Self-Adapting Federated Continual Learning With Gradient Causal Constraint for Fault Propagation Path Identification
- 25 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 22 (7) , 5830-5840
Abstract
In modern industrial scenarios, federated learning (FL) has been widely adopted due to its advantages in privacy preservation and distributed modeling. However, existing FL approaches rely on a single update paradigm, which significantly hampers communication efficiency. Moreover, the server preserves historical aggregation states to model causal propagation across training rounds, instead of performing memoryless per-round aggregation. For this end, we propose a self-adapting federated continual learning with gradient causal constraint (GCC-SFCL). First, the selection of synchronous or asynchronous communication across FL rounds is reformulated as continual learning task, where an experience accumulation mechanism records historical aggregation states to model long-term temporal dependencies among client updates. Based on the aggregated context, we further design a self-adapting scheduling strategy driven by multidimensional client state information, enabling the server to dynamically select optimal aggregation. Furthermore, a causality-steering gradient constraint is introduced to explicitly regulate gradient updates, improving the interpretability of the causal model and allowing the capture of fault propagation paths. Experimental results of a simulation case and the real-world case demonstrate that GCC-SFCL significantly improves not only communication efficiency but also the accuracy of fault propagation path identification.Keywords
Funding Information
- National Natural Science Foundation of China (62303015)
- National Key R&D Program of China (2024YFE03240300)
This publication has 25 references indexed in Scilit:
- Continuous Causal Learning of Multimode Industrial Processes for Comprehensive Root Cause AnalysisIEEE Internet of Things Journal, 2026
- Efficient Multitask Asynchronous Federated Learning in Edge Computing: A Two-Layer Optimization ApproachIEEE Internet of Things Journal, 2025
- Spatio-temporal interactive network: A knowledge-guided federated learning for fault propagation path identificationProcess Safety and Environmental Protection, 2025
- Interpretable vertical federated learning with privacy-preserving multi-source data integration for prognostic predictionEngineering Applications of Artificial Intelligence, 2025
- A fault hierarchical propagation reliability improvement method for CNC machine tools based on spatiotemporal factors couplingReliability Engineering & System Safety, 2024
- Adaptive Semi-Asynchronous Federated Learning Over Wireless NetworksIEEE Transactions on Communications, 2024
- Intrinsic Causality Embedded Concurrent Quality and Process Monitoring StrategyIEEE Transactions on Industrial Electronics, 2024
- Personalized Privacy-Preserving Framework for Cross-Silo Federated LearningIEEE Transactions on Emerging Topics in Computing, 2024
- Class-Imbalance Privacy-Preserving Federated Learning for Decentralized Fault Diagnosis With Biometric AuthenticationIEEE Transactions on Industrial Informatics, 2022
- Diagnosis of Interturn Short-Circuit Faults in Permanent Magnet Synchronous Motors Based on Few-Shot Learning Under a Federated Learning FrameworkIEEE Transactions on Industrial Informatics, 2021