Method and device for predicting service life of battery and vehicle

Abstract

The invention relates to a battery life prediction method and device and a vehicle, and the method comprises the steps: obtaining the charging and discharging information and battery parameter information of a target battery of a target vehicle in each preset period in a preset time period, and obtaining the vehicle operation rate of the target vehicle in the preset period, and according to the charging and discharging information, the battery parameter information and the vehicle operation rate, a battery life prediction result corresponding to the target battery is obtained through a pre-trained battery life prediction model. In this way, the active life influence factor of the battery when the vehicle runs and the passive life influence factor of the vehicle in the non-running state can be comprehensively considered, and the determination of the battery life influence factor is more comprehensive. Meanwhile, the battery life prediction model is adopted to predict the battery life, the influence condition of different battery parameters on the battery life can be accurately determined, and the reliability and accuracy of battery life prediction are improved.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle technology, and more specifically, to a method, apparatus, and vehicle for predicting battery life. Background Technology

[0002] With the development and popularization of electric vehicles, battery performance directly affects the driving range and safety of electric vehicles. Therefore, accurate prediction of battery life has important practical significance and broad application prospects.

[0003] Currently, failure thresholds are commonly used to predict and evaluate battery life. However, there are often significant performance differences between different batteries, resulting in low universality of the thresholds, which makes it difficult to meet diverse needs and affects the accuracy of battery life prediction results. Summary of the Invention

[0004] To address the aforementioned problems, this disclosure provides a method, apparatus, and vehicle for predicting battery life.

[0005] According to a first aspect of the present disclosure, a method for predicting battery life is provided, the method comprising: The system acquires the charging and discharging information and battery parameter information of the target battery of the target vehicle for each preset cycle within a preset time period, wherein the preset time period includes multiple preset cycles; it acquires the vehicle operating rate of the target vehicle within each preset cycle, wherein the vehicle operating rate represents the ratio between the running time of the target vehicle and the total duration of the preset cycle; and based on the charging and discharging information, the battery parameter information, and the vehicle operating rate, it obtains the battery life prediction result corresponding to the target battery through a pre-trained battery life prediction model.

[0006] Optionally, obtaining the battery life prediction result corresponding to the target battery through a pre-trained battery life prediction model based on the charge / discharge information, the battery parameter information, and the vehicle operating rate includes: performing data processing on the charge / discharge information, the battery parameter information, and the vehicle operating rate respectively to obtain multi-dimensional arrays corresponding to the charge / discharge information, the battery parameter information, and the vehicle operating rate; inputting the multiple multi-dimensional arrays obtained after data processing into the battery life prediction model to obtain the battery life prediction result output by the battery life prediction model.

[0007] Optionally, the multidimensional array includes matrices. The step of processing the charging / discharging information, the battery parameter information, and the vehicle operating rate to obtain multidimensional arrays corresponding to the charging / discharging information, the battery parameter information, and the vehicle operating rate respectively includes: establishing matrices corresponding to the charging / discharging information, the battery parameter information, and the vehicle operating rate respectively; and filling the corresponding matrices with the charging / discharging information, battery parameter information, and vehicle operating rate of each preset period within the preset time period, thereby obtaining multidimensional arrays corresponding to the charging / discharging information, the battery parameter information, and the vehicle operating rate respectively.

[0008] Optionally, the charge / discharge information includes the cumulative charge / discharge capacity; the battery parameter information includes at least one of the battery rate, battery temperature, and battery state of charge.

[0009] Optionally, the battery temperature includes the battery's maximum temperature, minimum temperature, and average temperature; the data processing of the battery parameter information further includes: taking a weighted average of the battery's maximum temperature, minimum temperature, and average temperature to obtain a weighted temperature; and using the weighted temperature as the battery temperature to be processed.

[0010] Optionally, the battery state of charge includes a maximum state of charge and a minimum state of charge; the data processing of the battery parameter information further includes: taking a weighted average of the maximum state of charge and the minimum state of charge to obtain a weighted state of charge; and using the weighted state of charge as the battery state of charge to be processed.

[0011] Optionally, before processing the charging / discharging information, the battery parameter information, and the vehicle operating rate, the method further includes normalizing the cumulative charging / discharging capacity, the battery rate, and the battery temperature.

[0012] Optionally, the battery life prediction model is pre-trained in the following manner: acquiring historical battery life prediction results, historical charge and discharge information, historical battery parameter information, and historical vehicle operating rate for each historical cycle within a historical time period; using the historical charge and discharge information, the historical battery parameter information, and the historical vehicle operating rate as input samples for a pre-trained self-attention model, and using the historical battery life prediction results as output samples for the pre-trained self-attention model, thereby training the battery life prediction model.

[0013] According to a second aspect of the present disclosure, a battery life prediction device is provided, the device comprising: The first acquisition module is used to acquire the charging and discharging information and battery parameter information of the target battery of the target vehicle in each preset cycle within a preset time period, wherein the preset time period includes multiple preset cycles. The second acquisition module is used to acquire the vehicle operation rate of the target vehicle in each preset period, wherein the vehicle operation rate represents the ratio between the running time of the target vehicle and the total duration of the preset period. The determination module is used to obtain the battery life prediction result corresponding to the target battery by using a pre-trained battery life prediction model based on the charging and discharging information, the battery parameter information, and the vehicle operating rate.

