• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>International Journal of Electrochemical Science >The Remaining Useful Life Estimation of Lithium-ion Batteries Based on the HKA -ML-ELM Algorithm
【24h】

The Remaining Useful Life Estimation of Lithium-ion Batteries Based on the HKA -ML-ELM Algorithm

机译：基于HKA -ML-ELM算法的锂离子电池剩余使用寿命估算

获取原文
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Lithium-ion batteries have become the core energy supply component for many electronic devices. Anaccurate prediction of the remaining useful life (RUL) of lithium-ion batteries is of great significancefor battery management and ensuring the reliability of electronic devices. The extreme learning machine(ELM) algorithm has been applied to predict the RUL of lithium-ion batteries; however, there are somedisadvantages in this method: (i). the single hidden layer structure of the ELM necessarily restricts itsability to capture effective features in high-dimensional data. (ii). the input weights and biases of theELM are generated randomly, which affects its prediction accuracy. To overcome these problems, thispaper proposes an HKA-ML-ELM method for predicting the RUL of lithium-ion batteries. First, a newmulti-layer ELM (ML-ELM) network is constructed. By adding an input layer into the last individualELM of the ML-ELM and implementing the random selection of these input nodes to partially connectwith the hidden layer, the network has higher robustness and can effectively prevent over-fitting. Second,the heuristic Kalman algorithm (HKA) is used to optimize the input weights and biases parameters ofthe ML-ELM, which improves the prediction accuracy. Finally, RUL prediction experiments are carriedout for battery packs with different rated capacities and different discharge currents. The experimentalresults verify the effectiveness of the proposed method. The comparisons with other algorithms showthat the proposed method has better prediction accuracy.
机译：锂离子电池已成为许多电子设备的核心能源供应组件。准确预测锂离子电池的剩余使用寿命（RUL）对于电池管理和确保电子设备的可靠性具有重要意义。极限学习机（ELM）算法已应用于预测锂离子电池的RUL。但是，此方法存在一些缺点：（i）。 ELM的单个隐藏层结构必然会限制其捕获高维数据中有效特征的能力。 （ii）。 ELM的输入权重和偏差是随机生成的，这会影响其预测精度。为了克服这些问题，本文提出了一种HKA-ML-ELM方法来预测锂离子电池的RUL。首先，构建了一个新的多层ELM（ML-ELM）网络。通过将输入层添加到ML-ELM的最后一个单独的ELM中并实现对这些输入节点的随机选择以部分地与隐藏层连接，网络具有更高的鲁棒性并可以有效地防止过度拟合。其次，启发式卡尔曼算法（HKA）用于优化ML-ELM的输入权重和参数偏差，提高了预测精度。最后，针对不同额定容量和不同放电电流的电池组进行了RUL预测实验。实验结果验证了该方法的有效性。与其他算法的比较表明，该方法具有较好的预测精度。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号