CN115598556A - Method for determining state of health of power battery of electric vehicle and server - Google Patents

Method for determining state of health of power battery of electric vehicle and server Download PDF

Info

Publication number
CN115598556A
CN115598556A CN202210529104.6A CN202210529104A CN115598556A CN 115598556 A CN115598556 A CN 115598556A CN 202210529104 A CN202210529104 A CN 202210529104A CN 115598556 A CN115598556 A CN 115598556A
Authority
CN
China
Prior art keywords
fault
battery
health
vehicle
value
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210529104.6A
Other languages
Chinese (zh)
Inventor
沈小杰
廖增成
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Daotonghe Innovative Energy Co ltd
Original Assignee
Shenzhen Daotonghe Innovative Energy Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Daotonghe Innovative Energy Co ltd filed Critical Shenzhen Daotonghe Innovative Energy Co ltd
Priority to CN202210529104.6A priority Critical patent/CN115598556A/en
Publication of CN115598556A publication Critical patent/CN115598556A/en
Priority to PCT/CN2023/077917 priority patent/WO2023221587A1/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/392—Determining battery ageing or deterioration, e.g. state of health
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/378—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC] specially adapted for the type of battery or accumulator
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
    • G01R31/396—Acquisition or processing of data for testing or for monitoring individual cells or groups of cells within a battery

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Secondary Cells (AREA)
  • Charge And Discharge Circuits For Batteries Or The Like (AREA)
  • Electric Propulsion And Braking For Vehicles (AREA)

Abstract

The invention relates to the technical field of new energy, 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: the method comprises the steps of obtaining battery data of a power battery and vehicle characteristics of an electric vehicle, calculating a normal health state attenuation value of the power battery according to real-time battery related parameters and a normal attenuation model corresponding to the vehicle characteristics, calculating a fault health state attenuation value of the power battery according to real-time fault type parameters and the fault attenuation model corresponding to the vehicle characteristics, 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. When the health state of the power battery is evaluated, the health state of the power battery can be quickly evaluated without controlling the power battery to be charged and discharged and without a first health state value of the power battery, so that the technical problem of low efficiency existing in the process of evaluating the health state of the power battery in the prior art is solved.

