Wear fault diagnosis in hydro-turbine via the incorporation of the IWSO algorithm optimized CNN-LSTM neural network

Abstract

Diagnosing hydro-turbine wear fault is crucial for the safe and stable operation of hydropower units. A hydro-turbine wear fault diagnosis method based on improved WT (wavelet threshold algorithm) preprocessing combined with IWSO (improved white shark optimizer) optimized CNN-LSTM (convolutional neural network-long-short term memory) is proposed. The improved WT algorithm is utilized for denoising the preprocessing of the original signals. The CNN-LSTM hydro-turbine wear fault diagnosis model is constructed. Aiming at the problem that the WSO algorithm quickly falls into local optimum and premature convergence, tent chaotic mapping is used to initialize the population and birds flock search behavior. The cosine elite variation strategy is introduced to improve convergence speed and accuracy. Hyperparameter tuning of CNN-LSTM model based on IWSO algorithm. The experimental results show that the accuracy of the proposed method reaches 96.2%, which is 8.9% higher than that of the IWSO-CNN-LSTM model without denoising. The study also found that the diagnostic accuracy of hydro-turbine wear faults increased with increasing sediment concentration in the water. This study can supplement the existing hydro-turbine condition monitoring and fault diagnosis system. Meanwhile, diagnosing wear faults in hydro-turbines can improve power generation efficiency and quality and minimize resource consumption.