A Survey of Predictive Maintenance Methods: An Analysis of Prognostics via Classification and Regression

2025-06-24

AI Summary

Existing predictive maintenance (PdM) research lacks systematic comparative analysis between regression and classification paradigms under identical task settings. Method: This work conducts the first direct performance comparison of both paradigms for remaining useful life (RUL) prediction and failure probability estimation, systematically reviewing state-of-the-art machine learning and deep learning approaches from 2018–2023. It identifies shared challenges—including class imbalance and high-dimensional features—and proposes principled trade-off guidelines for method selection based on task objectives, data characteristics, and deployment constraints. Contribution/Results: Regression excels in continuous RUL modeling but is sensitive to outliers; classification demonstrates superior robustness in failure interval discrimination yet suffers from granularity limitations. The study further explores hybrid modeling and AI-driven adaptive maintenance, advocating standardized benchmarks, open-source tooling, and interpretable evaluation frameworks—thereby providing theoretical foundations and practical guidance for robust, task-oriented next-generation PdM systems.

Technology Category

• Machine Learning: Classification and Regression
• Data Mining & Knowledge Management: Rule Mining & Pattern Mining
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Predictive maintenance (PdM) has become a crucial element of modern industrial practice. PdM plays a significant role in operational dependability and cost management by decreasing unforeseen downtime and optimizing asset life cycle management. Machine learning and deep learning have enabled more precise forecasts of equipment failure and remaining useful life (RUL). Although many studies have been conducted on PdM, there has not yet been a standalone comparative study between regression- and classification-based approaches. In this review, we look across a range of PdM methodologies, while focusing more strongly on the comparative use of classification and regression methods in prognostics. While regression-based methods typically provide estimates of RUL, classification-based methods present a forecast of the probability of failure across defined time intervals. Through a comprehensive analysis of recent literature, we highlight key advancements, challenges-such as data imbalance and high-dimensional feature spaces-and emerging trends, including hybrid approaches and AI-enabled prognostic systems. This review aims to provide researchers and practitioners with an awareness of the strengths and compromises of various PdM methods and to help identify future research and build more robust, directed adaptive maintenance systems. Future work may include a systematic review of practical aspects such as public datasets, benchmarking platforms, and open-source tools to support the advancement of PdM research.

Problem

• Compare classification and regression methods in predictive maintenance
• Analyze machine learning for equipment failure and RUL prediction
• Address data imbalance and high-dimensional feature space challenges

Innovation

• Comparative study of classification and regression methods
• Machine learning for precise failure forecasts
• Hybrid approaches in predictive maintenance