Description

Method for determining state of health of power battery of electric vehicle and server
Technical Field
The invention relates to the technical field of new energy, in particular to a method for determining the health state of a power battery of an electric vehicle and a server.
Background
The service life of the power battery is limited as the most main power source of the new energy electric vehicle, and active substances in the power battery are naturally lost along with the use process, so that the full capacity of the power battery is gradually reduced, and the service life of the power battery is usually evaluated by using the State of Health (SOH) of the battery in the industry.
The conventional method for evaluating the SOH value of the power battery mainly comprises an electrochemical mechanism method and a big data artificial intelligence evaluation method. The electrochemical mechanism method is to analyze data such as voltage, current and the like of the power battery through a charging and discharging process under certain conditions 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 charging and discharging conditions, the efficiency of evaluating the SOH value by the above-mentioned method is low.
The big data artificial intelligence evaluation method is used for obtaining the SOH value of the power battery from a large amount of historical data by utilizing a long-time scale data analysis algorithm. Since the SOH decay of the power battery is a slow and irreversible process, when the power battery of the electric vehicle used for a period of time is subjected to first SOH evaluation, the method lacks an initial value, so that when the power battery is subsequently evaluated by using a long-time scale data analysis algorithm, the convergence of the algorithm is slow, and the SOH value cannot be quickly and reliably output.
Disclosure of Invention
An object of the present invention is to provide a method and a server for determining a health status of a power battery of an electric vehicle, so as to improve the technical problem of low efficiency in evaluating the health status of the power battery in the prior art.
In a first aspect, an embodiment of the present invention provides a method for determining a state of health of a power battery of an electric vehicle, including:
acquiring battery data of the power battery and vehicle characteristics of the electric vehicle, wherein the battery data comprises real-time battery association parameters and real-time fault type parameters;
calculating a normal health state attenuation value of the power battery according to the real-time battery correlation parameter and a normal attenuation model corresponding to the vehicle characteristic;
calculating 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 characteristics;
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.
Optionally, the real-time battery related parameter is one of a driving mileage, an accumulated charging capacity or an accumulated discharging capacity of the power battery.
Optionally, the determining the comprehensive health evaluation value of the power battery according to the normal attenuation value and the fault attenuation value includes:
according to the following formula: SOH t ＝Std-Δα t -Δε t Determining the comprehensive health evaluation value of the power battery, wherein Std is the standard state of health value of the battery, SOH t Δ α for comprehensive health evaluation value t Attenuation value of normal health state, Δ ε t Is a fault health attenuation value.
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 characteristics;
the fault attenuation model is obtained by training second training data of power batteries of a plurality of second historical vehicles with the same vehicle characteristics with the normal attenuation model.
Optionally, the first history vehicle is a vehicle in which a specified battery failure has not occurred;
the second history vehicle is a vehicle in which a specified battery failure has occurred;
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.
Optionally, the normal attenuation model is:
Figure BDA0003645832640000021
wherein, delta alpha t The value of the attenuation is a normal state of health,
Figure BDA0003645832640000022
is the normal decay rate, P t The parameters are associated with the battery in real time.
Optionally, the first training data comprises a first historical battery association parameter and a first battery state of health value for a plurality of first historical vehicles having the same vehicle characteristics;
the normal attenuation rate is:
Figure BDA0003645832640000023
is a normal attenuation rate, η i The to-be-determined attenuation rate of the ith first history vehicle is obtained, and n is the total number of the first history vehicles participating in training the normal attenuation model;
and the undetermined attenuation rate of the ith first historical vehicle is obtained by calculation according to the first historical battery related parameter and the first battery state of health value of the ith first historical vehicle.
Optionally, when the first historical battery related parameter is mileage, the undetermined attenuation rate of the ith first historical vehicle is:
Figure BDA0003645832640000024
η i has the unit of%/10000 km, M wi Is the mileage, SOH, of the ith first history vehicle wi Is a first battery state of health value for an ith first lead vehicle.
Optionally, the fault attenuation model is:
Figure BDA0003645832640000025
wherein, delta epsilon t Attenuation value, x, for healthy state of failure j For the jth real-time fault type parameter, ε j The fault attenuation rate of the jth real-time fault type parameter.
Optionally, the real-time fault type parameter is one of overvoltage fault times, undervoltage fault times, charging overcurrent fault times, discharging overcurrent fault times, high-temperature fault times, low-temperature fault times or specified serious fault times.
Optionally, the second training data includes a plurality of second historical vehicle battery state-of-health values, second historical battery association parameters, and historical fault type parameters that are the same as the vehicle characteristic;
the fault attenuation rate of the jth second historical vehicle is obtained by performing determinant calculation on the health difference values and the historical fault type parameters of a plurality of second historical vehicles according to a linear regression algorithm;
the health difference value of the jth second historical vehicle is the difference value of the expected health value of the jth second historical vehicle and the jth second battery health value;
the expected health value of the jth second historical vehicle is calculated according to the jth second historical battery related parameter and the normal attenuation model.
Optionally, the fault attenuation rate of the jth real-time fault type parameter is:
Figure BDA0003645832640000031
Figure BDA0003645832640000032
Figure RE-GDA0003978545120000033
wherein, delta epsilon yj The health difference value of the jth second history vehicle,
Figure BDA0003645832640000034
for the expected health value, SOH, of the jth second history vehicle yj For the second battery health value of the jth second historical vehicle, std is a standard batteryThe value of the state of health is,
Figure BDA0003645832640000035
at a normal decay rate, P yj A fault history battery related parameter, x, for a jth second history vehicle sj Is the jth history fault type parameter, epsilon, of the s-th second history vehicle j The failure decay rate for the jth historical failure type parameter.
In a second aspect, an embodiment of the present invention provides a server, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the above-described method of determining a state of health of a power battery of an electric vehicle.
In a third aspect, embodiments of the present invention provide a storage medium having stored thereon computer-executable instructions for causing an electronic device to execute the above-described method of determining a state of health of a power battery of an electric vehicle.
In a fourth aspect, embodiments of the present invention provide a computer program product comprising a computer program stored on a non-volatile computer-readable storage medium, the computer program comprising program instructions that, when executed by an electronic device, cause the electronic device to perform the above-described method of determining a state of health of a power battery of an electric vehicle.
Compared with the prior art, the invention at least has the following beneficial effects: in the method for determining the health state of the power battery provided by the embodiment of the invention, the battery data of the power battery and the vehicle characteristics of the electric vehicle are obtained, the battery data comprise real-time battery associated 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 associated parameters and a 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.
Drawings
One or more embodiments are illustrated by way of example in the accompanying drawings, which correspond to the figures in which like reference numerals refer to similar elements and which are not to scale unless otherwise specified.
Fig. 1 is a schematic structural diagram of a state of health determination system for a power battery according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a method for determining a state of health of a power battery of an electric vehicle according to an embodiment of the present invention;
FIG. 3 is a schematic view of a scene for training a normal attenuation model and a fault attenuation model according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a state of health determination device for a power battery of an electric vehicle according to an embodiment of the present invention;
fig. 5 is a schematic circuit structure diagram of a server according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without any inventive step, are within the scope of the present invention.
It should be noted that, if not conflicted, the various features of the embodiments of the invention may be combined with each other within the scope of protection of the invention. Additionally, while functional block divisions are performed in device schematics, with logical sequences shown in flowcharts, in some cases, the steps shown or described may be performed in a different order than the block divisions in the devices, or in the flowcharts. Furthermore, the terms "first," "second," and "third," as used herein, do not limit the order of data and execution, but merely distinguish one element from another, whether identical or similar in function and effect.
Referring to fig. 1, a health status determining system 100 includes a Vehicle Communication device 11 (VCI) and a server 12, where the server 12 is in Communication connection with the Vehicle Communication device 11, where the Communication connection includes wired Communication connection or wireless Communication connection, and the wired Communication connection includes various Communication connections that use tangible media such as metal wires and optical fibers to transmit information. The wireless communication connection comprises 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.
The vehicle communication device 11 is configured to be plugged into an On Board Diagnostics (OBD) interface of the electric vehicle 13, and the vehicle communication device 11 communicates with the electric vehicle 13 based On the OBD interface to obtain vehicle data of the electric vehicle 13, where the vehicle data includes a fault code, battery data, or vehicle characteristics. The fault code is used to indicate the type of fault of the electric vehicle. The battery data is data associated with a power battery of the electric vehicle. The vehicle feature is a vehicle type feature and/or a property feature for representing an electric vehicle.
