Power battery capacity track prediction method, system, equipment and medium

By obtaining and subdividing the mileage and battery parameters of the electrified carrier during the sampling period, generating a sequence of target states and driving conditions, and inputting them into the capacity prediction model, the problem of low prediction accuracy of power battery capacity trajectory in the prior art is solved. Improved prediction accuracy and reliability.

CN119044781AActive Publication Date: 2024-11-29SHANGHAI TECH UNIV

Patent Information

Application Number
CN202411257468.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-09
Publication Date
2024-11-29
Estimated Expiration
2044-09-09

AI Technical Summary

Technical Problem

The prior art is difficult to accurately predict the attenuation trajectory of the maximum available capacity of the power battery, especially in complex practical application conditions, resulting in low prediction accuracy.

Method used

By obtaining the mileage and battery parameters of the electrified carrier during the sampling period, dividing the operating period, determining the target state sequence and the target driving condition sequence, and inputting it to the capacity prediction model to predict the capacity trajectory of the power battery.

Benefits of technology

It improves the accuracy and reliability of battery capacity trajectory prediction, takes into account user driving behavior, and achieves more accurate capacity prediction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119044781A_ABST
    Figure CN119044781A_ABST
Patent Text Reader

Abstract

The invention relates to a power battery capacity trajectory prediction method, system and device and a medium. The method comprises the following steps: in a preset sampling time period, acquiring the driving mileage of an electrified carrying tool and battery parameters of a corresponding power battery, and dividing the sampling time period into a plurality of operation time periods according to the battery parameters; determining a target state sequence and a target driving condition sequence of the power battery according to the battery parameters and the driving mileage of each operation period; and inputting the target state sequence and the target driving condition sequence into a capacity prediction model, and predicting a capacity track of the power battery in the next sampling period. According to the invention, the accuracy of power battery capacity trajectory prediction is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of battery technology, and in particular to a method, system, device and medium for predicting power battery capacity trajectory. Background Art

[0002] In order to improve the safety and economy of energy storage systems, accurate estimation of the state of health (SOH) of power batteries in electrified vehicles has become an issue of increasing concern. Electrified vehicles include but are not limited to electric vehicles, rail transit vehicles, electric ships, electric aircraft, electric bicycles, electric motorcycles, electric agricultural machinery or engineering machinery, etc. Power batteries include but are not limited to lithium-ion batteries, sodium-ion batteries, quasi-solid-state batteries, all-solid-state batteries, etc.

[0003] As the power battery ages, its maximum available capacity will gradually decay. Different types of power batteries and their operating conditions will lead to large differences in battery decay trajectories. Therefore, how to accurately predict the decay trajectory of the maximum available capacity of the power battery is of great significance for timely issuing alarm signals and optimizing user operations. Traditional methods for predicting the capacity trajectory of power batteries mainly rely on power battery aging test data in laboratory environments, but these methods cannot adapt well to complex working conditions in actual applications. Therefore, it is necessary to provide a method, system, device and medium for predicting the capacity trajectory of power batteries. Summary of the invention

[0004] In view of the above-mentioned shortcomings of the prior art, an object of the present invention is to provide a method, system, device and medium for predicting a power battery capacity trajectory, which improves the problem of low accuracy of power battery capacity trajectory prediction in the prior art.

[0005] To achieve the above-mentioned purpose and other related purposes, the present invention provides a method for predicting the capacity trajectory of a power battery, which is applied to an electric vehicle. The method includes: obtaining the mileage of the electric vehicle and the corresponding battery parameters of the power battery within a preset sampling period, and dividing the sampling period into multiple operating periods based on the battery parameters; determining the target state sequence and target driving condition sequence of the power battery based on the battery parameters and mileage of each operating period; inputting the target state sequence and the target driving condition sequence into a capacity prediction model to predict the capacity trajectory of the power battery in the next sampling period.

[0006] In one embodiment of the present invention, determining the target state sequence and target driving condition sequence of the power battery based on the battery parameters and mileage of each operating period includes: dividing all operating periods into multiple groups according to the mileage, and obtaining target state parameters and target driving condition parameters corresponding to a preset target state category and target driving condition category in each group; and arranging the target state parameters and target driving condition parameters of each group in chronological order to form a target state sequence and a target driving condition sequence.

[0007] In one embodiment of the present invention, the process of determining the category of the target state and the target driving condition is: grouping them according to the pre-acquired historical driving mileage, and obtaining the historical state sequence and historical driving condition sequence of the power battery based on the historical battery parameters in each group; and filtering out the category of the target state / the category of the target driving condition from the historical state sequence / the historical driving condition sequence based on feature engineering.

