Multi-Objective Optimization of Jet Pump Based on RBF Neural Network Model

In this study, an annular jet pump optimization method is proposed based on an RBF (Radial Basis Function) neural network model and NSGA-II (Non-Dominated Sorting Genetic Algorithm) optimization algorithm to improve the hydraulic performance of the annular jet pump applied in submarine trenching and dredging. Suction angle, diffusion angle, area ratio and flow ratio were selected as design variables. The computational fluid dynamics (CFD) model was used for numerical simulation to obtain the corresponding performance, and an accurate RBF neural network approximate model was established. Finally, the NSGA-II algorithm was selected to carry out multi-objective optimization and obtain the optimal design variable combination. The results show that the determination coefficient R2 of the two objective functions (jet pump efficiency and head ratio) of the approximate model of the RBF neural network were greater than 0.97. Compared with the original model, the optimized model’s suction angle increased, and the diffusion angle, flow ratio and area ratio decreased. In terms of performance, the head ratio increased by 30.46% after the optimization of the jet pump, and efficiency increased slightly. The proposed jet pump performance optimization method provides a reference for improving the performance of other pumps.

Parameter Analysis and Optimization of Annular Jet Pump Based on Kriging Model

Jet pump efficiency heavily relies on the geometrical parameters of the pump design and parameter global optimization in the full variable space is still a big challenge. This paper proposed a global optimization method for annular jet pump design combining computational fluid dynamics (CFD) simulation, the Kriging approximate model and experimental data. The suction angle, the flow ratio, the diffusion angle, and the area ratio are selected as the design variables for optimization. The optimal space filling design (OSF) method is used to generate sampling points from the design space of the four design variables. The optimization method solves the constrained optimization problem with a given head ratio by building the functional relationship established by the Kriging model between efficiency and design parameters, which makes the method more applicable. The design result shows that the annular jet pump efficiency is predicted well by the Kriging model; m is a key variable affecting the annular jet pump efficiency. As the area ratio m decreases, the mixing effect at the suction chamber outlet can be improved, but the frictional resistance increases.

Numerical Study on the Working Performance of a Streamlined Annular Jet Pump

To improve the working performance of the early annular jet pump (EAJP), a streamlined annular jet pump (SAJP) was proposed. The flow field and working performance of the EAJP and SAJP with an area ratio (m) of 1.75 were numerically studied and compared, separately, by using the combination of the Realizable k-ε turbulence model and the Schnerr–Sauer cavitation model. The results show that the efficiency of the SAJP is higher than that of the EAJP, when the flow ratio (q) is higher than 0.30, with a maximum increase of 1.2%. Furthermore, the high-efficiency area of the SAJP (q = 0.40~0.69) is wider than that of the EAJP (q = 0.36~0.57). There is no flow separation and low local pressure in the SAJP, due to the conjunction part of the suction chamber, throat, diffuser and outlet pipe without the structural mutation. It was found that the incipient cavitation number (σi) of the SAJP and EAJP was 0.541 and 0.578, respectively; therefore, the cavitation performance of the SAJP is better. Meanwhile, the critical flow ratio (qc) of the SAJP is 0.69, which is larger than that of the EAJP (qc = 0.57), implying that the SAJP has a wider normal working range than the EAJP. Importantly, the inception and development of cavitation appeared in the diffuser of the SAJP, different from that in the throat of the EAJP. Hence, it concluded that the cavitation in the SAJP has less influence on the flow field and working performance.