Fault detection and diagnosis in industrial machinery: Comparing the performance with support vector machines and random forests
Abstract
Industry 4.O. requires continual monitoring and technological transformation. Predictive maintenance is an essential strategy among maintenance strategies for reducing breakdowns and increasing industry productivity. Data-driven models are more effective than conventional ways of understanding machinery faults. In this article, machine learning classification methods such as Decision trees, Support vector machines, and random forests are applied to vibration signal temporal domain data to forecast equipment defects. Among these, random forests obtained the highest accuracy.
Fields of Study & Subjects
Machine Fault Diagnosis Techniques
Fault Detection and Control Systems
Industrial Vision Systems and Defect Detection
Publication details
- Journal / source
- AIP conference proceedings
- Volume
- 3406
- Pages
- 140001–140001
- Publication date
- 1 January 2026
- Language
- EN