Digital twin-driven edge–cloud collaborative remote fault diagnosis and intelligent predictive maintenance for critical hydropower equipment

Abstract

To address the problems of lagging remote monitoring, complex fault mechanisms, and inefficient maintenance decisions for key equipment in hydropower stations, this paper proposes a remote diagnosis and intelligent maintenance method based on edge-cloud collaboration and digital twin-driven approaches. A layered architecture encompassing equipment, perception, transmission, analysis, and service layers is constructed. A physical-geometric-behavior coupled digital twin model is established, and PLC-SCADA control systems, multi-source monitoring data, fault diagnosis models, and remaining life prediction methods are integrated to achieve a closed loop of equipment status perception, anomaly identification, degradation assessment, and maintenance optimization. Experimental verification is conducted on a dual-unit Pelton hydropower system. Results show that the proposed method exhibits higher fault diagnosis accuracy, better life prediction performance, and superior maintenance economy under complex operating conditions. Unlike existing digital twin-based monitoring systems, the proposed framework integrates edge–cloud collaboration, real-time physical–virtual synchronization, fault diagnosis, RUL prediction, and maintenance optimization into a unified workflow for critical hydropower equipment.