Method for determining the state of health of a power battery of an electric vehicle and server

Abstract

The application relates to the field of new energy technology, and discloses a method for determining the health state of a power battery of an electric vehicle and a server. The method comprises the following steps: obtaining battery data of the power battery and vehicle features of the electric vehicle; calculating a normal health state attenuation value of the power battery according to real-time battery correlation parameters and a normal attenuation model corresponding to the vehicle features; calculating a fault health state attenuation value of the power battery according to real-time fault type parameters and a fault attenuation model corresponding to the vehicle features; and determining a comprehensive health evaluation value of the power battery according to the normal health state attenuation value and the fault health state attenuation value. In the embodiment, the health state of the power battery can be quickly evaluated without controlling the power battery to perform charging and discharging, and without the first health state value of the power battery, so that the technical problem of low efficiency in evaluating the health state of the power battery in the prior art is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of new energy technology, in particular to a method for determining the state of health of a power battery of an electric vehicle and a server. BACKGROUND

[0002] As the main power source of new energy electric vehicles, the service life of the power battery is limited. The active material in the power battery naturally deteriorates during use, so the full capacity of the power battery gradually decreases. The industry often uses the state of health (SOH) of the battery to evaluate the service life of the power battery.

[0003] The existing methods for evaluating the SOH value of the power battery mainly include an electrochemical mechanism method and a big data artificial intelligence evaluation method. The electrochemical mechanism method analyzes the voltage, current and other data of the power battery through a certain condition of the charging and discharging process to obtain the SOH value of the power battery. Since the charging and discharging process of the power battery requires a certain charging and discharging time and conditions, the above method has a relatively low efficiency in evaluating the SOH value.

[0004] The big data artificial intelligence evaluation method uses long-time scale data analysis algorithms to obtain the SOH value of the power battery from a large amount of historical data. Since the SOH decay of the power battery is a slow and irreversible process, when the SOH of the power battery of an electric vehicle used for a period of time is evaluated for the first time, this method lacks initial values, so that when the long-time scale data analysis algorithm is used for subsequent evaluation, the convergence of the algorithm is relatively slow, and the SOH value cannot be quickly and reliably output. SUMMARY

[0005] One purpose of an embodiment of the present application is to provide a method for determining the state of health of a power battery of an electric vehicle and a server, which can improve the technical problem of low efficiency in evaluating the state of health of the power battery in the prior art.

[0006] In a first aspect, an embodiment of the present application provides a method for determining the state of health of a power battery of an electric vehicle, comprising:

[0007] obtaining battery data of the power battery and vehicle characteristics of the electric vehicle, the battery data including real-time battery-related parameters and real-time fault type parameters;

[0008] calculating a normal state of health decay value of the power battery according to the real-time battery-related parameters and a normal decay model corresponding to the vehicle characteristics;

[0009] According to the real-time fault type parameter and the fault attenuation model corresponding to the vehicle feature, a fault health state attenuation value of the power battery is calculated;

[0010] According to the normal health state attenuation value and the fault health state attenuation value, a comprehensive health evaluation value of the power battery is determined.

[0011] Optionally, the real-time battery-related parameter is one of a driving mileage, a cumulative charge capacity or a cumulative discharge capacity of the power battery.

[0012] Optionally, the determining of the comprehensive health evaluation value of the power battery according to the normal attenuation value and the fault attenuation value comprises:

[0013] The comprehensive health evaluation value of the power battery is determined according to the following formula: SOH t = Std-Δα t -Δε t , wherein Std is a standard battery health state value, SOH t is the comprehensive health evaluation value, Δα t is the normal health state attenuation value, and Δε t is the fault health state attenuation value.

[0014] Optionally, the normal attenuation model is trained according to first training data of power batteries of a plurality of first historical vehicles with the same vehicle feature as the vehicle;

[0015] The fault attenuation model is trained according to second training data of power batteries of a plurality of second historical vehicles with the same vehicle feature as the vehicle and the normal attenuation model.

[0016] Optionally, the first historical vehicle is a vehicle without a specified battery fault;

[0017] The second historical vehicle is a vehicle with a specified battery fault;

[0018] The specified battery fault is any one of an overvoltage fault, an undervoltage fault, a charging overcurrent fault, a discharging overcurrent fault, a high-temperature fault, a low-temperature fault or a specified serious fault.

[0019] Optionally, the normal attenuation model is: wherein Δα t is the normal health state attenuation value, is a normal attenuation rate, and P t is a real-time battery-related parameter.

[0020] Optionally, the first training data comprises first historical battery-related parameters and first battery state of health values of a plurality of first historical vehicles with the same vehicle characteristics as the vehicle;

[0021] The normal degradation rate is: η is the normal degradation rate, i ηi is the undetermined degradation rate of the i-th first historical vehicle, n is the total number of first historical vehicles participating in training the normal degradation model;

[0022] The undetermined degradation rate of the i-th first historical vehicle is calculated according to the first historical battery-related parameters and the first battery state of health values of the i-th first historical vehicle.

[0023] Optionally, when the first historical battery-related parameters are driving mileage, the undetermined degradation rate of the i-th first historical vehicle is: η i The unit of η is % / 10000km, M wi M is the driving mileage of the i-th first historical vehicle, SOH wi SOH is the first battery state of health value of the i-th first historical vehicle.

[0024] Optionally, the failure degradation model is: wherein Δε t Δε is the failure state of health degradation value, x j x is the j-th real-time failure type parameter, ε j εj is the failure degradation rate of the j-th real-time failure type parameter.

[0025] Optionally, the real-time failure type parameter is one of overvoltage failure times, under-voltage failure times, charging overcurrent failure times, discharging overcurrent failure times, high-temperature failure times, low-temperature failure times, or specified serious failure times.

[0026] Optionally, the second training data comprises second battery state of health values, second historical battery-related parameters, and historical failure type parameters of a plurality of second historical vehicles with the same vehicle characteristics as the vehicle;

[0027] The failure degradation rate of the j-th second historical vehicle is calculated according to a linear regression algorithm, and the determinant of the health difference and the historical failure type parameters of a plurality of second historical vehicles is calculated;

[0028] The health difference of the j-th second historical vehicle is the difference between the expected health value and the j-th second battery state of health value of the j-th second historical vehicle;

[0029] The expected health value of the jth second historical vehicle is calculated according to the jth second historical battery correlation parameter and the normal attenuation model.