[0014] Optionally, the determining module is used to process the charging and discharging information, the battery parameter information, and the vehicle operating rate respectively to obtain multi-dimensional arrays corresponding to the charging and discharging information, the battery parameter information, and the vehicle operating rate respectively; and input the multiple multi-dimensional arrays obtained after data processing into the battery life prediction model to obtain the battery life prediction result output by the battery life prediction model.

[0015] Optionally, the multidimensional array includes a matrix, and the determining module is used to establish matrices corresponding to the charging and discharging information, the battery parameter information, and the vehicle operating rate respectively; and to fill the corresponding matrices with the charging and discharging information, battery parameter information, and vehicle operating rate of each preset period within the preset time period as matrix elements, thereby obtaining the multidimensional arrays corresponding to the charging and discharging information, battery parameter information, and vehicle operating rate respectively.

[0016] Optionally, the charge / discharge information includes the cumulative charge / discharge capacity; the battery parameter information includes at least one of the battery rate, battery temperature, and battery state of charge.

[0017] Optionally, the battery temperature includes the highest battery temperature, the lowest battery temperature, and the average battery temperature; the determining module is further configured to perform a weighted average of the highest battery temperature, the lowest battery temperature, and the average battery temperature to obtain a weighted temperature; and use the weighted temperature as the battery temperature to be processed.

[0018] Optionally, the battery state of charge includes a maximum state of charge and a minimum state of charge; the determining module is further configured to perform a weighted average of the maximum state of charge and the minimum state of charge to obtain a weighted state of charge; and use the weighted state of charge as the battery state of charge to be processed.

[0019] Optionally, the determining module is further configured to normalize the cumulative charge / discharge capacity, the battery rate, and the battery temperature.

[0020] Optionally, the device further includes: a model training module, used to acquire historical battery life prediction results, historical charge and discharge information, historical battery parameter information, and historical vehicle operating rate for each historical cycle within a historical time period; using the historical charge and discharge information, the historical battery parameter information, and the historical vehicle operating rate as input samples for a pre-trained self-attention model, and using the historical battery life prediction results as output samples for the pre-trained self-attention model, to train the battery life prediction model.

[0021] According to a third aspect of the present disclosure, a vehicle is provided, including the battery life prediction device described in the second aspect of the present disclosure.

[0022] According to the above technical solution, by acquiring the charging and discharging information and battery parameter information of the target battery of the target vehicle in each preset cycle within a preset time period, and acquiring the vehicle operation rate of the target vehicle in each preset cycle, and based on the charging and discharging information, battery parameter information, and vehicle operation rate, the battery life prediction result corresponding to the target battery is obtained through a pre-trained battery life prediction model. This comprehensively considers the active life-influencing factors of the battery during vehicle operation, including state data such as charging and discharging information and battery parameter information, as well as the passive life-influencing factors when the vehicle is in a non-operational, idle state. This makes the battery life prediction result more compatible with the actual operation and idle scenarios of the vehicle, providing a more comprehensive determination of the factors influencing battery life. This allows the prediction method to adapt to the battery life assessment needs under different usage scenarios, effectively improving the accuracy of the battery life prediction results. Simultaneously, using a pre-established battery life prediction model for battery life prediction can accurately determine the impact of different battery parameters on battery life, further improving the reliability and accuracy of battery life prediction.

[0023] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0024] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart illustrating a method for predicting battery life according to an exemplary embodiment.

[0025] Figure 2 This is a flowchart illustrating another method for predicting battery life according to an exemplary embodiment.

[0026] Figure 3 This is a block diagram illustrating a battery life prediction device according to an exemplary embodiment.

[0027] Figure 4 This is a block diagram illustrating another battery life prediction device according to an exemplary embodiment.

[0028] Figure 5 This is a block diagram of an electronic device provided according to an exemplary embodiment of the present disclosure.

[0029] Figure 6 This is a block diagram of a vehicle provided according to an exemplary embodiment of the present disclosure. Detailed Implementation

[0030] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0031] In the following description, the words "first" and "second" are used only to distinguish the purpose of the description and should not be interpreted as indicating or implying relative importance or order.

[0032] In related technologies, with the development and popularization of electric vehicles, battery performance directly affects the driving range and safety of electric vehicles. Therefore, accurate prediction of battery life has significant practical importance and broad application prospects. Currently, failure thresholds are commonly used to predict and evaluate battery life. However, different batteries often have significant performance differences, resulting in low universality of thresholds, making it difficult to meet diverse needs and affecting the accuracy of battery life prediction results.

