A Comprehensive Review of Artificial Intelligence-Based Algorithms for Predicting the Remaining Useful Life of...

Area of Science:

• Engineering
• Computer Science
• Data Science

Background:

• Prognostic and health management (PHM) relies on predicting remaining useful life (RUL) for equipment reliability.
• Advancements in AI and hardware have improved RUL prediction, but research often lacks comprehensive algorithm comparison across diverse applications.

Purpose of the Study:

• To systematically categorize equipment RUL prediction scenarios and their requirements.
• To provide a comparative evaluation of suitable AI algorithms for RUL prediction.
• To analyze AI algorithm applicability across different operational contexts and challenges.

Main Methods:

• Rigorous analysis and categorization of equipment RUL prediction application scenarios.
• Comprehensive summary and comparative evaluation of various AI algorithms for RUL prediction.
• In-depth analysis of AI algorithm applicability based on scenario characteristics and algorithm research.

Main Results:

• Identification of distinct characteristics and requirements for various equipment RUL prediction scenarios.
• Delineation of strengths and limitations of different AI algorithms in the context of RUL prediction.
• Comparative insights into the contextual applicability of AI algorithms across diverse equipment types and operational conditions.

Conclusions:

• A holistic understanding of AI algorithm traits and their contextual applicability is crucial for optimal RUL prediction.
• This study provides a foundation for selecting appropriate AI techniques to enhance equipment PHM and operational decision-making.
• Future research should address current challenges and explore future prospects in AI-based RUL prediction.