Interpretable Fault

Interpretable fault diagnosis aims to identify and explain the causes of malfunctions in complex systems, moving beyond "black box" machine learning models to provide human-understandable insights. Current research emphasizes developing novel algorithms, such as those based on decision rule sets, integrated large language models, and attention mechanisms, to improve both the accuracy and explainability of fault detection and classification, particularly in scenarios with imbalanced or limited data. This work is crucial for enhancing the reliability and safety of critical systems across various domains, from industrial processes to energy grids, by enabling timely intervention and informed decision-making.

Papers

May 31, 2024

SLIM: a Scalable Light-weight Root Cause Analysis for Imbalanced Data in Microservice
Rui Ren, Jingbang Yang, Linxiao Yang, Xinyue Gu, Liang Sun
Imbalanced Data Root Cause Fault Localization Fault Classification Interpretable Fault

February 8, 2024

Integrating LLMs for Explainable Fault Diagnosis in Complex Systems
Akshay J. Dave, Tat Nghia Nguyen, Richard B. Vilim
Medical LLM High Explainability Complex System Interpretable Fault

November 9, 2023

ABIGX: A Unified Framework for eXplainable Fault Detection and Classification
Yue Zhuo, Jinchuan Qian, Zhihuan Song, Zhiqiang Ge
Classification Code Unified Framework Fault Diagnosis Fault Classification Interpretable 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 Interpretable Fault Limited Fault

April 15, 2022

Interpretable Fault Diagnosis of Rolling Element Bearings with Temporal Logic Neural Network
Gang Chen, Yu Lu, Rong Su, Zhaodan Kong
Temporal Logic Signal Temporal Logic Fault Diagnosis Rolling Bearing Machinery Fault Interpretable Fault

December 25, 2021

Explainable Signature-based Machine Learning Approach for Identification of Faults in Grid-Connected Photovoltaic Systems
Syed Wali, Irfan Khan
Machine Learning Person Identification Fault Detection Fault Diagnosis Post Fault Trajectory Statistical Signature Interpretable Fault

Interpretable Fault

Papers

SLIM: a Scalable Light-weight Root Cause Analysis for Imbalanced Data in Microservice

Integrating LLMs for Explainable Fault Diagnosis in Complex Systems

ABIGX: A Unified Framework for eXplainable Fault Detection and Classification

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

Interpretable Fault Diagnosis of Rolling Element Bearings with Temporal Logic Neural Network

Explainable Signature-based Machine Learning Approach for Identification of Faults in Grid-Connected Photovoltaic Systems