[0033] To address the aforementioned issues, this disclosure provides a method, apparatus, and vehicle for predicting battery life. It acquires charge / discharge information and battery parameter information of a target battery within a preset time period for each preset cycle, as well as the vehicle's operating rate within each preset cycle. Based on the charge / discharge information, battery parameter information, and vehicle operating rate, a pre-trained battery life prediction model is used to obtain the predicted battery life for the target battery. This comprehensively considers both the active life-influencing factors of the battery during vehicle operation (including charge / discharge information and battery parameter information) and the passive life-influencing factors when the vehicle is in a non-operational, idle state. This ensures the battery life prediction results are adapted to the actual operating and idle scenarios of the vehicle, providing a more comprehensive identification of battery life influencing factors. The prediction method can adapt to battery life assessment needs under different usage scenarios, effectively improving the accuracy of battery life prediction results. Furthermore, using a pre-established battery life prediction model allows for precise determination of the impact of different battery parameters on battery life, further enhancing the reliability and accuracy of battery life prediction.

[0034] The present disclosure will now be described in conjunction with specific embodiments.

[0035] Figure 1 This is a flowchart illustrating a method for predicting battery life according to an exemplary embodiment, such as... Figure 1 As shown, the method may include the following steps: In step S101, the charging and discharging information and battery parameter information of the target battery of the target vehicle in each preset cycle within a preset time period are obtained.

[0036] The target vehicle may include an electric vehicle or a hybrid vehicle. The target battery may include a power battery for providing driving energy to the target vehicle. The preset time period may include multiple preset cycles, for example, the preset time period may be n years, denoted as . , … The preset period can be months, and each year can include multiple months. For example, the first year can be the first month. The years are divided into Each month is denoted as... , … , The value can be 12. For example, charging / discharging information and battery parameter information for each month of the n years can be obtained. This charging / discharging information and battery parameter information can be obtained through a BMS (Battery Management System). The charging / discharging information can include information about the target battery during charging / discharging, such as charging / discharging capacity, charging / discharging current, and charging / discharging voltage. The battery parameter information can include battery performance parameters such as rate capability, temperature, and state of charge. Furthermore, it should be noted that after obtaining the charging / discharging information and battery parameter information, the collected information can be cleaned. Data cleaning methods can include filtering, noise reduction, and outlier handling. For example, the voltage distribution range can be determined based on the target battery type, and voltage data outside the voltage distribution range can be cleaned or interpolated. Data cleaning methods can be found in related technologies and will not be elaborated here.

[0037] In step S102, the vehicle operation rate of the target vehicle in each preset cycle is obtained.

[0038] The vehicle operation rate represents the ratio between the running time of the target vehicle and the total duration of the preset period. For example, the running time can be calculated in days, and the vehicle operation rate can be the ratio between the number of days the target vehicle runs in a month and the total number of days in that month. For instance, vehicle operation information for each preset period can be obtained through the ECU (Electronic Control Unit) of the target vehicle. This vehicle operation information may include the running time, number of runs, and mileage of the target vehicle, and the ratio between the running time of the target vehicle and the total duration of the preset period can be calculated to obtain the vehicle operation rate.

[0039] In step S103, based on the charging and discharging information, the battery parameter information, and the vehicle operating rate, the battery life prediction result corresponding to the target battery is obtained through a pre-trained battery life prediction model.

[0040] The battery life prediction result can include the battery health status prediction result of the target battery. This battery health status can include the battery capacity retention rate, which measures the energy storage capacity of the target battery, and the remaining useful life (RUL), which measures the number of cycles the target battery can withstand before it becomes unusable. This battery life prediction model supports deployment on the cloud and vehicle terminals. The deployment method can be determined according to actual application needs. In this embodiment, to improve the comprehensiveness and completeness of the samples in the battery life prediction model, multi-source big data can be acquired from the cloud to supplement the training samples of the battery life prediction model. Simultaneously, to improve the accuracy and efficiency of model calculations, cloud computing power can be relied upon to support model operation. Furthermore, the battery life prediction model can include multiple battery life prediction models corresponding to different vehicle state parameters. These vehicle state parameters can include vehicle model, battery type, rated capacity, and registration date, etc. For example, state parameters such as vehicle model, battery type, rated capacity, and registration date of the target vehicle can be extracted, and the battery life prediction model corresponding to the target vehicle can be determined from multiple battery life prediction models based on the extracted state parameters.

[0041] By employing the above technical solution, the charging and discharging information and battery parameter information of the target battery in a target vehicle can be obtained for each preset cycle within a preset time period. The vehicle's operating rate in each preset cycle can also be obtained. Based on the charging and discharging information, battery parameter information, and vehicle operating rate, a pre-trained battery life prediction model can be used to obtain the battery life prediction result for the target battery. This comprehensively considers both the active life-influencing factors of the battery during vehicle operation (including charging and discharging information and battery parameter information) and the passive life-influencing factors when the vehicle is in a non-operational, idle state. This ensures that the battery life prediction result is adapted to the actual operating and idle scenarios of the vehicle, providing a more comprehensive identification of the factors influencing battery life. This allows the prediction method to adapt to the battery life assessment needs under different usage scenarios, effectively improving the accuracy of the battery life prediction result. Furthermore, using a pre-established battery life prediction model for battery life prediction can accurately determine the impact of different battery parameters on battery life, further improving the reliability and accuracy of battery life prediction.

