Training method of battery state evaluation model, and battery state evaluation method and device

• Main Author: ZHAO KECHENG
• Format: Patent
• Language: Chinese; English
• Published: 02.05.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention provides a training method of a battery state evaluation model, and a battery state evaluation method and device, and relates to the technical field of battery management. The training method comprises the following steps: constructing a battery state evaluation model for evaluating a battery state based on a neural network; constructing a target function according to the working data of the plurality of sample batteries in the constant current charging stage; and on the basis of a genetic algorithm, according to the objective function and the training data, iteratively updating model parameters of the battery state evaluation model until a preset stop condition is met, and on the basis of the currently updated model parameters, obtaining a trained battery state evaluation model. According to the embodiment of the invention, the online evaluation of the battery state can be realized, and the evaluation efficiency of the battery state can be improved. 本申请提供了一种电池状态评估模型的训练方法、电池状态评估方法及装置，涉及电池管理技术领域。