Accurate prediction of performance indices using impeller parameters is of great importance for the initial and optimal design of centrifugal pump. In this study, a kernel-based non-parametric machine learning method named with Gaussian process regression (GPR) was proposed, with the purpose of predicting the performance of centrifugal pump with less effort based on available impeller parameters. Nine impeller parameters were defined as model inputs, and the pump performance indices, that is, the head and efficiency, were determined as model outputs. The applicability of three widely used nonlinear kernel functions of GPR including squared exponential (SE), rational quadratic (RQ) and Matern5/2 was investigated, and it was found by comparing with the experimental data that the SE kernel function is more suitable to capture the relationship between impeller parameters and performance indices because of the highest R square and the lowest values of max absolute relative error (MARE), mean absolute proportional error (MAPE), and root mean square error (RMSE). In addition, the results predicted by GPR with SE kernel function were compared with the results given by other three machine learning models. The comparison shows that the GPR with SE kernel function is more accurate and robust than other models in centrifugal pump performance prediction, and its prediction errors and uncertainties are both acceptable in terms of engineering applications. The GPR method is less costly in the performance prediction of centrifugal pump with sufficient accuracy, which can be further used to effectively assist the design and manufacture of centrifugal pump and to speed up the optimization design process of impeller coupled with stochastic optimization methods.
28 November 2016 in International Journal of Rotating Machinery
Aiming at the cavitation problem, the blade leading edge shape has been changed to analyze its impact on the cavitation performance for centrifugal pumps. And the response model has been established based on the Radial Basis Function. The calculation case results show that the leading edge extending forward along the shroud can improve the inlet flow condition and cavitation performance. But the cavitation performance has been reduced immensely when the leading edge extends backward along the shroud. Along with the leading edge which extends forward along the hub, the cavitation performance increases at first and then decreases. A better cavitation performance for centrifugal pumps has lower load of blade inlet and higher pressure of blade suction side. The pressure pulsation is affected by the vortex out of the impeller and the falling-off and collapsing of the cavitation bubbles. The lower the pressure pulsation for blade passing frequency and the second harmonics of the samples is, the better the cavitation performance is. A relatively accurate response model based on the Radial Basis Function has been established to predict the effect of the shape of blade leading edge on the cavitation performance of centrifugal pumps.