Research on the Collaborative Optimization of One-Way Surge Tanks Based on Water Hammer Theory and Intelligent Optimization Algorithms

Le résumé fourni par la source

A coupling optimization model is developed to coordinate the design of the one-way surge tank (OWST) volume and the valve closing rule. This approach aims to address the strong coupling regarding the parameters of the OWST and the inefficiency of manual optimization. First, a water hammer control equation incorporating the parameter coupling effect is derived, followed by the formulation and validation of an initial theoretical protection scheme that serves as a benchmark for constructing the sample database. The Back Propagation Neural Network (BPNN) is utilized to establish a nonlinear mapping relationship between pipeline characteristic evaluation indices and input parameters, whereas its network structure is optimized using Adaptive Particle Swarm Optimization (APSO) to enhance fitting accuracy. Finally, the Whale Optimization Algorithm (WOA) is applied to conduct a global search and parameter optimization. Compared with the theoretical design, the optimized scheme of the OWST volume is reduced by 30.3%, and the end valve closing speed is increased by 13.4%. The results indicate that the APSO-BPNN-WOA coupling optimization model facilitates global continuous optimization within the parameter range, effectively coordinates and optimizes the design parameters of the water hammer protection scheme, and demonstrates high practical value for engineering applications.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.