论文部分内容阅读
为了提高透平的内效率及降低制造成本 ,采用基于神经网络及遗传算法的叶轮机械叶片三维优化设计方法 ,开发了一种高载荷动叶片。该叶片是以 5个截面的重心沿径向积叠而成。每个截面的内背弧是以基于叶型中弧线的 Bezier曲线来构造。三维流动分析表明 ,新叶片提高效率0 .5 %。通过减少叶片数约 1 5 % ,新开发的高载荷动叶片不仅有效地提高了透平的内效率 ,同时降低了透平重量和制造成本。
In order to improve the internal efficiency of turbine and reduce the manufacturing cost, a three-dimensional optimization design method of impeller mechanical blade based on neural network and genetic algorithm was developed to develop a high-load moving blade. The blade is based on 5 cross-section of the center of gravity along the radial stack. The inner back arc for each section is constructed with a Bezier curve based on the arc in the leaf. Three-dimensional flow analysis showed that the new leaf increased efficiency by 0.5%. By reducing the number of blades by about 15%, the newly developed high-load moving blades not only effectively improve the turbine’s internal efficiency, but also reduce the turbine weight and manufacturing cost.