PSO优化的BiLSTM-Attention网络的锂电池健康状态评估

Estimation on Sate of Health for Lithium-ion Battery with PSO-optimized BiLSTM-Attention Network

锂离子电池作为一种高效的储能元件,被广泛应用到生产生活的各个领域,其健康状态事关系统的安全性,受到越来越多的重视。基于粒子群优化算法,优化了具有注意力机制的双向长短期记忆网络,实现了锂离子电池的健康评估。首先,考虑到锂电池数据的时序特征,采取了一种双向长短期记忆网络提高预测效果,并且引入注意力机制解决信息过载问题,提高任务处理的效率和准确性。接着,利用粒子群优化算法优化网络模型结构的参数,获得高效的锂电池健康状态估计。最后,引入NASA锂离子电池数据集。实验结果验证了所提方法的有效性。

As an efficient energy storage element, lithium-ion battery has been widely used in all fields of production and life. Its health status is related to the safety of system, and has been paid more and more attention. Pparticle swarm optimization(PSO) is introduced to optimize the bidirectional short-term memory(BiLSTM) network and attention mechanism(AM), and the estimation on state of health(SOH) for lithium-ion battery is realized. Firstly, considering the time series characteristics of lithium battery data, a BiLSTM network is adopted to improve the prediction effect. Moreover, attention mechanism is introduced to solve the problem of information overload and improve the efficiency and accuracy of task processing. Then, particle swarm optimization algorithm is used to optimize the network model of BiLSTM-AM, so as to obtain efficient lithium battery health state estimation. Finally, a lithium-ion battery dataset from NASA is introduced. Experimental results verify the effectiveness of the proposed method.