Scholarlink

<p>The accurate estimation of the state of charge (SOC) of lithium-ion batteries is crucial for real-time monitoring and safety control. This paper proposes a novel method for estimating SOC by optimizing the kernel extreme learning machine (KELM) with a radial basis function (RBF) kernel using an enhanced pelican optimization algorithm (POA), termed TWCS-PO-KELM. This approach addresses the challenges of real-time estimation and low accuracy in conventional methods. This paper improves the basic POA by incorporating Tent chaotic mapping to diversify the initial population, a nonlinear inertia weight factor to improve local optimization, and a Cauchy variation alongside a sparrow alert mechanism to enhance the algorithm’s robustness and optimization performance. The KELM model, based on the RBF kernel, enables efficient non-linear mapping of the input features, improving the accuracy of SOC estimation. Experimental results demonstrate that the TWCS-PO-KELM model offers superior SOC estimation with a mean absolute error (MAE) of 0.143%, root mean square error (RMSE) of 0.172%, and mean absolute percentage error (MAPE) of 1.344% under BBDST conditions, showcasing its strong tracking ability and robustness in comparison to other methods.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An improved pelican optimization-kernel extreme learning machine for highly accurate state of charge estimation of lithium-ion batteries in energy storage systems

  • 期刊论文

  • 发表日期：

    2025年4月28日

查看全文
  • Sheng Li,
  • Shunli Wang,
  • Wen Cao,
  • Liya Zhang,
  • Carlos Fernandez

摘要

The accurate estimation of the state of charge (SOC) of lithium-ion batteries is crucial for real-time monitoring and safety control. This paper proposes a novel method for estimating SOC by optimizing the kernel extreme learning machine (KELM) with a radial basis function (RBF) kernel using an enhanced pelican optimization algorithm (POA), termed TWCS-PO-KELM. This approach addresses the challenges of real-time estimation and low accuracy in conventional methods. This paper improves the basic POA by incorporating Tent chaotic mapping to diversify the initial population, a nonlinear inertia weight factor to improve local optimization, and a Cauchy variation alongside a sparrow alert mechanism to enhance the algorithm’s robustness and optimization performance. The KELM model, based on the RBF kernel, enables efficient non-linear mapping of the input features, improving the accuracy of SOC estimation. Experimental results demonstrate that the TWCS-PO-KELM model offers superior SOC estimation with a mean absolute error (MAE) of 0.143%, root mean square error (RMSE) of 0.172%, and mean absolute percentage error (MAPE) of 1.344% under BBDST conditions, showcasing its strong tracking ability and robustness in comparison to other methods.