Limited Fault

Limited fault data poses a significant challenge in developing effective fault detection and diagnosis systems across various domains, from power transformers to industrial machinery. Current research focuses on leveraging techniques like knowledge graphs, heterogeneous self-distillation, and supervised contrastive learning to improve model performance with scarce fault examples, often employing architectures such as convolutional neural networks, gradient boosting decision trees, and reinforcement learning algorithms. These advancements aim to enhance the accuracy and efficiency of fault prediction and root cause analysis, ultimately improving safety and reducing downtime in critical industrial applications. The development of data augmentation techniques, such as those based on generative adversarial networks, also plays a crucial role in addressing the data scarcity problem.

Papers

November 6, 2024

Multivariate Data Augmentation for Predictive Maintenance using Diffusion
Andrew Thompson, Alexander Sommers, Alicia Russell-Gilbert, Logan Cummins, Sudip Mittal, Shahram Rahimi, Maria Seale, Joseph Jaboure, Thomas Arnold, Joshua Church
Synthetic Data Diffusion Explainer Predictive Model Limited Fault

February 11, 2024

Power Transformer Fault Prediction Based on Knowledge Graphs
Chao Wang, Zhuo Chen, Ziyan Zhang, Chiyi Li, Kai Song
Knowledge Graph Power Transformer Limited Fault Transformer Fault

July 3, 2023

Efficient Visual Fault Detection for Freight Train Braking System via Heterogeneous Self Distillation in the Wild
Yang Zhang, Huilin Pan, Yang Zhou, Mingying Li, Guodong Sun
High Efficiency Wild Challenge Self Distillation Limited Fault

February 12, 2023

SCLIFD:Supervised Contrastive Knowledge Distillation for Incremental Fault Diagnosis under Limited Fault Data
Peng Peng, Hanrong Zhang, Mengxuan Li, Gongzhuang Peng, Hongwei Wang, Weiming Shen
Class Incremental Learning Fault Detection Long Tailed Fault Diagnosis Intelligent Fault Diagnosis Limited Fault

February 3, 2023

SCCAM: Supervised Contrastive Convolutional Attention Mechanism for Ante-hoc Interpretable Fault Diagnosis with Limited Fault Samples
Mengxuan Li, Peng Peng, Jingxin Zhang, Hongwei Wang, Weiming Shen
Contrastive Learning Fault Classification Limited Fault Interpretable Fault

January 10, 2023

Imbalanced Classification In Faulty Turbine Data: New Proximal Policy Optimization
Mohammad Hossein Modirrousta, Mahdi Aliyari Shoorehdeli, Mostafa Yari, Arash Ghahremani
Reinforcement Learning Proximal Policy Optimization Fault Detection Imbalanced Classification Data Driven Fault Limited Fault

June 24, 2022

Synthesizing Rolling Bearing Fault Samples in New Conditions: A framework based on a modified CGAN
Maryam Ahang, Masoud Jalayer, Ardeshir Shojaeinasab, Oluwaseyi Ogunfowora, Todd Charter, Homayoun Najjaran
New Framework Conditional Generative Adversarial Network Adverse Condition Condition Monitoring Data Driven Fault Journal Bearing Limited Fault

Limited Fault

Papers

Multivariate Data Augmentation for Predictive Maintenance using Diffusion

Power Transformer Fault Prediction Based on Knowledge Graphs

Efficient Visual Fault Detection for Freight Train Braking System via Heterogeneous Self Distillation in the Wild

SCLIFD:Supervised Contrastive Knowledge Distillation for Incremental Fault Diagnosis under Limited Fault Data

SCCAM: Supervised Contrastive Convolutional Attention Mechanism for Ante-hoc Interpretable Fault Diagnosis with Limited Fault Samples

Imbalanced Classification In Faulty Turbine Data: New Proximal Policy Optimization

Synthesizing Rolling Bearing Fault Samples in New Conditions: A framework based on a modified CGAN