Proactive Fault Detection in Rotating Machinery using Machine Learning- A Survey

Abstract

This study presents a survey of approaches for proactive fault detection in rotating machinery, with a focus on the early identification of bearing faults to enhance equipment reliability and operational efficiency. Traditional methods, relying on physical sensors and manual inspections, often lack the ability to provide timely insights into emerging faults. In contrast, the surveyed approaches integrate non-contact vibration sensors with advanced machine learning techniques, revolutionizing fault detection capabilities. The study presents a brief overview of the methods used in classification of the rotating machinery defects using the machine learning and recommends a combination of machine learning methods at different stages to overcome the challenges of the traditional methods. The collected vibration signals undergo noise reduction via the Hilbert transform, followed by dimensionality reduction and feature selection using Independent Component Analysis (ICA) and Genetic Algorithms (GA), respectively. The selected features are then employed for fault detection and categorization using Random Forest (RF) and Deep Belief Networks (DBN). The Future work will involve the implementation and evaluation of these approaches in real-world industrial settings to validate their effectiveness and reliability.