Scholarlink

<p>Small samples of performance degradation data are commonly obtained during an accelerated degradation test. This study leverages the global search capabilities of heuristic algorithms to enhance the performance of support vector regression (SVR) in degradation modeling with such constrained data, utilizing genetic algorithms to optimally select model parameters. The life prediction results from the Arrhenius model are used as a benchmark in the kernel function selection in the SVR model. Comparative analysis showed that the sigmoid kernel function demonstrated superior nonlinear mapping capabilities and achieved high prediction accuracy. Furthermore, the radial basis function neural network exhibited poorer generalization performance in scenarios involving small sample sizes compared with other models.</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

Degradation modeling and remaining useful life prediction method for operational amplifiers using the GA-optimized SVR

  • 期刊论文

  • 发表日期：

    2025年7月1日

查看全文
  • Xin Huang,
  • Ying Zeng,
  • Jing Li,
  • Zhenwei Zhou,
  • Hong-Zhong Huang

摘要

Small samples of performance degradation data are commonly obtained during an accelerated degradation test. This study leverages the global search capabilities of heuristic algorithms to enhance the performance of support vector regression (SVR) in degradation modeling with such constrained data, utilizing genetic algorithms to optimally select model parameters. The life prediction results from the Arrhenius model are used as a benchmark in the kernel function selection in the SVR model. Comparative analysis showed that the sigmoid kernel function demonstrated superior nonlinear mapping capabilities and achieved high prediction accuracy. Furthermore, the radial basis function neural network exhibited poorer generalization performance in scenarios involving small sample sizes compared with other models.