Method, device and storage medium for determining state of health of power battery

Abstract

The application relates to a power battery health state determination method, device, equipment and storage medium. The method comprises the following steps: obtaining historical charging and discharging data of a to-be-evaluated power battery and a target cumulative mileage of a vehicle where the to-be-evaluated power battery is located, determining a feature representation of the to-be-evaluated power battery, and inputting the feature representation into a health state evaluation model to obtain the health state of the to-be-evaluated power battery. According to the method, the influence of multidimensional data on the health of the power battery can be analyzed at the same time, and the evaluation result of the health of the battery is more accurate.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power batteries, in particular to a power battery health state determination method, device, equipment and storage medium. BACKGROUND

[0002] With the development of new energy vehicles, the health problem of power batteries on electric vehicles has gradually attracted social attention, and power battery health assessment technology has emerged.

[0003] The existing power battery health assessment scheme is usually to analyze a certain data of the power battery during charging to determine the health state of the power battery. However, this way is single in data, which leads to low accuracy of power battery health state evaluation in actual application, and needs to be improved. SUMMARY

[0004] Therefore, it is necessary to provide a power battery health state determination method, device, equipment and storage medium capable of accurately evaluating the health state of the power battery.

[0005] In a first aspect, the present application provides a power battery health state determination method, which comprises:

[0006] obtaining historical charging and discharging data of a power battery to be evaluated, and target cumulative mileage of a vehicle in which the power battery to be evaluated is located; wherein the historical charging and discharging data is at least one of a historical charging and discharging rate set, a historical charging depth set and a historical charging battery temperature set;

[0007] determining a feature representation of the power battery to be evaluated according to the historical charging and discharging data and the target cumulative mileage;

[0008] inputting the feature representation into a health state evaluation model to obtain the health state of the power battery to be evaluated.

[0009] In one embodiment, the feature representation of the power battery to be evaluated is determined according to the historical charging and discharging data and the cumulative mileage, comprising:

[0010] determining a first feature according to the target cumulative mileage; determining a second feature according to the historical charging and discharging rate set; determining a third feature according to the historical charging depth set; determining a fourth feature according to the historical charging battery temperature set; and fusing the first feature, the second feature, the third feature and the fourth feature to obtain the feature representation of the power battery to be evaluated.

[0011] In one embodiment, the historical charging and discharging rate set comprises a historical charging rate set and a historical discharging rate set; and the second feature is determined according to the historical charging and discharging rate set, comprising:

[0012] determine a charging probability distribution according to the charging times and a total number of the historical charging rates in the historical charging rate set; determine a discharging probability distribution according to a discharging times of the historical discharging rates in the historical discharging rate set and a total number of the historical discharging rates in the historical discharging rate set; and determine the second feature according to the charging probability distribution and the discharging probability distribution.

[0013] In one of the embodiments, the third feature is determined according to the historical charging depth set, including:

[0014] determine a charging depth times of the historical charging depths in the historical charging depth set in each set charging depth interval; and determine the third feature according to the charging depth times and a total number of the historical charging depths in the historical charging depth set.

[0015] In one of the embodiments, the fourth feature is determined according to the historical charging battery temperature set, including:

[0016] determine a charging temperature times of the historical charging battery temperatures in the historical charging battery temperature set in each set temperature interval; and determine the fourth feature according to the charging temperature times and a total number of the historical charging battery temperatures in the historical charging battery temperature set.

[0017] In one of the embodiments, the method further includes:

[0018] obtain sample charging and discharging data of a sample power battery and a sample cumulative mileage corresponding to the sample charging and discharging data; wherein the sample charging and discharging data includes at least one of a sample charging and discharging rate set, a sample charging depth set and a sample charging battery temperature set; take a state of health of the sample power battery as supervised data; and train the long short-term memory network by using the sample charging and discharging data, the sample cumulative mileage and the supervised data to obtain the state of health evaluation model.

[0019] In a second aspect, the application further provides a power battery state of health determination device, which includes:

[0020] a data acquisition module, configured to acquire historical charging and discharging data of a power battery to be evaluated and a target cumulative mileage of a vehicle in which the power battery to be evaluated is located; wherein the historical charging and discharging data includes at least one of a historical charging and discharging rate set, a historical charging depth set and a historical charging battery temperature set;

[0021] a feature determination module, configured to determine a feature representation of the power battery to be evaluated according to the historical charging and discharging data and the target cumulative mileage;

[0022] The state evaluation module is configured to input the feature representation into a health state evaluation model to obtain the health state of the power battery to be evaluated.

[0023] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0024] The historical charge-discharge data of the power battery to be evaluated and a target cumulative mileage of a vehicle where the power battery to be evaluated is located are obtained, wherein the historical charge-discharge data includes at least one of a historical charge-discharge rate set, a historical charge depth set and a historical charge battery temperature set.

[0025] The feature representation of the power battery to be evaluated is determined according to the historical charge-discharge data and the target cumulative mileage.

[0026] The feature representation is input into a health state evaluation model to obtain the health state of the power battery to be evaluated.

[0027] In a fourth aspect, the present application further provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0028] The historical charge-discharge data of the power battery to be evaluated and a target cumulative mileage of a vehicle where the power battery to be evaluated is located are obtained, wherein the historical charge-discharge data includes at least one of a historical charge-discharge rate set, a historical charge depth set and a historical charge battery temperature set.

[0029] The feature representation of the power battery to be evaluated is determined according to the historical charge-discharge data and the target cumulative mileage.

[0030] The feature representation is input into a health state evaluation model to obtain the health state of the power battery to be evaluated.

[0031] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, wherein the computer program is executed by a processor to implement the following steps:

[0032] The historical charge-discharge data of the power battery to be evaluated and a target cumulative mileage of a vehicle where the power battery to be evaluated is located are obtained, wherein the historical charge-discharge data includes at least one of a historical charge-discharge rate set, a historical charge depth set and a historical charge battery temperature set.