[0030] Optionally, the failure attenuation rate of the jth real-time failure type parameter is:

[0031]

[0032]

[0033]

[0034] wherein Δε yj is a health difference value of the jth second historical vehicle, is an expected health value of the jth second historical vehicle, SOH yj is a second battery health value of the jth second historical vehicle, and Std is a standard battery health state value, is a normal attenuation rate, P yj is a failure historical battery correlation parameter of the jth second historical vehicle, x sj is the jth historical failure type parameter of the s th second historical vehicle, ε j is a failure attenuation rate of the jth historical failure type parameter.

[0035] In a second aspect, an embodiment of the present application provides a server, comprising:

[0036] at least one processor; and

[0037] a memory connected with the at least one processor in communication; wherein

[0038] the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the health state determination method of the power battery of the electric vehicle.

[0039] In a third aspect, an embodiment of the present application provides a storage medium, the storage medium stores computer executable instructions, and the computer executable instructions are used to enable an electronic device to perform the health state determination method of the power battery of the electric vehicle.

[0040] In a fourth aspect, an embodiment of the present application provides a computer program product, the computer program product comprises a computer program stored on a non-volatile computer readable storage medium, and the computer program comprises program instructions, and when the program instructions are executed by an electronic device, the electronic device is enabled to perform the health state determination method of the power battery of the electric vehicle.

[0041] Compared with the prior art, the present application has at least the following beneficial effects: in the method for determining the health state of the power battery provided in the embodiment of the present application, the battery data of the power battery and the vehicle characteristics of the electric vehicle are obtained, the battery data includes real-time battery correlation parameters and real-time fault type parameters, the normal health state attenuation value of the power battery is calculated according to the real-time battery correlation parameters and the normal attenuation model corresponding to the vehicle characteristics, the fault health state attenuation value of the power battery is calculated according to the real-time fault type parameters and the fault attenuation model corresponding to the vehicle characteristics, and the comprehensive health evaluation value of the power battery is determined according to the normal health state attenuation value and the fault health state attenuation value. Therefore, when evaluating the health state of the power battery, the embodiment does not need to control the power battery to charge and discharge, nor does it need the first health state value of the power battery, and the health state of the power battery can be quickly evaluated, thereby improving the technical problem of low efficiency in evaluating the health state of the power battery in the prior art. BRIEF DESCRIPTION OF DRAWINGS

[0042] One or more embodiments are illustrated by way of example in the drawings that are for illustrative purposes only, and not for the limitation of the embodiments, elements having the same reference numerals in the drawings represent similar elements, unless otherwise specified, the drawings do not constitute a proportional limit.

[0043] Figure 1 A structural schematic diagram of a health state determination system of a power battery provided in the embodiment of the present application;

[0044] Figure 2 A flowchart of a method for determining the health state of a power battery of an electric vehicle provided in the embodiment of the present application;

[0045] Figure 3 A scene schematic diagram for training a normal attenuation model and a fault attenuation model provided in the embodiment of the present application;

[0046] Figure 4 A structural schematic diagram of a health state determination device of a power battery of an electric vehicle provided in the embodiment of the present application;

[0047] Figure 5 A circuit structural schematic diagram of a server provided in the embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0049] It should be noted that the various features of the embodiments of the present application can be combined with each other without conflict, and all fall within the protection scope of the present application. In addition, although the functional modules are divided in the device schematic diagram, and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a manner different from the module division in the device or the order in the flowchart. Furthermore, the "first", "second", "third" and the like used in the present application do not limit the data and execution order, but only distinguish the same items or similar items with basically the same function and effect.

[0050] The embodiment of the present application provides a kind of health state determination system of power battery, please refer to Figure 1 Health state determination system 100 includes vehicle communication device 11 (Vehicle Communication Interface, VCI) and server 12, server 12 is communicated with vehicle communication device 11 connection, it includes wired communication connection or wireless communication connection in communication connection, wired communication connection includes the various types of communication connections for transmitting information using tangible medium such as metal wire, optical fiber.Wireless communication connection includes 5G communication, 4G communication, 3G communication, 2G communication, CDMA, Bluetooth, wireless broadband, ultra-wideband communication, near field communication, CDMA2000, GSM, ISM, RFID, UMTS / 3GPPw / HSDPA, WiMAX, Wi-Fi or ZigBee and the like.

[0051] Vehicle communication device 11 is used to be plugged in the OBD interface (On Board Diagnostics, OBD) of electric vehicle 13, vehicle communication device 11 is communicated based on OBD interface with electric vehicle 13, to obtain the vehicle data of electric vehicle 13, vehicle data includes fault code, battery data or vehicle feature.Fault code is used to indicate the fault type of electric vehicle.Battery data is the data associated with the power battery of electric vehicle.Vehicle feature is used to indicate the model feature and / or local feature of electric vehicle.

[0052] As described above, the vehicle communication device 11 obtains the battery data and the vehicle features of the electric vehicle 13, and then sends the battery data and the vehicle features to the server 12 in a package, the server 12 selects the corresponding normal attenuation model 14 and the fault attenuation model 15 according to the vehicle features, and inputs the battery data into the normal attenuation model 14 and the fault attenuation model 15 respectively, and determines the comprehensive health evaluation value of the power battery according to the output results of the normal attenuation model 14 and the fault attenuation model 15.

[0053] It can be understood that the server here can be a physical server or a logical server virtually formed by a plurality of physical servers. The server can also be a server group composed of a plurality of servers that can be interconnected and communicated, and each functional module can be distributed on each server in the server group.

[0054] As another aspect of the embodiment of the present application, the embodiment of the present application provides a method for determining the health state of a power battery of an electric vehicle. The method provided by the embodiment can be applied to multiple application scenarios such as automobile aftermarket diagnosis, battery maintenance, public charging, insurance damage assessment, and residual value assessment. Please refer to Figure 2 , the method for determining the health state of the power battery of the electric vehicle comprises:

[0055] S21. Obtain battery data of the power battery and vehicle features of the electric vehicle, the battery data comprising real-time battery-related parameters and real-time fault type parameters.

[0056] In this step, the vehicle communication device communicates with the electric vehicle, the electric vehicle sends the battery data and the vehicle features of the power battery to the vehicle communication device, and the vehicle communication device packages and sends the battery data and the vehicle features to the server.

[0057] As described above, the battery data comprises real-time battery-related parameters, and the real-time battery-related parameters are parameters for indicating the health state of the power battery. The real-time fault type parameters are parameters for indicating the number of times of occurrence of corresponding fault types of the power battery.

[0058] In some embodiments, the real-time battery-related parameters are one of the driving mileage, the cumulative charging capacity or the cumulative discharging capacity of the power battery.

