Causality-inspired graph representation with adaptive thresholding for robust fault detection
- 23 September 2026
- journal article
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (38) , 386105
Abstract
Reliable fault detection in complex industrial systems requires capturing structured dependencies among process variables rather than relying solely on individual signal patterns. However, most existing approaches primarily depend on reconstruction or prediction errors, which may overlook relational interactions and lead to unstable detection performance under varying operating conditions. To address this limitation, this paper proposes a framework named causality-inspired graph representation with adaptive thresholding (CGRA). CGRA combines temporal causal representation to capture structured temporal dependencies from multivariate time series and graph attention representation to encode these relations into discriminative features for anomaly scoring. An adaptive thresholding strategy is further employed to obtain statistically reliable decision boundaries. Experimental results on multiple industrial datasets demonstrate consistent performance improvements over representative existing methods.Keywords
Funding Information
- Open Project of the Key Laboratory of Intelligent Operation and Maintenance of High-parameter Lifts, State Administration for Market Regulation of China (JSTJ-IOMHL-202501)
- Natural Science Foundation of the Jiangsu Higher Education Institutions of China (25KJD460006)
- National Natural Science Foundation of China (52505610)
- Natural Science Foundation of Jiangsu Province (BK20251073)
This publication has 39 references indexed in Scilit:
- Multi fault detection and root cause analysis of wind turbine using Multivariate time series data based on autoencoderEngineering Applications of Artificial Intelligence, 2026
- An adaptive threshold strategy based on empirical distribution functions and information entropy for battery abnormal diagnosis and fault alarmEnergy, 2025
- Discovering Granger causality with convolutional neural networksJournal of Intelligent Manufacturing, 2024
- Towards trustworthy rotating machinery fault diagnosis via attention uncertainty in transformerJournal of Manufacturing Systems, 2023
- Novel motor fault detection scheme based on one-class tensor hyperdiskKnowledge-Based Systems, 2023
- GRU-Auto-Encoder neural network based methods for diagnosing abnormal operating conditions of steam drums in coal gasification plantsComputers & Chemical Engineering, 2020
- A review on fault detection and diagnosis techniques: basics and beyondArtificial Intelligence Review, 2020
- A nonlinear quality-related fault detection approach based on modified kernel partial least squaresISA Transactions, 2017
- Robust one-class SVM for fault detectionChemometrics and Intelligent Laboratory Systems, 2016
- Fault detection based on Kernel Principal Component AnalysisEngineering Structures, 2010