基于SCSSA-CNN-BiLSTM的行驶工况下锂电池寿命预测

Lithium-ion battery life prediction under driving conditionsbased on SCSSA-CNN-BiLSTM

随着锂离子电池广泛应用,电池寿命预测的重要性日益突显。锂离子电池剩余寿命(RUL)的准确预测是其健康管理的关键组成部分。基于此提出了一种名为SCSSA-CNN-BiLSTM的算法,旨在实现应用于整车的锂离子电池RUL预测。采用卷积神经网络(CNN)和双向长短时记忆神经网络(BiLSTM),并结合了正余弦和柯西变异的麻雀优化算法(sine-cosine and Cauchy mutation sparrow search algorithm, SCSSA),形成了一种新型的混合神经网络,以提高锂离子电池RUL预测的准确性和稳定性。CNN用于电池健康状态(SOH)深度特征的全面提取,而BiLSTM以双向方式研究这些深度特征,并通过密集层生成锂离子电池的RUL预测。为验证所提出方法的有效性,首先使用NASA的电池数据,将多个常用模型与所提出的混合神经网络模型进行比较。研究结果显示,混合模型的决定系数(R2)提高了4%~23%,RUL绝对误差降至1,这表明模型具备更高的预测准确性。随后,在整车层面进行了CLTC动态工况下的循环试验,并对寿命衰减数据进行了预测。最终的结果显示,SCSSA-CNN-BiLSTM模型对应的均方根误差(RMSE)、R2分别为1.64、0.98 Ah,展现出了良好的预测和泛化性能。

As lithium-ion batteries become increasingly popular,the battery life prediction is of crucial importance.Accurate prediction of the remaining useful life(RUL)of lithium-ion batteries is a critical part of their health management.In light of this,this paper proposes an algorithm SCSSA-CNN-BiLSTM,aming to perform RUL prediction for lithium-ion batteries used on electric vehicles.By combining convolutional neural networks(CNN),bidirectional long short-term memory(BiLSTM),and sine-cosine and cauchy mutation sparrow search algorithm(SCSSA),our algorithm forms a novel hybrid neural network that enhances the accuracy and stability of RUL predictions for lithium-ion batteries.CNN is employed for comprehensive extraction of deep features related to the state of health(SOH)of the batteries,while BiLSTM investigates these deep features bidirectionally and generates RUL predictions through dense layers.To validate the effectiveness of the proposed approach,battery data from NASA are compared with multiple commonly used models.Our research results show the hybrid model improves the coefficient of determination(R 2)by 4%~23%and reduces the RUL absolute error to 1,demonstrating a higher prediction accuracy.The cyclic experiments are conducted later on vehicles under CLTC dynamic conditions,and predictions are made on battery life degradation.Our results reveal the SCSSA-CNN-BiLSTM model yields a root mean square error(RMSE)of 1.64 A·h and an R 2 value of 0.98,delivering strong predictive and generalization performances.