[0008] In one embodiment of the present invention, the method of filtering out the category of the target state / the category of the target driving condition from the historical state sequence / the historical driving condition sequence based on feature engineering includes: respectively calculating the Pearson correlation coefficient between each parameter in the historical state sequence / the historical driving condition sequence and the average maximum available battery capacity of the historical state sequence; counting the Pearson correlation coefficient of each parameter, and taking the parameter category with a Pearson correlation coefficient greater than a preset correlation threshold as the corresponding target state / target driving condition category.

[0009] In one embodiment of the present invention, the acquisition of target state parameters and target driving condition parameters corresponding to the preset target state category and target driving condition category includes: acquiring the target state parameters of the current sampling period corresponding to the target state category based on the battery parameters of each operating period and the corresponding driving mileage; acquiring the target driving condition parameters of the current sampling period corresponding to the target driving condition category based on the battery parameters of each operating period and the corresponding driving mileage.

[0010] In one embodiment of the present invention, the target state parameters and target driving condition parameters corresponding to the preset target state categories and target driving condition categories are obtained, including: obtaining the target state parameters of the current sampling period corresponding to the target state categories based on the battery parameters and the corresponding mileage of each operating period; monitoring the operating conditions of the electrified vehicle, and predicting the operating conditions of the next sampling period based on the monitored operating conditions, and when it is predicted that the operating conditions will change within the next sampling period, inputting the operating conditions of the next sampling period into a pre-trained driving condition prediction model to predict the target driving condition parameters of the next sampling period.

[0011] In one embodiment of the present invention, the target state sequence and the target driving condition sequence are input into a capacity prediction model to predict the capacity trajectory of the power battery in the next sampling period, including: inputting the target state sequence and the target driving condition sequence into an encoder of the capacity prediction model, and acquiring a hidden state vector based on the time dependency between various parameters; inputting the hidden state vector into a decoder of the capacity prediction model, gradually decoding the hidden state vector, and predicting the capacity trajectory of the power battery in the next sampling period.

[0012] In one embodiment of the present invention, a prediction system for the capacity trajectory of a power battery is also provided, the system comprising: a data acquisition module, for acquiring the mileage of an electric vehicle and the corresponding battery parameters of a power battery within a preset sampling period, and dividing the sampling period into a plurality of operating periods according to the battery parameters; a grouping feature extraction module, for determining a target state sequence and a target driving condition sequence of the power battery according to the battery parameters and mileage of each operating period; a capacity prediction module, for inputting the target state sequence and the target driving condition sequence into a capacity prediction model, and predicting the capacity trajectory of the power battery in the next sampling period.

[0013] In one embodiment of the present invention, an electronic device is also provided, including: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the electronic device implements any of the above-mentioned methods for predicting the power battery capacity trajectory.

[0014] In one embodiment of the present invention, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer executes any of the above-mentioned methods for predicting the capacity trajectory of a power battery.

[0015] As described above, the method, system, device and medium for predicting the capacity trajectory of a power battery of the present invention have the following beneficial effects: by acquiring and subdividing the mileage and battery parameters of an electrified vehicle within a sampling period, a target state sequence and a target driving condition sequence are generated. Since the data in the target driving condition sequence are closely related to the user's driving behavior, these data are input into the capacity prediction model, and a more accurate battery capacity trajectory prediction is achieved while taking into account the user's driving behavior, thereby improving the accuracy and reliability of the battery capacity trajectory prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic flow chart of a method for predicting a power battery capacity trajectory provided by an embodiment of the present invention;

[0017] Figure 2 Shown is a structural block diagram of a power battery capacity trajectory prediction system provided by an embodiment of the present invention;

[0018] Figure 3 Shown is a structural schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0020] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0021] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0022] The inventors found that as the running time of electric vehicles increases, the power batteries installed in them will gradually age, and the maximum available capacity of the power batteries will also decay. Accurately predicting this decay trajectory is of great guiding significance for timely issuing alarm signals and optimizing user operations. In addition, such electric vehicles are usually operated by humans, and different driving behaviors will have different effects on the decay trajectory of the maximum available capacity of the power battery.

[0023] In view of the above situation, the present invention provides a method for predicting the capacity trajectory of a power battery, which generates a target state sequence and a target driving condition sequence by acquiring and subdividing the mileage and battery parameters of an electric vehicle within a sampling period. Since the data in the target driving condition sequence is closely related to the user's driving behavior, these data are input into the capacity prediction model, and a more accurate battery capacity trajectory prediction is achieved while considering the user's driving behavior, thereby improving the accuracy and reliability of the battery capacity trajectory prediction.

