Dynamic information transfer in vibration signal applied to early fault detection of hydropower generation unit

Abstract

Early fault detection of hydropower generation unit (HGU) is of great significance for the safe operation of the hydropower plant. Most of the related research focuses on the decomposition and feature extraction of single vibration monitoring signals. However, HGU is a typical coupling system with multi-channel vibration signals, and the subtle information transfer among signals is the precursor factor leading to the changes in the whole system. There has not been any research considering this potential factor in HGU or other system. Here, we proposed a novel monitoring method based on dynamic information transfer and principal component analysis (DIT-PCA). The process state of the unit is monitored by principal component analysis of the subtle dynamic transmitted information between the unit monitoring variables, which information is revealed for the first time. Normal monitoring samples are used for the offline training at first. Then, the confidence limits and fault contribution rates of two monitoring indicators Hotelling statistic and square prediction error of the model after training are applied to monitor the same test samples to achieve online fault detection and location. Moreover, the proposed model is applied to the state process of a real HGU, which has a superior sensitivity than two available detection methods. The results provide a direct reference for the early fault detection of the engineering system.