摘要
在汽轮机转子钢热脆性无损检测技术的开发中,将遗传规划法应用到30Cr2MoV钢韧脆性转变温度预测模型的建立中,以提高检测精度。把材料的脆性转变温度作为预测模型的因变量,将单环动电位再活化法测得的峰值电流密度、电解液温度、材料的化学成分参数(J参数)、材料中Cr质量分数、S质量分数、材料的维氏硬度和晶粒度作为自变量,将因变量和自变量的试验测定结果分为训练样本数据和检验样本数据。依据训练样本数据,经过遗传规划法求得最优预测模型,并用检验样本数据对所得的预测模型进行检验。结果表明:所得模型的预测误差为±20℃,精度较高。因此可以将遗传规划法应用到汽轮机转子钢预测模型的建立中。
The genetic programming approach is proposed to predict temper embrittlement of rotor steel （30Cr2MoV）. Two independent data sets are obtained experimentally： training data and verifying data. Peak current density of reactivation, temperature of electrolyte, the general chemical composition parameter （J-factor）, chemical composition of Cr and S, hardness and the grain size parameter of the material are used as independent variables, while fracture appearance transition temperature as dependent variable. On the basis of training data, the best model is obtained by genetic programming, and the accuracy of it is verified with the verifying data. The prediction error of the model is within the scatter of ±20℃. The results suggest that, the prediction model obtained by genetic programming is feasible and effective.
出处
《机械工程学报》
EI
CAS
CSCD
北大核心
2007年第10期211-214,共4页
Journal of Mechanical Engineering
基金
国家电力公司科技资助项目(SP11-2001-02-29)
关键词
汽轮机转子
热脆性
电化学极化
遗传规划
Steam turbine rotor Temper embrittlement Electrochemical polarization Genetic programming
