Real-time comprehensive health status assessment of hydropower units based on multi-source heterogeneous uncertainty information

Abstract

An effective health status assessment (HSA) method of hydropower unit (HU) is the key to obtaining the real status of HU and providing technical support for safety operation decisions. Thus, a real-time comprehensive HSA method for HUs is proposed. Firstly, a multi-scale data cleaning method based on Gaussian mixture model and density-based spatial clustering of applications with noise (GMM-DBSCAN) is proposed to eliminate outliers and dense anomalies while considering for the variation of operating conditions. Secondly, the correlation analysis method is used to select important measurement points reflecting HU operation status to create multi-source evaluation indices. Then, a novel health indicator (HI) based on Gaussian cloud model (GCM) is proposed to analyze HU condition changes, considering the uncertainty of monitoring signal changes. Further, a hybrid weighting calculation method is proposed to establish a real-time comprehensive health index (RCHI) for assessing HU status. Finally, the proposed approach is verified by a case study using data from a hydropower station in China. The results show that the method improved the stability and smoothness of the state assessment curve compared to other studies.