Dynamic health prediction of plain reservoirs based on deep learning algorithms

The healthy operation of reservoirs is crucial for fulfilling their functions and preventing harm to human populations and riverine ecosystems. This study addresses the issues of poor model generalization and low diagnostic accuracy resulting from imbalanced sample distribution in the health prediction of plain reservoirs. We innovatively propose a sample augmentation model (VAE-CGAN) that combines Variational Autoencoder (VAE) and Conditional Generative Adversarial Network (CGAN). Additionally, we present a classification model (CNNBiLSTM) based on Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory Network (BiLSTM). The VAE-CGAN model learns the data distribution of authentic samples through alternating training of the encoder, generator, and discriminator, thereby achieving augmentation of fault samples and effectively addressing the issue of sample imbalance. The CNN-BiLSTM model utilizes CNN to capture global key features and BiLSTM to capture bi-directional features of time series, efficiently classifying the augmented and balanced data and accurately identifying the health status of the reservoir. In practical applications at two plain reservoirs in China, our method demonstrated superior robustness compared to three other mainstream deep learning models when handling data with varying degrees of imbalance, achieving an accuracy rate of 0.94, which is significantly higher than that of other models. Even under extreme imbalance ratios of 1:20, the accuracy rate improved from 0.80 to 0.93 through sample augmentation. This study not only enhances the dynamic perception and understanding of the operational health of reservoirs but also significantly bolsters the reliability of risk mitigation decisions, offering a novel technical approach for reservoir health management.