基于CDPSO-EBRB的锂离子电池健康状态估计

锂离子电池在武器系统中广泛应用,对其健康状态的评估对于保证武器系统作战效能具有重要意义.但构建锂离子电池退化过程的物理模型难度较大,同时由于数据的不确定性与不完整性影响,使用纯数据驱动的方式也不能准确描述此过程.扩展置信规则库模型结合了知识结构和证据推理的特性,可对数据的不确定性与不完整性进行定量描述,但原始模型的参数选择对其性能影响较大,针对以上问题,提出了一种中心离散粒子群算法(CDPSO)优化的扩展置信规则库(EBRB)模型,并将该模型应用于锂离子电池的健康状态评估中,使用数据驱动方式将规则集转化为规则,采用CDPSO对初始参数进行训练,最后使用测试数据集来测试模型的有效性,通过与传统的方法进行比对,验证了所提出方法的有效性.

An Estimation for the Health Status to Lithium Ion Batteries Based on CDPSO-EBRB

Lithium ion battery is widely used in weapon systems. The evaluation for its health status to lithium ion is of great significance to ensure the operational effectiveness of weapon systems. Aimed at the problems that building a physical model is comparatively difficult in the degradation process of lithium ion battery, simultaneously the process is very hard to be described accurately due to the uncertainty and incomplete data by the pure data driven method. Being the extended belief rule base model combined with the characteristics of the knowledge structure and evidence reasoning, the uncertainty and incompleteness of data may be quantitatively described, but the parameters of the original model had a greater influence on the choice of its performance. In view of the mentioned above problems, an extended belief rule base (EBRB) model of center de center particle swarm optimization is proposed, and the model is applied in the lithium ion battery health status evaluation. The EBRB based on the optimization of the CDPSO converts the rule set into rules in a data driven way, the initial parameters with CDPSO are trained, and finally, the validity of the model with the test data set is tested. By comparing with the traditional method, the validity of the proposed method is verified.