论文部分内容阅读
应用遗传算法结合神经网络技术通过对候选叶片表面速度分布与目标速度分布之间误差的极小化，求解给定表面速度分布下的扩压器叶片形线。叶片形线利用Ｂｅｚｉｅｒ曲线参数化表示，候选叶片形线的流场分析由ＢＰ神经网完成。所提出的方法用于一离心压缩机平行直壁扩压器的二元等厚叶片设计，结果显示该方法是有效和可行的
The genetic algorithm and neural network are used to solve the diffuser vane line with given surface velocity distribution by minimizing the error between the candidate vane surface velocity distribution and the target velocity distribution. Leaf shape line using Bezier curve parametric expression, candidate leaf shape flow field analysis by BP neural network. The proposed method is applied to the design of a bivariate equal-thickness blade for a parallel straight-wall diffuser of a centrifugal compressor. The results show that this method is effective and feasible