[0042] In some embodiments, step S103 above may include: S1031. Perform data processing on the charging / discharging information, the battery parameter information, and the vehicle operating rate respectively to obtain multi-dimensional arrays corresponding to the charging / discharging information, the battery parameter information, and the vehicle operating rate respectively.

[0043] In one possible implementation, the multidimensional array may include a matrix. Matrices corresponding to the charge / discharge information, battery parameter information, and vehicle operating rate can be created, and the charge / discharge information, battery parameter information, and vehicle operating rate for each preset period within the preset time period can be used as matrix elements to fill their respective matrices, resulting in multidimensional arrays corresponding to the charge / discharge information, battery parameter information, and vehicle operating rate.

[0044] For example, taking the charge / discharge information matrix as an example, the charge / discharge information for each preset period within the preset time period is used as matrix elements and filled into the charge / discharge information matrix according to a preset arrangement order to obtain a multi-dimensional array corresponding to the charge / discharge information. The preset arrangement order can be arranged from top to bottom according to the time order of the year, or from left to right according to the time order of the month. For example, when the preset time period includes... For each year within the preset time period, the charging and discharging information for the first year can be filled into the first column of the first row of the matrix, along with the charging and discharging information for the second month of the first year. Similarly, the charging and discharging information for the twelfth month of the first year can be filled into the twelfth column of the first row of the matrix. Then, the charging and discharging information for the first through twelfth months of the second year can be sequentially filled into the first through twelfth columns of the second row of the matrix, and so on. The charging and discharging information for the first to twelfth months of each year is sequentially filled into the matrix. The multidimensional array corresponding to the charging and discharging information is obtained from columns 1 to 12 of the row. It should be noted that the preset arrangement order is only an illustrative example and this disclosure does not impose any specific limitations on it. In addition, the filling method of the battery parameter information matrix and the vehicle operating rate matrix can be referred to the relevant description of the filling method of the charging and discharging information matrix, which will not be repeated here.

[0045] In some embodiments, the charge / discharge information may include cumulative charge / discharge capacity, and the battery parameter information may include at least one of battery rate, battery temperature, and battery state of charge.

[0046] The cumulative charge-discharge capacity can be the cumulative amount of electricity released or absorbed by the target battery during multiple charge-discharge cycles within a preset period. The battery rate is used to measure the target battery's ability to maintain its capacity under different charge-discharge currents, and can be calculated using the following formula: ,in This refers to the battery's rate of return. This represents the number of current sampling samples for the target battery. For the first The sampling points correspond to the current of the target battery. In this way, through multidimensional statistical analysis of the data, the application status of the battery is comprehensively evaluated, resulting in a more comprehensive determination of the factors affecting battery life. This allows for adaptation to the battery life assessment needs of different usage scenarios and improves the accuracy of battery life prediction results.

[0047] S1032. Input the multiple multidimensional arrays obtained after data processing into the battery life prediction model to obtain the battery life prediction result output by the battery life prediction model.

[0048] The multiple multidimensional arrays may include a cumulative charge / discharge capacity matrix, a battery rate matrix, a battery temperature matrix, a battery state of charge matrix, and a vehicle operating rate matrix. For example, the cumulative charge / discharge capacity matrix, the battery rate matrix, the battery temperature matrix, the battery state of charge matrix, and the vehicle operating rate matrix can be used as inputs to the battery life prediction model to obtain the battery capacity retention rate prediction result and the remaining service life prediction result output by the battery life prediction model.

[0049] In some embodiments, the battery temperature may include the battery maximum temperature, the battery minimum temperature, and the battery average temperature. Step S1031 may further include: taking a weighted average of the battery maximum temperature, the battery minimum temperature, and the battery average temperature to obtain a weighted temperature, and using the weighted temperature as the battery temperature to be processed.

[0050] For example, the highest battery temperature for each month within the preset time period can be obtained. Minimum battery temperature and average battery temperature The first temperature weight corresponding to the highest temperature of the battery. The second temperature weight corresponding to the lowest temperature of the battery. The third temperature weight corresponding to the average temperature of the battery It can be determined based on historical data and the actual parameters of the target battery. , and The sum of these values ​​is 1. In this embodiment, the influence of temperature distribution on battery life can be determined by setting... , , .

[0051] The weighted temperature can be calculated using the following formula:

[0052] in, For this weighted temperature, This is the highest temperature of the battery. This is the first temperature weight. This is the lowest temperature of the battery. For this second temperature weight, This is the average temperature of the battery. This is the third temperature weight.

[0053] In this way, when battery temperature data is needed, using the weighted data of the battery's highest temperature, lowest temperature, and average temperature can comprehensively evaluate the battery's temperature information, making the battery temperature data more comprehensive and accurate, and further improving the accuracy of subsequent battery life prediction results.