As described above, the vehicle communication device 11 obtains the battery data and the vehicle characteristics of the electric vehicle 13, and then packages the battery data and the vehicle characteristics to the server 12, and the server 12 selects the corresponding normal damping model 14 and the corresponding fault damping model 15 according to the vehicle characteristics, inputs the battery data into the normal damping model 14 and the fault damping model 15, respectively, and determines the comprehensive health evaluation value of the power battery according to the output results of the normal damping model 14 and the fault damping model 15.
It is understood that the server may be a physical server or a logical server virtualized from a plurality of physical servers. The server may also be a server cluster formed by a plurality of servers capable of communicating with each other, and each functional module may be respectively distributed on each server in the server cluster.
As another aspect of the embodiments of the present invention, an embodiment of the present invention provides a method for determining a state of health of a power battery of an electric vehicle, and the method provided by this embodiment is applied to a plurality of application scenarios, such as after-market diagnosis of an automobile, battery maintenance, public charging, insurance damage assessment, and residual value assessment. Referring to fig. 2, the method for determining the state of health of the power battery of the electric vehicle includes:
s21, battery data of the power battery and vehicle characteristics of the electric vehicle are obtained, wherein the battery data comprise real-time battery association parameters and real-time fault type parameters.
In this step, the vehicle communication device communicates with the electric vehicle, the electric vehicle sends the battery data and the vehicle characteristics of the power battery to the vehicle communication device, and the vehicle communication device packages the battery data and the vehicle characteristics and sends the packaged data and the packaged vehicle characteristics to the server.
As mentioned above, the battery data includes the real-time battery related parameter, the real-time battery related parameter is a parameter for indicating the state of health of the power battery, and the real-time fault type parameter is a number of times for indicating the corresponding fault type of the power battery.
In some embodiments, the real-time battery-related parameter is one of a mileage, an accumulated charge capacity or an accumulated discharge capacity of the power battery.
The driving mileage is kilometers of the electric vehicle, and the unit of the driving mileage may be ten thousand kilometers (10000 kilometers). The driving mileage is related to the health state of the power battery, the larger the driving mileage is, the stronger the attenuation degree of the power battery is, and the smaller the driving mileage is, the weaker the attenuation degree of the power battery is, so that the driving mileage can reflect the health state of the power battery.
The accumulated charging capacity is the sum of the charging capacities of the power battery in multiple times of charging, and the accumulated discharging capacity is the sum of the discharging capacities of the power battery in multiple times of 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 accumulated charging capacity is correlated with the health state of the power battery, the larger the accumulated charging capacity is, the stronger the attenuation degree of the power battery is, and the smaller the accumulated charging capacity is, the weaker the attenuation degree of the power battery is, so the accumulated charging capacity can reflect the health state of the power battery.
As previously described, the battery data includes a real-time fault type parameter, which in some embodiments is one of a number of over-voltage faults, a number of under-voltage faults, a number of charging over-current faults, a number of discharging over-current faults, a number of high-temperature faults, a number of low-temperature faults, or a number of other serious faults.
The overvoltage fault frequency is a total frequency corresponding to the overvoltage fault, where the overvoltage fault e1 includes an overvoltage fault of each single battery or a total overvoltage fault of the system, 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 overvoltage faults, and the number of overvoltage faults =2. At time t3, the power battery has overvoltage faults, and the number of overvoltage faults =3.
The number of times of the undervoltage faults is the total number of times corresponding to the undervoltage faults, wherein the undervoltage faults e2 include undervoltage faults of each single battery, short-circuit faults in the single battery or total voltage undervoltage faults of the system and the like.
The charging overcurrent fault frequency is the total frequency corresponding to the charging overcurrent fault type, wherein the charging overcurrent fault e3 comprises a fast and slow charging overcurrent fault or a charging current abnormal fault and the like.
The discharge overcurrent fault frequency is the total frequency corresponding to the discharge overcurrent fault, wherein the discharge overcurrent fault e4 includes a discharge overcurrent fault, a discharge current abnormal fault or a short-circuit fault and the like.
The high-temperature fault frequency is the total frequency corresponding to the high-temperature fault, wherein the high-temperature fault e5 comprises a battery charging high-temperature fault, a battery discharging high-temperature fault, an environmental high-temperature fault, a thermal management high-temperature fault or a controller high-temperature fault and the like.
The low-temperature fault frequency is the total frequency corresponding to the low-temperature fault, wherein the low-temperature fault e6 comprises a battery charging low-temperature fault, a battery discharging low-temperature fault, an environmental low-temperature fault, a thermal management low-temperature fault and the like.
The number of designated serious faults is the total number corresponding to the designated serious faults, wherein the designated serious fault e7 is a fault except the fault type in the above 6.
It can be understood that in the battery management system of the electric vehicle, there are hundreds of battery faults related to the power battery, and the present embodiment classifies the battery faults affecting the health state of the power battery into the above 7 categories according to the comprehensive analysis of the characteristics and the electrochemical mechanism of the power battery. However, it is understood that those skilled in the art can classify the battery faults associated with the power battery according to other classification purposes, and the above-provided 7-class battery faults do not set any limit to the protection scope of the present invention.
In some embodiments, the vehicle characteristics include vehicle type characteristics of the electric vehicle, and the vehicle type characteristics are used for the vehicle type of the electric vehicle, wherein the vehicle type characteristics may be represented by MMYB information, and the MMYB information is a general term of information such as a manufacturer (Make), a vehicle type (Model), a Year money (Year), and a Battery version (Battery) of the new energy vehicle.
In some embodiments, the vehicle characteristic includes a property characteristic of the electric vehicle, the property characteristic being used to represent a territory in which the electric vehicle is driven, wherein the property characteristic can be represented by geographic location information, the geographic location information being localizable by a localization system of the electric vehicle, such as where the geographic location information is southern mountain in Guangdong Shenzhen.
And S22, calculating a normal health state attenuation value of the power battery according to the real-time battery correlation parameter and a normal attenuation model corresponding to the vehicle characteristic.
In this step, the normal attenuation model is a model for calculating a normal healthy state attenuation value, and the normal healthy state attenuation value is an attenuation value of the power battery evaluated from a normal dimension of the power battery. In the embodiment, after the real-time battery related parameters are input into the normal attenuation model, the normal attenuation model can output the normal state of health attenuation value of the power battery.
It can be understood that the vehicle characteristics of the electric vehicles are different, and the similarity of the battery health attenuation curves between the electric vehicles is smaller, or the vehicle characteristics of the electric vehicles are the same, and the similarity of the battery health attenuation curves between the electric vehicles is larger, so that the embodiment can construct a normal attenuation model according to the vehicle characteristics, and different vehicle characteristics correspond to different normal attenuation models, thereby being beneficial to improving the accuracy of calculating the attenuation value in the normal health state.
In some embodiments, the present embodiment obtains a vehicle feature, and searches a normal attenuation model matching the vehicle feature in a normal model library according to the vehicle feature and a normal feature tag, where the normal model library includes a plurality of normal feature tags and normal attenuation models corresponding to the normal feature tags.
And S23, calculating a fault health state attenuation value of the power battery according to the real-time fault type parameters and the fault attenuation model corresponding to the vehicle characteristics.
In this step, the fault attenuation model is a model for calculating a fault state-of-health attenuation value, and the fault state-of-health attenuation value is an attenuation value of the power battery evaluated from a fault dimension of the power battery. In the embodiment, after the real-time fault type parameters are input into the fault attenuation model, the fault attenuation model can output the fault health state attenuation value of the power battery.
As described above, the vehicle characteristics of the electric vehicles are different, and the similarity of the battery key attenuation curves between the electric vehicles is relatively small, so that the fault attenuation model can be constructed according to the vehicle characteristics in the embodiment, and different vehicle characteristics correspond to different fault attenuation models, which is beneficial to improving the accuracy of calculating the fault health state attenuation value.
In some embodiments, the present embodiment obtains vehicle characteristics, and searches a fault attenuation model matching the vehicle characteristics in a fault model library according to the vehicle characteristics and fault characteristic labels, where the fault model library includes a plurality of fault characteristic labels and fault attenuation models corresponding to the fault characteristic labels.
In some embodiments, the vehicle features are vehicle type features, and the present embodiment searches for a normal attenuation model and a fault attenuation model respectively matching the vehicle type features, that is, a single vehicle type feature may correspond to a normal attenuation model and a fault attenuation model respectively.
In some embodiments, the vehicle feature is an attribute feature, and the present embodiment searches for a normal attenuation model and a fault attenuation model matching the attribute feature respectively, that is, a single attribute feature may correspond to the normal attenuation model and the fault attenuation model respectively.
In some embodiments, the vehicle features are vehicle type features and location features, and the present embodiment searches for a normal attenuation model and a fault attenuation model matching the vehicle type features and the location features, respectively, that is, the normal attenuation model and the fault attenuation model are determined by the vehicle type features and the location features together.