[0024] See also Figure 1 ,The prediction method of power battery capacity trajectory includes the following steps:

[0025] S1. Within a preset sampling period, the mileage of the electric vehicle and the battery parameters of the corresponding power battery are obtained, and the sampling period is divided into multiple operating time periods according to the battery parameters.

[0026] When predicting the maximum available capacity trajectory of the power battery in the electric vehicle, first, the mileage of the electric vehicle at each sampling point and various battery parameters of the power battery to be tested in the electric vehicle are obtained through the cloud server within the preset sampling period. Among them, the mileage refers to the cumulative distance traveled by the electric vehicle, and the battery parameters are used to reflect the operating status of the power battery under different working conditions. The battery parameters include but are not limited to the state of charge, voltage and current. According to the change trend of the state of charge or current in the battery parameters, the sampling period is divided into multiple operating periods, wherein the operating period includes a charging period and a discharging period. Exemplarily, according to the change of the state of charge in the battery parameters, the sampling period is divided into multiple charging periods and multiple discharging periods. Among them, the charging period is a time period in which the power battery to be tested is receiving energy. During this time period, the power battery to be tested is charged by an external power supply, and the state of charge of the power battery to be tested gradually increases. The discharging period is a time period in which the power battery to be tested releases energy for external purposes (such as driving an electric vehicle or a power supply device). During this time period, the state of charge of the power battery to be tested gradually decreases.

[0027] It should be noted that the present invention can process data in a charging period or a discharging period, so the "operating period" mentioned later refers to a charging period or a discharging period within a sampling period.

[0028] It is understandable that, considering the process of data interaction between the cloud server and the electrified vehicle, due to communication errors and other reasons, abnormal data points may appear in the received battery parameters or mileage and other data. In order to ensure the accuracy of subsequent data processing, the present invention also performs data cleaning on the received battery parameters and mileage to remove abnormal values ​​in the data. Among them, the data cleaning method includes but is not limited to interpolation or deletion of abnormal values, as long as the data quality can be improved, it is not limited here. It should be further explained that in order to ensure the consistency of battery parameters and mileage in time, the present invention also synchronizes the acquired battery parameters and mileage according to their respective timestamps to ensure that at each sampling point, the relevant data of mileage and battery parameters can correctly correspond.

[0029] S2. Determine a target state sequence and a target driving condition sequence of the power battery according to the battery parameters and driving mileage in each operating period.

[0030] According to the battery parameters (such as voltage, current, state of charge, etc.) in different operating periods and the mileage corresponding to these periods, several different categories of state parameters are obtained, and these state parameters are used to reflect the operating state of the power battery. In addition, several different categories of driving condition parameters are also obtained, and these driving condition parameters are used to characterize the operating conditions related to the battery pack or battery cell in the power battery. Among them, the state parameters include but are not limited to the average maximum available battery capacity, cumulative mileage, average driving period mileage, etc., and the driving condition parameters include but are not limited to the average battery pack voltage, average battery pack current, average ambient temperature, etc. These state parameters are arranged in chronological order to obtain the target state sequence. Similarly, these driving condition parameters are arranged in chronological order to obtain the target driving condition sequence.

[0031] Specifically, in one embodiment of the present invention, determining the target state sequence and target driving condition sequence of the power battery according to the battery parameters and driving mileage in each operating period includes:

[0032] Dividing all the operating time periods into a plurality of groups according to the driving mileage, and obtaining a target state parameter and a target driving condition parameter corresponding to a preset target state category and a preset target driving condition category in each group;

[0033] The target state parameters and target driving condition parameters of each group are arranged in chronological order to form a target state sequence and a target driving condition sequence.

[0034] According to the preset mileage interval (such as 500 kilometers), all operating time periods are divided into multiple groups, and each group corresponds to a time period with a fixed mileage interval. According to the preset target state category and target driving condition category, the corresponding target state parameters and target driving condition parameters are calculated in each group according to the mileage and the battery parameters of the corresponding time period. The target state parameters and target driving condition parameters of all groups are arranged in chronological order to form a target state sequence and a target driving condition sequence. It should be noted that since the corresponding operating states of the electrified vehicle are different during the charging period and the discharging period, the target state category may also be different in these two time periods.

[0035] Specifically, in one embodiment of the present invention, the process of determining the target state and the category of the target driving condition is:

[0036] According to the historical driving mileage acquired in advance, the historical driving mileage is grouped, and based on the historical battery parameters in each group, a historical state sequence and a historical driving condition sequence of the power battery are acquired;

[0037] Based on feature engineering, the category of the target state / the category of the target driving condition is screened out from the historical state sequence / the historical driving condition sequence.