[0033] The feature representation of the power battery to be evaluated is determined according to the historical charge-discharge data and the target cumulative mileage.

[0034] The feature representation is input into a health state evaluation model to obtain the health state of the power battery to be evaluated.

[0035] The power battery health state determination method, device, equipment and storage medium, by obtaining the historical charge and discharge data of the power battery to be evaluated and the target cumulative mileage of the vehicle where the power battery to be evaluated is located, the feature representation of the power battery to be evaluated can be determined, and then the feature representation is input into the health state evaluation model, so that the health state of the power battery to be evaluated can be obtained. The above scheme simultaneously analyzes the influence of multi-dimensional data on the health of the power battery, so that the evaluation result of the health of the battery is more accurate. BRIEF DESCRIPTION OF DRAWINGS

[0036] Figure 1 It is an application environment diagram of the power battery health state determination method in an embodiment;

[0037] Figure 2 It is a flowchart of the power battery health state determination method in an embodiment;

[0038] Figure 3 It is a flowchart of feature extraction of the power battery in an embodiment;

[0039] Figure 4 It is a flowchart of the method for determining the second feature of the power battery in an embodiment;

[0040] Figure 5 It is a flowchart of the method for determining the third feature of the power battery in an embodiment;

[0041] Figure 6 It is a flowchart of the method for determining the fourth feature of the power battery in an embodiment;

[0042] Figure 7 It is a flowchart of training the health state evaluation model in an embodiment;

[0043] Figure 8 It is a flowchart of the power battery health state determination method in another embodiment;

[0044] Figure 9 It is a structural block diagram of the power battery health state determination device in an embodiment;

[0045] Figure 10 It is a structural block diagram of the power battery health state determination device in another embodiment;

[0046] Figure 11 It is an internal structure diagram of the computer equipment in an embodiment. DETAILED DESCRIPTION

[0047] In order to make the purposes, 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 not intended to limit the present application.

[0048] The power battery health state determination method provided by the embodiments of the present application can be applied in an application environment as shown in Figure 1 . The terminal 102 communicates with the server 104 through a network. The data storage system can store data required to be processed by the server 104. For example, historical charging and discharging data and accumulated mileage of an electric vehicle. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. In the present embodiment, the server 104 determines the feature representation of the power battery to be evaluated by obtaining the historical charging and discharging data of the power battery to be evaluated and the target accumulated mileage of the vehicle in which the power battery to be evaluated is located, and then inputs the feature representation into the health state evaluation model to obtain the health state of the power battery to be evaluated. Further, the server 104 can send the analyzed results to the terminal 102 for display. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones and tablet computers, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0049] In one embodiment, as shown in Figure 2 , a power battery health state determination method is provided. Taking the server in Figure 1 as an example, the method comprises the following steps:

[0050] S201, obtaining the historical charging and discharging data of the power battery to be evaluated and the target accumulated mileage of the vehicle in which the power battery to be evaluated is located.

[0051] In this embodiment, the historical charge-discharge data is the charge-discharge data of the power battery to be evaluated in a period of time; optionally, the historical charge-discharge data can include at least one of a historical charge-discharge rate set, a historical charge depth set and a historical charge battery temperature set. The historical charge-discharge rate set can include a historical charge rate set and a historical discharge rate set; the historical charge rate set includes a plurality of historical charge rates, and the historical discharge rate set also includes a plurality of historical discharge rates; the charge rate is determined based on the rated capacity of the power battery and the current during charging, and the discharge rate is determined based on the rated capacity of the power battery and the current during discharging; the historical charge depth set also includes a plurality of historical charge depths, and the charge depth is determined based on the state of charge at the beginning of charging and the state of charge at the end of charging; the historical charge battery temperature set also includes a plurality of historical charge battery temperatures, and the charge battery temperature is the average temperature or the maximum temperature of the power battery during the charging process of the power battery.

[0052] The target cumulative mileage refers to the cumulative mileage of the electric vehicle in which the power battery is located when the health state of the power battery is determined.

[0053] Optionally, in the case where it is detected that the health state of the power battery to be evaluated needs to be determined, the server can obtain the target cumulative mileage of the vehicle in which the power battery to be evaluated is located from the database; further, one of the historical charge-discharge rate set, the historical charge depth set, the historical charge battery temperature set and other data of the power battery to be evaluated can also be obtained, and multiple items can also be obtained at the same time.

[0054] Among them, the way to detect that the health state of the power battery to be evaluated needs to be determined can be various, and the embodiment does not limit it. One way is to detect that the current time meets the preset time period of the power battery to be evaluated; another way is to receive the evaluation instruction for evaluating the health state of the power battery to be evaluated sent by the terminal.

[0055] Further, the server can directly determine the subsequent health state based on the obtained data; or the obtained data can be cleaned, and then the cleaned data is used to determine the health state of the power battery to be evaluated.

[0056] S202, according to the historical charge-discharge data and the target cumulative mileage, the feature representation of the power battery to be evaluated is determined.

[0057] Among them, the feature representation of the power battery refers to the representation of the related features of the power battery to be evaluated after the related data of the power battery to be evaluated is abstracted. Optionally, the feature representation can be in the form of a vector or a matrix.

[0058] Specifically, after obtaining the historical charge-discharge data of the to-be-evaluated power battery and the target cumulative mileage of the vehicle where the to-be-evaluated power battery is located, the related data of the to-be-evaluated power battery can be feature extracted. For example, the historical charge-discharge data of the power battery and the target cumulative mileage of the vehicle where the power battery is located can be input into a trained power battery feature extraction model. The power battery feature extraction model can automatically extract and output the feature representation of the to-be-evaluated power battery based on the input related data of the to-be-evaluated power battery and the parameters pre-set in the model.

