Scholarlink

Unexpected equipment failures in innovative industries cause production downtime, excessive energy consumption due to thermal losses and machine restarts, and increased operational costs. Conventional reactive and preventive maintenance strategies do not account for the actual condition of equipment, leading to inefficient energy use and a higher risk of failure. This paper analyzes real-world applications of predictive maintenance, with an emphasis on artificial intelligence (AI)-based approaches, across multiple industrial sectors. The study is based on major scientific databases and recent publications from 2019 to 2025, focusing on energy consumption optimization and the improvement of industrial system sustainability within the context of Industry 4.0. The results indicate that predictive maintenance enhances the detection of energy anomalies by 30–60%, reduces major failures by up to 75%, decreases maintenance costs by 20–40%, and limits energy waste. These outcomes contribute to a net energy gain despite the digital infrastructure’s own consumption. The study concludes that predictive maintenance serves as a strategic tool to improve energy efficiency, extend equipment lifespan, and support sustainable industrial production. Future research should explore more energy-efficient technologies and algorithms to further advance sustainable industrial operations.

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

Reducing Direct and Indirect Energy Consumption Through Predictive Maintenance in the Context of Industry 4.0

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Zouhair Marmoucha,
  • Hayat El Hailouch,
  • Mohamed El Khaili,
  • Hasna Nhaila,
  • Aziz Soulhi

摘要

Unexpected equipment failures in innovative industries cause production downtime, excessive energy consumption due to thermal losses and machine restarts, and increased operational costs. Conventional reactive and preventive maintenance strategies do not account for the actual condition of equipment, leading to inefficient energy use and a higher risk of failure. This paper analyzes real-world applications of predictive maintenance, with an emphasis on artificial intelligence (AI)-based approaches, across multiple industrial sectors. The study is based on major scientific databases and recent publications from 2019 to 2025, focusing on energy consumption optimization and the improvement of industrial system sustainability within the context of Industry 4.0. The results indicate that predictive maintenance enhances the detection of energy anomalies by 30–60%, reduces major failures by up to 75%, decreases maintenance costs by 20–40%, and limits energy waste. These outcomes contribute to a net energy gain despite the digital infrastructure’s own consumption. The study concludes that predictive maintenance serves as a strategic tool to improve energy efficiency, extend equipment lifespan, and support sustainable industrial production. Future research should explore more energy-efficient technologies and algorithms to further advance sustainable industrial operations.