[0059] The driving mileage is the number of kilometers driven by the electric vehicle, and the unit of the driving mileage can be per ten thousand kilometers (10000 kilometers). The driving mileage is related to the health state of the power battery. The greater the driving mileage, the stronger the attenuation degree of the power battery, and the smaller the driving mileage, the weaker the attenuation degree of the power battery. Therefore, the driving mileage can reflect the health state of the power battery.

[0060] The cumulative charging capacity is the sum of the charging capacity of the power battery in multiple charging, and the cumulative discharging capacity is the sum of the discharging capacity of the power battery in multiple discharging. For example, when the power battery is charged for the first time, the charging capacity is C1. When the power battery is charged for the second time, the charging capacity is C2, and the cumulative charging capacity = C1+C2. When the power battery is charged for the third time, the charging capacity is C3, and the cumulative charging capacity = C1+C2+C3. The cumulative charging capacity is correlated with the state of health of the power battery. The greater the cumulative charging capacity, the stronger the degree of attenuation of the power battery, and the smaller the cumulative charging capacity, the weaker the degree of attenuation of the power battery. Therefore, the cumulative charging capacity can reflect the state of health of the power battery.

[0061] As described above, the battery data includes a real-time fault type parameter, which in some embodiments is one of an overvoltage fault frequency, an undervoltage fault frequency, a charging overcurrent fault frequency, a discharging overcurrent fault frequency, a high-temperature fault frequency, a low-temperature fault frequency, or other serious fault frequency.

[0062] The overvoltage fault frequency is the total number of overvoltage faults, wherein the overvoltage fault e1 includes overvoltage fault of each single battery or system total pressure overvoltage fault, etc. For example, at time t1, the power battery has an overvoltage fault, and the overvoltage fault frequency = 1. At time t2, the power battery has an overvoltage fault, and the overvoltage fault frequency = 2. At time t3, the power battery has an overvoltage fault, and the overvoltage fault frequency = 3.

[0063] The undervoltage fault frequency is the total number of undervoltage faults, wherein the undervoltage fault e2 includes undervoltage fault of each single battery, single battery internal short circuit fault, or system total pressure undervoltage fault, etc.

[0064] The charging overcurrent fault frequency is the total number of charging overcurrent fault types, wherein the charging overcurrent fault e3 includes fast / slow charging overcurrent fault or charging current abnormal fault, etc.

[0065] The discharging overcurrent fault frequency is the total number of discharging overcurrent faults, wherein the discharging overcurrent fault e4 includes discharging overcurrent fault, discharging current abnormal fault, or short circuit fault, etc.

[0066] The high-temperature fault frequency is the total number of high-temperature faults, wherein the high-temperature fault e5 includes battery charging high-temperature fault, battery discharging high-temperature fault, environmental high-temperature fault, thermal management high-temperature fault, or controller high-temperature fault, etc.

[0067] The low-temperature fault frequency is the total number of low-temperature faults, wherein the low-temperature fault e6 includes battery charging low-temperature fault, battery discharging low-temperature fault, environmental low-temperature fault, or thermal management low-temperature fault, etc.

[0068] The specified serious fault number is a total number corresponding to the specified serious fault, wherein the specified serious fault e7 is a fault type other than the above-mentioned six fault types.

[0069] It can be understood that there are hundreds of battery faults related to the power battery in the battery management system of the electric vehicle. According to the characteristics and electrochemical mechanism of the power battery, the battery faults affecting the health state of the power battery are classified into the above-mentioned seven categories. However, it can be understood that those skilled in the art can also classify the battery faults related to the power battery according to other classification purposes. The seven categories of battery faults provided above do not cause any undue limitation on the protection scope of the present application.

[0070] In some embodiments, the vehicle feature includes a model feature of the electric vehicle, and the model feature is used to represent a model of the electric vehicle. The model feature can be represented by MMYB information, which is a general term for information such as the make, model, year, battery version, etc. of the new energy vehicle.

[0071] In some embodiments, the vehicle feature includes a local feature of the electric vehicle, and the local feature is used to represent the region where the electric vehicle is driven. The local feature can be represented by geographic location information, which can be generated by a positioning system of the electric vehicle. For example, the geographic location information is Nanshan District, Shenzhen, Guangdong.

[0072] S22. According to the real-time battery correlation parameter and the normal attenuation model corresponding to the vehicle feature, the normal health state attenuation value of the power battery is calculated.

[0073] In this step, the normal attenuation model is a model used to calculate the normal health state attenuation value, and the normal health state attenuation value is an attenuation value of the power battery evaluated from the normal dimension of the power battery. After the real-time battery correlation parameter is input into the normal attenuation model, the normal attenuation model can output the normal health state attenuation value of the power battery.

[0074] It can be understood that the similarity of the battery health attenuation curves between electric vehicles is relatively small when the vehicle features of the electric vehicles are different, or the similarity of the battery health attenuation curves between electric vehicles is relatively large when the vehicle features of the electric vehicles are the same. Therefore, the normal attenuation model can be constructed according to the vehicle feature in the present embodiment, and different vehicle features correspond to different normal attenuation models, which is helpful to improve the accuracy of calculating the normal health state attenuation value.

[0075] In some embodiments, the vehicle feature is obtained, and a normal attenuation model matching the vehicle feature is searched from the normal model library according to the vehicle feature and the normal feature label, wherein the normal model library comprises a plurality of normal feature labels and normal attenuation models corresponding to the normal feature labels.

[0076] S23. A fault health state attenuation value of the power battery is calculated according to the real-time fault type parameter and the fault attenuation model corresponding to the vehicle feature.

[0077] In this step, the fault attenuation model is a model for calculating the fault health state attenuation value, and the fault health state attenuation value is an attenuation value of the power battery from the fault dimension. After the real-time fault type parameter is input into the fault attenuation model, the fault attenuation model can output the fault health state attenuation value of the power battery.

[0078] As described above, the vehicle features of electric vehicles are different, and the similarity of the battery health attenuation curves between electric vehicles is relatively small. Therefore, the fault attenuation model can be constructed according to the vehicle feature, different vehicle features correspond to different fault attenuation models, which is beneficial to improve the accuracy of calculating the fault health state attenuation value.

[0079] In some embodiments, the vehicle feature is obtained, and a fault attenuation model matching the vehicle feature is searched from the fault model library according to the vehicle feature and the fault feature label, wherein the fault model library comprises a plurality of fault feature labels and fault attenuation models corresponding to the fault feature labels.

[0080] In some embodiments, the vehicle feature is a vehicle model feature, and the normal attenuation model and the fault attenuation model matching the vehicle model feature are searched respectively, that is, a single vehicle model feature can correspond to the normal attenuation model and the fault attenuation model respectively.