[0038] The categories of target state and target driving condition are determined in advance based on the operating characteristics of power batteries and electrified vehicles and historical data analysis. When determining the categories of target state and target driving condition, it is first necessary to collect the historical mileage and corresponding historical battery parameters of the electrified vehicle within a historical sampling period (such as 1 month), and divide the sampling period into multiple operating periods according to the historical battery parameters. According to the aforementioned mileage interval (such as 500 kilometers), the historical operating periods are grouped, and each group corresponds to a fixed mileage interval. For each group: extract the historical mileage and battery parameters of each operating period in the group, and calculate the historical state parameters and historical driving condition parameters of the group based on the extracted data and the category of the operating period. Arrange the historical state parameters and historical driving condition parameters of each group in chronological order to form a historical state sequence and a historical driving condition sequence. And through feature engineering, the category of the target state and the category of the target driving condition are screened out.

[0039] Specifically, when the operating period is a charging period, each charging period in the historical sampling period is grouped according to the mileage to obtain multiple historical charging intervals. For each historical charging interval, the various historical state parameters of the historical charging interval are calculated according to the battery parameters such as voltage, current, temperature, charge and state of charge of each charging period. Among them, the historical state parameters of each historical charging interval include but are not limited to the average maximum available battery capacity, cumulative mileage, average driving period mileage, average driving period discharge depth, average battery output energy, average change rate of voltage to state of charge, and average change rate of voltage to charge, a total of 7 historical state parameters. Among them, the average maximum available battery capacity is the average of the maximum available battery capacity of each period in the current interval, in ampere-hours. The cumulative mileage is the total mileage in the current interval, in kilometers. The average driving period mileage is the average mileage of all periods in the current interval, in kilometers. The average driving period discharge depth is the average of the discharge depth of each operating period in the current interval, in percentage (%). The average battery output energy is the average of the output energy of each operating period in the current interval, in kilowatt-hours. The average rate of change of voltage to state of charge is the average value of the voltage change rate corresponding to the unit state of charge change in the current interval, expressed as Where, ΔV iΔSOC is the change in the battery pack voltage during the i-th operating period, obtained by the voltage difference between the battery pack at the beginning and end of the operating period. d_i is the change in the state of charge during the i-th operating period, obtained by the difference in the state of charge of the battery pack at the start and end of the operating period, and N is the total number of operating periods in the current interval. The average rate of change of voltage to charge is the average of the voltage change rate corresponding to the unit charge change in the current interval, expressed as Among them, ΔQ d_i is the change in charge amount in the i-th operating period. It can be understood that, since each historical charging interval will obtain these 7 historical state parameters, arranging the historical state parameters of all historical charging intervals in sequence can form 7 historical state sequences.

[0040] Furthermore, the driving condition parameters are used to characterize the relevant parameters of the battery pack and the battery cells. The historical driving condition parameters of each historical charging interval include but are not limited to the average battery pack voltage, the average battery pack current, the average ambient temperature, the average driving period single cell voltage range, the average driving period single cell voltage average value, the average driving period single cell voltage standard deviation, the average driving period single cell voltage maximum and minimum values, the average driving period temperature probe range, the average driving period temperature probe average value and the average driving period temperature probe standard deviation, a total of 11 driving condition parameters. Among them, the average battery pack voltage is the average of the battery pack voltages in each driving period in the interval, in volts. The average battery pack current is the average of the battery pack currents in each driving period in the interval, in amperes. The average ambient temperature is the average of the ambient temperatures in each driving period in the interval, in degrees Celsius. The average driving period single cell voltage range is the difference between the maximum and minimum values ​​of the battery cell voltage in the interval, in volts. The average driving period single cell voltage average value is the average of the battery cell voltages in all operating periods in the interval, expressed as Where M is the total number of battery cells in the battery pack, N is the total number of operating time periods in the interval, and V' i,j is the voltage of the jth battery cell in the ith operating period in the interval. The average driving period single cell voltage standard deviation is the mean of the battery cell voltage standard deviation in each operating period in the interval. The average driving period single cell voltage maximum / minimum value interval is the average of the maximum / minimum values ​​of the battery cell voltage in each operating period, in volts. The average driving period temperature probe range is the average of the difference between the highest and lowest temperatures measured by the temperature probe in each operating period in the interval, in degrees Celsius. It can be understood that since each historical charging interval will obtain these 11 historical driving condition parameters, arranging the historical driving condition parameters of all historical charging intervals in sequence can form 11 historical driving condition sequences.

[0041] When the operation period is the discharge period, the vehicle may be in operation. In addition to the above 7 parameters, the state parameters also include the average charge consumption per unit mileage and the average charge state loss per unit mileage. The average charge consumption per unit mileage is the average value of the charge consumption per unit mileage in the interval, expressed as Among them, Δm i is the difference in mileage during the i-th operating period, obtained based on the difference in mileage between the start and end of the operating period, ΔQ d_i is the change in charge during the i-th operating period. The average unit mileage state of charge loss is the average value of the unit mileage state of charge loss in the interval, expressed as When the operation period is a discharge period, the driving condition parameters are the same as those of the charging period. Therefore, when the operation period is a discharge period, 9 historical state sequences and 11 historical driving condition sequences can be generated.