[0059] In S203, the feature representation is input into the health state evaluation model to obtain the health state of the to-be-evaluated power battery.

[0060] The health state evaluation model is a neural network model for evaluating the health state of a power battery. Optionally, a lot of related data of power batteries can be obtained from actual scenarios to construct samples and train the neural network model, so as to obtain the health state evaluation model. Optionally, the training process of the health state evaluation model will be described in detail in subsequent embodiments, which will not be described here.

[0061] Specifically, the feature representation of the to-be-evaluated power battery is input into the health state evaluation model, and the health state evaluation model processes the input feature representation based on its own parameters, so as to obtain and output the health state of the to-be-evaluated power battery.

[0062] Optionally, after determining the health state of the to-be-evaluated power battery, the health state can be fed back to the terminal. Further, different determined health states correspond to different feedback results to the terminal. For example, if the health state is unhealthy, a red warning icon is used to feed back to the terminal; if the health state is healthy, a green icon is used to feed back to the terminal.

[0063] In the above method for determining the health state of a power battery, the historical charge-discharge data of the to-be-evaluated power battery and the target cumulative mileage of the vehicle where the to-be-evaluated power battery is located are obtained to determine the feature representation of the to-be-evaluated power battery, and then the feature representation is input into the health state evaluation model to obtain the health state of the to-be-evaluated power battery. The above scheme simultaneously analyzes the influence of multi-dimensional data on the health of the power battery, so that the evaluation result of the health of the battery is more accurate.

[0064] Based on the operation of feature extracting at least one item in the historical charge-discharge data of the to-be-evaluated power battery to obtain the feature representation in the last embodiment, a more comprehensive optional embodiment is provided, as shown in Figure 3 Each item of the historical charge-discharge data can be feature extracted to obtain the feature representation, specifically including the following steps:

[0065] S301, determine a first feature according to a target cumulative mileage.

[0066] Optionally, the target cumulative mileage data of the vehicle where the power battery to be evaluated is located can be directly encoded, that is, the first feature of the power battery to be evaluated can be obtained; or the target cumulative mileage of the vehicle where the power battery to be evaluated is located can be directly input into the trained first feature extraction network, and the first feature of the power battery to be evaluated is output by the first feature extraction network.

[0067] S302, determine a second feature according to a historical charging and discharging rate set.

[0068] Optionally, the historical charging rate set and the historical discharging rate set in the historical charging and discharging rate set of the power battery to be evaluated can be input into the trained second feature extraction network respectively, and the charging feature and the discharging feature of the power battery to be evaluated are output by the second feature extraction network; further, the charging feature and the discharging feature are fused, that is, the second feature of the power battery to be evaluated can be obtained.

[0069] Alternatively, the historical charging rate set and the historical discharging rate set in the historical charging and discharging rate set of the power battery to be evaluated can be respectively statistically processed to obtain the cumulative distribution of the historical charging rate and the historical discharging rate; further, based on the cumulative distribution of the historical charging rate and the historical discharging rate, the second feature of the power battery to be evaluated can be obtained.

[0070] S303, determine a third feature according to a historical charging depth set.

[0071] Optionally, the historical charging depth in the historical charging depth set of the power battery to be evaluated can be directly input into the trained third feature extraction network, and the third feature of the power battery to be evaluated is output by the third feature extraction network.

[0072] Alternatively, the historical charging depth in the historical charging depth set of the power battery to be evaluated can be statistically processed to obtain the cumulative distribution of the historical charging depth; further, based on the cumulative distribution of the historical charging depth, the third feature of the power battery to be evaluated can be obtained.

[0073] S304, determine a fourth feature according to a historical charging battery temperature set.

[0074] Optionally, the historical charging battery temperature in the historical charging battery temperature set of the power battery to be evaluated can be directly input into the trained fourth feature extraction network, and the fourth feature of the power battery to be evaluated is output by the fourth feature extraction network.

[0075] Alternatively, the historical charging battery temperature of the historical charging battery temperature set of the to-be-evaluated power battery can also be statistically analyzed to obtain the cumulative distribution of the historical charging battery temperature; further, based on the cumulative distribution of the historical charging battery temperature, the fourth feature of the to-be-evaluated power battery can be obtained.

[0076] S305, the first feature, the second feature, the third feature and the fourth feature are fused to obtain the feature representation of the to-be-evaluated power battery.

[0077] Alternatively, the first feature, the second feature, the third feature and the fourth feature extracted can be directly spliced in a set order to obtain the feature representation of the to-be-evaluated power battery; or the first feature, the second feature, the third feature and the fourth feature extracted from the to-be-evaluated power battery can be input into a trained feature fusion network for feature fusion, and the feature fusion network outputs the feature representation of the to-be-evaluated power battery.

[0078] In the embodiment, the feature representation is obtained by feature extraction on each item in the historical charging and discharging data of the to-be-evaluated power battery, which can more comprehensively represent the feature state of the to-be-evaluated power battery, and further improve the accuracy of the to-be-evaluated power battery health state determination.

[0079] For example, on the basis of the above embodiment, the embodiment further explains and describes the second feature determined according to the historical charging rate set in detail. As shown in the figure, Figure 4 The specific steps include the following steps:

[0080] S401, the number of times of charging of the historical charging rate located in each set charging and discharging rate interval in the historical charging rate set is determined.

[0081] Alternatively, the set charging and discharging rate interval is an interval divided in advance based on the range of the charging and discharging rate of the power battery. For example, the range of the charging and discharging rate of the power battery can be divided into four non-overlapping interval ranges, such as 0-0.1C, 0.1-0.5C, 0.5-1C and greater than 1C. Among them, 0-0.1C represents a trickle current; 0.1-0.5C represents a medium current; 0.5-1C represents a large current; and greater than 1C represents a fast charging / peak power current.