[0054] In some embodiments, the battery state of charge may include a maximum state of charge and a minimum state of charge. Step S1031 may further include: taking a weighted average of the maximum state of charge and the minimum state of charge to obtain a weighted state of charge, and using the weighted state of charge as the battery state of charge to be processed.

[0055] For example, the extreme values ​​of the state of charge of the target battery in multiple charge-discharge cycles within each preset period can be obtained, and each extreme value of the state of charge can be denoted as... , , ..., Each minimum value of a charged state is denoted as... , , ..., , This refers to the number of charge-discharge cycles, at which point you can... , , ..., The maximum state of charge at the first preset quantile is taken as the maximum state of charge for that preset period, denoted as . ,Will , , ..., The minimum state of charge at the second preset quantile is taken as the minimum state of charge for that preset period, denoted as . The first and second preset quantiles can be determined based on historical data and actual conditions. For example, the first preset quantile can be 95%, and the second preset quantile can be 5%. The weight of the first state of charge corresponding to the maximum state of charge. The weight of the second charge state corresponding to the minimum charge state It can be determined based on historical data and the actual parameters of the target battery. and The sum of these values ​​is 1. In this embodiment, the influence of the state of charge distribution on battery life can be determined by setting... , The weighted state of charge can be calculated using the following formula:

[0056] in, For this weighted state of charge, This is the maximum state of charge. This is the weight of the first charged state. This is the minimum state of charge. This is the weight for the second state of charge. Thus, when battery state of charge data is needed, using the weighted data of the maximum and minimum state of charge allows for a comprehensive evaluation of the battery's state of charge information, making the state of charge data more comprehensive and accurate, and further improving the accuracy of subsequent battery life prediction results.

[0057] In some embodiments, to improve numerical stability, the method may further include normalizing the cumulative charge / discharge capacity, the battery rate, and the battery temperature before processing the charge / discharge information, the battery parameter information, and the vehicle operating rate, respectively.

[0058] For example, the cumulative charge-discharge capacity can be normalized using the following formula:

[0059] in, This is the initial value of the cumulative charge / discharge capacity within the preset period to be processed. This is the preprocessing value of the cumulative charge and discharge capacity within the preset period to be processed.

[0060]

[0061] in, This is the preprocessing value of the cumulative charge and discharge capacity within the preset period to be processed. This is the normalized value of the cumulative charge and discharge capacity within the preset period. It is the minimum value among all the preprocessed cumulative charge and discharge capacities within the year of the preset period. It is the maximum value among the preprocessed values ​​of all cumulative charge and discharge capacities within the year of the preset period.

[0062] For example, the battery rate can be normalized using the following formula:

[0063] in, This represents the initial value of the battery rate within the preset period to be processed. This is the normalized value of the battery rate within the preset period. It is the minimum initial value among all battery rate values ​​within the year of the preset cycle. It is the maximum value among the initial values ​​of all battery rates within the year of the preset cycle.

[0064] For example, the battery temperature can be normalized using the following formula:

[0065] in, This represents the initial value of the battery temperature within the preset cycle to be processed. This is the normalized value of the battery temperature within the preset cycle. It is the minimum initial value of all battery temperatures within the year of the preset cycle. It is the maximum value among all the initial values ​​of battery temperature within the year of the preset cycle.

[0066] In this way, by scaling the calculated data of cumulative charge and discharge capacity, battery rate, and battery temperature through data normalization, the calculation scale of various types of data can be unified, which can improve the accuracy and robustness of subsequent model calculations.

[0067] In some embodiments, the battery life prediction model is pre-trained by: acquiring historical battery life prediction results, historical charge and discharge information, historical battery parameter information, and historical vehicle operating rate for each historical cycle within a historical time period; using the historical charge and discharge information, the historical battery parameter information, and the historical vehicle operating rate as input samples for a pre-trained self-attention model; and using the historical battery life prediction results as output samples for the pre-trained self-attention model to train the battery life prediction model.

[0068] The historical time period can be multiple years prior to the preset time period, and the historical period can be the month within each year of the historical time period. The historical battery life prediction result can include historical battery capacity retention rate, such as a battery capacity retention rate matrix with years as rows and months as columns, obtained based on battery capacity decay rate assessment methods or experimental measurements; it can also include measured results of historical remaining lifespan. The pre-trained self-attention model can be a neural network model containing an attention layer, such as an RNN (Recurrent Neural Network), LSTM (Long Short-Term Memory), or Transformer network. For input samples, the pre-trained self-attention model can transform them into query (Q) matrices, key (K) matrices, and value (V) matrices using randomly generated weight matrices. Then, it calculates the dot product of the query matrix and the key matrix, normalizes it using the softmax function, calculates the attention weights, applies the attention weights to the value matrix, and performs a weighted summation among the query matrix, key matrix, and value matrix to output the prediction result of the pre-trained self-attention model. During the training process of this pre-trained self-attention model, a loss calculation method can be used to correct the prediction results of the pre-trained self-attention model based on historical battery life prediction results, thereby training the battery life prediction model. For example, historical battery life prediction results, historical charge / discharge information, historical battery parameter information, and historical vehicle operating rates can be obtained for each historical period within the historical timeframe, considering different vehicle models, battery types, rated capacities, and registration dates. Based on the training of the pre-trained self-attention model, multiple battery life prediction models corresponding to different vehicle state parameters can be obtained.