[0042] It should be noted that the categories of historical driving condition parameters and historical status parameters listed above are only specific examples. For different electrified vehicles, technicians in this field can adaptably select corresponding parameter categories based on specific needs, and no limitation is made here.

[0043] In one embodiment of the present invention, the step of filtering out the target state category / target driving condition category from the historical state sequence / the historical driving condition sequence based on feature engineering includes:

[0044] respectively calculating the Pearson correlation coefficient between each parameter in the historical state sequence / the historical driving condition sequence and the average maximum available battery capacity of the historical state sequence;

[0045] The Pearson correlation coefficient of each parameter is counted, and the parameter category with a Pearson correlation coefficient greater than a preset correlation threshold is used as the category of the corresponding target state / target driving condition.

[0046] Although the state parameters and driving condition parameters extracted above can characterize the relevant performance of the power battery, the amount of data is relatively large. In order to reduce the amount of calculation, the present invention also screens out multiple parameters that are strongly correlated with the power battery capacity through feature engineering. Specifically, the state parameters and driving condition parameters of the same type extracted in each group are arranged in chronological order to form multiple historical state sequences and historical driving condition sequences. These parameter sequences are respectively compared with the average battery maximum available capacity sequence according to formula (1) to calculate the Pearson correlation coefficient:

[0047]

[0048] in, is the i-th parameter sequence x i Pearson correlation coefficient between the average battery maximum available capacity, x ij is the jth parameter value in the i-th parameter sequence, is the mean of the i-th parameter sequence, z j is the jth parameter value in the average battery maximum available capacity sequence, is the mean of all data in the average battery maximum available capacity sequence, and n is the total number of data points in the sequence. The above parameter sequence refers to a historical state parameter sequence or a historical driving condition parameter sequence.

[0049] Through the above process, the parameters with a Pearson correlation coefficient greater than a preset correlation threshold (such as 0.6) are selected as the target state parameters and target driving condition parameters. It can be understood that different models of electric vehicles have different corresponding target states and target driving condition categories due to different selected historical state parameters and historical driving condition parameters.

[0050] Exemplarily, for a certain type of electric vehicle, when the operation period is the discharge period, the corresponding target state categories are average maximum available battery capacity, cumulative mileage, average charge consumption per unit mileage, average depth of discharge during the driving period, average loss of state of charge per unit mileage, and average rate of change of voltage to state of charge, and the target driving condition categories are average driving period battery cell voltage minimum value, average driving period temperature probe average value. For another type of electric vehicle, when the operation period is the discharge period, the corresponding target state categories are average maximum available battery capacity and cumulative mileage, and the corresponding target driving condition categories are average driving period cell voltage extreme difference, average driving period cell voltage average value, average driving period cell voltage maximum and minimum values, average driving period temperature probe extreme difference, average driving period temperature probe average value, and average driving period temperature probe standard deviation.

[0051] In one embodiment of the present invention, the step of obtaining target state parameters and target driving condition parameters corresponding to the preset target state category and target driving condition category includes:

[0052] According to the battery parameters and the corresponding driving mileage of each operating period, obtaining the target state parameters of the current sampling period corresponding to the category of the target state;

[0053] According to the battery parameters and the corresponding driving mileage in each operating period, the target driving condition parameters of the current sampling period corresponding to the type of the target driving condition are obtained.

[0054] By using the battery parameters and corresponding mileage of each current operating period, according to the category of the target state and the category of the target driving condition obtained above, the target state parameters corresponding to these categories and the target driving condition parameters of the current sampling period are calculated.

[0055] When the operating condition of the vehicle is in a stable state in a short period of time, the target state parameters and target driving condition parameters of the current sampling period can be obtained according to the battery parameters and mileage of the current sampling period, according to the categories of the target state and the target driving condition. Specifically, after all the operating periods are grouped according to the mileage, for each group, the target state parameters corresponding to the target state category are calculated based on the obtained battery parameters and mileage. After all the groups are processed, the target state parameters of the same category are arranged in sequence to obtain the corresponding target state sequence. Exemplarily, if the target state category is "average battery maximum available capacity", the average battery maximum available capacity of the group can be obtained by calculating the mean of the battery maximum available capacity of each operating period in the group. The average battery maximum available capacity of all groups is arranged according to the order of the timestamps to obtain the target state sequence "average battery maximum available capacity sequence". Similarly, for the same group, the target driving condition parameters corresponding to the target driving condition category are obtained according to the battery parameters and mileage in all the operating periods in the group. After all the groups are processed, the target driving condition parameters of the same category are arranged in sequence to obtain the corresponding target state sequence. For example, if the target driving condition category is "average ambient temperature", the average ambient temperature of the group can be obtained by calculating the average of the ambient temperature in each operating period in the group. The average ambient temperatures of all groups are arranged in the order of timestamps to obtain the target driving condition sequence "average ambient temperature sequence".

