CN-121995225-A - Battery life prediction method and device and vehicle

CN121995225ACN 121995225 ACN121995225 ACN 121995225ACN-121995225-A

Abstract

The method comprises the steps of obtaining charge and discharge information and battery parameter information of a target battery of a target vehicle in each preset period in a preset time period, obtaining the vehicle running rate of the target vehicle in the preset period, and obtaining a battery life prediction result corresponding to the target battery through a pre-trained battery life prediction model according to the charge and discharge information, the battery parameter information and the vehicle running rate. Therefore, the active life influencing factors of the battery in the running state of the vehicle and the passive life influencing factors of the vehicle in the non-running state can be comprehensively considered, and the battery life influencing factors can be more comprehensively determined. Meanwhile, the battery life prediction model is adopted to predict the battery life, so that the influence condition of different battery parameters on the battery life can be accurately determined, and the reliability and the accuracy of the battery life prediction are improved.

Inventors

ZHANG RUI
SHAO GENGHUA
LIU YIN
MA KAIXUAN
HUANG MENG
FU JUN
GUO SHAOJIE
WEI XIANGLONG
XIA SHUXIAN
Kang Haiqin
WANG RAN
LU JIAJIA
FENG QIANQIAN

Assignees

北汽福田汽车股份有限公司

Dates

Publication Date: 20260508
Application Date: 20251230

Claims (10)

1. A method of predicting battery life, the method comprising: acquiring charge and discharge information and battery parameter information of a target battery of a target vehicle in each preset period in a preset time period, wherein the preset time period comprises a plurality of preset periods; Acquiring a vehicle operation rate of the target vehicle in each preset period, wherein the vehicle operation rate represents a ratio between the operation duration of the target vehicle and the total duration of the preset periods; And obtaining a battery life prediction result corresponding to the target battery through a pre-trained battery life prediction model according to the charge and discharge information, the battery parameter information and the vehicle running rate.
2. The method according to claim 1, wherein the obtaining, according to the charge and discharge information, the battery parameter information, and the vehicle operation rate, the battery life prediction result corresponding to the target battery through a battery life prediction model trained in advance includes: Respectively carrying out data processing on the charge and discharge information, the battery parameter information and the vehicle running rate to obtain multidimensional arrays respectively corresponding to the charge and discharge information, the battery parameter information and the vehicle running rate; And inputting the multi-dimensional arrays obtained through data processing into the battery life prediction model to obtain a battery life prediction result output by the battery life prediction model.
3. The method according to claim 2, wherein the multi-dimensional array includes a matrix, the data processing is performed on the charge and discharge information, the battery parameter information, and the vehicle operation rate, respectively, to obtain multi-dimensional arrays corresponding to the charge and discharge information, the battery parameter information, and the vehicle operation rate, respectively, including: Establishing matrixes respectively corresponding to the charge and discharge information, the battery parameter information and the vehicle running rate; And filling the charge and discharge information, the battery parameter information and the vehicle operation rate of each preset period in the preset time period into respective corresponding matrixes to obtain multidimensional arrays respectively corresponding to the charge and discharge information, the battery parameter information and the vehicle operation rate.
4. The method of claim 3, wherein the step of, The charge and discharge information comprises accumulated charge and discharge capacity; the battery parameter information includes at least one of a battery rate, a battery temperature, and a battery state of charge.
5. The method of claim 4, wherein the battery temperature comprises a highest battery temperature, a lowest battery temperature, and an average battery temperature, wherein the data processing the battery parameter information further comprises: Carrying out weighted average on the highest temperature of the battery, the lowest temperature of the battery and the average temperature of the battery to obtain weighted temperature; And taking the weighted temperature as the battery temperature to be subjected to data processing.
6. The method of claim 4, wherein the battery state of charge comprises a maximum state of charge and a minimum state of charge, wherein the data processing the battery parameter information further comprises: carrying out weighted average on the maximum charge state and the minimum charge state to obtain a weighted charge state; and taking the weighted charge state as the charge state of the battery to be subjected to data processing.
7. The method of claim 4, wherein prior to data processing the charge and discharge information, the battery parameter information, and the vehicle operating rate, respectively, the method further comprises: and normalizing the accumulated charge-discharge capacity, the battery multiplying power and the battery temperature.
8. The method of any one of claims 1-7, wherein the battery life prediction model is pre-trained by: Acquiring a historical battery life prediction result, historical charge and discharge information, historical battery parameter information and historical vehicle operation rate of each historical period in a historical time period; and taking the historical charge and discharge information, the historical battery parameter information and the historical vehicle running rate as input samples of a pre-training self-attention model, taking the historical battery life prediction result as output samples of the pre-training self-attention model, and training to obtain the battery life prediction model.
9. A battery life prediction apparatus, the apparatus comprising: the first acquisition module is used for acquiring charge and discharge information and battery parameter information of a target battery of a target vehicle in each preset period in a preset time period, wherein the preset time period comprises a plurality of preset periods; The second acquisition module is used for acquiring the vehicle operation rate of the target vehicle in each preset period, wherein the vehicle operation rate represents the ratio between the operation duration of the target vehicle and the total duration of the preset periods; And the determining module is used for obtaining a battery life prediction result corresponding to the target battery through a battery life prediction model trained in advance according to the charge and discharge information, the battery parameter information and the vehicle running rate.
10. A vehicle comprising the battery life prediction apparatus according to claim 9.

