基于支持向量回归机的汽轮机转子应力修正系数模型  

Model of the Stress Correction Coefficient of Steam Turbine Rotors Based on SVR

作　　者：方宁[1] 纪冬梅[1] 姚秀平[1] 程超锋[1] 杨宇[2] 史进渊[2] 

机构地区：[1]上海电力学院能源与环境工程学院,上海200090 [2]上海发电设备成套设计研究院,上海200240

出　　处：《动力工程学报》2010年第3期166-169,共4页Journal of Chinese Society of Power Engineering

基　　金：国家863计划重点资助项目(2007AA04Z429);上海市本科教育高地资助项目(A88001)

摘　　要：提出了基于支持向量回归机的汽轮机转子应力修正系数预测方法.介绍了支持向量回归算法及其参数选择,并将该算法应用于某600 MW汽轮机高中压转子应力修正系数的建模计算,同时与径向基神经网络模型所预测的结果进行了对比,结果表明:基于支持向量回归机的计算模型可以对转子的应力修正系数进行准确估算,具有更好的计算精度和泛化性能.A prediction method of stress correction coefficient of steam turbine rotors was proposed based on support vector regression（SVR）.The algorithm of SVR and the parameter selection were introduced,and the algorithm was applied into the modeling and calculation of stress correction coefficient for high-middle-pressure rotors of a 600 MW steam turbine.The result was compared with that predicted by the model of radial basis function network.Results show that the model based on SVR can estimate the stress correction coefficient of the rotor accurately and has better calculation precision and generalization.

关 键 词：汽轮机 高中压转子 应力修正系数 支持向量回归机 

分 类 号：TK263.6[动力工程及工程热物理—动力机械及工程]