[0069] In this way, when training the battery life prediction model, an attention mechanism is introduced to automatically select the feature parameters that affect battery life, thereby improving the accuracy of the prediction. Furthermore, the attention mechanism can be applied to automatically obtain the dependency relationship of feature parameters between different time points, effectively improving the accuracy of the model prediction.

[0070] Figure 2 This is a flowchart illustrating another method for predicting battery life according to an exemplary embodiment, such as... Figure 2 As shown, the method may include the following steps: S201. Obtain the charging and discharging information and battery parameter information of the target battery of the target vehicle in each preset cycle within a preset time period.

[0071] The target vehicle may include electric vehicles or hybrid vehicles. The target battery may include a power battery. The preset time period may include multiple preset cycles. The charge / discharge information and battery parameter information can be obtained through the BMS. The charge / discharge information may include the cumulative charge / discharge capacity, and the battery parameter information may include the battery rate, battery temperature, and battery state of charge. The battery temperature may include the maximum battery temperature, the minimum battery temperature, and the average battery temperature, and the battery state of charge may include the maximum state of charge and the minimum state of charge.

[0072] S202. Obtain the vehicle operation rate of the target vehicle in each preset cycle.

[0073] The vehicle operation rate represents the ratio between the running time of the target vehicle and the total duration of the preset cycle.

[0074] S203. Normalize the cumulative charge / discharge capacity, the battery rate, and the battery temperature.

[0075] S204. Take the weighted average of the battery's highest temperature, lowest temperature, and average temperature to obtain the weighted temperature.

[0076] The weighted temperature can be calculated using the following formula:

[0077] in, For this weighted temperature, This is the highest temperature of the battery. The first temperature weight corresponding to the highest battery temperature. This is the lowest temperature of the battery. This is the second temperature weight corresponding to the lowest temperature of the battery. This is the average temperature of the battery. This is the third temperature weight corresponding to the average temperature of the battery.

[0078] S205. Use this weighted temperature as the battery temperature to be processed.

[0079] S206. Take a weighted average of the maximum and minimum states of charge to obtain the weighted state of charge.

[0080] The weighted charge state can be calculated using the following formula:

[0081] in, For this weighted state of charge, This is the maximum state of charge. The weight of the first charge state corresponding to the maximum charge state. This is the minimum state of charge. This is the weight of the second charge state corresponding to the minimum charge state.

[0082] S207. Use the weighted state of charge as the battery state of charge to be processed.

[0083] S208. Perform data processing on the charging / discharging information, the battery parameter information, and the vehicle operating rate respectively to obtain multi-dimensional arrays corresponding to the charging / discharging information, the battery parameter information, and the vehicle operating rate respectively.

[0084] The multidimensional array includes matrices. Matrices corresponding to the charge / discharge information, battery parameter information, and vehicle operating rate can be established. The charge / discharge information, battery parameter information, and vehicle operating rate for each preset period within the preset time period are used as matrix elements and filled into their respective matrices to obtain multidimensional arrays corresponding to the charge / discharge information, battery parameter information, and vehicle operating rate. S209: The multiple multidimensional arrays obtained after data processing are input into the battery life prediction model to obtain the battery life prediction result output by the battery life prediction model.

[0085] The battery life prediction result may include the battery health status prediction result of the target battery, or the remaining service life prediction result of the target battery. The battery life prediction model can be pre-trained in the following way: obtain the historical battery life prediction result, historical charge and discharge information, historical battery parameter information and historical vehicle operating rate for each historical cycle within a historical time period, and use the historical charge and discharge information, historical battery parameter information and historical vehicle operating rate as input samples for the pre-trained self-attention model, and use the historical battery life prediction result as the output sample for the pre-trained self-attention model to train the battery life prediction model.

[0086] The above method allows for the acquisition of charge / discharge information and battery parameter information of the target battery in a target vehicle for each preset cycle within a preset time period, as well as the vehicle's operating rate in each preset cycle. Based on the charge / discharge information, battery parameter information, and vehicle operating rate, a pre-trained battery life prediction model is used to obtain the battery life prediction result for the target battery. This comprehensively considers both the active life-influencing factors of the battery during vehicle operation (including charge / discharge information and battery parameter information) and the passive life-influencing factors when the vehicle is in a non-operational, idle state. This ensures that the battery life prediction result is adapted to the actual operating and idle scenarios of the vehicle, providing a more comprehensive identification of the factors influencing battery life. This allows the prediction method to adapt to the battery life assessment needs under different usage scenarios, effectively improving the accuracy of the battery life prediction results. Furthermore, using a pre-established battery life prediction model for battery life prediction can accurately determine the impact of different battery parameters on battery life, further enhancing the reliability and accuracy of battery life prediction.

