Water supply pump stations operate under multiple and often conflicting requirements related to energy efficiency, hydraulic safety, and equipment durability. To address this problem, this study develops a digital-twin-assisted multi-objective optimisation framework for pump station operation, in which energy consumption, water hammer peak pressure, and equipment lifespan are considered simultaneously. Using the first-stage pumping station of the South Main Line of the Yellow River Diversion Project in Shanxi Province as a case study, a digital twin model is constructed from historical records, equipment parameters, and real-time monitoring data, and an improved Non-dominated Sorting Genetic Algorithm II (NSGA-II) is introduced to generate feasible Pareto solutions under operational constraints. The model validation results show that the mean simulation errors of energy consumption, water hammer peak pressure, and lifespan prediction are 3.13%, 2.14%, and 7.29%, respectively, while the response time remains within 0.4 s. Compared with the conventional operating scheme, the selected compromise solution reduces energy consumption by 12.0%, lowers water hammer peak pressure by 15.0%, and improves equipment lifespan by 9.0%, with full constraint satisfaction. The improved NSGA-II also shows better convergence, diversity, and feasible-solution performance than the traditional algorithm. Field trial results further indicate that the proposed framework can support safer, more efficient, and more stable pump station operation. This study provides a practical basis for multi-objective operational optimisation of water supply pump stations under dynamic operating conditions.
Liu et al. (Tue,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: