The health of the hydroelectric generator determines the safe, stable, and reliable operation of the hydropower station. In order to keep the hydroelectric generator in a better state of health and avoid accidents, it is crucial to detect its faults. In recent years, fault detection methods based on sound and vibration signals have gradually become research hotspots due to their high sensitivity, achievable continuous dynamic monitoring, and easy adaptation to complex environments. Therefore, this paper is a supplement to the existing state monitoring and fault diagnosis system of the hydroelectric generator; it divides the hydroelectric generator into two significant parts: hydro-generator and hydro-turbine, and summarizes the research and application of fault detect technology based on sound signal vibration in hydroelectric generator and introduces some new technology developments in recent years, and puts forward the existing problems in the current research and future development directions, and it is expected to provides some reference for the research on fault diagnosis of the hydroelectric generator.

The accuracy of hydro-turbine fault diagnosis directly impacts the safety and operational efficiency of hydroelectric power generation systems. This paper addresses the challenge of low diagnostic accuracy in traditional methods under complex environments. This is achieved by proposing a signal preprocessing method that combines complete ensemble empirical mode decomposition with adaptive noise and multiscale permutation entropy (CEEMDAN-MPE) and that is optimized with the crested porcupine optimizer algorithm for the bidirectional long- and short-term memory network (CPO-BILSTM) model for hydro-turbine fault diagnosis. The method performs signal denoising using CEEMDAN, while MPE extracts key features. Furthermore, the hyperparameters of the CPO-optimized BILSTM model are innovatively introduced. The extracted signal features are fed into the CPO-BILSTM model for fault diagnosis. A total of 150 sets of acoustic vibrational signals are collected for validation using the hydro-turbine test bench under different operating conditions. The experimental results demonstrate that the diagnostic accuracy of the method is 96.67%, representing improvements of 23.34%, 16.67%, and 6.67% over traditional models such as LSTM (73.33%), CNN (80%), and BILSTM (90%), respectively. In order to verify the effectiveness of the signal preprocessing method, in this paper, the original signal, the signal processed by CEEMDAN, CEEMDAN-PE, and CEEMDAN-MPE are input into the CPO-BILSTM model for controlled experiments. The results demonstrate that CEEMDAN-MPE effectively denoises hydro-turbine acoustic vibrational signals while preserving key features. The method in this paper integrates signal preprocessing and deep learning models and, with the help of intelligent optimization algorithms, significantly enhances the model’s adaptive ability, improves the model’s applicability under complex operating conditions, and provides a valuable supplement for hydro-turbine fault diagnosis.

Studies show that sediment erosion is one of the main factors attributing to hydraulic turbine failure. The present paper represents an investigation into acoustic vibration signals generated by the water flow impacting the hydraulic turbine runner under three different operating conditions. Collected signals were denoised using the ICEEMDAN-wavelet threshold method, and then the spectral characteristics and sample entropy characteristics of the signals for the three operating conditions were analyzed. The results show that when clean water flows through the hydraulic turbine, the sample entropy reaches its smallest values and the dominant frequency component in the spectrogram is 59.39 Hz. When transitioning from clean water to the flood flow containing 2–4 mm sediment particles, the sample entropy is increasing and a high-frequency component higher than 59.39 Hz becomes the prominent frequency of the spectrogram. Meanwhile, the formation of high-frequency components increases with the sand-containing particle size. Based on the spectral characteristics and sample entropy characteristics of the acoustic vibration signals under different operating conditions, it can provide a reference for the sand avoidance operation of the hydraulic turbine during flood season. In addition, it provides a supplement to the existing hydraulic turbine condition’s monitoring systems and a new avenue for subsequent research on early warning of hydraulic turbine failure.