[0081] In some embodiments, the vehicle feature is a region feature, and the normal attenuation model and the fault attenuation model matching the region feature are searched respectively, that is, a single region feature can correspond to the normal attenuation model and the fault attenuation model respectively.

[0082] In some embodiments, the vehicle feature is a vehicle model feature and a region feature, and the normal attenuation model and the fault attenuation model matching the vehicle model feature and the region feature are searched respectively, that is, the normal attenuation model and the fault attenuation model are determined by the vehicle model feature and the region feature.

[0083] S24. A comprehensive health evaluation value of the power battery is determined according to the normal health state attenuation value and the fault health state attenuation value.

[0084] In this step, the comprehensive health evaluation value is a value for evaluating the health of the power battery, wherein the comprehensive health evaluation value includes a battery health state value, for example, the battery health state value can be represented by the SOH value as described above, and the embodiment determines the comprehensive health evaluation value of the power battery according to the following formula: SOH t = Std- Δa t - Δε t , wherein Std is a standard battery health state value, SOH t is the comprehensive health evaluation value, Δa t is a normal health state attenuation value, and Δε t is a failure health state attenuation value. In some embodiments, the standard battery health state value Std can be customized by an engineer according to business needs, for example, the standard battery health state value Std is 100%.

[0085] In some embodiments, the method for determining the health state of the power battery of the electric vehicle further includes: determining whether the comprehensive health evaluation value is less than or equal to a first preset threshold, if yes, generating battery warning information, and if no, generating battery health evaluation information according to the comprehensive health evaluation value, wherein the battery warning information is used to prompt the user to replace or maintain the power battery, and the battery warning information can be any form of warning information, such as text warning information, voice warning information, or flashing warning information. The battery health evaluation information is health level information for evaluating the health state of the power battery, for example, the battery health evaluation information includes "very good", "good", or "general", etc.

[0086] It can be understood that the first preset threshold can be customized by an engineer according to business needs, for example, the first preset threshold is 70%.

[0087] In some embodiments, the difference from the above-mentioned embodiments is that the comprehensive health evaluation value includes a battery health attenuation value, and the embodiment can add the normal health state attenuation value and the failure health state attenuation value to obtain the battery health attenuation value, and the embodiment determines the battery health attenuation value of the power battery according to the following formula: ΔSOH t = Δa t + Δε t .

[0088] In some embodiments, the method for determining the health state of the power battery of the electric vehicle further includes: determining whether the comprehensive health evaluation value is greater than or equal to a second preset threshold, if yes, generating battery warning information, and if no, generating battery health evaluation information according to the comprehensive health evaluation value.

[0089] It can be understood that the second preset threshold can be customized by an engineer according to business needs, for example, the second preset threshold is 80%.

[0090] As described above, in the present embodiment, the health state of the power battery is evaluated without the need to control the power battery to charge and discharge, i.e. the user does not need to set up equipment for controlling the power battery to charge and discharge, and the health state of the power battery can be quickly evaluated when the electric vehicle is in a stopped working state, thereby improving the technical problem of low efficiency in evaluating the health state of the power battery in the prior art, and expanding the application range of the method.

[0091] As described above, in the present embodiment, the health state of the power battery is evaluated without the need for the initial health state value of the power battery, i.e. the comprehensive health evaluation value of the electric vehicle can be output once for the electric vehicle without historical data, thereby improving the technical problem of low efficiency in evaluating the health state of the power battery in the prior art. In addition, when the initial SOH value is needed for tracking and evaluating the comprehensive health evaluation value of the electric vehicle by using the electrochemical mechanism method or the big data artificial intelligence evaluation method, the present embodiment can provide the initial SOH value, and thus it can be seen that the application range of the method provided by the present embodiment is more flexible and extensive.

[0092] In addition, the electrochemical mechanism method or the big data artificial intelligence evaluation method often lacks an initial value, resulting in slow convergence of the algorithm. As described above, the present embodiment can provide the initial SOH value, and when the electrochemical mechanism method or the big data artificial intelligence evaluation method is used subsequently, it is beneficial to improve the convergence speed and accuracy of the above two algorithms.

[0093] In some embodiments, the normal degradation model is trained according to first training data of power batteries of a plurality of first historical vehicles having the same vehicle characteristics as the vehicle. The failure degradation model is trained according to second training data of power batteries of a plurality of second historical vehicles having the same vehicle characteristics as the vehicle and the normal degradation model.

[0094] The first training data is data used for training to generate the normal degradation model. The second training data is data used for training to generate the failure degradation model in cooperation with the normal degradation model. The first historical vehicle is an electric vehicle before the normal degradation model is trained to be generated. The second historical vehicle is an electric vehicle before the failure degradation model is trained to be generated. For example, the normal degradation model is trained at time point t11, and the present embodiment selects training data of a plurality of first electric vehicles as the first training data, where the first electric vehicle is the first historical vehicle. The failure degradation model is trained at time point t22, and the present embodiment selects training data of a plurality of second electric vehicles as the second training data, where the second electric vehicle is the second historical vehicle.

[0095] The embodiment can generate the fault attenuation model by evolution of the normal attenuation model, and compared with the method of constructing the fault attenuation model separately from the normal attenuation model, the method provided by the embodiment can improve the fusion degree between the normal attenuation model and the fault attenuation model, and is beneficial to generating a more reliable and accurate fault attenuation model.

[0096] In some embodiments, the vehicle feature is a model feature, and the embodiment can select the training data of the power battery of the first historical vehicle with the same model feature as the first training data, and select the training data of the power battery of the second historical vehicle with the same model feature as the second training data.

[0097] In some embodiments, different from the above embodiments, the vehicle feature is a region feature, and the embodiment can select the training data of the power battery of the first historical vehicle with the same region feature as the first training data, and select the training data of the power battery of the second historical vehicle with the same region feature as the second training data.

[0098] In some embodiments, different from the above embodiments, the vehicle feature includes a model feature and a region feature, and the embodiment can select the training data of the power battery of the first historical vehicle with the same model feature and the same region feature as the first training data, and select the training data of the power battery of the second historical vehicle with the same model feature and the same region feature as the second training data.

[0099] In some embodiments, the first historical vehicle and the second historical vehicle are both vehicles that have occurred a specified battery fault, and the specified battery fault is any one of an overvoltage fault, an undervoltage fault, a charging overcurrent fault, a discharging overcurrent fault, a high-temperature fault, a low-temperature fault, or a specified serious fault.

