Battery SOH evaluation method and device and vehicle

Abstract

The invention provides a battery SOH evaluation method and device and a vehicle, and relates to the technical field of batteries, and the method comprises the steps: receiving a vehicle information data set; dividing the vehicle information data set through a cross validation method to obtain a first data set; training a DA-RNN model by using the first data set to obtain a DA-RNN training model; optimizing the DA-RNN training model through a grid search method to obtain a battery SOH evaluation model; and evaluating battery information of the vehicle by using the battery SOH evaluation model to obtain a battery SOH evaluation value. According to the battery SOH evaluation method and device and the vehicle provided by the invention, the SOH value of the battery can be known in time, and the driving safety of the electric vehicle is ensured.

Description

Technical Field

[0001] The present invention relates to the field of battery technology, and in particular to a battery SOH evaluation method, device and vehicle. Background Art

[0002] Currently, power batteries are widely used in vehicles, aircraft, ships, energy storage systems and other fields.

[0003] During use, evaluating the battery SOH value can assess the battery safety. When the battery SOH value is lower than a certain value, it can be considered that the battery is no longer suitable for continued use and should be replaced or repaired in a timely manner, which is conducive to ensuring the safe driving of electric vehicles. Summary of the invention

[0004] At present, with the rapid development of electric vehicles and energy storage systems, the performance and safety of power batteries have become key issues. By evaluating the SOH value of the battery, it is possible to quickly determine whether the battery is suitable for continued use. The purpose of the present invention is to provide a battery SOH evaluation method, a battery SOH evaluation device, and a vehicle equipped with a battery SOH evaluation device for the above-mentioned problems. According to the actual use of the vehicle, the present invention divides a plurality of charging current ranges and charging time ranges in advance, calculates the partial charging capacity within each specified range, and calculates the maximum value of the partial charging capacity within each specified range, and uses the maximum value to replace the rated partial charging capacity of the power battery to correct the remaining partial charging capacity to obtain the SOH evaluation value. This SOH evaluation model uses the DA-RNN algorithm based on the recursive neural network time series prediction of the dual-stage attention as the framework, extracts characteristic variables and partial charging capacity from the historical operation data of the vehicle to train the DA-RNN model, and then uses the grid search method to optimize the model parameters to obtain the optimal parameter model to predict the SOH value of the vehicle power battery.

[0005] Based on the above-mentioned purpose, the present invention provides a battery SOH evaluation method, which may include: receiving a vehicle information data group; dividing the vehicle information data group by a cross-validation method to obtain a first data set; using the first data set to train a DA-RNN model to obtain a DA-RNN training model; optimizing the DA-RNN training model by a grid search method to obtain a battery SOH evaluation model; using the battery SOH evaluation model to evaluate the battery information of the vehicle to obtain a battery SOH evaluation value.

[0006] In one embodiment, receiving a vehicle information data group may include: receiving vehicle information; obtaining a first segment from the vehicle information, the first segment being a charging and discharging segment; obtaining a second segment from the first segment, the second segment being a charging segment; obtaining a third segment from the first segment, the third segment being a discharging segment; verifying whether a second charging voltage range obtained from the second segment belongs to the first charging voltage range, and if not, deleting the first segment; otherwise, obtaining a first portion of the charging capacity within the first charging voltage range, the first portion of the charging capacity referring to the total amount of electricity charged into the vehicle within the first charging voltage range; and extracting a factor affecting capacity attenuation from the first segment as a vehicle information data group.

[0007] In one embodiment, the vehicle information data set may include: battery probe temperature within the charging range, single cell consistency, charging time used to charge partial capacity, discharge current distribution probability, charging current, and vehicle cumulative mileage.

[0008] In one embodiment, the calculation method of the discharge current distribution probability may be: defining the discharge current distribution probability as P dc ; According to the vehicle operation conditions, four current ranges are divided into <0, 0~0.5C, 0.5C~1C and greater than 1C; the proportion of the number of data rows in the four current ranges to the total number of data rows in the discharge segment is recorded as P dc1 , P dc2 , P dc3 , P dc4 ;but, ; in, is the number of data rows corresponding to the four current ranges, is the total number of data rows of the collected discharge segments.

