Intelligent transformation in the operational maintenance of pumped storage units: Hydraulic-mechanical multi-scenario fault diagnosis based on tensor feature extraction indicators

Abstract

The intelligent transformation of pumped storage units (PSUs) is an essential step in the construction of smart power stations, with intelligent fault diagnosis being a crucial component of this process. Deep mining of anomaly information in massive equipment data is key to achieving fault diagnosis of PSUs, directly influencing the success or failure of intelligent operation and maintenance for power stations. To overcome the challenge of existing feature extraction techniques in jointly mining anomaly information across temporal and spectral domains, this study proposes tensor-weighted fuzzy dispersion entropy (TWFDE), a nonlinear dynamic feature extraction indicator enhanced through tensor learning for multi-scenario hydraulic–mechanical applications in PSUs. This indicator effectively extracts signal state features from the dual space of temporal and spectral domains, and a data-driven diagnostic framework encompassing data acquisition, feature extraction, and pattern recognition is developed around TWFDE. Firstly, a nonlinear dynamics index named weighted fuzzy dispersion entropy (WFDE) is proposed, which combines structural complexity and magnitude quantitative dynamics. Secondly, WFDE is generalized to TWFDE by incorporating hierarchical analysis and multiscale analysis, thereby facilitating the extraction of multi-dimensional anomaly characteristics from the tensor-space perspective. Ultimately, TWFDE and random forest (RF) are fused to construct a data-driven fault diagnostic framework applicable to multiple scenarios. In cases of hydraulic anomaly identification and mechanical fault diagnosis of the micro pumped storage power plant, the model achieves diagnostic accuracies of at least 98.428 % and 99.928 %, respectively, demonstrating significant advantages over other mainstream methods. The proposed feature extraction indicator provides effective support for improving the operation and maintenance level and the energy conversion efficiency of pumped storage hydropower plants.