[0100] The embodiment can generate the normal attenuation model according to the first training data of the first historical vehicle, so as to output the normal health state attenuation value by using the normal attenuation model, and generate the fault attenuation model according to the second training data of the second historical vehicle and the normal attenuation model, so as to output the fault health state attenuation value by using the fault attenuation model, and compared with the prior art, the embodiment can also quickly evaluate the health state of the power battery.

[0101] In some embodiments, different from the above embodiments, the first historical vehicle is a vehicle that has not occurred the specified battery failure, and the second historical vehicle is a vehicle that has occurred the specified battery failure. According to the first training data and the second training data at this time, the normal attenuation model and the failure attenuation model are obtained, respectively, so as to quickly evaluate the health state of the power battery.

[0102] In some embodiments, different from the above embodiments, the first historical vehicle is a vehicle that has not occurred the specified battery failure, and the second historical vehicle is a vehicle that has occurred the specified battery failure. Since the first historical vehicle is a vehicle that has not occurred the specified battery failure, the training data of the vehicle that has not occurred the specified battery failure is selected as the first training data, and the influence of the training data of the vehicle that has occurred the specified battery failure on the normal attenuation model is eliminated, which is beneficial to generate a more accurate and reliable normal attenuation model.

[0103] Similarly, since the second historical vehicle is a vehicle that has occurred the specified battery failure, the influence of the training data of the vehicle that has not occurred the specified battery failure on the failure attenuation model is eliminated, and the training data of the vehicle that has occurred the specified battery failure is selected as the second training data, which is beneficial to generate a more accurate and reliable failure attenuation model.

[0104] In some embodiments, the normal attenuation model is: wherein, Δα t is a normal health state attenuation value, is a normal attenuation rate, and P t is a real-time battery correlation parameter. The normal attenuation rate is an evaluation of the attenuation rate of the power battery from the normal dimension of the power battery.

[0105] When the server obtains the real-time battery correlation parameter P t of the electric vehicle, the real-time battery correlation parameter P t is substituted into the normal attenuation model, and the normal attenuation model can output the normal health state attenuation value Δα t .

[0106] In some embodiments, the first training data includes first historical battery association parameters and first battery health status values ​​of multiple first historical vehicles with the same vehicle characteristics. As mentioned above, the first historical battery association parameters may be one of the following: driving mileage, cumulative charging capacity of the power battery, or cumulative discharging capacity. The first battery health status value is the battery health status value of the first historical vehicles obtained in advance. It is understood that the first battery health status value can be calculated by any suitable algorithm for evaluating the SOH value of the power battery. The server directly calls the result provided by the algorithm for evaluating the SOH value of the power battery. Alternatively, the first battery health status value can also be obtained by evaluating the SOH value of the power battery using the method provided in this embodiment, and then iteratively updated using the existing first battery health status value.

[0107] The normal attenuation rate is: For the normal attenuation rate, η i Let be the undetermined degradation rate of the i-th first historical vehicle, and n be the total number of first historical vehicles participating in training the normal degradation model. The undetermined degradation rate of the i-th first historical vehicle is calculated based on the first historical battery association parameters and the first battery health status value of the i-th first historical vehicle.

[0108] For example, if the total number of first-historical vehicles (n) participating in training the normal decay model is 100, the undetermined decay rate for the first first-historical vehicle is η1, the undetermined decay rate for the second first-historical vehicle is η2, and so on, until the final normal decay rate is determined. This embodiment obtains the normal attenuation rate by averaging the undetermined attenuation rates of multiple first historical vehicles. This helps to obtain a more accurate and reliable normal attenuation rate.

[0109] In some embodiments, when the first historical battery associated parameter is the driving mileage, the undetermined degradation rate of the i-th first historical vehicle is: η i The unit is % / 10000km, M wi Let SOH be the mileage of the i-th first historical vehicle. wi This represents the first battery health state value for the i-th historical vehicle. For example, M... wi For 100,000 km, SOH wi If it is 95%, then η i It is 0.5, and its unit is % / 10000km, that is, % / 10,000 kilometers.

[0110] For another example, suppose that after averaging multiple unknown attenuation rates, the normal attenuation rate is obtained. The value is 0.5. Assume the real-time battery correlation parameter P... tFor 60000km = 60000 / 10000 = 6 million kilometers, which is substituted into the normal attenuation model Then

[0111] In some embodiments, different from the above embodiments, the first historical battery-related parameter can also be the cumulative charge capacity or the cumulative discharge capacity, and the pending attenuation rate of the i-th first historical vehicle is: η i The unit is % / Ah, C wi is the cumulative charge capacity or the cumulative discharge capacity of the i-th first historical vehicle.

[0112] In some embodiments, the failure attenuation model is: Wherein, Δε t is the failure health state attenuation value, x j is the j-th real-time failure type parameter, ε j is the failure attenuation rate of the j-th real-time failure type parameter. Wherein, the failure attenuation rate ε j of the j-th real-time failure type parameter is to evaluate the attenuation rate of the power battery under the failure action of the j-th real-time failure type from the failure dimension of the power battery. For example, the failure attenuation model has a total of 7 real-time failure type parameters, and the failure attenuation rates of the 7 real-time failure type parameters are 0.244, 0.112, 1.112, 0.774, 0.365, 0.585, and 0.119, respectively.

[0113] In some embodiments, the real-time failure type parameter is one of the overvoltage failure times, the undervoltage failure times, the charging overcurrent failure times, the discharging overcurrent failure times, the high-temperature failure times, the low-temperature failure times, or the specified severe failure times. Assuming that the 7 real-time failure type parameters of the electric vehicle D1 are {f1, f2, f3, f4, f5, f6, f7} = {4, 6, 8, 3, 1, 5, 4} in order, and the 7 real-time failure type parameters of the electric vehicle D1 are input into the failure attenuation model, then the failure health state attenuation value is:

[0114] Δε t

[0115] = 0.244*4 + 0.112*6 + 1.112*8 + 0.774*3 + 0.365*1 + 0.585*5 + 0.119*4 = 16.632.

[0116] Assuming that the 7 real-time fault type parameters of the electric vehicle D2 are {f1, f2, f3, f4, f5, f6, f7} = {3, 6, 5, 5, 3, 4, 3} in sequence, the 7 real-time fault type parameters of the electric vehicle D2 are input into the fault attenuation model, and the fault health state attenuation value is:

[0117] Δε t

[0118] = 0.244*3 + 0.112*6 + 1.112*5 + 0.774*5 + 0.365*3 + 0.585*4 + 0.119*3 = 14.626.632.

