基于小波神经网络的无叶扩压器失速分析

用来自不同文献的实验数据作为样本,对小波神经网络进行训练,并利用训练好的神经网络研究叶轮和扩压器几何尺寸对无叶扩压器失速的影响.计算分析结果表明:几何尺寸对于宽、窄扩压器失速的影响表现不同,这也证明了不同宽度的扩压器的确存在不同的失速机理.文章的结果,对无叶扩压器的设计具有一定的借鉴意义.

Analysis of stall in vaneless diffuser based on wavelet neural network

Wavelet neural network(WNN) was trained with experimental data collected from a variety of literature and then was utilized to study influences of geometries of impeller and diffuser on rotating stall in vaneless diffuser,and the results were presented in graphs.Results show that diffusers with different width ratios exhibit distinct responses to geometry variation,proving that different stall mechanisms exist for wide diffuser and narrow diffuser.The conclusions provide reference to the design of vaneless diffuser.