[0082] Further, each historical charging rate in the historical charging rate set of the to-be-evaluated power battery is compared with the value of each set charging and discharging rate interval, and based on the comparison result, the number of times of charging of the historical charging rate in each set charging and discharging rate interval can be counted.

[0083] S402, the charging probability distribution is determined according to the number of times of charging and the total number of historical charging rates in the historical charging rate set.

[0084] Specifically, the charging times of the historical charging rates in each set charging and discharging rate interval of the power battery to be evaluated are compared with the total number of the historical charging rates in the historical charging rate set, so that the charging probability of each set charging and discharging rate interval is obtained; further, the charging probabilities of each set charging and discharging rate interval are combined, so that the charging probability distribution of the power battery to be evaluated is obtained.

[0085] S403, the discharging times of the historical discharging rates in each set charging and discharging rate interval in the historical discharging rate set are determined.

[0086] Similarly, when the discharging times of the historical charging rates in each set charging and discharging rate interval are counted, four non-overlapping interval ranges can be used, for example, the range of the charging and discharging rate of the power battery to be evaluated can be divided into four non-overlapping intervals, such as 0-0.1C, 0.1-0.5C, 0.5-1C and greater than 1C.

[0087] Further, each historical discharging rate in the historical discharging rate set of the power battery to be evaluated is compared with the value of each set charging and discharging rate interval, and based on the comparison result, the discharging times of the historical discharging rates in each set charging and discharging rate interval are counted.

[0088] S404, the discharging probability distribution is determined according to the discharging times and the total number of the historical discharging rates in the historical discharging rate set.

[0089] Specifically, the charging times of the historical discharging rates in each set charging and discharging rate interval of the power battery to be evaluated are compared with the total number of the historical discharging rates in the historical discharging rate set, so that the charging probability of each set charging and discharging rate interval is obtained; further, the charging probabilities of each set charging and discharging rate interval are combined, so that the charging probability distribution of the power battery to be evaluated is obtained.

[0090] S405, the second feature is determined according to the charging probability distribution and the discharging probability distribution.

[0091] Specifically, the obtained charging probability distribution and discharging probability distribution are spliced, so that the second feature of the power battery to be evaluated is obtained.

[0092] For example, in the present embodiment, since the charging and discharging rate range is divided into four intervals, the second feature can be represented as a feature vector with a length of 8. For example, D CR = [P c1 , P c2 , P c3 , P c4 , P d1 , P d2 , P d3P d4 ], wherein D CR refers to the second feature; P c1 -P c4 refers to the charging probability in each set of charging and discharging rate interval; P d1 -P d4 refers to the discharging probability in each set of charging and discharging rate interval.

[0093] In this embodiment, by introducing the set of charging and discharging rate interval, the probability distribution statistics of the historical charging and discharging rate can make the second feature of the to-be-evaluated power battery more accurate, thereby improving the accuracy of the health evaluation of the to-be-evaluated power battery.

[0094] For example, on the basis of the above embodiment, this embodiment further explains and describes in detail the determination of the third feature according to the historical charging depth set. As shown in the following table, the specific steps include the following steps: Figure 5

[0095] S501, determining the charging depth times of the historical charging depth in each set of charging depth interval in the historical charging depth set.

[0096] For example, the set of charging depth interval is an interval divided based on the charging depth range of the power battery. For example, the charging depth range of the power battery can be divided into five non-overlapping interval ranges, such as 0-20%, 20%-40%, 40%-60%, 60%-80% and 80%-100%.

[0097] Further, each historical charging depth in the historical charging depth set of the to-be-evaluated power battery is compared with the value of each set of charging depth interval, and based on the comparison result, the charging depth times of the historical charging depth in each set of charging depth interval can be counted.

[0098] S502, determining the third feature according to the charging depth times and the total number of historical charging depth in the historical charging depth set.

[0099] Specifically, the charging depth times in each set of charging depth interval of the to-be-evaluated power battery is compared with the total number of historical charging depth in the historical charging depth set, and the charging depth probability of each set of charging depth interval can be obtained; further, the charging depth probability of each set of charging depth interval is combined, and the third feature of the to-be-evaluated power battery can be obtained.

[0100] For example, in this embodiment, since the charging depth range is divided into five intervals, the third feature can be represented as a feature vector with a length of five. For example, SOC USE =[D1, D2, D3, D4, D5], wherein SOC​USE D1-D5 refer to the charging depth probability in each set charging depth interval.

[0101] In the embodiment, by introducing the set charging depth interval, the probability distribution statistics of the historical charging depth can make the third feature of the to-be-evaluated power battery more accurate, and thus improve the accuracy of the health evaluation of the to-be-evaluated power battery.

[0102] On the basis of the above embodiment, a preferred embodiment for determining the fourth feature according to the historical charging battery temperature set is provided, as shown in the following. Figure 6 The preferred embodiment specifically comprises the following steps.

[0103] S601, determining the charging temperature times of the historical charging battery temperature in each set temperature interval in the historical charging battery temperature set.

[0104] Exemplarily, the set temperature interval refers to an interval divided based on the charging battery temperature range of the power battery. For example, the charging battery temperature range of the power battery can be divided into four non-overlapping interval ranges, such as 0-15℃, 15-30℃, 30-45℃ and higher than 45℃.

[0105] Further, each historical charging battery temperature in the historical charging battery temperature set of the to-be-evaluated power battery is compared with the value of each set temperature interval, and based on the comparison result, the charging temperature times of the historical charging battery temperature in each set temperature interval can be counted.

[0106] S602, determining the fourth feature according to the charging temperature times and the total number of the historical charging battery temperature in the historical charging battery temperature set.

