Intelligent Fault Detection

Intelligent Fault Detection (IFD) uses machine learning to automatically identify malfunctions in complex systems, aiming to improve reliability and reduce downtime. Current research heavily focuses on addressing data limitations—such as imbalanced or scarce datasets—through techniques like deep transfer learning and generative adversarial networks, often employing convolutional neural networks, vision transformers, and neural processes to analyze sensor data (e.g., vibration signals) and extract relevant features. These advancements are crucial for improving the accuracy and robustness of fault detection in various applications, particularly in industrial settings where maintaining equipment health is paramount. The resulting improvements in predictive maintenance and system reliability have significant economic and safety implications.

Papers

February 20, 2024

Scalable and reliable deep transfer learning for intelligent fault detection via multi-scale neural processes embedded with knowledge
Zhongzhi Li, Jingqi Tu, Jiacheng Zhu, Jianliang Ai, Yiqun Dong
Transfer Learning Multi Scale Uncertainty Estimation Knowledge Based Fault Detection Deep Transfer Intelligent Fault Detection

September 19, 2022

Fault Detection in Ball Bearings
Joshua Pickard, Sarah Moll
Machine Learning Convolutional Neural Network Fault Detection Vibration Signal Preprocessing Method Rolling Bearing Intelligent Fault Detection

August 15, 2022

A Vision Transformer-Based Approach to Bearing Fault Classification via Vibration Signals
Abid Hasan Zim, Aeyan Ashraf, Aquib Iqbal, Asad Malik, Minoru Kuribayashi
Deep Learning Convolutional Neural Network Vision Paper Transformer Based Approach Vibration Signal Rolling Bearing Fault Classification Frequency Imaging Intelligent Fault Detection

March 18, 2022

Holistic Fault Detection and Diagnosis System in Imbalanced, Scarce, Multi-Domain (ISMD) Data Setting for Component-Level Prognostics and Health Management (PHM)
Ali Rohan
Transfer Learning Fault Detection Diagnosis System Domain Knowledge Transfer Imbalanced Domain Data Driven Prognostic Prognostic and Health Management Intelligent Fault Detection

Intelligent Fault Detection

Papers

Scalable and reliable deep transfer learning for intelligent fault detection via multi-scale neural processes embedded with knowledge

Fault Detection in Ball Bearings

A Vision Transformer-Based Approach to Bearing Fault Classification via Vibration Signals

Holistic Fault Detection and Diagnosis System in Imbalanced, Scarce, Multi-Domain (ISMD) Data Setting for Component-Level Prognostics and Health Management (PHM)