And S24, 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 this step, the comprehensive health evaluation value is a value for evaluating the health of the power battery, where the comprehensive health evaluation value includes a battery state of health value, for example, the battery state of health value may be represented by the SOH value as described above, and this embodiment is according to the following formula: SOH t ＝Std-Δα t -Δε t Determining the comprehensive health evaluation value of the power battery, wherein Std is the health state value of the standard battery, SOH t Δ α for comprehensive health evaluation value t Is a normal healthValue of steady state attenuation,. DELTA.. Epsilon t Is a fault health attenuation value. In some embodiments, the standard state of health value Std may be customized by engineers according to business needs, such as a standard state of health value Std of 100%.
In some embodiments, the method for determining the state of health of a power battery of an electric vehicle further comprises: and judging whether the comprehensive health evaluation value is less than or equal to a first preset threshold value, if so, generating battery health evaluation information, and if not, generating battery health evaluation information according to the comprehensive health evaluation value, wherein the battery warning information is used for prompting a user to replace or maintain the power battery, and the battery warning information can be warning information in any form, for example, the battery warning information is character warning information, voice warning information or flash warning information. The battery health evaluation information is health grade information in which the health state of the power battery is evaluated, for example, the battery health evaluation information includes "good", or "general" and the like.
It is understood that the first preset threshold may be customized by engineers according to business requirements, such as 70% for example.
In some embodiments, different from the above embodiments, the integrated health evaluation value includes a battery health attenuation value, and the present embodiment may add the normal state of health attenuation value and the fault state of health attenuation value to obtain the battery health attenuation value, and the present embodiment is according to the following formula: Δ SOH t ＝Δα t +Δε t And determining a battery health attenuation value of the power battery.
In some embodiments, the method for determining state of health of a power battery of an electric vehicle further comprises: and judging whether the comprehensive health evaluation value is greater than or equal to a second preset threshold value, if so, generating battery warning information, and if not, generating battery health evaluation information according to the comprehensive health evaluation value.
It is understood that the second preset threshold may be customized by engineers according to business requirements, such as 80% for the second preset threshold.
As described above, different from the prior art, in the embodiment, when the health state of the power battery is evaluated, the power battery does not need to be controlled to be charged and discharged, that is, a user needs to set equipment for controlling the power battery to be charged and discharged, and the health state of the power battery can be quickly evaluated when the electric vehicle is in a stop working state, so that the technical problem of low efficiency when the health state of the power battery is evaluated in the prior art is solved, and the application range of the method is expanded.
As described above, unlike the prior art, in the present embodiment, when evaluating the state of health of the power battery, the first state of health value of the power battery is not needed, that is, the comprehensive health evaluation value of the electric vehicle can be output for one-time detection of the electric vehicle without historical data, thereby improving the technical problem of low efficiency when evaluating the state of health of the power battery in the prior art. In addition, an electrochemical mechanism method or a big data artificial intelligence evaluation method is adopted subsequently, when the comprehensive health evaluation value of the electric vehicle is tracked and evaluated and the initial SOH value is needed, the initial SOH value can be provided by adopting the method, and therefore the method provided by the embodiment is more flexible and wider in application range.
In addition, the electrochemical mechanism method or the big data artificial intelligence evaluation method is often lack of an initial value, so that the convergence of the algorithm is slow.
In some embodiments, the normal decay model is trained from first training data for power cells of a first plurality of historical vehicles having the same vehicle characteristics. The fault attenuation model is obtained by training the normal attenuation model according to second training data of power batteries of a plurality of second historical vehicles with the same characteristics as the vehicles.
The first training data is data for training to generate a normal attenuation model. The second training data is data for training the generation of the fault attenuation model in cooperation with the normal attenuation model. The first historical vehicle is: the electric vehicle before the generation of the normal damping model is trained. The second history vehicle is: the electric vehicle before the fault attenuation model is generated is trained. For example, training at the time point t11 generates a normal attenuation model, and the present embodiment selects training data of a plurality of first electric vehicles as the first training data, where the first electric vehicles are first historical vehicles. At the time point t22, the fault attenuation model is generated by training, and the embodiment selects training data of a plurality of second electric vehicles as second training data, where the second electric vehicles are second historical vehicles.
In the embodiment, the normal attenuation model is trained first, and then the fault attenuation model is trained by combining the second training data on the basis of the normal attenuation model, so that the fault attenuation model can be generated by utilizing the evolution of the normal attenuation model, and compared with a method for constructing the fault attenuation model separately by abandoning 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 favorable for generating a more reliable and accurate fault attenuation model.
In some embodiments, the vehicle characteristic is a vehicle type characteristic, and the present embodiment may select training data of a power battery of a first historical vehicle identical to the vehicle type characteristic as the first training data, and may select training data of a power battery of a second historical vehicle identical to the vehicle type characteristic as the second training data.
In some embodiments, the point of difference from the above-described embodiments is that the vehicle feature is an attribute feature, and the present embodiment may select, as the first training data, training data of a power battery of a first history vehicle that is the same as the attribute feature, and may select, as the second training data, training data of a power battery of a second history vehicle that is the same as the attribute feature.
In some embodiments, different from the above-described embodiments in that the vehicle characteristics include a vehicle type characteristic and an attribute characteristic, the present embodiment may select, as the first training data, training data of a power battery of a first history vehicle that is the same as the vehicle type characteristic and the same as the attribute characteristic, and may select, as the second training data, training data of a power battery of a second history vehicle that is the same as the vehicle type characteristic and the same as the attribute characteristic.
In some embodiments, the first and second history vehicles are both vehicles in which a specified battery failure has occurred, the specified battery failure being any one of an overvoltage failure, an undervoltage failure, a charging overcurrent failure, a discharging overcurrent failure, a high-temperature failure, a low-temperature failure, or a specified severe failure.
In the embodiment, the normal attenuation model can be trained and generated 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, the fault attenuation model can be trained and generated 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 health state of the power battery can be rapidly evaluated in the embodiment.
In some embodiments, different from the above embodiments, the first historical vehicle is a vehicle in which a specified battery fault has occurred, and the second historical vehicle is a vehicle in which a specified battery fault has not occurred.
In some embodiments, the point different from the above-described embodiments is that the first history vehicle is a vehicle in which a specified battery failure has not occurred, and the second history vehicle is a vehicle in which a specified battery failure has occurred. The first historical vehicle is a vehicle without the specified battery fault, the training data of the vehicle without the specified battery fault is selected as the first training data, and the influence of the training data of the vehicle with the specified battery fault on the normal attenuation model is eliminated, so that the generation of a more accurate and reliable normal attenuation model is facilitated.
In the same way, the second historical vehicle is a vehicle with the specified battery fault, the influence of the training data of the vehicle without the specified battery fault on the fault attenuation model is eliminated, and the training data of the vehicle with the specified battery fault is selected as the second training data, so that the more accurate and reliable fault attenuation model is generated.
In some embodiments, the normal attenuation model is:
Figure BDA0003645832640000101
wherein, delta alpha t The value of the attenuation is a normal state of health,
Figure BDA0003645832640000102
at a normal decay rate, P t The parameters are associated with the real-time battery. Wherein, the normal attenuation rate is the attenuation rate of the power battery evaluated from the normal dimension of the power battery.
When the server obtains the real-time battery related parameter P of the electric vehicle t Then the real-time battery related parameter P can be associated t Substituting the normal attenuation model into which the normal attenuation model can output the attenuation value delta alpha in the normal health state t 。
In some embodiments, the first training data includes a first historical battery association parameter and a first battery state of health value for a plurality of first historical vehicles having the same vehicle characteristics. As previously described, the first historical battery related parameter may be one of a mileage, an accumulated charge capacity or an accumulated discharge capacity of the power battery, and the first battery state of health value may be a battery state of health value of the first historical vehicle obtained in advance. It is to be understood that the first battery state-of-health value may be calculated by any suitable algorithm for estimating the SOH value of the power battery, and the server directly calls the result provided by the algorithm for estimating the SOH value of the power battery, or the first battery state-of-health value may also be obtained by estimating the SOH value of the power battery by the method provided in this embodiment, and then, the existing first battery state-of-health value is used for performing iterative update.
The normal attenuation rate is:
Figure BDA0003645832640000111
is a normal attenuation rate, η i And n is the total number of the first historical vehicles participating in training the normal attenuation model. The undetermined attenuation rate of the ith first historical vehicle is according to the ith first historical vehicleA first history battery related parameter and a first battery state of health value of the history vehicle are calculated.