[0087] It should be noted that the above Figure 2 The descriptions of each step in the illustrated embodiments can be found in the descriptions of the relevant steps in the foregoing embodiments, and will not be repeated here.

[0088] Furthermore, for the sake of simplicity, the above method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions. For example, steps S204 to S205 and steps S206 to S207 are not limited to the order shown in the current embodiment. Steps S206 to S207 can be executed first, followed by steps S204 to S205, or steps S204 to S205 and steps S206 to S207 can be executed simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0089] Figure 3 This is a block diagram illustrating a battery life prediction device 300 according to an exemplary embodiment, with reference to... Figure 3 The device includes: The first acquisition module 301 is used to acquire the charging and discharging information and battery parameter information of the target battery of the target vehicle in each preset cycle within a preset time period, wherein the preset time period includes multiple preset cycles. The second acquisition module 302 is used to acquire the vehicle operation rate of the target vehicle in each preset period, wherein the vehicle operation rate represents the ratio between the running time of the target vehicle and the total duration of the preset period. The determination module 303 is used to obtain the battery life prediction result corresponding to the target battery through a pre-trained battery life prediction model based on the charging and discharging information, the battery parameter information, and the vehicle operating rate.

[0090] Optionally, the determining module 303 is used to perform data processing on the charge / discharge information, the battery parameter information, and the vehicle operating rate respectively to obtain multi-dimensional arrays corresponding to the charge / discharge information, the battery parameter information, and the vehicle operating rate respectively; and input the multiple multi-dimensional arrays obtained after data processing into the battery life prediction model to obtain the battery life prediction result output by the battery life prediction model.

[0091] Optionally, the multidimensional array includes a matrix. The determining module 303 is used to establish matrices corresponding to the charging and discharging information, the battery parameter information, and the vehicle operating rate, respectively. The charging and discharging information, battery parameter information, and vehicle operating rate of each preset period within the preset time period are used as matrix elements and filled into their respective matrices to obtain the multidimensional arrays corresponding to the charging and discharging information, the battery parameter information, and the vehicle operating rate, respectively.

[0092] Optionally, the charge / discharge information includes the cumulative charge / discharge capacity; the battery parameter information includes at least one of the battery rate, battery temperature, and battery state of charge.

[0093] Optionally, the battery temperature includes the highest battery temperature, the lowest battery temperature, and the average battery temperature; the determining module 303 is further configured to perform a weighted average of the highest battery temperature, the lowest battery temperature, and the average battery temperature to obtain a weighted temperature; and use the weighted temperature as the battery temperature to be processed.

[0094] Optionally, the battery state of charge includes a maximum state of charge and a minimum state of charge; the determining module 303 is further configured to perform a weighted average of the maximum state of charge and the minimum state of charge to obtain a weighted state of charge; and use the weighted state of charge as the battery state of charge to be processed.

[0095] Optionally, the determining module 303 is also used to normalize the cumulative charge / discharge capacity, the battery rate, and the battery temperature.

[0096] Optionally, such as Figure 4 As shown, the device also includes: a model training module 304, used to acquire historical battery life prediction results, historical charge and discharge information, historical battery parameter information and historical vehicle operating rate for each historical cycle within a historical time period; using the historical charge and discharge information, the historical battery parameter information and the historical vehicle operating rate as input samples for a pre-trained self-attention model, and using the historical battery life prediction results as output samples for the pre-trained self-attention model to train the battery life prediction model.

[0097] Using the aforementioned device, the charging and discharging information and battery parameter information of the target battery in a target vehicle can be acquired for each preset cycle within a preset time period. The vehicle's operating rate within each preset cycle is also obtained. Based on the charging and discharging information, battery parameter information, and vehicle operating rate, a pre-trained battery life prediction model is used to obtain the battery life prediction result for the target battery. This comprehensively considers both the active life-influencing factors of the battery during vehicle operation (including charging and discharging information and battery parameter information) and the passive life-influencing factors when the vehicle is in a non-operational, idle state. This ensures that the battery life prediction result is adapted to the actual operating and idle scenarios of the vehicle, providing a more comprehensive identification of the factors influencing battery life. This allows the prediction method to adapt to the battery life assessment needs under different usage scenarios, effectively improving the accuracy of the battery life prediction results. Furthermore, using a pre-established battery life prediction model for battery life prediction can accurately determine the impact of different battery parameters on battery life, further enhancing the reliability and accuracy of battery life prediction.

[0098] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0099] Figure 5 This is a block diagram of an electronic device 500 provided according to an exemplary embodiment of the present disclosure. Figure 5 As shown, the electronic device 500 may include a processor 501 and a memory 502. The electronic device 500 may also include one or more of a multimedia component 503, an input / output (I / O) interface 504, and a communication component 505.