[0009] In one embodiment, the first charging voltage range may be the voltage value corresponding to when the charge is in the first range, wherein the first range is the range of 40% to 80% of the total charge of the battery; the second charging voltage range may be the voltage range from the starting total charging voltage to the ending total charging voltage, wherein the starting total charging voltage and the ending total charging voltage are data extracted from the charging segments respectively.

[0010] In one embodiment, dividing the vehicle information data group by cross-validation method to obtain a first data set may include: 80% of the data before division is used as a training set, and 20% of the data after division is used as a test set. When the error between the model test result and the actual SOH of the battery is within the range of ±5%, the test is completed; optimizing the DA-RNN training model by grid search method to obtain the optimal parameters of the battery SOH evaluation model, the embedding layer size is 256, and the learning rate is 0.001.

[0011] In one embodiment, a battery SOH evaluation model is used to evaluate the battery information of a vehicle, and obtaining a battery SOH evaluation value may include: dividing the vehicle information by multiple charging current ranges and charging time ranges; counting the partial charging capacity of each charging current range and each charging time range within a predetermined driving mileage of multiple vehicles, wherein the partial charging capacity refers to the total amount of electricity charged to the vehicle within each charging current range and each charging time range; counting the maximum value of the partial charging capacity within each charging current range and each charging time range; replacing the rated partial charging capacity of the battery with the maximum value of the partial charging capacity, and correcting the remaining partial charging capacity to obtain a battery SOH evaluation value.

[0012] In one embodiment, the rated partial charging capacity of the battery may refer to the total amount of electricity charged into the vehicle within the second charging voltage range, and the remaining partial charging capacity may refer to the total amount of remaining electricity obtained by subtracting the partial charging capacity from the rated partial charging capacity.

[0013] According to another aspect of the present invention, a battery SOH evaluation device is provided, which may include: an input unit for receiving vehicle information; an evaluation unit for executing a battery SOH evaluation method according to an embodiment of the present invention and generating a battery SOH evaluation value; and an output unit for outputting a battery SOH evaluation value.

[0014] According to another aspect of the present invention, a vehicle is provided, which may include the battery SOH evaluation device according to the embodiment of the present invention.

[0015] Based on the embodiments of the present invention, the SOH value of the battery can be known in time, and the user can be prompted to maintain the battery to ensure the driving safety of the electric vehicle. In addition, the power battery can be recycled according to the situation with reference to the various parameter states of the battery to improve the resource utilization rate of the battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 4 is a flow chart of battery SOH evaluation according to an embodiment of the present invention.

[0018] Figure 2 The flowchart of receiving vehicle information data group is shown in FIG.

[0019] Figure 3 It is a schematic diagram showing the data structure of a vehicle information data group.

[0020] Figure 4 It is a flow chart showing the method for calculating the probability of discharge current distribution.

[0021] Figure 5 It is a schematic diagram showing the charging voltage range.

[0022] Figure 6 The flowchart is a diagram showing how to obtain a first data set by dividing the vehicle information data set through a cross-validation method.

[0023] Figure 7 It is a schematic diagram showing the partitioning of the data set and the optimal embedding layer size and learning rate.

[0024] Figure 8 It is a flow chart showing how to use the evaluation model to evaluate vehicle battery information and obtain a battery SOH evaluation value.

[0025] Fig. 9 It is a schematic diagram showing the rated partial charging capacity and the remaining partial charging capacity.

[0026] Fig.10 It is a schematic diagram showing the structure of a battery SOH evaluation device.

[0027] Fig.11 It is a schematic diagram of the vehicle structure.

[0028] Description of reference numerals: 30: Vehicle information data group; 31: Battery probe temperature within the charging range; 32: Single cell consistency; 33: Charging time for partial capacity; 34: Discharge current distribution probability; 35: Charging current; 36: Vehicle cumulative mileage; A: Rated partial charging capacity; B: Partial charging capacity; C: Remaining partial charging capacity; 9: Battery SOH evaluation device; 901: Input unit; 902: Evaluation unit; 903: Output unit; 10: Vehicle. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] Combine the following Figure 1-Figure 11 A battery SOH evaluation method, a battery SOH evaluation device, and a vehicle equipped with the battery SOH evaluation device of the present invention are described.

[0031] Figure 1 4 is a flow chart of battery SOH evaluation according to an embodiment of the present invention.

[0032] like Figure 1 As shown, according to the battery SOH evaluation method according to the embodiment of the present invention, firstly, a vehicle information data set may be received in step S101.