[0107] Specifically, the charging temperature times in each set temperature interval of the to-be-evaluated power battery are compared with the total number of the historical charging battery temperature in the historical charging battery temperature set, and thus the charging temperature probability of each set temperature interval can be obtained; further, the charging temperature probability of each set temperature interval is combined, and thus the fourth feature of the to-be-evaluated power battery can be obtained.

[0108] Exemplarily, in the embodiment, since the charging temperature range is divided into four intervals, the fourth feature can be represented as a feature vector with a length of four. For example, D tep = [P T1 , P T2 , P T3 , P T4 ], wherein D tep refers to the fourth feature; P T1 -P T4Refers to the probability of the temperature of the charged battery in each set temperature interval.

[0109] In the embodiment, by introducing the set temperature interval, the probability distribution statistics of the historical charged battery temperature depth are performed, so that the obtained fourth feature of the to-be-evaluated power battery is more accurate, and the accuracy of the health evaluation of the to-be-evaluated power battery is improved.

[0110] On the basis of the above embodiment, an optimal embodiment is provided for constructing a health state evaluation model, as shown in the following. Figure 7 The specific steps include the following steps:

[0111] S701, obtaining sample charging and discharging data of a sample power battery and sample cumulative mileage corresponding to the sample charging and discharging data.

[0112] The sample charging and discharging data includes at least one of a sample charging and discharging rate set, a sample charging depth set, and a sample charged battery temperature set.

[0113] Specifically, a part of electric vehicles registered on a battery monitoring platform provided by a server are selected as target electric vehicles, the power battery of the target electric vehicle is referred to as a sample power battery, and sample charging and discharging data corresponding to each sample power battery and sample cumulative mileage corresponding to the sample charging and discharging data are obtained from related data of the sample power battery.

[0114] Further, the sample charging and discharging data corresponding to each sample power battery and the sample cumulative mileage data corresponding to the sample charging and discharging data can be feature extracted to obtain a feature representation corresponding to each sample power battery.

[0115] S702, taking the health state of the sample power battery as supervision data.

[0116] The supervision data refers to standard data as reference data when the model is trained.

[0117] It can be understood that the battery capacity, power, internal resistance, cycle number, and peak power of the power battery can reflect the health state of the power battery to some extent. Optionally, the battery capacity is taken as an example to determine the health state of the power battery.

[0118] Optionally, the charging power of the sample power battery is calculated based on the battery load state and the size of the charging current at the start and end of charging. Specifically, since the charging current of the power battery is most stable when the charging load state is 40%-80%, in the embodiment, the charging range of 40%-80% is selected to calculate the charging power of the sample power battery, as shown in formula 1. Wherein, C partCHG refers to the charging power of the sample power battery; tSOC SOC (t) refers to the state of charge of the sample power battery during charging; I (t) refers to the size of the current during charging.

[0119]

[0120] Further, as shown in formula 2, the actual capacity of the sample power battery can be calculated based on the charging capacity of the sample power battery and the change value of the state of charge of the battery at the start and end of charging. Wherein, C CHG SOC (t) refers to the state of charge of the sample power battery during charging; I (t) refers to the size of the current during charging.

[0121]

[0122] Further, the actual capacity of the sample power battery calculated is compared with the initial capacity, that is, the health state of the sample power battery can be obtained. Wherein, the initial capacity is the capacity of the sample power battery when it leaves the factory.

[0123] S703, the sample charge-discharge data, the sample cumulative mileage and the supervision data are used to train the long short-term memory network to obtain the health state evaluation model.

[0124] Specifically, before training, the extracted feature representation of the sample power battery is compressed by dimension reduction using principal component analysis method; at the same time, the particle swarm algorithm is used to optimize the parameters in the long short-term memory network.

[0125] Further, based on the feature representation of the sample power battery after dimension reduction compression, and taking the battery health state corresponding to each sample power battery as supervision data, the long short-term memory network with initial parameters is trained, and the health state evaluation model can be obtained through multiple training.

[0126] In this embodiment, the actual data of the electric vehicle is used as a sample to train the long short-term memory network, so that the obtained health state evaluation model is closer to reality, and the accuracy of the power battery health evaluation is improved.

[0127] Figure 8 For another embodiment of the flowchart of the power battery health state determination method, on the basis of the above embodiment, the present embodiment provides an optional example of a power battery health state determination method. Combined with Figure 8 , the specific implementation process is as follows:

[0128] S801, obtaining sample charge-discharge data of a sample power battery and sample cumulative mileage corresponding to the sample charge-discharge data.

[0129] S802, taking the health state of the sample power battery as supervision data.

[0130] S803, training the long short-term memory network by taking the sample charge-discharge data, the sample cumulative mileage and the supervision data, to obtain a health state evaluation model.

[0131] S804, obtaining historical charge-discharge data of a power battery to be evaluated and a target cumulative mileage of a vehicle where the power battery to be evaluated is located.

[0132] S805, determining a first feature according to the target cumulative mileage.

[0133] S806, determining a second feature according to the historical charge-discharge rate set.

[0134] S807, determining a third feature according to the historical charge depth set.

[0135] S808, determining a fourth feature according to the historical charge battery temperature set.

[0136] S809, fusing the first feature, the second feature, the third feature and the fourth feature to obtain a feature representation of the power battery to be evaluated.

[0137] S810, inputting the feature representation into the health state evaluation model to obtain a health state of the power battery to be evaluated.

[0138] The specific process of S801-S810 can be referred to the description of the method embodiments, and the implementation principle and technical effects are similar, which will not be repeated here.

[0139] It should be understood that, although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise stated herein, the execution of these steps has no strict sequence limitation, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps.