For example, the total number n of the first historical vehicles participating in the training of the normal attenuation model is 100, and the undetermined attenuation rate of the 1 st first historical vehicle is η 1 The undetermined decay rate of the 2 nd first history vehicle is η 2 By analogy, the final normal attenuation rate
Figure BDA0003645832640000112
The embodiment obtains the normal attenuation rate by averaging the undetermined attenuation rates of a plurality of first historical vehicles
Figure BDA0003645832640000113
The method is favorable for obtaining more accurate and reliable normal attenuation rate.
In some embodiments, when the first historical battery related parameter is mileage, the pending decay rate of the ith first historical vehicle is:
Figure BDA0003645832640000114
η i has the unit of%/10000 km, M wi Is the mileage, SOH, of the ith first history vehicle wi Is the first battery state of health value for the ith first history vehicle. For example, M wi Is 100000km, SOH wi Is 95%, then η i Is 0.5, which has a unit of%/10000 km, i.e.% 1 ten thousand km.
For another example, the normal attenuation rate is obtained by averaging a plurality of undetermined attenuation rates
Figure BDA0003645832640000117
Is 0.5. Assuming real-time battery associated parameters P t 60000km =60000/10000=6 kilometres, and substituting it into the normal attenuation model
Figure BDA0003645832640000115
Then there is
Figure BDA0003645832640000116
In some embodiments, different from the above embodiments, when the first historical battery related parameter may also be an accumulated charge capacity or an accumulated discharge capacity, the undetermined attenuation rate of the ith first historical vehicle is:
Figure BDA0003645832640000121
η i in units of%/Ah, C wi The accumulated charge capacity or the accumulated discharge capacity of the ith first history vehicle.
In some embodiments, the fault attenuation model is:
Figure BDA0003645832640000122
wherein, delta epsilon t Attenuation value, x, for the faulty health status j For the jth real-time fault type parameter, ε j The fault decay rate for the jth real-time fault type parameter. Wherein the fault attenuation rate epsilon of the jth real-time fault type parameter j In the fault dimension of the power battery, the decay rate of the power battery under the fault action of the jth real-time fault type is evaluated. For example, the fault attenuation model has a total of 7 real-time fault type parameters, and the fault attenuation rates of the 7 real-time fault type parameters are respectively 0.244, 0.112, 1.112, 0.774, 0.365, 0.585 and 0.119 in sequence.
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 specified number of catastrophic faults. Assuming that the 7 real-time fault type parameters of the electric vehicle D1 are sequentially { f1, f2, f3, f4, f5, f6, f7} = {4,6,8,3,1,5,4}, respectively, and the 7 real-time fault type parameters of the electric vehicle D1 are input into the fault attenuation model, the fault health state attenuation value is:
Δε t
＝0.244*4+0.112*6+1.112*8+0.774*3+0.365*1+0.585*5+0.119*4＝16.6 32。
assuming that 7 real-time fault type parameters of the electric vehicle D2 are { f1, f2, f3, f4, f5, f6, f7} = {3,6,5, 3,4,3}, respectively, and inputting the 7 real-time fault type parameters of the electric vehicle D2 into the fault attenuation model, the fault health state attenuation value is:
Δε t
＝0.244*3+0.112*6+1.112*5+0.774*5+0.365*3+0.585*4+0.119*3＝14.6 26.632。
assuming that 7 real-time fault type parameters of the electric vehicle D3 are { f1, f2, f3, f4, f5, f6, f7} = {1,2,1,0, 1,3} in sequence, and inputting the 7 real-time fault type parameters of the electric vehicle D3 into the fault attenuation model, the fault health state attenuation value is:
Δε t
＝0.244*1+0.112*2+1.112*4+0.774*0+0.365*0+0.585*1+0.119*3＝5.85 8。
in some embodiments, the second training data includes a second battery state of health value, a second historical battery association parameter, and a historical fault type parameter for a plurality of second historical vehicles having the same vehicle characteristics. As previously described, the second historical battery related parameter may be one of a driving distance, an accumulated charging capacity or an accumulated discharging capacity of the power battery, and the second battery state of health value may be a battery state of health value of the second historical vehicle obtained in advance. It can be understood that the second battery state of health value may be calculated by any suitable algorithm for estimating the SOH value of the power battery, and the server directly calls the result provided by the algorithm for estimating the SOH value of the power battery, or the second battery state of health value may also be obtained by estimating the SOH value of the power battery by the method provided in this embodiment, and then the second battery state of health value is updated iteratively by using the existing second battery state of health value. The historical fault type parameter may be one of the number of overvoltage faults, the number of undervoltage faults, the number of charging overcurrent faults, the number of discharging overcurrent faults, the number of high-temperature faults, the number of low-temperature faults, or the number of specified serious faults.
And the fault attenuation rate of the jth second historical vehicle is obtained by performing determinant calculation on the health difference values and the historical fault type parameters of a plurality of second historical vehicles according to a linear regression algorithm, wherein the health difference value of the jth second historical vehicle is the difference value between the expected health value of the jth second historical vehicle and the health value of a jth second battery, and the expected health value of the jth second historical vehicle is obtained by calculation according to the associated parameters of the jth second historical battery and a normal attenuation model.
It will be appreciated that any suitable type of linear regression algorithm may be selected for the linear regression algorithm herein, such as a least squares method.
The expected health value for the jth second historical vehicle is:
Figure BDA0003645832640000131
the expected state of health of the jth second historical vehicle, std is a standard battery state of health value,
Figure BDA0003645832640000132
at a normal decay rate, P yj A failure history battery association parameter for the jth second history vehicle.
As previously described, the jth second battery health value may be derived by the server invoking existing battery health values of the jth second historical vehicle.
The health difference value of the jth second history vehicle is:
Figure BDA0003645832640000133
Δε yj is the health Difference, SOH, of the jth second History vehicle yj Is a second battery health value for a jth second history vehicle.
The failure attenuation rate of the jth second history vehicle is:
Figure RE-GDA0003978545120000134
wherein x is sj For the jth historical fault type parameter, ε, of the s-th second historical vehicle j The unit of each fault attenuation rate is% for the fault attenuation rate of the jth historical fault type parameter.
For example, assume that the fault attenuation model has a total of 7 real-time fault type parameters, i.e., r =7. Assume again that 7 historical fault type parameters for 5 second historical vehicles are taken.
The 7 historical failure type parameters of the electric vehicle L1 are respectively {4,6,8,3,1,5,4},
Figure BDA0003645832640000135
91.6% SOH y1 The content was found to be 75%. The 7 historical failure type parameters of the electric vehicle L2 are {2,4,5,7,2,5,3},
Figure BDA0003645832640000136
95.9% SOH y2 The content was 80%. The 7 historical failure type parameters of the electric vehicle L3 are respectively {3,5,6,7,1,6,4},
Figure BDA0003645832640000137
89.7% of SOH y3 The content was 72%. The 7 historical fault type parameters of the electric vehicle L4 are {3,6,5, 3,4,3},
Figure BDA0003645832640000141
96.6% SOH y4 The content was 82%. The 7 historical failure type parameters of the electric vehicle L5 are respectively {2,6,8,4,1, 4},
Figure BDA0003645832640000142
94.3% of SOH y5 The content was 78%. The 7 historical failure type parameters of the electric vehicle L6 are {0, 1,0,2} respectively,
Figure BDA0003645832640000143
94.7% SOH y5 The content was 93%. The 7 historical failure type parameters of the electric vehicle L7 are {1,2,1,0, 1,3} respectively,
Figure BDA0003645832640000144
92.5% SOH y5 The content was 90%. Then there are:
Δε y1 ＝16.6％，Δε y2 ＝15.9％，Δε y3 ＝17.7％，Δε y4 ＝14.6％，Δε y5 ＝16.3％，
Δε y6 ＝1.7％，Δε y7 ＝2.5％
Figure RE-GDA0003978545120000145
the above formula is identified according to the least square method to obtain epsilon 1 、ε 2 、ε 3 、ε 4 、ε 5 、 ε 6 、ε 7 Respectively as follows: 0.244, 0.112, 1.112, 0.774, 0.365, 0.585, 0.119, and the failure attenuation rates of 7 battery failures can be obtained, it can be understood that, in this embodiment, the failure attenuation rate of each battery failure can be estimated by the least square method by adding 8 or 9 battery failures, and matching one failure attenuation rate for each battery failure.
It will also be appreciated that a smaller number of battery faults may be added and a fault attenuation rate may be matched for each battery fault, for example, only 2 battery faults may be added and the fault attenuation rates of the two battery faults may be estimated by a minimum two-step multiplication.
As described above, in this embodiment, a plurality of battery faults are associated, the fault attenuation rate of each battery fault is comprehensively calculated through a linear regression algorithm, and the fault attenuation rates of a plurality of battery faults are substituted into the fault attenuation rates
Figure BDA0003645832640000146
Calculating a fail state of health decay value Δ ε relative to using a single battery fault t The present embodiment is capable of attenuating various battery faults versus fault state of health by a value Δ ε t Synthesizing and correlating to reduce error versus fault state-of-health attenuation value delta epsilon for single battery faults t So that a more reliable and accurate fault attenuation model can be trained.
As mentioned above, the present embodiment is divided into a model training process and an actual application process, wherein fig. 1 shows the actual application process for rapidly evaluating the comprehensive health evaluation value of the power battery, and the model training process is described in detail below with reference to fig. 3, specifically as follows:
as shown in fig. 3, the vehicle characteristics of each of the first history vehicles 31 and each of the second history vehicles 32 are the same, for example, each of the first history vehicles 31 and each of the second history vehicles 32 are the same vehicle type characteristics and the same attribute characteristics.
The first vehicle communication device 33 is plugged into an OBD interface of the first historic vehicle 31, and the first vehicle communication device 33 communicates with the first historic vehicle 31 based on the OBD interface to acquire first training data of the first historic vehicle 31, wherein the first training data includes first battery data and first vehicle characteristics, and the battery data includes a first driving range, 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 and generates the normal attenuation model 35 according to the first driving range and the first battery state of health value.
The second vehicle communication device 36 is plugged into an OBD interface of the second historic vehicle 32, and the second vehicle communication device 36 communicates with the second historic vehicle 32 based on the OBD interface to obtain second training data of the second historic vehicle 32, wherein the second training data includes second battery data and second vehicle characteristics, and the battery data includes a second driving mileage, a second battery health status value and a second fault type parameter. The second vehicle communication device 36 transmits the second training data to the server 34.
