BP算法对Pb-Al层状复合材料界面结合强度的预测  

Prediction of Interfacial Bonding Strength of Pb-Al Multilayer Materials Based on BP Neural Network

作　　者：周生刚[1] 张喆[1] 廖玉祥[1] 孙丽达[2] 

机构地区：[1]昆明理工大学材料科学与工程学院,云南昆明650093 [2]红河学院理学院,云南蒙自661400

出　　处：《昆明理工大学学报（自然科学版）》2013年第1期12-15,共4页Journal of Kunming University of Science and Technology(Natural Science)

基　　金：国家自然科学基金资助项目(51201080;51264025);云南省应用基础研究项目(KKSY201251086)

摘　　要：基于键参数函数理论,分析了制备Pb-Al层状复合材料的热力学可行性;采用热物理温度场浸镀及热包覆铸造的方法制备出了Pb-Al层状复合材料,通过室温拉伸剪切试验,测试出其界面结合的力学性能,并以目前较为成熟的人工神经网络BP算法建立起拉伸剪切强度预测模型.结果表明,该模型的结果与实测值有很好的对应关系.根据网络估测的结果可定量地设计抗拉强度的制板工艺,为制备一种新型Pb-Al层状复合材料提供了一种科学方法.Based on bond parameter function theory, electro - negativity difference theory and atomic size differ- ence theory, the thermodynamic feasibility for preparation of Pb - Al multilayer materials are analyzed. Pb - Al muhilayer materials are prepared by the thermo - physical field plating and melted metallic fluid - gladding. The mechanical properties are tested around bonding interface by tensile sheer test at room temperature. The matured Back -Propagation（BP） algorithm is used to establish a tensile sheer strength model. It is showed that the calcu- lation values of the model are similar to those of the laboratory measurement and have a low average error, which provides a referential method for preparation of a new Pb - Al multilayer material.

关 键 词：难混溶金属 键参数函数 电负性差 BP算法 拉伸剪切强度 

分 类 号：TB331[一般工业技术—材料科学与工程]