损失及落后角代理模型在多级轴流压气机特性预测中的应用  

Application of Loss and Deviation Surrogate Models on Prediction of Multistage Axial Compressor Characteristics

作　　者：韩昌富 刘波[1] 张博涛 HAN Chang-fu;LIU Bo;ZHANG Bo-tao(School of Power and Energy,Northwestern Polytechnical University,Xi'an 710129,China)

机构地区：[1]西北工业大学动力与能源学院,陕西西安710129

出　　处：《推进技术》2020年第7期1493-1501,共9页Journal of Propulsion Technology

基　　金：国家自然科学基金(51676162,51790512)。

摘　　要：为了提高轴流压气机设计能力,进而提高发动机的特性,需要掌握一种能够较好预测轴流压气机的压比、效率等特性的方法。结合运用三元流动理论和传统损失落后角模型计算出的压气机流场数据,利用正则化径向基函数神经网络取代经验公式搭建了一种新的损失及落后角模型,计算了E3十级高压压气机的特性;并分别研究了不进行正则化和进行正则化对损失及落后角预测的影响与其对压气机效率和压比特性预测的影响。结果表明,在多级压气机中,在训练样本区分转静子、区分转速、区分工况条件下,使用正则化的径向基神经网络代理模型在大部分情况下能够较好地预测损失、落后角及多级压气机整体特性,但是对沿叶高分布的损失及落后角预测能力还有待提高。In order to improve the design capability of axial compressor and characteristics of the engine,researchers need to master a method which can better predict pressure ratio and efficiency of axial compressor.Combining the data of compressor flow field calculated by theory of three-dimensional flow and empirical loss and deviation angle formulas,a new loss and deviation angle model was established by using regularized radial basis function neural network instead of empirical formulas,and the characteristics of E310-stage high pressure compressor were calculated.The effects of non-regularization and regularization on loss and deviation angle prediction were studied,respectively,as well as the influence of compressor efficiency and pressure ratio prediction was investigated.The results showed that in a multistage compressor,under the conditions of distinguishing rotor and stator,rotating speed and operating conditions,the regularized radial basis function neural network surrogate model could better predict the loss and deviation angle and overall characteristics of a multistage compressor in most cases.However,this kind of work could not have a satisfying performance on the prediction of loss and deviation angle from shroud to hub.

关 键 词：轴流压气机 代理模型 损失 落后角 特性预测 三维流动 

分 类 号：V231.3[航空宇航科学与技术—航空宇航推进理论与工程]