences of capacity retention rates for multiple vehicles, all of which are of the same model.

[0096] The analysis submodule is used to analyze the historical data sequence of capacity retention rate of multiple vehicles and identify multiple target vehicles among them.

[0097] The first determining submodule is used to take the historical data sequence of capacity retention rate corresponding to each target vehicle as the capacity retention rate data sequence of the corresponding target vehicle.

[0098] In some optional implementations, the analysis submodule includes:

[0099] The first calculation unit is used to calculate multiple incremental values ​​for the corresponding vehicle based on the historical data sequence of capacity retention rate of each vehicle. The incremental values ​​are calculated from the historical data of capacity retention rate of the corresponding vehicle at the first time and the historical data of capacity retention rate at the second time. The second time is the time before the first time.

[0100] The second calculation unit is used to calculate the average and standard deviation of multiple incremental values ​​corresponding to multiple vehicles;

[0101] The first determining unit is used to determine the abnormal decay threshold based on the average and standard deviation of multiple incremental values ​​corresponding to multiple vehicles respectively;

[0102] The comparison unit is used to compare multiple incremental values ​​of each vehicle with the abnormal decay threshold to obtain the comparison results;

[0103] The second determining unit is used to identify vehicles with incremental values ​​greater than the abnormal decay threshold as target vehicles based on the comparison results.

[0104] In some optional implementations, the first acquisition submodule includes:

[0105] The acquisition unit is used to acquire historical capacity retention rate data for multiple vehicles. The historical capacity retention rate data includes capacity retention rate data and corresponding timestamps.

[0106] The cleaning unit is used to clean the historical data of capacity retention rate of each measurement using a preset data cleaning method, so as to obtain the historical data of capacity retention rate of each vehicle after cleaning.

[0107] The filling unit is used to fill missing values ​​in the historical data of capacity retention rate after cleaning of each vehicle, so as to obtain the historical data of capacity retention rate after filling of the corresponding vehicle.

[0108] The sorting unit is used to sort the historical capacity retention rate data of each vehicle after filling according to the timestamp, so as to obtain a sequence of historical capacity retention rate data of multiple vehicles.

[0109] In some optional implementations, the aforementioned associated module 403 includes:

[0110] The second determination submodule is used to determine the corresponding degradation type identifier for each target vehicle. The degradation type identifier is used to determine the degradation type information of the corresponding target vehicle.

[0111] The association submodule is used to associate the data sequences of each target vehicle capacity retention rate with the corresponding decline type identifier to obtain the associated dataset.

[0112] This embodiment provides a device for identifying abnormal degradation of vehicle power batteries, such as... Figure 5 As shown, it includes:

[0113] The second acquisition module 501 is used to acquire the capacity retention rate data sequence of the target vehicle to be identified;

[0114] The identification module 502 is used to input the capacity retention rate data sequence of the target vehicle to be identified into the vehicle power battery abnormal degradation identification model, so that the vehicle power battery abnormal degradation identification model outputs the vehicle power battery degradation type information corresponding to the target vehicle to be identified. The vehicle power battery abnormal degradation identification model is constructed by the vehicle power battery abnormal degradation identification model construction method of the above embodiment.

[0115] The determination module 503 is used to determine the abnormal degradation identification result of the on-board power battery based on the degradation type information of the on-board power battery corresponding to the target vehicle to be identified.

[0116] In some optional implementations, the second acquisition module 501 includes:

[0117] The second acquisition submodule is used to acquire the capacity retention rate data sequence of the vehicle to be identified;

[0118] The calculation submodule is used to calculate multiple incremental values ​​of the vehicle to be identified based on the capacity retention rate data sequence of the vehicle to be identified;

[0119] The third determination submodule is used to take the capacity retention rate data of the vehicle to be identified as the capacity retention rate data sequence of the target vehicle if the number of multiple incremental values ​​is greater than a preset threshold and there is an incremental value among the multiple incremental values ​​that is greater than the abnormal decline threshold.

[0120] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0121] In this embodiment, the on-board power battery abnormal degradation identification model construction device and the on-board power battery abnormal degradation identification device are presented in the form of functional units. Here, a unit refers to an ASIC (Application Specific Integrated Circuit), a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0122] This invention also provides a computer device having the above-described features. Figure 4 The device for constructing an abnormal degradation identification model for vehicle-mounted power batteries shown above, or having the above-mentioned features, may be used. Figure 5 The image shows an onboard power battery abnormal degradation identification device.

[0123] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 6 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 6 Take a processor 10 as an example.

[0124] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0125] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0126] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0127] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0128] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0129] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0130] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for constructing an identification model for abnormal degradation of vehicle-mounted power batteries, characterized in that, The method includes: Acquire a capacity retention rate data sequence of multiple target vehicles, wherein the multiple target vehicles are of the same model, and the capacity retention rate data sequence of the multiple target vehicles is used to characterize the change in capacity retention rate over time when the on-board power battery of the corresponding target vehicle degrades. The capacity retention rate data sequence of the multiple target vehicles is analyzed to determine the degradation type information of the on-board power battery corresponding to each target vehicle. The capacity retention rate data sequences of the multiple target vehicles are correlated with the corresponding decay type information to obtain a correlated dataset; The preset model is trained using the associated dataset until the preset conditions are met, thus obtaining the vehicle power battery abnormal degradation identification model.