[0140] Based on the same inventive concept, the embodiments of the present application further provide a power battery health state determination device for implementing the power battery health state determination method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more power battery health state determination device embodiments provided below can refer to the limitations of the power battery health state determination method described above, which will not be repeated here.

[0141] In one embodiment, as shown in Figure 9 a power battery health state determination device 1 is provided, comprising a data acquisition module 10, a feature determination module 20 and a state evaluation module 30, wherein:

[0142] The data acquisition module 10 is configured to acquire historical charge-discharge data of a power battery to be evaluated and a target cumulative mileage of a vehicle in which the power battery to be evaluated is located, wherein the historical charge-discharge data comprises at least one of a historical charge-discharge rate set, a historical charge depth set and a historical charge battery temperature set.

[0143] The feature determination module 20 is configured to determine a feature representation of the power battery to be evaluated according to the historical charge-discharge data and the target cumulative mileage.

[0144] The state evaluation module 30 is configured to input the feature representation into a health state evaluation model to obtain a health state of the power battery to be evaluated.

[0145] In one embodiment, as shown in Figure 10 the feature determination module 20 comprises:

[0146] The first feature unit 21 is configured to determine a first feature according to the target cumulative mileage.

[0147] The second feature unit 22 is configured to determine a second feature according to the historical charge-discharge rate set.

[0148] The third feature unit 23 is configured to determine a third feature according to the historical charge depth set.

[0149] The fourth feature unit 24 is configured to determine a fourth feature according to the historical charge battery temperature set.

[0150] The feature fusion unit 25 is configured to fuse the first feature, the second feature, the third feature and the fourth feature to obtain the feature representation of the power battery to be evaluated.

[0151] In one embodiment, the second feature unit 22 is specifically further configured to:

[0152] determine a charging probability distribution according to the charging times and a total number of the historical charging rates in the historical charging rate set; determine a discharging probability distribution according to a discharging times of the historical discharging rates in each set charging and discharging rate interval in the historical discharging rate set and a total number of the historical discharging rates in the historical discharging rate set; and determine the second feature according to the charging probability distribution and the discharging probability distribution.

[0153] In one embodiment, the third feature unit 23 is specifically further configured to:

[0154] determine a charging depth times of the historical charging depths in each set charging depth interval in a historical charging depth set; determine a third feature according to the charging depth times and a total number of the historical charging depths in the historical charging depth set.

[0155] In one embodiment, the fourth feature unit 24 is specifically further configured to:

[0156] determine a charging temperature times of the historical charging battery temperatures in each set temperature interval in a historical charging battery temperature set; and determine a fourth feature according to the charging temperature times and a total number of the historical charging battery temperatures in the historical charging battery temperature set.

[0157] In one embodiment, the power battery health state determination apparatus 1 further comprises a training unit, which is specifically configured to:

[0158] obtain sample charging and discharging data of a sample power battery and a sample cumulative mileage corresponding to the sample charging and discharging data; wherein the sample charging and discharging data comprises at least one of a sample charging and discharging rate set, a sample charging depth set and a sample charging battery temperature set; take a health state of the sample power battery as a supervision data; and train the long short-term memory network by using the sample charging and discharging data, the sample cumulative mileage and the supervision data to obtain the health state evaluation model.

[0159] The above-mentioned various modules in the power battery health state determination apparatus can be realized by software, hardware and combinations thereof in whole or in part. The above-mentioned various modules can be embedded in or independent of a processor in a computer device in a hardware form, or can be stored in a memory in a computer device in a software form, so as to be called and executed by a processor to perform operations corresponding to the above-mentioned various modules.

[0160] In one embodiment, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in Figure 11The computer device shown in the figure includes a processor, a memory and a network interface connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store historical charging data of the power battery, cumulative mileage and other data. The network interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement a power battery health state determination method.

[0161] Those skilled in the art can understand that, Figure 11 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0162] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the following steps:

[0163] Obtaining historical charging and discharging data of the power battery to be evaluated and target cumulative mileage of the vehicle in which the power battery to be evaluated is located; wherein the historical charging and discharging data includes at least one of a historical charging and discharging rate set, a historical charging depth set and a historical charging battery temperature set;

[0164] Determining a feature representation of the power battery to be evaluated according to the historical charging and discharging data and the target cumulative mileage;

[0165] Inputting the feature representation into a health state evaluation model to obtain the health state of the power battery to be evaluated.

[0166] In one embodiment, when the processor executes the logic in the computer program for determining the feature representation of the power battery to be evaluated according to the historical charging and discharging data and the cumulative mileage, the following steps are specifically implemented:

[0167] Determining a first feature according to the target cumulative mileage; determining a second feature according to the historical charging and discharging rate set; determining a third feature according to the historical charging depth set; determining a fourth feature according to the historical charging battery temperature set; and fusing the first feature, the second feature, the third feature and the fourth feature to obtain the feature representation of the power battery to be evaluated.

[0168] In one embodiment, when the processor executes the logic in the computer program for determining the second feature according to the set of historical charging rates, the following steps are implemented:

[0169] determining, in the set of historical charging rates, a number of times of charging of the historical charging rate located in each set charging and discharging rate interval; determining a charging probability distribution according to the number of times of charging and a total number of historical charging rates in the set of historical charging rates; determining, in the set of historical discharging rates, a number of times of discharging of the historical discharging rate located in each set charging and discharging rate interval; determining a discharging probability distribution according to the number of times of discharging and a total number of historical discharging rates in the set of historical discharging rates; and determining the second feature according to the charging probability distribution and the discharging probability distribution.

[0170] In one embodiment, when the processor executes the logic in the computer program for determining the third feature according to the set of historical charging depths, the following steps are implemented:

[0171] determining, in the set of historical charging depths, a number of times of charging depth of the historical charging depth located in each set charging depth interval; and determining the third feature according to the number of times of charging depth and a total number of historical charging depths in the set of historical charging depths.

