摘要
利用超高强度300M、30CrMnSiA调质钢、A3普通碳素结构钢的试验数据作为训练样本,预测了LY12CZ铝合金的疲劳寿命,并与试验数据在疲劳寿命N、子样平均值X、中值疲劳寿命N50方面分别进行分析比较,结果表明模型的误差控制在2%以内,证明了模型预测方法的可行性和有效性,也为预测新材料的疲劳寿命提供了方法和依据。
Test data of 300M ultrahigh strength steel, 30CrMnSiA steel and A3 structural carbon steel are applied as training samples. Then using this model the fatigue life of LY12CZ aluminium alloy is predicted. By comparing fatigue life(N), average value of sample and median fatigue life (N50) in simulation results with those in test results, it is found that the error of the model is less than 2%. This model is proved feasible and effective, also a method and basis for fatigue life prediction of new materials are provided.
出处
《航空精密制造技术》
2008年第1期35-37,45,共4页
Aviation Precision Manufacturing Technology
关键词
冷挤压孔
疲劳寿命
BP神经网络
cold-expanded hole
fatigue life
BP neural network