The server 34 inputs the second driving range into the normal decay model 35 resulting in the expected health value. The server 34 then subtracts the expected health value from the second battery state of health value to obtain a health difference value. Then, the server calculates the failure attenuation rate of each battery failure according to the health difference values of the plurality of second history vehicles 32 and the second failure type parameters. Finally, the server generates a fault attenuation model 37 based on the fault attenuation rate for each battery fault.
It should be noted that, in the foregoing embodiments, a certain order does not necessarily exist between the foregoing steps, and those skilled in the art can understand, according to the description of the embodiments of the present invention, that in different embodiments, the foregoing steps may have different execution orders, that is, may be executed in parallel, may also be executed interchangeably, and the like.
As another aspect of the embodiments of the present invention, the embodiments of the present invention provide a state of health determination apparatus for a power battery of an electric vehicle. The state of health determining apparatus of a power battery of an electric vehicle may be a software module, where the software module includes a plurality of instructions, and the instructions are stored in a memory, and the processor may access the memory and call the instructions to execute the instructions, so as to complete the state of health determining method of a power battery of an electric vehicle set forth in the foregoing embodiments.
In some embodiments, the health status determination device of the power battery of the electric vehicle may also be built by hardware devices, for example, the health status determination device of the power battery of the electric vehicle may be built by one or more than two chips, and the chips may work in coordination with each other to complete the health status determination method of the power battery of the electric vehicle as set forth in the above embodiments. For another example, the health status determination apparatus for a power battery of an electric vehicle may also be built up from various types of 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 device, discrete gate or transistor logic, discrete hardware components, or any combination of these components.
Referring to fig. 4, the state of health determination apparatus 400 for a power battery of an electric vehicle includes: a data acquisition module 41, a normal attenuation calculation module 42, a fault attenuation calculation module 43, and a state of health determination module 44. The data acquiring module 41 is configured to acquire battery data of the power battery and vehicle characteristics of the electric vehicle, where the battery data includes a real-time battery association parameter and a real-time fault type parameter. The normal attenuation calculating module 42 is configured to calculate a normal health state attenuation value of the power battery according to the real-time battery related parameter and a normal attenuation model corresponding to the vehicle characteristic. The fault attenuation calculating module 43 is configured to calculate a fault state-of-health attenuation value of the power battery according to the real-time fault type parameter and the fault attenuation model corresponding to the vehicle characteristic. 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.
When the health state of the power battery is evaluated, the health state of the power battery can be quickly evaluated without controlling the power battery to charge and discharge and without the first health state value of the power battery, so that the technical problem of low efficiency existing in the process of evaluating the health state of the power battery in the prior art is solved.
In some embodiments, the real-time battery-related parameter is one of a mileage, an accumulated charge capacity or an accumulated discharge capacity of the power battery.
In some embodiments, the health status determination module 44 is specifically configured to: according to the following formula: SOH t ＝Std-Δα t -Δε t Determining the comprehensive health evaluation value of the power battery, wherein Std is the health state value of the standard battery, SOH t For comprehensive health assessment value, Δ α t Attenuation value of normal health state, Δ ε t Is a fault health attenuation value.
In some embodiments, the normal decay model is trained from first training data for power cells of a first plurality of historical vehicles having the same vehicle characteristics. The fault attenuation model is obtained by training the normal attenuation model according to second training data of power batteries of a plurality of second historical vehicles with the same characteristics as the vehicles.
In some embodiments, the first history vehicle is a vehicle in which a specified battery failure has not occurred. The second history vehicle is a vehicle in which a specified battery failure has occurred. 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.
In some embodiments, the normal attenuation model is:
Figure BDA0003645832640000161
wherein, delta alpha t The value of the attenuation is a normal state of health,
Figure BDA0003645832640000162
at a normal decay rate, P t The parameters are associated with the real-time battery.
In some embodiments, the first training data includes a first historical battery association parameter and a first battery state of health value for a plurality of first historical vehicles having the same vehicle characteristics. The normal attenuation rate is:
Figure BDA0003645832640000163
is a normal attenuation rate, η i The undetermined attenuation rate of the ith first historical vehicle is shown, and n is the total number of the first historical vehicles participating in the training of the normal attenuation model. The to-be-determined attenuation rate of the ith first historical vehicle is obtained by calculation according to the first historical battery related parameter and the first battery state of health value of the ith first historical vehicle.
In some embodiments, when the first historical battery related parameter is mileage, the pending decay rate of the ith first historical vehicle is:
Figure BDA0003645832640000171
η i has the unit of%/10000 km, M wi Is the mileage, SOH, of the ith first history vehicle wi Is a first battery state of health value for an ith first lead vehicle.
In some embodiments, the fault attenuation model is:
Figure BDA0003645832640000172
wherein, delta epsilon t Attenuation value of health status of fault, x j For the jth real-time fault type parameter, ε j The fault decay rate for the jth real-time fault type parameter.
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 specified number of catastrophic faults.
In some embodiments, the second training data includes second battery state of health values, second historical battery association parameters, and historical fault type parameters for a second plurality of historical vehicles having the same vehicle characteristics.
And the fault attenuation rate of the jth second historical vehicle is obtained by carrying out determinant calculation on the health difference values and the historical fault type parameters of a plurality of second historical vehicles according to a linear regression algorithm.
The health difference value of the jth second historical vehicle is the difference value of the expected health value of the jth second historical vehicle and the jth second battery health value;
the expected health value of the jth second historical vehicle is calculated according to the jth second historical battery related parameter and the normal attenuation model.
In some embodiments, the fault decay rate of the jth real-time fault type parameter is:
Figure BDA0003645832640000173
Figure BDA0003645832640000174
Figure RE-GDA0003978545120000175
wherein, Δ ε yj For the health difference value of the jth second history vehicle,
Figure BDA0003645832640000176
for the expected health value, SOH, of the jth second history vehicle yj A second battery state of health value for a jth second historical vehicle, std a standard battery state of health value,
Figure BDA0003645832640000177
at a normal decay rate, P yj A fault history battery related parameter, x, for a jth second history vehicle sj Is the jth history fault type parameter of the s second history vehicle, epsilon j The fault decay rate for the jth historical fault type parameter.
The device for determining the state of health of the power battery of the electric vehicle can execute the method for determining the state of health of the power battery of the electric vehicle provided by the embodiment of the invention, and has functional modules and beneficial effects corresponding to the execution method. For technical details that are not elaborately described in the embodiment of the apparatus for determining state of health of a power battery of an electric vehicle, reference may be made to a method for determining state of health of a power battery of an electric vehicle provided by an embodiment of the present invention.
Referring to fig. 5, fig. 5 is a schematic circuit diagram of a server according to an embodiment of the present invention. As shown in fig. 5, the server 500 includes one or more processors 51 and a memory 52. In fig. 5, one processor 51 is taken as an example.
The processor 51 and the memory 52 may be connected by a bus or other means, such as the bus connection in fig. 5.
The memory 52 is a storage medium, and can be used to store nonvolatile software programs, nonvolatile computer-executable programs, and modules, such as program instructions/modules corresponding to the method for determining the state of health of a power battery of an electric vehicle in the embodiment of the present invention. The processor 51 executes various functional applications and data processing of the state of health determination device of the power battery of the electric vehicle by running the nonvolatile software programs, instructions and modules stored in the memory 52, that is, the state of health determination method of the power battery of the electric vehicle provided by the above method embodiment and the functions of the various modules or units of the above device embodiment are realized.
The memory 52 may include high speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state memory device. In some embodiments, the memory 52 may optionally include memory located remotely from the processor 51, and such remote memory may be connected to the processor 51 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The program instructions/modules are stored in the memory 52 and, when executed by the one or more processors 51, perform the method of determining the state of health of a power battery of an electric vehicle in any of the method embodiments described above.
Embodiments of the present invention also provide a storage medium storing computer-executable instructions, which are executed by one or more processors, such as one of the processors 51 in fig. 5, and enable the one or more processors to execute the method for determining the state of health of a power battery of an electric vehicle in any of the above method embodiments.
Embodiments also provide a computer program product comprising a computer program stored on a non-volatile computer readable storage medium, the computer program comprising program instructions which, when executed by a server, cause the server to perform any one of the methods of determining a state of health of a power battery of an electric vehicle.
The above-described embodiments of the apparatus or device are merely illustrative, wherein the unit modules described as separate parts may or may not be physically separate, and the parts displayed as module units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network module units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment may be implemented by software plus a general hardware platform, and may also be implemented by hardware. Based on such understanding, the above technical solutions essentially or contributing to the related art may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; within the idea of the invention, also technical features in the above embodiments or in different embodiments may be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Claims (13)

