基于ANN的ZA35合金热处理后阻尼性能的预测  

Prediction of damping property of ZA35 alloy after heat treatment based on ANN

作　　者：刘敬福[1] 韩明明 李赫亮[1] 吴晓刚 庄伟彬[1] Liu Jingfu;Han Mingming;Li Heliang;Wu Xiaogang;Zhuang Weibin(College of Materials Science and Engineering,Liaoning Technical University,Fuxin Liaoning 123000,China)

机构地区：[1]辽宁工程技术大学材料科学与工程学院

出　　处：《金属热处理》2018年第9期223-226,共4页Heat Treatment of Metals

基　　金：辽宁省自然科学基金(201602356)

摘　　要：基于人工神经网络（ANN）,建立了ZA35合金热处理工艺对阻尼性能影响的人工神经网络模型,预测了固溶时效处理后ZA35合金的阻尼性能。模型输入参数为固溶时间、固溶温度、时效时间和时效温度,输出参数为ZA35合金的内耗值。结果表明：该模型可以预测ZA35合金在不同热处理工艺参数下的阻尼性能,也可以优化热处理工艺参数。预测的最大相对误差为13.54%,拟合率为0.982,最终确定ZA35合金阻尼性能最佳的工艺参数是340℃×5 h固溶＋150℃×8 h时效处理。Based on the artificial neural network（ ANN）,the ANN model regarding the effect of heat treatment process on damping performance of ZA35 alloy was established. The input parameters of the neural network（ NN） model were solid solution temperature,solid solution time,aging temperature and aging time. The output of the NN model was internal friction value of ZA35 alloy. The results of ANN module show that the biggest relative error and coincidence rate is 13. 54% and 0. 982,respectively. The model can be used for the prediction of damping property of ZA35 alloy as functions of heat treatment parameters. It can also be used for the optimization of the heat treatment parameters. The optimized heat treatment process is 340 ℃ × 5 h solid solution and 150 ℃ × 8 h aging treatment.

关 键 词：ZA35合金 人工神经网络(ANN) 固溶 时效 阻尼性能 

分 类 号：TG249.2[金属学及工艺—铸造]