Online Equipment Fault Diagnosis

6 projects

Addressing the evolving physical characteristics and data-distribution drift across an asset's full lifecycle, lifelong learning and Bayesian deep learning together build a "diagnose–warn–predict-life" capability, deployed at General Motors, Taiyuan Heavy Industry, CITIC Dicastal, and other enterprises

Ongoing

Physics-Informed Hypergraph Networks for Compound Fault Diagnosis and Traceability

Mapping physical topology into hypergraph priors, combined with a physics-informed multi-task network and uncertainty-driven cascaded inference, achieves 99.55% compound-fault diagnosis accuracy

Physics-Informed Network Hypergraph Learning Compound Fault

Completed

Precision Remaining-Useful-Life Prediction for High-End Equipment (PHM 2025 World Champion)

An operating-condition-aligned, risk-aware remaining-useful-life prediction framework that won first place worldwide, by a clear margin, at the PHM 2025 international data-challenge

Remaining Useful Life Few-Shot Learning PHM Competition Champion

Ongoing

Multimodal Industrial Spatiotemporal Large Model for Rail-Transit Intelligent Diagnosis

A large-model agent diagnostic framework fusing rail images, time-series waveforms, and text logbooks achieves 96% visual rail-corrugation recognition accuracy, delivering fully automated fine-grained diagnosis under complex operating conditions

Multimodal Large Model Agent Diagnosis High-Speed/Urban Rail