1. A method of determining a state of health of a power battery of an electric vehicle, characterized by comprising:
acquiring battery data of the power battery and vehicle characteristics of the electric vehicle, wherein the battery data comprises real-time battery association parameters and real-time fault type parameters;
calculating a normal health state attenuation value of the power battery according to the real-time battery correlation parameter and a normal attenuation model corresponding to the vehicle characteristic;
calculating 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 characteristics;
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.
2. The method of claim 1, wherein the real-time battery-related parameter is one of a mileage, a cumulative charge capacity or a cumulative discharge capacity of a power battery.
3. The method according to claim 1, wherein the determining a comprehensive health assessment value of the power battery according to the normal attenuation value and the fault attenuation value comprises:
according to the following formula: SOH t ＝Std-Δα t -Δε t Determining the comprehensive health evaluation value of the power battery, wherein Std is the standard state of health value of the battery, SOH t Δ α for comprehensive health evaluation value t Attenuation value of normal health state, Δ ε t Is a fault health attenuation value.
4. The method of claim 1,
the normal attenuation model is obtained by training according to first training data of power batteries of a plurality of first historical vehicles with the same vehicle characteristics;
the fault attenuation model is obtained by training a plurality of second training data of power batteries of a second historical vehicle, which have the same vehicle characteristics, with the normal attenuation model.
5. The method of claim 4,
the first historical vehicle is a vehicle without a specified battery fault;
the second history vehicle is a vehicle in which a specified battery failure has occurred;
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.
6. The method of claim 4, wherein the first and second light sources are selected from the group consisting of,the normal attenuation model is characterized by comprising the following steps:
Figure FDA0003645832630000011
wherein, delta alpha t The value of the attenuation is a normal state of health,
Figure FDA0003645832630000012
at a normal decay rate, P t The parameters are associated with the real-time battery.
7. The method of claim 4,
the first training data comprises a first historical battery association parameter and a first battery state of health value of a plurality of first historical vehicles having the same vehicle characteristic;
the normal attenuation rate is:
Figure FDA0003645832630000021
Figure FDA0003645832630000022
is a normal attenuation rate, η i The undetermined attenuation rate of the ith first historical vehicle is n, and the n is the total number of the first historical vehicles participating in training the normal attenuation model;
and the undetermined attenuation rate of the ith first historical vehicle is obtained by calculation according to the first historical battery related parameter and the first battery state of health value of the ith first historical vehicle.
8. The method of claim 7, wherein when the first historical battery related parameter is mileage, the pending decay rate for the ith first historical vehicle is:
Figure FDA0003645832630000023
η i the unit of (b) is%/10000km, M wi Is the mileage, SOH, of the ith first history vehicle wi Is the ith of the first history vehicleA battery state of health value.
9. The method of claim 4, wherein the fault attenuation model is:
Figure FDA0003645832630000024
wherein, delta epsilon t Attenuation value for fault health, x j For the jth real-time fault type parameter, ε j The fault attenuation rate of the jth real-time fault type parameter.
10. The method of claim 9, wherein the real-time fault type parameter is one of a number of over-voltage faults, a number of under-voltage faults, a number of charging over-current faults, a number of discharging over-current faults, a number of high-temperature faults, a number of low-temperature faults, or a specified number of severe faults.
11. The method of claim 9,
the second training data comprises second battery state-of-health values, second historical battery association parameters and historical fault type parameters of a plurality of second historical vehicles with the same vehicle characteristics;
the fault attenuation rate of the jth second historical vehicle is obtained by performing determinant calculation on the health difference values and the historical fault type parameters of a plurality of second historical vehicles according to a linear regression algorithm;
the health difference value of the jth second historical vehicle is the difference value of the expected health value of the jth second historical vehicle and the jth second battery health value;
the expected health value of the jth second historical vehicle is calculated according to the jth second historical battery related parameter and the normal attenuation model.
12. The method of claim 11, wherein the fault decay rate of the jth real-time fault type parameter is:
Figure RE-FDA0003978545110000024
Figure RE-FDA0003978545110000025
Figure RE-FDA0003978545110000026
wherein, delta epsilon yj For the health difference value of the jth second history vehicle,
Figure RE-FDA0003978545110000031
for the expected health value, SOH, of the jth second history vehicle yj A second battery state of health value for a jth second historical vehicle, std a standard battery state of health value,
Figure RE-FDA0003978545110000032
is the normal decay rate, P yj A failure history battery related parameter, x, for the jth second history vehicle sj For the jth historical fault type parameter, ε, of the s-th second historical vehicle j The failure decay rate for the jth historical failure type parameter.
13. A server, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of determining state of health of a power cell of an electric vehicle as claimed in any one of claims 1 to 12.
CN202210529104.6A 2022-05-16 2022-05-16 Method for determining state of health of power battery of electric vehicle and server Pending CN115598556A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202210529104.6A CN115598556A (en) 2022-05-16 2022-05-16 Method for determining state of health of power battery of electric vehicle and server
PCT/CN2023/077917 WO2023221587A1 (en) 2022-05-16 2023-02-23 Method for determining state of health of power battery of electric vehicle, and server