2. The method according to claim 1, characterized in that, The steps for obtaining a sequence of capacity retention rate data for multiple target vehicles include: Obtain historical data sequences of capacity retention rates for multiple vehicles of the same model; Analyze the historical data sequence of capacity retention rate of the multiple vehicles to identify multiple target vehicles among the multiple vehicles; The historical data sequence of capacity retention rate corresponding to each target vehicle is used as the capacity retention rate data sequence of the corresponding target vehicle.

3. The method according to claim 2, characterized in that, The steps of analyzing the historical data sequence of capacity retention rates of the multiple vehicles and identifying multiple target vehicles among the multiple vehicles include: Based on the historical data sequence of capacity retention rate of each vehicle, multiple incremental values ​​for the corresponding vehicle are calculated. The incremental values ​​are calculated from the historical data of capacity retention rate of the corresponding vehicle at the first time and the historical data of capacity retention rate at the second time, where the second time is the time preceding the first time. Calculate the average and standard deviation of multiple incremental values ​​corresponding to multiple vehicles; The abnormal degradation threshold is determined based on the average and standard deviation of the multiple incremental values ​​corresponding to the multiple vehicles; The multiple incremental values ​​of each vehicle are compared with the abnormal decay threshold to obtain the comparison results; Based on the comparison results, vehicles with an incremental value greater than the abnormal degradation threshold are identified as target vehicles.

4. The method according to claim 2, characterized in that, The steps for obtaining historical data sequences of capacity retention rates for multiple vehicles include: Acquire historical capacity retention rate data for multiple vehicles, wherein the historical capacity retention rate data includes capacity retention rate data and corresponding timestamps; The historical data of capacity retention rate of each measurement is cleaned using a preset data cleaning method to obtain the historical data of capacity retention rate of each vehicle after cleaning. Missing values ​​were filled into the historical data of capacity retention rate of each vehicle after cleaning to obtain the corresponding historical data of capacity retention rate after filling. The historical capacity retention rate data of each vehicle after filling is sorted according to the timestamp to obtain a sequence of historical capacity retention rate data for multiple vehicles.

5. The method according to claim 1, characterized in that, The step of associating the capacity retention rate data sequences of the multiple target vehicles with the corresponding degradation type information to obtain the associated dataset includes: Determine the corresponding degradation type identifier for each target vehicle, wherein the degradation type identifier is used to correspond to the degradation type information of the target vehicle; By associating the data sequences of each target vehicle capacity retention rate with the corresponding decline type identifier, an associated dataset is obtained.

6. A method for identifying abnormal degradation of vehicle-mounted power batteries, characterized in that, The method includes: Obtain the capacity retention rate data sequence of the target vehicle to be identified; The capacity retention rate data sequence of the target vehicle to be identified is input into the vehicle power battery abnormal degradation identification model, so that the vehicle power battery abnormal degradation identification model outputs the vehicle power battery degradation type information corresponding to the target vehicle to be identified. The vehicle power battery abnormal degradation identification model is constructed by the vehicle power battery abnormal degradation identification model construction method as described in any one of claims 1 to 5. The abnormal degradation identification result of the on-board power battery is determined based on the degradation type information of the target vehicle.

7. The method according to claim 6, characterized in that, The steps for obtaining the capacity retention rate data sequence of the target vehicle to be identified include: Obtain the capacity retention rate data sequence of the vehicle to be identified; Calculate multiple incremental values ​​for the vehicle to be identified based on the capacity retention rate data sequence of the vehicle to be identified; If the number of the plurality of incremental values ​​is greater than a preset threshold, and there is an incremental value among the plurality of incremental values ​​that is greater than an abnormal decay threshold, then the capacity retention rate data sequence of the vehicle to be identified is taken as the capacity retention rate data sequence of the target vehicle to be identified.

8. A device for constructing a model to identify abnormal degradation of vehicle-mounted power batteries, characterized in that, The device includes: The first acquisition module is used to acquire a capacity retention rate data sequence of multiple target vehicles. The multiple target vehicles are of the same model. The capacity retention rate data sequence of the multiple target vehicles is used to characterize the change in capacity retention rate over time when the on-board power battery of the corresponding target vehicle degrades. The analysis module is used to analyze the capacity retention rate data sequence of the multiple target vehicles to determine the degradation type information of the on-board power battery corresponding to each target vehicle. The association module is used to associate the capacity retention rate data sequences of the multiple target vehicles with the corresponding decay type information to obtain an association dataset; The training module is used to train the preset model using the associated dataset until the preset conditions are met, thereby obtaining the vehicle power battery abnormal degradation identification model.

9. A device for identifying abnormal degradation of vehicle power batteries, characterized in that, The device includes: The second acquisition module is used to acquire the capacity retention rate data sequence of the target vehicle to be identified; The identification module is used to input the capacity retention rate data sequence of the target vehicle to be identified into the vehicle power battery abnormal degradation identification model, so that the vehicle power battery abnormal degradation identification model outputs the vehicle power battery degradation type information corresponding to the target vehicle to be identified. The vehicle power battery abnormal degradation identification model is constructed by the vehicle power battery abnormal degradation identification model construction method as described in any one of claims 1 to 5. The determination module is used to determine the abnormal degradation identification result of the on-board power battery based on the degradation type information of the on-board power battery corresponding to the target vehicle to be identified.

10. A computer device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the vehicle power battery abnormal degradation identification model construction method according to any one of claims 1 to 5, or the vehicle power battery abnormal degradation identification method according to claim 6 or 7.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, which are used to cause the computer to execute the method for constructing an abnormal degradation identification model for a vehicle power battery as described in any one of claims 1 to 5, or to execute the method for identifying abnormal degradation of a vehicle power battery as described in claim 6 or 7.

Images