[0033] The receiving method can be downloaded from the vehicle system APP, directly received from the vehicle through a USB interface, or transmitted using Bluetooth, Wifi, etc.

[0034] In step S102 , the vehicle information data set may be divided by a cross-validation method to obtain a first data set.

[0035] In step S102, the first data set can also be obtained by dividing the vehicle information data group through ten-fold cross validation, leave-one-out cross validation, leave-P-out cross validation, k-fold cross validation, stratified k-fold cross validation, repeated k-fold cross validation, Monte Carlo cross validation, time series cross validation, leave-one-group cross validation, leave-P-group cross validation, and self-service sampling cross validation.

[0036] In step S103, the DA-RNN model may be trained using the first data set to obtain a DA-RNN training model.

[0037] In step S103, the first data set can also be used to train an LSTM (Long Short-Term Memory) model, a GRU (Gated Recurrent Unit) model, an Attention-Based RNN model, a Seq2Seq (Sequence-to-Sequence) Model with Attention model, a Transformer model, a CRNN (Convolutional Recurrent Neural Network) model, a T-RNN (Temporal Recurrent Neural Network) model, and a DeepAR (Deep Attention Recurrent Network) model.

[0038] In step S104, the battery SOH evaluation model can be obtained by optimizing the DA-RNN training model through the grid search method.

[0039] In step S104, the battery SOH evaluation model can also be obtained by optimizing the DA-RNN training model through random search, Bayesian optimization, genetic algorithm, particle swarm optimization (PSO), gradient descent, random grid search, and halving grid search.

[0040] In step S105 , the battery SOH evaluation model may be used to evaluate the battery information of the vehicle to obtain a battery SOH evaluation value.

[0041] Figure 2 The flowchart of receiving vehicle information data group is shown in FIG.

[0042] like Figure 2 As shown, step S201 corresponds to Figure 1 In step S101 of Figure 2 In step S201, receiving the vehicle information data set may include: In step S2011, vehicle information may be received, which may be downloaded from a vehicle system APP, directly received from the vehicle via a USB interface, or transmitted via Bluetooth, Wifi, or the like.

[0043] In step S2012, the charging and discharging segments may be acquired from the vehicle information.

[0044] In step S2013, the charging segment may be acquired from the vehicle information.

[0045] In step S2014, the discharge segment may be acquired from the vehicle information.

[0046] In step S2015 , it may be verified whether the second charging voltage range obtained from the charging segment belongs to the first charging voltage range.

[0047] If it does not belong to the above, that is, in the case of "No", the process proceeds to step S2016, and the charging and discharging segment can be deleted.

[0048] Otherwise, in the case of yes, that is, in the case of "yes", the process proceeds to step S2017, and the first partial charging capacity can be obtained within the first charging voltage range.

[0049] In step S2018, factors affecting capacity decay may be extracted from the charging and discharging segments as a vehicle information data set.

[0050] According to this embodiment, unnecessary charging and discharging segments can be deleted to ensure calculation accuracy and improve calculation speed.

[0051] Figure 3 It is a schematic diagram showing the data structure of a vehicle information data group.

[0052] like Figure 3 As shown, the vehicle information data set 30 may include: battery probe temperature 31 within the charging range, single cell consistency 32, charging time 33 for charging partial capacity, discharge current distribution probability 34, charging current 35, and vehicle cumulative mileage 36.

[0053] It should be noted that the data included in the vehicle information data group can be increased or decreased as needed.

[0054] According to this embodiment, characteristic variables can be extracted from the historical operation data of the vehicle as needed. Based on the characteristic variables, a DA-RNN model that meets the vehicle characteristics can be established, and the DA-RNN model can be used to obtain a battery SOH evaluation model that meets the vehicle characteristics, which can greatly improve the accuracy and efficiency of SOH evaluation.

[0055] Figure 4 It is a flow chart showing the method for calculating the probability of discharge current distribution.

[0056] like Figure 4 As shown, in step S401, the discharge current distribution probability can be defined as P dc .

[0057] In step S402 , four current ranges of <0, 0-0.5C, 0.5C-1C and greater than 1C may be divided according to the vehicle operation conditions.