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210529104.6A CN115598556A (en) 2022-05-16 2022-05-16 Method for determining state of health of power battery of electric vehicle and server

Publications (1)

Publication Number Publication Date
CN115598556A true CN115598556A (en) 2023-01-13

Family

ID=84841848

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210529104.6A Pending CN115598556A (en) 2022-05-16 2022-05-16 Method for determining state of health of power battery of electric vehicle and server

Country Status (2)

Country Link
CN (1) CN115598556A (en)
WO (1) WO2023221587A1 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116552321A (en) * 2023-07-07 2023-08-08 徐州徐工汽车制造有限公司 Management method and device for power battery of vehicle and vehicle
WO2023221587A1 (en) * 2022-05-16 2023-11-23 深圳市道通合创数字能源有限公司 Method for determining state of health of power battery of electric vehicle, and server
CN117368742A (en) * 2023-11-23 2024-01-09 安徽来福电子科技有限公司 Battery state evaluation system of new energy automobile

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117805663B (en) * 2024-02-28 2024-05-10 常州拜特测控技术有限公司 Battery testing method, device, equipment and medium based on running state

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110261790A (en) * 2019-04-10 2019-09-20 北京海博思创科技有限公司 Predictor method, the apparatus and system of cell health state
US10942223B1 (en) * 2019-07-31 2021-03-09 Cox Automotive, Inc. Systems and methods for determining vehicle battery health
KR20210041511A (en) * 2019-10-07 2021-04-15 삼성에스디아이 주식회사 Method and apparatus for estimating state of health of battery
CN111968268A (en) * 2020-06-29 2020-11-20 南斗六星系统集成有限公司 New energy vehicle health condition remote evaluation method and system
CN112505570A (en) * 2020-12-03 2021-03-16 摩登汽车(盐城)有限公司 Method for estimating battery health state of electric automobile
CN112946483B (en) * 2021-02-05 2022-05-06 重庆长安新能源汽车科技有限公司 Comprehensive evaluation method for battery health of electric vehicle and storage medium
CN113219357A (en) * 2021-04-28 2021-08-06 东软睿驰汽车技术（沈阳）有限公司 Battery pack health state calculation method and system and electronic equipment
CN113306449B (en) * 2021-06-15 2023-11-03 安徽信息工程学院 Battery health reminding method and system for new energy automobile
CN113806171A (en) * 2021-09-12 2021-12-17 济南浪潮数据技术有限公司 Server health assessment method, system, equipment and medium
CN113933732A (en) * 2021-10-13 2022-01-14 中国汽车工程研究院股份有限公司 New energy automobile power battery health state analysis method, system and storage medium
CN114290960B (en) * 2021-12-30 2023-10-27 中国第一汽车股份有限公司 Method and device for acquiring battery health of power battery and vehicle
CN115598556A (en) * 2022-05-16 2023-01-13 深圳市道通合创新能源有限公司（Cn） Method for determining state of health of power battery of electric vehicle and server

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023221587A1 (en) * 2022-05-16 2023-11-23 深圳市道通合创数字能源有限公司 Method for determining state of health of power battery of electric vehicle, and server
CN116552321A (en) * 2023-07-07 2023-08-08 徐州徐工汽车制造有限公司 Management method and device for power battery of vehicle and vehicle
CN116552321B (en) * 2023-07-07 2023-10-13 徐州徐工汽车制造有限公司 Management method and device for power battery of vehicle and vehicle
CN117368742A (en) * 2023-11-23 2024-01-09 安徽来福电子科技有限公司 Battery state evaluation system of new energy automobile

Also Published As

Publication number Publication date
WO2023221587A1 (en) 2023-11-23

Similar Documents

Publication Publication Date Title
CN115598556A (en) Method for determining state of health of power battery of electric vehicle and server
Park et al. LSTM-based battery remaining useful life prediction with multi-channel charging profiles
Caliwag et al. Hybrid VARMA and LSTM method for lithium-ion battery state-of-charge and output voltage forecasting in electric motorcycle applications
Kim et al. Data-driven state of health estimation of li-ion batteries with RPT-reduced experimental data
US11221367B2 (en) Evaluation device, energy storage system, evaluation method and non-transitory computer readable medium
CN112068004A (en) Method and device for determining battery abnormity and battery charging remaining time
CN110412470B (en) SOC estimation method for power battery of electric vehicle
CN108205114B (en) Method and system for predicting service life of battery
KR102297343B1 (en) Battery Output Voltage Response and State-of-Charge Forecasting Method using Hybrid VARMA and LSTM
CN116154900B (en) Active safety three-stage prevention and control system and method for battery energy storage power station
Lin et al. Reliability prediction of battery management system for electric vehicles based on accelerated degradation test: A semi-parametric approach
CN111505511B (en) Method for measuring capacity of single battery cell of electric vehicle, electronic equipment and storage medium
CN115808922B (en) Commercial electric vehicle energy consumption prediction method and device and computer equipment
CN112366708A (en) Charging management method, device, equipment and storage medium
CN114879070A (en) Battery state evaluation method and related equipment
Kharlamova et al. Evaluating Machine-Learning-Based Methods for Modeling a Digital Twin of Battery Systems Providing Frequency Regulation
CN117169761A (en) Battery state evaluation method, apparatus, device, storage medium, and program product
CN116562427A (en) Charging load prediction method and device of charging station, storage medium and equipment
CN115128468A (en) Chemical energy storage battery PHM undervoltage fault prediction method
CN115219932A (en) Method and device for evaluating the relative aging state of a battery of a device
CN115219931A (en) Method and device for operating a system for providing a predictive aging state of an electrical energy store
Memon et al. Estimating State of Charge and State of Health of Electrified Vehicle Battery by Data Driven Approach: Machine Learning
CN113689014A (en) Shared electric vehicle maintenance management method, device, storage medium and device
CN115825790B (en) Early warning method, device and system for battery insulation fault and computer equipment
Chen et al. Battery Lifetime Prediction and Capacity Estimation Based on Entropy and Bayesian Neural Networks

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 518000 The first, second, third and sixth floors of Rainbow Science and Technology Building, 36 North High-tech North Road, Songpingshan Community, Xili Street, Nanshan District, Shenzhen, Guangdong Province

Applicant after: Shenzhen Daotong Hechuang Digital Energy Co.,Ltd.

Address before: 518000 101, building B2, Nanshan Zhiyuan, No. 1001, Xueyuan Avenue, Changyuan community, Taoyuan Street, Nanshan District, Shenzhen, Guangdong

Applicant before: Shenzhen daotonghe innovative energy Co.,Ltd.