[0056] In another embodiment of the present invention, the step of obtaining target state parameters and target driving condition parameters corresponding to preset target state categories and target driving condition categories includes:

[0057] According to the battery parameters and the corresponding driving mileage of each operating period, obtaining the target state parameters of the current sampling period corresponding to the category of the target state;

[0058] Monitor the operating conditions of the electrified vehicle and predict the operating conditions of the next sampling period based on the monitored operating conditions. When it is predicted that the operating conditions will change within the next sampling period, input the operating conditions of the next sampling period into a pre-trained driving condition prediction model to predict the target driving condition parameters of the next sampling period.

[0059] According to the monitored operating conditions of the vehicle in the current sampling period, the operating conditions of the next sampling period are predicted, wherein the operating conditions include but are not limited to the driving speed, load conditions, external environmental conditions, etc. of the electric vehicle. When it is predicted that the operating conditions of the electric vehicle will change in the next sampling period, for example, the ambient temperature of the next sampling period changes, or the driving speed slows down, etc., these situations may cause the target driving condition parameters of the current sampling period to fail to accurately represent the future operating state. In order to achieve accurate prediction of the battery capacity trajectory, the target driving condition parameters of the next sampling period can be predicted based on the predicted operating conditions. Specifically, the predicted operating conditions of the next sampling period are input into the trained driving condition prediction model to obtain the target driving condition parameters of the next sampling period. Among them, the driving condition prediction model can be any machine learning or deep learning model, which is not limited here. Preferably, the driving condition prediction model and the capacity prediction model described below have the same model architecture. It can be understood that when the operating conditions of the vehicle remain unchanged in the next sampling period, the target driving condition parameters of the current sampling period can be obtained by the aforementioned battery parameters and mileage of the current sampling period. The target driving condition parameters for the next sampling period can also be predicted by the above method.

[0060] S3. Input the target state sequence and the target driving condition sequence into a capacity prediction model to predict the capacity trajectory of the power battery in the next sampling period.

[0061] Specifically, in one embodiment of the present invention, the step of inputting the target state sequence and the target driving condition sequence into a capacity prediction model to predict the capacity trajectory of the power battery in the next sampling period includes:

[0062] Inputting the target state sequence and the target driving condition sequence into an encoder of the capacity prediction model, and obtaining a hidden state vector based on the time dependency between various parameters;

[0063] The latent state vector is input into the decoder of the capacity prediction model, the latent state vector is decoded step by step, and the capacity trajectory of the power battery in the next sampling period is predicted.

[0064] The capacity prediction model can be a deep learning model of any sequence-to-sequence (Seq2Seq) framework. The Seq2Seq framework includes an encoder and a decoder, both of which can be composed of neural networks. Among them, the neural networks that constitute the encoder and the decoder include but are not limited to bidirectional gated recurrent units (Bi-directional Gate Recurrent Unit, Bi-GRU), recurrent neural networks (Recurrent Neural Network, RNN), long short-term memory networks (Long Short-Term Memory, LSTM), bidirectional long short-term memory models (Bi-directional LSTM, Bi-LSTM), etc. Exemplarily, when the capacity prediction model is a bidirectional long short-term memory model, the target state sequence and the target driving condition sequence are input into the encoder of the capacity prediction model, and the time dependency information therein is extracted and multiple hidden state vectors are generated. Each hidden state vector is input into the decoder, and each time step is processed recursively according to the current hidden state vector and the output of the previous time step, and the capacity trajectory of the next sampling period is gradually generated. It can be understood that since there are two types of target driving condition sequences, the present invention can use two different data to predict the capacity trajectory of the next sampling period. One is to input the target state sequence of the current sampling period and the target driving condition sequence of the current sampling period into the capacity prediction model to obtain the capacity trajectory of the next sampling period. The other is to input the target state sequence of the current sampling period and the target driving condition sequence of the next sampling period into the capacity prediction model to obtain the capacity trajectory of the next sampling period.