[0058] In step S402, less than four current ranges may be divided, or more than four current ranges may be divided. The divided current ranges may be, for example, three current ranges of <0, 0-0.8C, and greater than 0.8C. Alternatively, the divided current ranges may be, for example, five current ranges of <0, 0-0.4C, 0.4C-0.8C, 0.8C-1.2C, and greater than 1.2C.

[0059] In step S403, the proportion of the number of data rows in the four current ranges to the total number of data rows in the discharge segment can be set as P dc1 , P dc2 , P dc3 , P dc4 ,but, ; in, The number of data rows corresponding to the four current ranges can be N dcharge It can be the total number of data rows of the collected discharge segments.

[0060] Figure 4 correspond Figure 3 A method for calculating the probability of discharge current distribution 34.

[0061] According to this embodiment, the discharge current distribution probability in the vehicle information data set can be accurately calculated, which helps to improve the accuracy of receiving the vehicle information data set, thereby laying a solid foundation for the subsequent calculation of an accurate battery SOH value.

[0062] Figure 5 It is a schematic diagram showing the charging voltage range.

[0063] like Figure 5 As shown in (a), the first charging voltage range may be a voltage value corresponding to a charge level in the first range, wherein the first range may be a range of 40% to 80% of the total charge level of the battery. The first range may also be a range defined as required. In this embodiment, the preferred range is a range of 40% to 80% of the total charge level of the battery.

[0064] like Figure 5As shown in (b), the second charging voltage range may be a voltage range from a starting charging total voltage to a cutting-off charging total voltage, wherein the starting charging total voltage and the cutting-off charging total voltage are data extracted from the charging segments, respectively. The starting charging total voltage and the cutting-off charging total voltage may also be self-defined data.

[0065] The first charging voltage range corresponds to Figure 2 The second charging voltage range corresponds to the first charging voltage range in step S215. Figure 2 The second charging voltage range in step S215.

[0066] According to this embodiment, the definitions of the first charging voltage range and the second charging voltage range can be clarified, the ambiguity of data definition can be eliminated, and the consistency of data definition can be achieved, thereby promoting the standardized development of the industry.

[0067] Figure 6 The flowchart is a diagram showing how to obtain a first data set by dividing the vehicle information data set through a cross-validation method.

[0068] like Figure 6 As shown, in step S601, dividing the vehicle information data group by a cross-validation method to obtain a first data set may include: Step S6011, the first 80% of the data can be divided into a training set, and the last 20% of the data can be divided into a test set. When the error between the model test result and the actual SOH of the battery is within the range of ±5%, the test is completed; In step S6012, the optimal parameters of the battery SOH evaluation model can be obtained by optimizing the DA-RNN training model through the grid search method, with an embedding layer size of 256 and a learning rate of 0.001.

[0069] Step S601 corresponds to Figure 1 Step S102 in .

[0070] Figure 7 It is a schematic diagram showing the partitioning of the data set and the optimal embedding layer size and learning rate. Figure 7 As shown, Figure 7 (a) shows the result of dividing the data set according to different proportions. The data set can be divided according to different proportions as needed. In this embodiment, the first 80% of the data is divided into a training set and the last 20% of the data is divided into a test set, which will achieve the best performance. When the error between the model test result and the actual SOH of the battery is within the range of ±5%, the test is completed.

[0071] Figure 7 (b) is a graph showing the effects of different learning rates. Different learning rates can be set. In this embodiment, the best performance is achieved when the learning rate is 0.001.

[0072] Figure 7 (c) is a diagram showing the effects of different embedding layer sizes. The embedding layer can be set to different sizes. In this embodiment, the best performance is achieved when the embedding layer size is 256.

[0073] According to this embodiment, dividing the data set according to the optimal ratio can ensure that the model has enough data to learn during the training process, while leaving data for model verification and testing, so as to evaluate the generalization ability of the model. Learning at the optimal learning rate can speed up the convergence of the model, avoid falling into the local optimal solution, and reduce the shock during the training process. Setting the optimal embedding layer size helps the model learn and capture the intrinsic characteristics of the data more effectively. According to this embodiment, by optimizing the key factors of model training, the learning efficiency and prediction accuracy of the model are improved, while avoiding overfitting and underfitting, ensuring that the model has good generalization ability.

[0074] Figure 8 It is a flow chart showing how to use the evaluation model to evaluate vehicle battery information and obtain a battery SOH evaluation value.

