Maximizing hydropower station safety against earthquake through extreme learning machine-enabled shear waves velocity prediction

Abstract

Hydropower stations are important infrastructures for generating clean energy. However, they are vulnerable to natural disasters such as earthquakes, which can cause severe damage and even lead to catastrophic failures. Therefore, it is essential to develop effective strategies for maximizing hydropower station safety against earthquakes. To evaluate the potential shear rate of surrounding rock layers, the shear wave velocity (Vs) parameter can be used as a useful tool. This parameter helps to determine the velocity at which shear waves travel through the rock layers, which can indicate their stability and susceptibility to earthquakes. This study will investigate the significance of the Vs parameter in evaluating the potential shear rate of rock layers surrounding hydropower stations and how it can be used to ensure their safety and efficiency in earthquake-prone regions. Furthermore, a novel approach is proposed in this research, which involves using extreme learning machine (ELM) technology to predict Vs and enhance the seismic safety of hydropower stations. The ELM model predicts the Vs of the soil layers around the hydropower station, a crucial factor in determining the structure’s seismic response. The predicted Vs is then used to assess seismic hazard and design appropriate safety measures. The ML-ELM model outperformed both the ELM and empirical models, with an RMSE of 0.0432 μs/ft and R2 of 0.9954, as well as fewer outlier data predictions. This approach shows promise for predicting Vs in similar environments, and future research could explore its effectiveness in other datasets and practical applications.