[0065] It should be noted that the capacity prediction model is obtained through training, and the data set for training the capacity prediction model can be obtained through open source channels or collected by yourself. Among them, the open source channel can be obtained through the National Big Data Alliance of New Energy Vehicles (NDANEV), from which the operation data period of 200 electric buses from January 2019 to December 2019 is obtained, and each period represents a charging or discharging process. There are 2 different models in the 200 vehicles, and each model contains 100 vehicles. In the training stage, considering that some vehicle data is less, the present invention selects 172 vehicles (86 each) with a cumulative mileage of more than 30,000 kilometers from two models and 100 vehicles for constructing training sets, validation sets and test sets. For each model, 5 groups of training sets and validation sets are constructed using the cross-validation method (each group of training sets and validation sets have the same division ratio, the training set contains 64 vehicles, the validation set contains 16 vehicles, and the 16 vehicles in each validation set are not repeated), and the remaining 6 vehicles are used as test sets. Five Seq2Seq models were trained using these five training and validation sets, and the model with the smallest validation error was selected as the final capacity trajectory prediction model. The trained capacity trajectory prediction model performed well on the test set, with a maximum mean absolute error of 0.78% and a maximum root mean square error of 0.94%, demonstrating the high accuracy and reliability of the model.

[0066] See also Figure 2 , the prediction system 100 of the power battery capacity trajectory includes: a data acquisition module 110, a grouping feature extraction module 120 and a capacity prediction module 130. Among them, the data acquisition module 110 is used to obtain the mileage of the electrified vehicle and the corresponding battery parameters of the power battery within a preset sampling period, and divide the sampling period into multiple operating periods according to the battery parameters. The grouping feature extraction module 120 is used to determine the target state sequence and target driving condition sequence of the power battery according to the battery parameters and mileage of each operating period. The capacity prediction module 130 is used to input the target state sequence and the target driving condition sequence into the capacity prediction model to predict the capacity trajectory of the power battery in the next sampling period.

[0067] For the specific limitations of the prediction system for the power battery capacity trajectory, please refer to the limitations of the prediction method for the power battery capacity trajectory mentioned above, which will not be repeated here. Each module in the above-mentioned prediction system for the power battery capacity trajectory can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware format, or can be stored in the memory of the computer device in software format, so that the processor can call the operations corresponding to the above modules.

[0068] It should be noted that, in order to highlight the innovative part of the present invention, the present embodiment does not introduce modules that are not closely related to solving the technical problem proposed by the present invention, but this does not mean that there are no other modules in the present embodiment.

[0069] See also Figure 3 The electronic device 1 may include a memory 12, a processor 13 and a bus, and may also include a computer program stored in the memory 12 and executable on the processor 13, such as a prediction program for a power battery capacity trajectory.

[0070] Among them, the memory 12 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 12 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 12 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 12 can also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 12 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code for predicting the power battery capacity trajectory, etc., but can also be used to temporarily store data that has been output or is to be output.

[0071] In some embodiments, the processor 13 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 13 is the control core (Control Unit) of the electronic device 1, and uses various interfaces and lines to connect the various components of the entire electronic device 1, and executes or executes programs or modules stored in the memory 12 (such as a prediction program for the power battery capacity trajectory, etc.), and calls the data stored in the memory 12 to execute various functions of the electronic device 1 and process data.

[0072] The processor 13 executes the operating system and various installed applications of the electronic device 1. The processor 13 executes the applications to implement the steps in the above-mentioned method for predicting the power battery capacity trajectory.

[0073] Exemplarily, the computer program may be divided into one or more modules, which are stored in the memory 12 and executed by the processor 13 to complete the present application. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the electronic device 1. For example, the computer program may be divided into a data acquisition module 110, a grouping feature extraction module 120, and a capacity prediction module 130.

[0074] The above-mentioned integrated unit implemented in the form of a software function module can be stored in a computer-readable storage medium, and the computer-readable storage medium can be non-volatile or volatile. The above-mentioned software function module is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, a computer device, or a network device, etc.) or a processor to perform part of the functions of the method for predicting the power battery capacity trajectory described in each embodiment of the present application.

[0075] In summary, the present invention discloses a method, system, device and medium for predicting the capacity trajectory of a power battery, which generates a target state sequence and a target driving condition sequence by acquiring and subdividing the mileage and battery parameters of an electrified vehicle within a sampling period. Since the data in the target driving condition sequence is closely related to the user's driving behavior, these data are input into the capacity prediction model, and a more accurate battery capacity trajectory prediction is achieved while taking the user's driving behavior into consideration, thereby improving the accuracy and reliability of the power battery capacity trajectory prediction. Therefore, the present invention effectively overcomes the various shortcomings of the prior art and has a high industrial utilization value.

