Scholarlink

This paper aims to examine renewable energy conversion systems with an eye towards using deep learning for fault diagnosis and detection. Nevertheless, hyperparameter selection is crucial to the performance of deep learning models. The work exploits a genetic algorithm to tweak these hyperparameters in this study to improve the overall efficiency and performance of the considered renewable energy conversion system. By conducting extensive simulations and analysis, the study determines how to optimise the hyperparameters to minimise the effects of the system’s performance, tackling possible faults and making the most of deep learning within the framework of a renewable energy conversion system. The diagnostic achievements show that the calculation time is improved and the efficiency is achieved when compared to classical solutions available in the related literature.

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

Deep Learning for Fault Diagnosis

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Robert Johnson,
  • Benjamin Y. P. Liang,
  • Fu Kuo Manchu,
  • Silvio Simani

摘要

This paper aims to examine renewable energy conversion systems with an eye towards using deep learning for fault diagnosis and detection. Nevertheless, hyperparameter selection is crucial to the performance of deep learning models. The work exploits a genetic algorithm to tweak these hyperparameters in this study to improve the overall efficiency and performance of the considered renewable energy conversion system. By conducting extensive simulations and analysis, the study determines how to optimise the hyperparameters to minimise the effects of the system’s performance, tackling possible faults and making the most of deep learning within the framework of a renewable energy conversion system. The diagnostic achievements show that the calculation time is improved and the efficiency is achieved when compared to classical solutions available in the related literature.