[0100] The processor 501 controls the overall operation of the electronic device 500 to complete all or part of the steps in the aforementioned battery life prediction method. The memory 502 stores various types of data to support the operation of the electronic device 500. This data may include, for example, instructions for any application or method operating on the electronic device 500, and application-related data such as contact data, sent and received messages, pictures, audio, video, etc. The memory 502 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 503 may include a screen and audio components. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 502 or transmitted via communication component 505. The audio component also includes at least one speaker for outputting audio signals. I / O interface 504 provides an interface between processor 501 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical. Communication component 505 is used for wired or wireless communication between the electronic device 500 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IoT, eMTC, or other 5G technologies, or combinations thereof, is not limited here. Therefore, the corresponding communication component 505 may include: a Wi-Fi module, a Bluetooth module, an NFC module, etc.

[0101] In an exemplary embodiment, the electronic device 500 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the battery life prediction method described above.

[0102] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the battery life prediction method described above. For example, the computer-readable storage medium may be the memory 502 including program instructions described above, which may be executed by the processor 501 of the electronic device 500 to complete the battery life prediction method described above.

[0103] Figure 6 This is a structural block diagram of a vehicle 600 according to an exemplary embodiment, the vehicle 600 including the aforementioned battery life prediction device 300.

[0104] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0105] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0106] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A method for predicting battery life, characterized in that, The method includes: The charging and discharging information and battery parameter information of the target battery of the target vehicle are obtained for each preset cycle within a preset time period, wherein the preset time period includes multiple preset cycles; The vehicle operation rate of the target vehicle in each preset period is obtained, and the vehicle operation rate represents the ratio between the running time of the target vehicle and the total duration of the preset period. Based on the charging and discharging information, the battery parameter information, and the vehicle operating rate, the battery life prediction result corresponding to the target battery is obtained through a pre-trained battery life prediction model.

2. The method according to claim 1, characterized in that, The step of obtaining the battery life prediction result corresponding to the target battery through a pre-trained battery life prediction model based on the charging and discharging information, the battery parameter information, and the vehicle operating rate includes: The charging / discharging information, the battery parameter information, and the vehicle operating rate are processed separately to obtain multi-dimensional arrays corresponding to the charging / discharging information, the battery parameter information, and the vehicle operating rate, respectively. The multiple multidimensional arrays obtained after data processing are input into the battery life prediction model to obtain the battery life prediction result output by the battery life prediction model.

3. The method according to claim 2, characterized in that, The multidimensional array includes a matrix. The data processing of the charge / discharge information, the battery parameter information, and the vehicle operating rate to obtain multidimensional arrays corresponding to the charge / discharge information, battery parameter information, and vehicle operating rate respectively includes: Establish matrices corresponding to the charging / discharging information, the battery parameter information, and the vehicle operating rate, respectively; The charging and discharging information, battery parameter information, and vehicle operating rate of each preset cycle within the preset time period are used as matrix elements and filled into their respective matrices to obtain multidimensional arrays corresponding to the charging and discharging information, the battery parameter information, and the vehicle operating rate, respectively.

4. The method according to claim 3, characterized in that, The charge / discharge information includes the cumulative charge / discharge capacity. The battery parameter information includes at least one of the following: battery rate, battery temperature, and battery state of charge.

5. The method according to claim 4, characterized in that, The battery temperature includes the battery's maximum temperature, minimum temperature, and average temperature; the data processing of the battery parameter information further includes: The weighted average of the battery's highest temperature, lowest temperature, and average temperature is calculated to obtain the weighted temperature. The weighted temperature is used as the battery temperature to be processed.

6. The method according to claim 4, characterized in that, The battery state of charge includes a maximum state of charge and a minimum state of charge; the data processing of the battery parameter information further includes: The weighted average of the maximum state of charge and the minimum state of charge is obtained to obtain the weighted state of charge. The weighted state of charge is used as the battery state of charge to be processed.

7. The method according to claim 4, characterized in that, Before processing the charging / discharging information, the battery parameter information, and the vehicle operating rate, the method further includes: The cumulative charge / discharge capacity, the battery rate, and the battery temperature are normalized.

8. The method according to any one of claims 1-7, characterized in that, The battery life prediction model is pre-trained in the following manner: Obtain historical battery life prediction results, historical charge and discharge information, historical battery parameter information, and historical vehicle operating rate for each historical cycle within a historical time period; The historical charge / discharge information, the historical battery parameter information, and the historical vehicle operating rate are used as input samples for the pre-trained self-attention model, and the historical battery life prediction results are used as output samples for the pre-trained self-attention model to train the battery life prediction model.

9. A device for predicting battery life, characterized in that, The device includes: The first acquisition module is used to acquire the charging and discharging information and battery parameter information of the target battery of the target vehicle in each preset cycle within a preset time period, wherein the preset time period includes multiple preset cycles. The second acquisition module is used to acquire the vehicle operation rate of the target vehicle in each preset period, wherein the vehicle operation rate represents the ratio between the running time of the target vehicle and the total duration of the preset period. The determination module is used to obtain the battery life prediction result corresponding to the target battery by using a pre-trained battery life prediction model based on the charging and discharging information, the battery parameter information, and the vehicle operating rate.

10. A vehicle, characterized in that, Includes the battery life prediction device as described in claim 9.

Images