Description

Battery life prediction method and device and vehicle Technical Field The disclosure relates to the technical field of vehicles, and in particular relates to a battery life prediction method and device and a vehicle. Background With the development and popularization of electric vehicles, the performance of the battery directly affects the cruising ability and safety of the electric vehicle. Therefore, the method has important practical significance and wide application prospect for accurate prediction of the service life of the battery. At present, a failure judgment threshold value is generally adopted to predict and evaluate the service life of the battery, but larger performance differences often exist among different batteries, the universality of the threshold value is low, diversified requirements are difficult to meet, and the accuracy of a battery service life prediction result is affected. Disclosure of Invention In order to solve the problems, the disclosure provides a battery life prediction method, a battery life prediction device and a vehicle. According to a first aspect of embodiments of the present disclosure, there is provided a method of predicting battery life, the method comprising: The method comprises the steps of obtaining charge and discharge information and battery parameter information of a target battery of a target vehicle in each preset period in a preset time period, obtaining the vehicle running rate of the target vehicle in each preset period, representing the ratio between the running duration of the target vehicle and the total duration of the preset period, and obtaining a battery life prediction result corresponding to the target battery through a pre-trained battery life prediction model according to the charge and discharge information, the battery parameter information and the vehicle running rate. Optionally, the battery life prediction result corresponding to the target battery is obtained through a battery life prediction model trained in advance according to the charge and discharge information, the battery parameter information and the vehicle operation rate, the method comprises the steps of respectively carrying out data processing on the charge and discharge information, the battery parameter information and the vehicle operation rate to obtain multidimensional arrays corresponding to the charge and discharge information, the battery parameter information and the vehicle operation rate, and inputting the multidimensional arrays obtained through data processing into the battery life prediction model to obtain the battery life prediction result output by the battery life prediction model. Optionally, the multi-dimensional array includes a matrix, and the data processing is performed on the charge and discharge information, the battery parameter information and the vehicle operation rate to obtain multi-dimensional arrays corresponding to the charge and discharge information, the battery parameter information and the vehicle operation rate respectively, including building the matrix corresponding to the charge and discharge information, the battery parameter information and the vehicle operation rate respectively; and filling the charge and discharge information, the battery parameter information and the vehicle operation rate of each preset period in the preset time period into respective corresponding matrixes to obtain multidimensional arrays respectively corresponding to the charge and discharge information, the battery parameter information and the vehicle operation rate. Optionally, the charge and discharge information comprises accumulated charge and discharge capacity, and the battery parameter information comprises at least one of battery multiplying power, battery temperature and battery charge state. Optionally, the battery temperature comprises a battery maximum temperature, a battery minimum temperature and a battery average temperature, the data processing is carried out on the battery parameter information, the method further comprises the step of carrying out weighted average on the battery maximum temperature, the battery minimum temperature and the battery average temperature to obtain weighted temperatures, and the weighted temperatures are used as the battery temperatures to be subjected to the data processing. Optionally, the battery state of charge includes a maximum state of charge and a minimum state of charge, and the data processing is performed on the battery parameter information, and further includes performing weighted average on 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 subjected to data processing. Optionally, before data processing is performed on the charge and discharge information, the battery parameter information and the vehicle operation rate respectively, the method further comprises normalizin