[0076] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A method for predicting power battery capacity trajectory, characterized in that: Applied to an electric vehicle, the method comprises: Acquire the mileage of the electric vehicle and the battery parameters of the corresponding power battery within a preset sampling period, and divide the sampling period into a plurality of operating periods according to the battery parameters; Determine the target state sequence and target driving condition sequence of the power battery based on the battery parameters and driving mileage in each operating period; The target state sequence and the target driving condition sequence are input into a capacity prediction model to predict the capacity trajectory of the power battery in the next sampling period.

2. The method for predicting the power battery capacity trajectory according to claim 1, characterized in that: Determining the target state sequence and target driving condition sequence of the power battery according to the battery parameters and driving mileage in each operating period includes: Dividing all the operating time periods into a plurality of groups according to the driving mileage, and obtaining a target state parameter and a target driving condition parameter corresponding to a preset target state category and a preset target driving condition category in each group; The target state parameters and target driving condition parameters of each group are arranged in chronological order to form a target state sequence and a target driving condition sequence.

3. The method for predicting the power battery capacity trajectory according to claim 2, characterized in that: The process of determining the target state and the category of the target driving condition is as follows: According to the historical driving mileage acquired in advance, the historical driving mileage is grouped, and based on the historical battery parameters in each group, a historical state sequence and a historical driving condition sequence of the power battery are acquired; Based on feature engineering, the category of the target state / the category of the target driving condition is screened out from the historical state sequence / the historical driving condition sequence.

4. The method for predicting the power battery capacity trajectory according to claim 3, characterized in that: The step of filtering out the target state category / target driving condition category from the historical state sequence / the historical driving condition sequence based on feature engineering includes: respectively calculating the Pearson correlation coefficient between each parameter in the historical state sequence / the historical driving condition sequence and the average maximum available battery capacity of the historical state sequence; The Pearson correlation coefficient of each parameter is counted, and the parameter category with a Pearson correlation coefficient greater than a preset correlation threshold is used as the category of the corresponding target state / target driving condition.

5. The method for predicting the power battery capacity trajectory according to claim 2, characterized in that: The step of obtaining target state parameters and target driving condition parameters corresponding to preset target state categories and target driving condition categories includes: According to the battery parameters and the corresponding driving mileage of each operating period, obtaining the target state parameters of the current sampling period corresponding to the category of the target state; According to the battery parameters and the corresponding driving mileage in each operating period, the target driving condition parameters of the current sampling period corresponding to the type of the target driving condition are obtained.

6. The method for predicting the power battery capacity trajectory according to claim 2, characterized in that: The step of obtaining target state parameters and target driving condition parameters corresponding to preset target state categories and target driving condition categories includes: According to the battery parameters and the corresponding driving mileage of each operating period, obtaining the target state parameters of the current sampling period corresponding to the category of the target state; Monitor the operating conditions of the electrified vehicle and predict the operating conditions of the next sampling period based on the monitored operating conditions. When it is predicted that the operating conditions will change within the next sampling period, input the operating conditions of the next sampling period into a pre-trained driving condition prediction model to predict the target driving condition parameters of the next sampling period.

7. The method for predicting the power battery capacity trajectory according to claim 1, characterized in that: The step of inputting the target state sequence and the target driving condition sequence into a capacity prediction model to predict the capacity trajectory of the power battery in the next sampling period includes: Inputting the target state sequence and the target driving condition sequence into an encoder of the capacity prediction model, and obtaining a hidden state vector based on the time dependency between various parameters; The latent state vector is input into the decoder of the capacity prediction model, the latent state vector is decoded step by step, and the capacity trajectory of the power battery in the next sampling period is predicted.

8. A prediction system for power battery capacity trajectory, characterized in that: The system comprises: A data acquisition module, used to acquire the mileage of the electric vehicle and the battery parameters of the corresponding power battery within a preset sampling period, and divide the sampling period into a plurality of operating time periods according to the battery parameters; A grouping feature extraction module is used to determine the target state sequence and target driving condition sequence of the power battery according to the battery parameters and driving mileage in each operating period; The capacity prediction module is used to input the target state sequence and the target driving condition sequence into the capacity prediction model to predict the capacity trajectory of the power battery in the next sampling period.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the electronic device to implement the method for predicting the power battery capacity trajectory as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is enabled to execute the method for predicting the power battery capacity trajectory as described in any one of claims 1 to 7.

Citation Information

Patent Citations

  • Battery health state end-cloud collaborative estimation method based on constant-voltage charging segment

    CN115097344A

  • Battery management control method and device

    CN115476722A

  • Lithium battery health state real-time monitoring method and system

    CN116643190A

  • Battery state of health prediction method and apparatus, and electronic device and readable storage medium

    WO2022161002A1

Cited By

  • Battery cell temperature prediction method, device, equipment and program product

    CN121069209A