[0119] Assuming that the 7 real-time fault type parameters of the electric vehicle D3 are {f1, f2, f3, f4, f5, f6, f7} = {1, 2, 1, 0, 0, 1, 3} in sequence, the 7 real-time fault type parameters of the electric vehicle D3 are input into the fault attenuation model, and the fault health state attenuation value is:

[0120] Δε t

[0121] = 0.244*1 + 0.112*2 + 1.112*4 + 0.774*0 + 0.365*0 + 0.585*1 + 0.119*3 = 5.858.

[0122] In some embodiments, the second training data includes second battery health state values, second historical battery-related parameters and historical fault type parameters of a plurality of second historical vehicles with the same vehicle characteristics. As described above, the second historical battery-related parameters can be one of the driving mileage, the cumulative charging capacity or the cumulative discharging capacity of the power battery, and the second battery health state values are the battery health state values of the second historical vehicles obtained in advance. It can be understood that the second battery health state values can be calculated by any suitable algorithm for evaluating the SOH value of the power battery, the server directly calls the result provided by the algorithm for evaluating the SOH value of the power battery, or the second battery health state values can also be obtained by the method provided in the embodiment for evaluating the SOH value of the power battery, and the existing second battery health state values are used for iterative updating subsequently. The historical fault type parameters can be one of the overvoltage fault frequency, the undervoltage fault frequency, the charging overcurrent fault frequency, the discharging overcurrent fault frequency, the high-temperature fault frequency, the low-temperature fault frequency or the specified serious fault frequency.

[0123] The failure decay rate of the jth second historical vehicle is calculated according to a linear regression algorithm on a plurality of second historical vehicle health difference and historical failure type parameters, wherein the health difference of the jth second historical vehicle is the difference between the expected health value of the jth second historical vehicle and the jth second battery health value, and the expected health value of the jth second historical vehicle is calculated according to the jth second historical battery correlation parameter and the normal decay model.

[0124] It can be understood that the linear regression algorithm here can select any suitable type of linear regression algorithm, such as a linear regression algorithm using the least squares method.

[0125] The expected health value of the jth second historical vehicle is: is the expected health value of the jth second historical vehicle, and Std is the standard battery health state value, is the normal decay rate, and P yj is the failure history battery correlation parameter of the jth second historical vehicle.

[0126] As mentioned earlier, the jth second battery health value can be obtained by the server calling the existing battery health value of the jth second historical vehicle.

[0127] The health difference of the jth second historical vehicle is: Δε yj is the health difference of the jth second historical vehicle, and SOH yj is the second battery health value of the jth second historical vehicle.

[0128] The failure decay rate of the jth second historical vehicle is:

[0129]

[0130] wherein x sj is the jth historical failure type parameter of the s th second historical vehicle, and ε j is the failure decay rate of the jth historical failure type parameter, and each failure decay rate has a unit of %.

[0131] For example, assume that the failure decay model has a total of 7 real-time failure type parameters, i.e. r = 7. Assume that 7 historical failure type parameters of 5 second historical vehicles are taken.

[0132] The 7 historical failure type parameters of the electric vehicle L1 are {4, 6, 8, 3, 1, 5, 4}, is 91.6%, and SOH y1 is 75%. The 7 historical failure type parameters of the electric vehicle L2 are {2, 4, 5, 7, 2, 5, 3}, 95.9% SOH y2 80% SOH 89.7% SOH y3 72% SOH 96.6% SOH y4 82% SOH 94.3% SOH y5 78% SOH 94.7% SOH y5 93% SOH 92.5% SOH y5 90% SOH

[0133] Δε y1 = 16.6% Δε y2 = 15.9% Δε y3 = 17.7% Δε y4 = 14.6% Δε y5 = 16.3% Δε

[0134] Δε y6 = 1.7% Δε y7 = 2.5% Δε

[0135]

[0136] According to the least square method, the above formula is identified, and ε1, ε2, ε3, ε4, ε5, ε6, and ε7 are respectively: 0.244, 0.112, 1.112, 0.774, 0.365, 0.585, and 0.119. The failure attenuation rates of the seven battery failures can be obtained. It can be understood that the embodiment can also add eight or nine or more battery failures, and match a failure attenuation rate for each battery failure, and estimate the failure attenuation rate of each battery failure by the least square method.

[0137] It can also be understood that the embodiment can also add a smaller number of battery failures, and match a failure attenuation rate for each battery failure, such as adding only two battery failures, and estimating the failure attenuation rates of the two battery failures by the least square method.

[0138] As described above, the present embodiment is to associate various battery faults, and to calculate the fault attenuation rate of each battery fault by a linear regression algorithm, and then to substitute the fault attenuation rates of the plurality of battery faults into the calculation of the fault health state attenuation value Δε t , the present embodiment can comprehensively and associate various battery faults with the fault health state attenuation value Δε t , reduce the influence of the error of a single battery fault on the fault health state attenuation value Δε t , and thus can train a more reliable and accurate fault attenuation model.

[0139] As described above, the present embodiment is divided into a model training process and an actual application process, wherein FIG. 1 has shown the actual application process of quickly evaluating the comprehensive health evaluation value of the power battery, and the following will make a detailed elaboration on the model training process, as follows: Figure 3

[0140] As shown in Figure 3 , the vehicle features of each first historical vehicle 31 and each second historical vehicle 32 are the same, such as the same vehicle model features and the same territorial features.

[0141] The first vehicle communication device 33 is plugged into the OBD interface of the first historical vehicle 31, and the first vehicle communication device 33 communicates with the first historical vehicle 31 based on the OBD interface to obtain the first training data of the first historical vehicle 31, the first training data including first battery data and first vehicle features, wherein the battery data includes a first driving mileage, a first battery health state value and a first fault type parameter. The first vehicle communication device 33 sends the first training data to the server 34, and the server 34 trains to generate a normal attenuation model 35 according to the first driving mileage and the first battery health state value.

[0142] The second vehicle communication device 36 is plugged into the OBD interface of the second historical vehicle 32, and the second vehicle communication device 36 communicates with the second historical vehicle 32 based on the OBD interface to obtain the second training data of the second historical vehicle 32, the second training data including second battery data and second vehicle features, wherein the battery data includes a second driving mileage, a second battery health state value and a second fault type parameter. The second vehicle communication device 36 sends the second training data to the server 34.

[0143] ​The server 34 inputs the second driving range into the normal degradation model 35 to obtain an expected health value. Then, the server 34 subtracts the expected health value from the second battery health state value to obtain a health difference value. Then, the server calculates a failure degradation rate of each battery failure according to the health difference values and the second failure type parameters of the plurality of second historical vehicles 32. Finally, the server generates the failure degradation model 37 according to the failure degradation rate of each battery failure.

