基于响应面模型的螺旋迷宫泵结构优化

Structural Optimization of Labyrinth Screw Pump Based on Response Surface Model

针对螺旋迷宫泵效率偏低的问题,以迷宫泵的效率、轴功率和扬程为目标函数,以泵的结构参数为优化参数,建立了基于试验设计和响应面估值的螺旋迷宫泵结构优化模型。首先通过尺寸关联性将迷宫泵的结构参数进行合理简化,将16个设计参数简化为11个,然后进行参数灵敏度分析确定需要优化的9个重要结构参数。采用优化空间填充设计法对优化参数进行组合生成样本点。最后通过神经网络型响应面和多目标遗传算法对螺旋迷宫泵进行结构优化,并在符合条件的结构参数组合中,根据实际需求选取其中一个作为优化结果的最终解。研究结果表明,螺旋迷宫泵定子和转子的结构参数之间存在交互性影响,相较于原模型,优化后的迷宫泵效率提升了90.06%,扬程提升了77.34%。研究结果可为螺旋迷宫泵结构的进一步优化提供参考。

The labyrinth screw pump is deficient for low efficiency. In this paper, a structural optimization model of labyrinth screw pump was established based on experimental design and response surface estimation, with the efficiency, shaft power and head of the labyrinth pump as the objective functions, and the structural parameters of the pump as the optimized parameters. Firstly, according to size correlation, 16 structural parameters of the labyrinth pump were rationally simplified to 11 parameters, and then the parameter sensitivity analysis was performed to determine the 9 important structural parameters to be optimized. The optimized space-filling design method was used to combine the optimized parameters to generate sample points. Finally, the structure of the labyrinth screw pump was optimized by neural network response surface and multi-objective genetic algorithm, and one of the qualified structural parameter combinations was selected according to actual needs as the final solution of the optimization. The study results show that there is an interactive influence between structural parameters of the stator and rotor of the labyrinth screw pump, and compared with the original model, the efficiency of the optimized labyrinth screw pump is increased by 90.06% and the head is increased by 77.34%. The study results can provide a reference for the structural optimization of labyrinth screw pumps.