[0075] Figure 8 Step S701 corresponds to Figure 1 Step S105 in .

[0076] like Figure 8 As shown, using the battery SOH evaluation model to evaluate the battery information of the vehicle, obtaining the battery SOH evaluation value may include: In step S7011, the vehicle information may be divided into multiple charging current ranges and charging time ranges, or may be divided into one charging current range and charging time range.

[0077] Step S7012, partial charging capacity of each charging current range and each charging time range within the scheduled driving mileage of multiple vehicles may be counted, wherein the partial charging capacity may refer to the total amount of electricity charged by the vehicle within each charging current range and each charging time range. The partial charging capacity of each charging current range and each charging time range within the scheduled driving mileage of one vehicle may also be counted.

[0078] In step S7013, the maximum values ​​of the partial charging capacities within each charging current range and each charging time range may be counted.

[0079] In step S7014, the rated partial charging capacity of the battery can be replaced by the maximum value of the partial charging capacity, and the remaining partial charging capacity can be corrected to obtain the battery SOH evaluation value.

[0080] According to this embodiment, by dividing the vehicle information into different ranges, the SOH value of the battery can be analyzed and evaluated more carefully. Replacing the rated partial charge capacity of the battery with the maximum value of the partial charge capacity and correcting the remaining partial charge capacity to obtain the battery SOH evaluation value can more accurately reflect the current capacity state of the battery and reduce the evaluation error caused by battery aging or capacity attenuation during use.

[0081] Fig. 9 It is a schematic diagram showing the rated partial charging capacity and the remaining partial charging capacity.

[0082] like Fig. 9 As shown, the rated partial charge capacity A of the battery may refer to the total amount of electricity charged into the vehicle within the second charging voltage range. Figure 5 As described in (b), the second charging voltage range may refer to a voltage range from a starting charging total voltage to a cutting-off charging total voltage.

[0083] like Fig. 9 As shown in (b), the remaining partial charging capacity C may refer to the total remaining power obtained by subtracting the partial charging capacity B from the rated partial charging capacity A. Figure 8 As described in step S7012 in , the partial charging capacity B may refer to the total amount of electricity charged into the vehicle within each charging current range and each charging time range.

[0084] According to this embodiment, it is crucial for the battery management system to clearly know the rated partial charge capacity and the remaining partial charge capacity of the battery, which can help the system more accurately evaluate the remaining life of the battery and optimize the battery usage and maintenance strategy.

[0085] Fig.10 It is a schematic diagram showing the structure of a battery SOH evaluation device.

[0086] like Fig.10 As shown, the battery SOH evaluation device 9 of the present invention may include: an input unit 901 , an evaluation unit 902 , and an output unit 903 .

[0087] The input unit 901 may receive vehicle information.

[0088] The evaluation unit 902 may utilize a battery SOH evaluation method and generate a battery SOH evaluation value.

[0089] The battery SOH evaluation method may include: receiving a vehicle information data group; dividing the vehicle information data group by a cross-validation method to obtain a first data set; using the first data set to train a DA-RNN model to obtain a DA-RNN training model; optimizing the DA-RNN training model by a grid search method to obtain a battery SOH evaluation model; using the battery SOH evaluation model to evaluate the battery information of the vehicle to obtain a battery SOH evaluation value.

[0090] The output unit 903 may output the battery SOH evaluation value when the evaluation unit 902 evaluates the battery SOH evaluation value.

[0091] Ways of outputting the battery SOH evaluation value may include: text output, image output, and sound output.

[0092] Fig.11 It is a schematic diagram of the vehicle structure.

[0093] like Fig.11 As shown, the vehicle 10 may include a battery SOH evaluation device 9. The battery SOH evaluation device 9 may include: an input unit that receives vehicle information; an evaluation unit that executes a battery SOH evaluation method and generates a battery SOH evaluation value; and an output unit that outputs the battery SOH evaluation value.

[0094] Among them, the battery SOH evaluation method may include: receiving a vehicle information data group; dividing the vehicle information data group by a cross-validation method to obtain a first data set; using the first data set to train a DA-RNN model to obtain a DA-RNN training model; optimizing the DA-RNN training model by a grid search method to obtain a battery SOH evaluation model; using the battery SOH evaluation model to evaluate the battery information of the vehicle to obtain a battery SOH evaluation value.

