Scholarlink

With Industry 4.0, Predictive Maintenance (PdM) has emerged as powerful strategy to identify operational anomalies and potential equipment failures. PdM incorporates sensor data and Machine Learning (ML) techniques to enhance predictive accuracy and decision making. A key aspect of PdM is the estimation or Remaining Useful Life (RUL) which provides insights into the lifespan of equipment and help prioritize maintenance actions. In this sense, this study conducts a comparative analysis to evaluate various ML models for RUL forecasting, addressing both regression and classification approaches using the C-MAPSS dataset.

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

Decision Framework for Predictive Maintenance

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Boudour Barkia,
  • Omar Ayedi,
  • Faouzi Masmoudi

摘要

With Industry 4.0, Predictive Maintenance (PdM) has emerged as powerful strategy to identify operational anomalies and potential equipment failures. PdM incorporates sensor data and Machine Learning (ML) techniques to enhance predictive accuracy and decision making. A key aspect of PdM is the estimation or Remaining Useful Life (RUL) which provides insights into the lifespan of equipment and help prioritize maintenance actions. In this sense, this study conducts a comparative analysis to evaluate various ML models for RUL forecasting, addressing both regression and classification approaches using the C-MAPSS dataset.