Prediction of Kaplan turbine coordination tests based on least squares support vector machine with an improved grey wolf optimization algorithm

The optimum combination of blade angle of the runner and guide vane opening with Kaplan turbine can improve the hydroelectric generating the set operation efficiency and the suppression capability of oscillations. Due to time and cost limitations and the complex operation mechanism of the Kaplan turbine, the coordination test data is insufficient, making it challenging to obtain the whole curves at each head under the optimum coordination operation by field tests. The field test data is employed to propose a least-squares support vector machine (LSSVM)-based prediction model for Kaplan turbine coordination tests. Considering the small sample characteristics of the test data of Kaplan turbine coordination, the LSSVM parameters are optimized by an improved grey wolf optimization (IGWO) algorithm with mixed non-linear factors and static weights. The grey wolf optimization (GWO) algorithm has some deficiencies, such as the linear convergence factor, which inaccurately simulates the actual situation, and updating the position indeterminately reflects the absolute leadership of the leader wolf. The IGWO algorithm is employed to overcome the aforementioned problems. The prediction model is simulated to verify the effectiveness of the proposed IGWO-LSSVM. The results show high accuracy with small samples, a 2.59% relative error in coordination tests, and less than 1.85% relative error in non-coordination tests under different heads.