[0095] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A battery SOH evaluation method, characterized in that: include: receiving a vehicle information data group; Dividing the vehicle information data group by a cross-validation method to obtain a first data set; Using the first data set to train a DA-RNN model to obtain a DA-RNN training model; The battery SOH evaluation model is obtained by optimizing the DA-RNN training model through a grid search method; The battery SOH evaluation model is used to evaluate the battery information of the vehicle to obtain a battery SOH evaluation value.

2. The battery SOH evaluation method according to claim 1, characterized in that: The received vehicle information data group includes: Receive vehicle information; Acquire a first segment from the vehicle information, where the first segment is a charging and discharging segment; Acquire a second segment from the first segment, where the second segment is a charging segment; Acquire a third segment from the first segment, wherein the third segment is a discharge segment; verifying whether the second charging voltage range obtained from the second segment belongs to the first charging voltage range, If it does not belong to the above, delete the first segment; Otherwise, obtaining a first portion of the charging capacity within the first charging voltage range, where the first portion of the charging capacity refers to the total amount of electricity charged to the vehicle within the first charging voltage range; A capacity decay influencing factor is extracted from the first segment as the vehicle information data set.

3. The battery SOH evaluation method according to claim 2, characterized in that: The vehicle information data set includes: battery probe temperature within the charging range, single cell consistency, charging time used to charge partial capacity, discharge current distribution probability, charging current, and vehicle cumulative mileage.

4. The battery SOH evaluation method according to claim 3, characterized in that: The calculation method of the discharge current distribution probability is: The discharge current distribution probability is defined as P dc ; According to the vehicle operation conditions, four current ranges are divided into <0, 0~0.5C, 0.5C~1C and greater than 1C; The ratio of the number of data rows in the four current ranges to the total number of data rows in the discharge segment is recorded as P dc1 , P dc2 , P dc3 , P dc4 ;but, ； in, is the number of data rows corresponding to the four current ranges, N dcharge is the total number of data rows collected for the discharge segment.

5. The battery SOH evaluation method according to claim 3, characterized in that: The first charging voltage range is a voltage value corresponding to when the power is in the first range, wherein the first range is a range of 40% to 80% of the total power of the battery; The second charging voltage range is a voltage range from a starting charging total voltage to a cutting-off charging total voltage, wherein the starting charging total voltage and the cutting-off charging total voltage are data extracted from the charging segments respectively.

6. The battery SOH evaluation method according to claim 1, characterized in that: The step of dividing the vehicle information data group by a cross-validation method to obtain a first data set comprises: The first 80% of the data is divided into training sets, and the second 20% of the data is divided into test sets. When the error between the model test result and the actual SOH of the battery is within ±5%, the test is completed. The optimal parameters of the battery SOH evaluation model obtained by optimizing the DA-RNN training model through the grid search method are: the embedding layer size is 256, and the learning rate is 0.

001.

7. The battery SOH evaluation method according to claim 2, characterized in that: Using the battery SOH evaluation model to evaluate the battery information of the vehicle, obtaining the battery SOH evaluation value includes: Dividing the vehicle information into multiple charging current ranges and charging time ranges; Counting partial charging capacities of each of the charging current ranges and each of the charging time ranges within a predetermined driving mileage of a plurality of vehicles, wherein the partial charging capacity refers to the total amount of electricity charged by the vehicle within each of the charging current ranges and each of the charging time ranges; Counting the maximum values ​​of the partial charged capacities within each of the charging current ranges and each of the charging time ranges; The rated partial charging capacity of the battery is replaced by the maximum value of the partial charging capacity, and the remaining partial charging capacity is corrected to obtain the battery SOH evaluation value.

8. The battery SOH evaluation method according to claim 7, characterized in that: The rated partial charging capacity of the battery refers to the total amount of electricity charged into the vehicle within the second charging voltage range. The remaining partial charging capacity refers to the total remaining power obtained by subtracting the partial charging capacity from the rated partial charging capacity.

9. A battery SOH evaluation device, characterized in that: include: An input unit for receiving vehicle information; An evaluation unit, executing the battery SOH evaluation method according to claim 6 and generating a battery SOH evaluation value; as well as An output unit outputs the battery SOH evaluation value.

10. A vehicle, characterized in that: Includes the battery SOH evaluation device as claimed in claim 9.

Images