Research on performance curve prediction of centrifugal pump based on improved whale optimization algorithm and characteristic deformation method

This article proposes an improved hybrid method combining whale optimization algorithm (IMWOA) and the characteristic deformation method (CDM) to predict the performance curve of centrifugal pumps. The traditional whale optimization algorithm (WOA) is enhanced by introducing chaos mapping, adaptive weight, nonlinear convergence factor strategies, and mutation concept from the genetic algorithm. These improvements make IMWOA significantly superior to the traditional WOA in the basic criterion test functions. To address the limitations of sample set size and differences in data characteristics in practical applications, this paper also introduces CDM strategies, including dynamic parameter adjustment strategy and mixed standardization strategy. Comparative analysis shows that the IMWOA-CDM method achieves better results in various performance evaluation indicators. The final experimental results validated the high accuracy and reliability of the IMWOA-CDM method in predicting the performance curve of centrifugal pumps, with a maximum absolute error of 1.21 m for head and 1.08% for efficiency.