[0144] It should be noted that in the above various embodiments, the above steps do not necessarily have a certain order, and those skilled in the art can understand from the description of the embodiments of the present application that the above steps can have different execution orders in different embodiments, that is, they can be executed in parallel, or they can be exchanged and executed, etc.

[0145] As another aspect of the embodiments of the present application, the embodiments of the present application provide a health state determination device of a power battery of an electric vehicle. The health state determination device of the power battery of the electric vehicle can be a software module, which includes a plurality of instructions stored in a memory, and a processor can access the memory to call the instructions for execution to complete the health state determination method of the power battery of the electric vehicle described in the above various embodiments.

[0146] In some embodiments, the health state determination device of the power battery of the electric vehicle can also be built by hardware devices, for example, the health state determination device of the power battery of the electric vehicle can be built by one or more than two chips, and each chip can work in coordination with each other to complete the health state determination method of the power battery of the electric vehicle described in the above various embodiments. For another example, the health state determination device of the power battery of the electric vehicle can also be built by various logic devices, such as a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a single-chip microcomputer, an ARM (Acorn RISC Machine), or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, or any combination of these components.

[0147] Please refer to Figure 4The health state determination device 400 of the power battery of the electric vehicle comprises a data acquisition module 41, a normal attenuation calculation module 42, a fault attenuation calculation module 43, and a health state determination module 44. The data acquisition module 41 is configured to acquire battery data of the power battery and vehicle features of the electric vehicle, wherein the battery data comprises real-time battery-related parameters and real-time fault type parameters. The normal attenuation calculation module 42 is configured to calculate a normal health state attenuation value of the power battery according to the real-time battery-related parameters and a normal attenuation model corresponding to the vehicle features. The fault attenuation calculation module 43 is configured to calculate a fault health state attenuation value of the power battery according to the real-time fault type parameters and a fault attenuation model corresponding to the vehicle features. The health state determination module 44 is configured to determine an integrated health evaluation value of the power battery according to the normal health state attenuation value and the fault health state attenuation value.

[0148] In the embodiment, the health state of the power battery can be evaluated quickly without controlling the power battery to charge and discharge and without the first health state value of the power battery, thereby improving the technical problem of low efficiency in the prior art.

[0149] In some embodiments, the real-time battery-related parameters are one of a driving mileage, a cumulative charging capacity, or a cumulative discharging capacity of the power battery.

[0150] In some embodiments, the health state determination module 44 is specifically configured to determine the integrated health evaluation value of the power battery according to the following formula: SOH t = Std-Δα t -Δε t , wherein Std is a standard battery health state value, SOH t is the integrated health evaluation value, Δα t is the normal health state attenuation value, and Δε t is the fault health state attenuation value.

[0151] In some embodiments, the normal attenuation model is trained according to first training data of power batteries of a plurality of first historical vehicles with the same vehicle features. The fault attenuation model is trained according to second training data of power batteries of a plurality of second historical vehicles with the same vehicle features and the normal attenuation model.

[0152] In some embodiments, the first historical vehicles are vehicles without a specified battery fault. The second historical vehicles are vehicles with a specified battery fault. The specified battery fault is any one of an overvoltage fault, an under-voltage fault, a charging overcurrent fault, a discharging overcurrent fault, a high-temperature fault, a low-temperature fault, or a specified severe fault.

[0153] In some embodiments, the normal degradation model is: wherein Δα t is a normal health state degradation value, is a normal degradation rate, P t is a real-time battery-related parameter.

[0154] In some embodiments, the first training data comprises first historical battery-related parameters and first battery health state values of a plurality of first historical vehicles having the same vehicle characteristics as the vehicle. The normal degradation rate is: wherein η i is an undetermined degradation rate of the i-th first historical vehicle, and n is a total number of the first historical vehicles participating in training of the normal degradation model. The undetermined degradation rate of the i-th first historical vehicle is calculated according to the first historical battery-related parameters and the first battery health state values of the i-th first historical vehicle.

[0155] In some embodiments, when the first historical battery-related parameter is a driving mileage, the undetermined degradation rate of the i-th first historical vehicle is: η i has a unit of % / 10000km, M wi is a driving mileage of the i-th first historical vehicle, SOH wi is the first battery health state value of the i-th first historical vehicle.

[0156] In some embodiments, the fault degradation model is: wherein Δε t is a fault health state degradation value, x j is a j-th real-time fault type parameter, ε j is a fault degradation rate of the j-th real-time fault type parameter.

[0157] In some embodiments, the real-time fault type parameter is one of a number of overvoltage faults, a number of undervoltage faults, a number of charging overcurrent faults, a number of discharging overcurrent faults, a number of high-temperature faults, a number of low-temperature faults, or a number of specified serious faults.

[0158] In some embodiments, the second training data comprises second battery health state values, second historical battery-related parameters, and historical fault type parameters of a plurality of second historical vehicles having the same vehicle characteristics as the vehicle.

[0159] The fault degradation rate of the j-th second historical vehicle is calculated according to a linear regression algorithm, a determinant of the health difference values and the historical fault type parameters of the plurality of second historical vehicles.

[0160] The health difference of the jth second historical vehicle is the difference between the expected health value of the jth second historical vehicle and the jth second battery health value;

[0161] The expected health value of the jth second historical vehicle is calculated according to the jth second historical battery correlation parameter and the normal decay model.

[0162] In some embodiments, the failure decay rate of the jth real-time failure type parameter is:

[0163]

[0164]

[0165]

[0166] wherein Δε yj is the health difference of the jth second historical vehicle, is the expected health value of the jth second historical vehicle, SOH yj is the second battery health value of the jth second historical vehicle, and Std is a standard battery health state value, is a normal decay rate, P yj is the failure history battery correlation parameter of the jth second historical vehicle, x sj is the jth historical failure type parameter of the s th second historical vehicle, ε j is the failure decay rate of the jth historical failure type parameter.

[0167] It should be noted that the health state determination device of the power battery of the electric vehicle can perform the health state determination method of the power battery of the electric vehicle provided by the embodiments of the present application, and has the corresponding function modules and beneficial effects of performing the method. Technical details not described in detail in the embodiments of the health state determination device of the power battery of the electric vehicle can be referred to the health state determination method of the power battery of the electric vehicle provided by the embodiments of the present application.

[0168] Please refer to Figure 5 , Figure 5 is a circuit structure diagram of a server provided by an embodiment of the present application. As Figure 5 shown, the server 500 includes one or more processors 51 and a memory 52. Among them, Figure 5 take one processor 51 as an example.

