Comparison of multiple machine learning models for the regression of water hammer with column separation

This paper seeks to harness the potential of machine learning techniques to substantially enhance both the precision and efficacy of predicting water hammer phenomena, while simultaneously reducing time, safeguarding pipeline, and conserving resources. A novel mathematical model is proposed by integrating the two-fluid model and the interphase relaxation model with an improved Godunov–Harten–Lax–van Leer numerical method. The study conducts a comprehensive evaluation of the performance of four prominent machine learning algorithms—Back Propagation Neural Network (BP neural network), deep forest, Long Short-Term Memory (LSTM), and Extreme Gradient Boosting (XGBoost)—for the regression analysis of water hammer with column separation. In terms of predictive accuracy, the LSTM model achieves an impressive accuracy of 0.981 94. The BP neural network, deep forest, and XGBoost models yield accuracies of 0.975 01, 0.929 83, and 0.928 65, respectively. Regarding computational efficiency, XGBoost shows a clear advantage, with an overall average execution time of 4.13 s. Deep forest is distinguished by its simplicity in parameter configuration. This research provides valuable insights for selecting the optimal model for regression analysis of water hammer with column separation under a variety of conditions. Furthermore, the paper employs data visualization to directly generate visual trend representations of the overall pressure distribution, thereby eliminating the need for cumbersome numerical comparisons typical of traditional methods.