Overview

Fault diagnosis studies how to detect abnormal behavior, identify its source and severity, and provide evidence that can guide repair in systems such as machinery, power grids, vehicles, networks, and software. Common approaches learn patterns from vibration, electrical signals, images, or logs using classifiers, anomaly detectors, and graph or sequence models; physics-based models, digital twins, causal graphs, and knowledge retrieval can add structure when data are scarce or explanations matter. Recent systems also use language-model agents to investigate incidents and communicate findings, often alongside explicit checks that ground conclusions in telemetry or maintenance records. Strong results on known faults and benchmark data do not always carry over to new operating conditions or unseen failures, making reliable evaluation, uncertainty handling, and real-world validation central challenges.

Latest papers

CardsList

156 papers14 papers in the last four weeks, down 18% on the four weeks before. 0.1% of all new papers.

  1. Explainability for Fault Detection System in Chemical Processes

    Feb 18, 2026Georgios Gravanis, Dimitrios Kyriakou, Spyros Voutetakis +2Industrial Fault DiagnosisFault Diagnosis

  2. Axle Sensor Fusion for Online Continual Wheel Fault Detection in Wayside Railway Monitoring

    Feb 18, 2026Afonso Lourenço, Francisca Osório, Diogo Risca +1Fault DiagnosisOnline Anomaly Detection

  3. AgentRx: Diagnosing AI Agent Failures from Execution Trajectories

    Feb 2, 2026Shraddha Barke, Arnav Goyal, Alind Khare +3Fault DiagnosisAI Agent Reliability

  4. ProDER: A Continual Learning Approach for Fault Classification and Localization in Evolving Smart Grids

    Nov 7, 2025Emad Efatinasab, Nahal Azadi, Davide Dalle Pezze +3Replay-Based Continual LearningPrototype-Based Classification

  5. RoboFAC: A Comprehensive Framework for Robotic Failure Analysis and Correction

    May 18, 2025Zewei Ye, Weifeng Lu, Minghao Ye +4Robot Failure RecoveryRobustness of VLA Models

  6. Prognostics for Autonomous Deep-Space Habitat Health Management under Multiple Unknown Failure Modes

    Nov 19, 2024Benjamin Peters, Ayush Mohanty, Xiaolei Fang +2RUL EstimationFault Diagnosis