[0172] In one embodiment, when the processor executes the logic in the computer program for determining the fourth feature according to the set of historical charging battery temperatures, the following steps are implemented:

[0173] determining, in the set of historical charging battery temperatures, a number of times of charging temperature of the historical charging battery temperature located in each set temperature interval; and determining the fourth feature according to the number of times of charging temperature and a total number of historical charging battery temperatures in the set of historical charging battery temperatures.

[0174] In one embodiment, when the processor executes the logic in the computer program, the following steps are further implemented:

[0175] obtaining sample charging and discharging data of a sample power battery and a sample cumulative mileage corresponding to the sample charging and discharging data; wherein the sample charging and discharging data includes at least one of a set of sample charging and discharging rates, a set of sample charging depths and a set of sample charging battery temperatures; taking a state of health of the sample power battery as supervision data; and training the long short-term memory network with the sample charging and discharging data, the sample cumulative mileage and the supervision data to obtain the state of health evaluation model.

[0176] In one embodiment, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0177] obtain historical charge-discharge data of the to-be-evaluated power battery, and a target cumulative mileage of a vehicle in which the to-be-evaluated power battery is located; wherein the historical charge-discharge data includes at least one of a historical charge-discharge rate set, a historical charge depth set, and a historical charge battery temperature set;

[0178] determine a feature representation of the to-be-evaluated power battery according to the historical charge-discharge data and the target cumulative mileage;

[0179] input the feature representation into a health state evaluation model to obtain a health state of the to-be-evaluated power battery.

[0180] In one embodiment, when the code logic in the computer program for determining the feature representation of the to-be-evaluated power battery according to the historical charge-discharge data and the cumulative mileage is executed by the processor, the following steps are specifically implemented:

[0181] determine a first feature according to the target cumulative mileage, determine a second feature according to the historical charge-discharge rate set, determine a third feature according to the historical charge depth set, determine a fourth feature according to the historical charge battery temperature set, and fuse the first feature, the second feature, the third feature, and the fourth feature to obtain the feature representation of the to-be-evaluated power battery.

[0182] In one embodiment, when the code logic in the computer program for determining the second feature according to the historical charge-discharge rate set is executed by the processor, the following steps are specifically implemented:

[0183] determine a number of times of charging of the historical charge rate in each set charge-discharge rate interval in the historical charge rate set, determine a charging probability distribution according to the number of times of charging and a total number of historical charge rates in the historical charge rate set, determine a number of times of discharging of the historical discharge rate in each set charge-discharge rate interval in the historical discharge rate set, determine a discharging probability distribution according to the number of times of discharging and a total number of historical discharge rates in the historical discharge rate set, and determine the second feature according to the charging probability distribution and the discharging probability distribution.

[0184] In one embodiment, when the code logic in the computer program for determining the third feature according to the historical charge depth set is executed by the processor, the following steps are specifically implemented:

[0185] determine a number of times of charge depth of the historical charge depth in each set charge depth interval in the historical charge depth set, and determine the third feature according to the number of times of charge depth and a total number of historical charge depths in the historical charge depth set.

[0186] In one embodiment, when the code logic in the computer program for determining the fourth feature according to the historical charge battery temperature set is executed by the processor, the following steps are specifically implemented:

[0187] Determine a historical charging battery temperature set, a charging temperature number of the historical charging battery temperature in each set temperature interval; determine a fourth feature according to the charging temperature number and a total number of the historical charging battery temperature in the historical charging battery temperature set.

[0188] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0189] Obtain sample charging and discharging data of a sample power battery and sample cumulative mileage corresponding to the sample charging and discharging data; wherein the sample charging and discharging data includes at least one of a sample charging and discharging rate set, a sample charging depth set and a sample charging battery temperature set; take a state of health of the sample power battery as supervision data; train the long short-term memory network with the sample charging and discharging data, the sample cumulative mileage and the supervision data to obtain the state of health evaluation model.

[0190] In one embodiment, a computer program product is provided, including a computer program which, when executed by the processor, implements the following steps:

[0191] Obtain historical charging and discharging data of a power battery to be evaluated and a target cumulative mileage of a vehicle in which the power battery to be evaluated is located; wherein the historical charging and discharging data includes at least one of a historical charging and discharging rate set, a historical charging depth set and a historical charging battery temperature set;

[0192] Determine a feature representation of the power battery to be evaluated according to the historical charging and discharging data and the target cumulative mileage;

[0193] Input the feature representation into the state of health evaluation model to obtain a state of health of the power battery to be evaluated.

[0194] In one embodiment, the computer program, when executed by the processor, determines a feature representation of the power battery to be evaluated according to the historical charging and discharging data and the cumulative mileage, specifically implements the following steps:

[0195] Determine a first feature according to the target cumulative mileage; determine a second feature according to the historical charging and discharging rate set; determine a third feature according to the historical charging depth set; determine a fourth feature according to the historical charging battery temperature set; and fuse the first feature, the second feature, the third feature and the fourth feature to obtain the feature representation of the power battery to be evaluated.

[0196] In one embodiment, the computer program, when executed by the processor, determines a second feature according to the historical charging and discharging rate set, specifically implements the following steps:

[0197] determine a charging probability distribution according to the charging times and a total number of the historical charging rates in the historical charging rate set; determine a discharging probability distribution according to a discharging times of the historical discharging rates in the historical discharging rate set and a total number of the historical discharging rates in the historical discharging rate set; and determine the second feature according to the charging probability distribution and the discharging probability distribution.

[0198] In one embodiment, when the computer program is executed by the processor to determine the third feature according to the historical charging depth set, the following steps are specifically implemented:

[0199] determine a charging depth times of the historical charging depths in the historical charging depth set in each set charging depth interval; and determine the third feature according to the charging depth times and a total number of the historical charging depths in the historical charging depth set.

