When it comes to creating hydraulic structures, the acoustic and hydraulic performances of centrifugal pumps are connected and incompatible. To address this issue, a genetic algorithm (GA) and radial basis function (RBF) neural network-based approach for improving volute design has been developed. The entire amount of sound pressure level and the centrifugal pump's efficiency are the objectives for optimization. The factors that are optimized are the base circle diameter, the height of the volute diffuser tube, the volute tongue installation angle, and the volute tongue installation angle. Using the Latin hyper-cube sampling (LHS) method, the sample space is constructed. An agent model is constructed between the optimization variables and the objectives using the RBF neural network technique. Finally, the GA technique is used to perform multi-objective optimization. To do a comparative investigation of the hydraulic and acoustic performance of the individuals in the Pareto solution set under a variety of diverse operating situations, the first two individuals and the two individuals from the set's extremes are chosen. According to the results, under the rated working conditions, the ideal individual of efficiency increases by 3.79%, while the optimal individual of sound pressure level experiences a 2.3% decrease in external noise and a 5.5% decrease in internal noise. The outcomes show even more how inefficient the first individual was compared to the ideal individual. Centrifugal pumps, genetic algorithms, RBF neural networks, and multi-objective optimization are a few keywords that must be employed.

When it comes to creating hydraulic structures, the acoustic and hydraulic performances of centrifugal pumps are connected and incompatible.