[0169] The processor 51 and the memory 52 can be connected through a bus or other means, Figure 5 take the bus connection as an example.

[0170] The memory 52 can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as the program instructions / modules corresponding to the method for determining the state of health of the power battery of the electric vehicle in the embodiments of the present application. The processor 51 executes the various functional applications and data processing of the device for determining the state of health of the power battery of the electric vehicle by running the non-volatile software programs, instructions and modules stored in the memory 52, i.e. realizes the functions of the method for determining the state of health of the power battery of the electric vehicle provided by the above method embodiments and the functions of each module or unit of the above device embodiments.

[0171] The memory 52 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 52 can optionally include a memory remotely arranged relative to the processor 51, and these remote memories can be connected to the processor 51 through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0172] The program instructions / modules are stored in the memory 52, and when executed by the one or more processors 51, the program instructions / modules execute the method for determining the state of health of the power battery of the electric vehicle in any of the above method embodiments.

[0173] The embodiments of the present application also provide a storage medium, which stores computer executable instructions, and the computer executable instructions are executed by one or more processors, such as the processor 51 in the above embodiments, so that the above one or more processors can execute the method for determining the state of health of the power battery of the electric vehicle in any of the above method embodiments. Figure 5

[0174] The embodiments of the present application also provide a computer program product, which includes a computer program stored on a non-volatile computer readable storage medium, and the computer program includes program instructions, and when the program instructions are executed by a server, the server executes any of the above methods for determining the state of health of the power battery of the electric vehicle.

[0175] The above described device or equipment embodiments are only illustrative, wherein the unit modules described as separate components can or can not be physically separated, and the components displayed as module units can or can not be physical units, i.e. can be located in one place or can be distributed on multiple network module units. Some or all of the modules can be selected according to actual needs to achieve the purposes of the present embodiment solutions.

[0176] ​Those skilled in the art can clearly understand the technical solutions of the various embodiments from the above description of the embodiments, and the various embodiments can be implemented by means of software plus a general hardware platform, and of course can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part that makes contributions to the related art, can be embodied in the form of a software product. The computer software product can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, and the like, and includes a plurality of instructions to cause a computer device (which can be a personal computer, a server, or a network device, and the like) to execute the methods described in the various embodiments or some parts of the embodiments.

[0177] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; under the idea of the present application, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other changes of the different aspects of the present application as described above. In order to be brief, they are not provided in details; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of determining a state of health of a power battery of an electric vehicle, characterized by, The method comprises: obtaining battery data of the power battery and vehicle features of the electric vehicle, the battery data comprising real-time battery-related parameters and real-time fault type parameters; calculating a normal health state decay value of the power battery according to the real-time battery-related parameters and a normal decay model corresponding to the vehicle features; calculating a fault health state decay value of the power battery according to the real-time fault type parameters and a fault decay model corresponding to the vehicle features; determining a comprehensive health evaluation value of the power battery according to the normal health state decay value and the fault health state decay value; The normal attenuation model is: wherein, is a normal healthy state attenuation value, is a normal attenuation rate, is a real-time battery correlation parameter; The failure attenuation model is: wherein, is a failure health state attenuation value, is a jth real-time failure type parameter, is a failure attenuation rate of the jth real-time failure type parameter, and m is a number of real-time failure type parameters.

2. The method of claim 1, wherein, the real-time battery-related parameters are one of driving range, cumulative charging capacity or cumulative discharging capacity of the power battery.

3. The method of claim 1, wherein, The determination of the comprehensive health evaluation value of the power battery according to the normal health state decay value and the fault health state decay value comprises: According to the following formula: , a comprehensive health evaluation value of the power battery is determined, is a standard battery health state value, is a comprehensive health evaluation value, is a normal health state attenuation value, is a failure health state attenuation value.

4. The method of claim 1, wherein: the normal decay model is trained according to first training data of power batteries of a plurality of first historical vehicles with the same vehicle features as the vehicle features; the fault decay model is trained according to second training data of power batteries of a plurality of second historical vehicles with the same vehicle features as the vehicle features and the normal decay model.

5. The method of claim 4, wherein: the first historical vehicles are vehicles without a specified battery fault; the second historical vehicles are vehicles with a specified battery fault; the specified battery fault is any one of overvoltage fault, undervoltage fault, charging overcurrent fault, discharging overcurrent fault, high temperature fault, low temperature fault or specified serious fault.

6. The method of claim 4, wherein: the first training data comprises first historical battery-related parameters and first battery health state values of the plurality of first historical vehicles with the same vehicle features as the vehicle features; the normal decay rate is: , the normal decay rate is, the pending decay rate of the i-th first historical vehicle, the total number of the first historical vehicles participating in training the normal decay model; the pending decay rate of the i-th first historical vehicle is calculated according to the first historical battery-related parameters and the first battery health state values of the i-th first historical vehicle.

7. The method of claim 6, wherein, when the first historical battery-related parameter is the driving range, the pending degradation rate of the i-th first historical vehicle is: , in % / 10000km, is the driving range of the i-th first historical vehicle, is the first battery state of health value of the i-th first historical vehicle.

8. The method of claim 1, wherein, the real-time fault type parameters are one of overvoltage fault frequency, undervoltage fault frequency, charging overcurrent fault frequency, discharging overcurrent fault frequency, high temperature fault frequency, low temperature fault frequency or specified serious fault frequency.

9. The method of claim 4, wherein: the second training data comprises second battery health state values, second historical battery-related parameters and historical fault type parameters of the plurality of second historical vehicles with the same vehicle features as the vehicle features; the fault decay rate of the j-th second historical vehicle is calculated according to a linear regression algorithm by calculating the determinant of the health difference value and the historical fault type parameters of the plurality of second historical vehicles; the health difference value of the j-th second historical vehicle is the difference between the expected health value and the j-th second battery health value of the j-th second historical vehicle; the expected health value of the j-th second historical vehicle is calculated according to the j-th second historical battery-related parameters and the normal decay model.

10. The method of claim 9, wherein, the fault decay rate of the j-th real-time fault type parameter is: ； ； ； wherein, is a health difference value for the jth second historical vehicle, is an expected health value for the jth second historical vehicle, is a second battery health value for the jth second historical vehicle, is a standard battery health state value, is a normal decay rate, is a failure history battery correlation parameter for the jth second historical vehicle, is the jth historical failure type parameter for the s th second historical vehicle, r is the number of real-time failure type parameters, is a failure decay rate for the jth historical failure type parameter.

11. A server, characterized by The method comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method for determining the state of health of a power battery of an electric vehicle according to any one of claims 1 to 10.

Images