[0200] In one embodiment, when the computer program is executed by the processor to determine the fourth feature according to the historical charging battery temperature set, the following steps are specifically implemented:

[0201] determine a charging temperature times of the historical charging battery temperatures in the historical charging battery temperature set in each set temperature interval; and determine the fourth feature according to the charging temperature times and a total number of the historical charging battery temperatures in the historical charging battery temperature set.

[0202] In one embodiment, when the computer program is executed by the processor, the following steps are further specifically implemented:

[0203] obtain sample charging and discharging data of a sample power battery and a sample cumulative mileage corresponding to the sample charging and discharging data; wherein the sample charging and discharging data includes at least one of a sample charging and discharging rate set, a sample charging depth set and a sample charging battery temperature set; take a state of health of the sample power battery as supervision data; and train the long short-term memory network by using the sample charging and discharging data, the sample cumulative mileage and the supervision data to obtain the state of health evaluation model.

[0204] It should be noted that the user data (including but not limited to the cumulative mileage of the electric vehicle held by the user, the related data of the power battery in the electric vehicle, etc., wherein the related data of the power battery includes but is not limited to the charging and discharging data of the power battery) involved in the present application are all data authorized by the user or fully authorized by all parties.

[0205] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0206] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0207] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for determining the state of health of a power battery, characterized in that The method comprises: obtaining historical charge-discharge data of a power battery to be evaluated and a target cumulative mileage of a vehicle in which the power battery to be evaluated is located; wherein the historical charge-discharge data comprises at least one of a historical charge-discharge rate set, a historical charge depth set and a historical charge battery temperature set; the historical charge-discharge rate set comprises a historical charge rate set and a historical discharge rate set; determining a first feature according to the target cumulative mileage; determining, in the historical charge rate set, a charge number of historical charge rates located in each set charge-discharge rate interval, and determining a charge probability distribution according to the charge number and a total number of historical charge rates in the historical charge rate set; determining, in the historical discharge rate set, a discharge number of historical discharge rates located in each set charge-discharge rate interval, and determining a discharge probability distribution according to the discharge number and a total number of historical discharge rates in the historical discharge rate set; determining a second feature according to the charge probability distribution and the discharge probability distribution; determining a third feature according to the historical charge depth set; determining a fourth feature according to the historical charge battery temperature set; fusing the first feature, the second feature, the third feature and the fourth feature to obtain a feature representation of the power battery to be evaluated; inputting the feature representation into a health state evaluation model to obtain a health state of the power battery to be evaluated.

2. The method of claim 1, wherein, The determining of the third feature according to the historical charge depth set comprises: determining, in the historical charge depth set, a charge depth number of historical charge depths located in each set charge depth interval; determining the third feature according to the charge depth number and a total number of historical charge depths in the historical charge depth set.

3. The method of claim 1, wherein, The determining of the fourth feature according to the historical charge battery temperature set comprises: determining, in the historical charge battery temperature set, a charge temperature number of historical charge battery temperatures located in each set temperature interval; determining the fourth feature according to the charge temperature number and a total number of historical charge battery temperatures in the historical charge battery temperature set.

4. The method of claim 3, wherein, The determining of the fourth feature according to the charge temperature number and a total number of historical charge battery temperatures in the historical charge battery temperature set comprises: for each set temperature interval, determining a charge temperature probability of the set temperature interval according to a ratio of the charge temperature number in the set temperature interval to the total number of historical charge battery temperatures in the historical charge battery temperature set; combining the charge temperature probability of each set temperature interval to obtain the fourth feature.

5. The method of claim 1, wherein, The fusing of the first feature, the second feature, the third feature and the fourth feature to obtain the feature representation of the power battery to be evaluated comprises: splicing the first feature, the second feature, the third feature and the fourth feature according to a set order to obtain the feature representation of the power battery to be evaluated.

6. The method of claim 1, wherein, The method further comprises: obtain sample charge-discharge data of a sample power battery and sample cumulative mileage corresponding to the sample charge-discharge data; wherein the sample charge-discharge data comprises at least one of a sample charge-discharge rate set, a sample charge depth set and a sample charge battery temperature set; take the health state of the sample power battery as supervised data; train a long short-term memory network by using the sample charge-discharge data, the sample cumulative mileage and the supervised data, to obtain a health state evaluation model.

7. A power cell state of health determination apparatus, characterized by The device comprises: a data acquisition module configured to obtain historical charge-discharge data of a power battery to be evaluated and target cumulative mileage of a vehicle in which the power battery to be evaluated is located; wherein the historical charge-discharge data comprises at least one of a historical charge-discharge rate set, a historical charge depth set and a historical charge battery temperature set; the historical charge-discharge rate set comprises a historical charge rate set and a historical discharge rate set; a feature determination module configured to determine a first feature according to the target cumulative mileage; determine a charge number of historical charge rates in each set charge-discharge rate interval in the historical charge rate set, and determine a charge probability distribution according to the charge number and a total number of historical charge rates in the historical charge rate set; determine a discharge number of historical discharge rates in each set charge-discharge rate interval in the historical discharge rate set, and determine a discharge probability distribution according to the discharge number and a total number of historical discharge rates in the historical discharge rate set; determine a second feature according to the charge probability distribution and the discharge probability distribution; determine a third feature according to the historical charge depth set; determine a fourth feature according to the historical charge battery temperature set; and fuse the first feature, the second feature, the third feature and the fourth feature to obtain a feature representation of the power battery to be evaluated; a state evaluation module configured to input the feature representation into a health state evaluation model to obtain a health state of the power battery to be evaluated.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the method of any one of claims 1 to 6.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

Images