材料期刊网，材料期刊，材料类期刊，材料期刊投稿

Plasticity Enhancement Processes in NiAl and MoSi_2

R.Gibala H.Chang C.M.Czarnik K.M.Edwards A.Misra Department of Materials Science and Engineering , University of Michigan , Ann Arbor , Michigan 48109-2136 , USA

材料科学技术（英文）

This paper demonstrates that plasticity enhancement processes previously observed in bcc metals and associated with the presence of surface films and precipitates or dispersoids are operative in or- dered intermetallic compounds.' Some specific results are given for NiAl-and MoSi_2-based materials.The plasticity of NiAl and related B2 ordered alloys at room temperature during monotonic deformation can be enhanced by application of surface films such as electroless nickel platings.Sig- nificant effects are also observed during cyclic deformation.The presence of ductile second phases such as fcc γ or the ordered phase γ' introduced by alloying also enhances the plasticity of NiAl. MoSi_2 exhibits similar effects of surface films and second phases,but primarily at elevated tempera- tures,T>900℃.In this paper,we illustrate the effects of ZrO_2 surface films deposited near room temperature and TiC particulate additions introduced by powder processing techniques.In all cases, the plasticity enhancement is associated with enhanced dislocation generation processes under the conditions of constrained deformation at the film-substrate or precipitate/dispersoid-matrix inter- face of the composite system.

关键词: plasticity , null , null , null

Optimization of Machining Characteristics for Al/SiCp Composites using ANN/GA

R.Karthikeyan , R.Adalarasan , B.C.Pai

材料科学技术（英文）

The present work is focused on optimization of machining characteristics of Al/SiCp composites. The machining characteristics such as specific energy, tool wear and surface roughness were studied. The parameters such as volume fraction of SiC, cutting speed and feed rate were considered. Artificial neural networks (ANN) were used to train and simulate the experimental data. Genetic algorithms (GA) was interfaced with ANN to optimize the machining conditions for the desired machining characteristics. Validation of optimized results was also performed by confirmation experiments.

关键词: Al/SiCp composites , null , null

Study on Process Parameters Optimization of Sheet Metal Forming Based on PFEA/ANN/GA

Juhua HUANG , Jinjun RAO , Xuefeng LI

材料科学技术（英文）

Sheet metal forming is widely applied to automobile, aviation, space flight, ship, instrument, and appliance industries. In this paper, based on analyzing the shortcoming of general finite element analysis (FEA), the conception of parametric finite element analysis (PFEA) is presented. The parametric finite element analysis, artificial neural networks (ANN) and genetic algorithm (GA) are combined to research thoroughly on the problems of process parameters optimization of sheet metal forming. The author programs the optimization scheme and applies it in a research of optimization problem of inside square hole flanging technological parameters. The optimization result coincides well with the result of experiment. The research shows that the optimization scheme offers a good new way in die design and sheet metal forming field.

关键词: Sheet metal forming , null , null , null

影响六方BN颗粒表面化学镀镍过程的因素及其ANN优化

李钒 , 张登君 , 李报厚 , 罗世民

稀有金属 doi:10.3969/j.issn.0258-7076.2002.05.004

在分析氨络合体系六方BN表面化学镀镍的热力学基础上, 分别研究了影响镀覆反应速率的主要因素及其变化规律. 用人工神经网络(ANN)方法对小型试验和放大试验的工艺参数进行优化与预测, 试验结果与预测结果基本吻合, 表明对本研究体系的ANN方法优化与预测可用于指导实践, 并克服了多因素复杂体系及交互影响带来研究的困难.

关键词: 六方BN , 化学镀镍 , 人工神经网络 , 工艺参数优化

基于BP-ANN的陶粒轻骨料混凝土抗压强度预测及影响因素分析

吴涛 , 黄凯 , 姚东方

硅酸盐通报

优化多层前馈神经网络(BP-ANN)模型使用弹性反向传播算法及提前终止技术,输入各层神经元几何与材料特性可用以预测混凝土强度等级.基于多层前馈神经网络建立了轻骨料混凝土抗压强度预测模型,采用MATLAB程序,完成了国内444个混凝土试块、148组配合比试验结果与BP-ANN计算结果的对比研究;采用基于BP-ANN模型,分析了水胶比及陶粒筒压强度对轻骨料混凝土强度影响.研究表明:采用神经网络模型所得计算结果与试验值吻合良好,离散程度较小;水胶比和陶粒筒压强度对混凝土强度影响显著,且有不同变化趋势.

关键词: 轻骨料混凝土 , 神经网络 , 强度 , 水胶比 , 筒压强度

网络化的ANN-GA系统优化中空纤维镍基板制备工艺参数

李钒 , 王习东 , 张登君 , 张梅 , 盖鑫磊

金属学报

在实验室研究中空纤维镍基板的制备工艺的基础上, 采用自制的网络化的ANN-GA系统对58个样本进行了工艺参数优化和寻优, 得到的最佳工艺参数如下: 中空镍纤维含量为97%; 烧结温度为1275 K; 保温时间为20 min; 造孔剂 PVB, PP和Ni(OH)2的含量分别为5%, 3.5%和1%. 在最优工艺条件基础上, 获得了性能优异、孔率接近87%的基板材料. 并用计算机分析和预报了各单因素的影响规律, 预测结果与文献报道的实验结果一致.

关键词: 中空纤维镍基板 , ANN-GA program on computer network

网络化的ANN-GA系统优化中空纤维镍基板制备工艺参数

李钒 , 王习东 , 张登君 , 张梅 , 盖鑫磊

金属学报 doi:10.3321/j.issn:0412-1961.2005.12.012

在实验室研究中空纤维镍基板的制备工艺的基础上,采用自制的网络化的ANN-GA系统对58个样本进行了工艺参数优化和寻优,得到的最佳工艺参数如下:中空镍纤维含量为97%;烧结温度为1275 K;保温时间为20 min;造孔剂PVB,PP和Ni(OH)2的含量分别为5%,3.5%和1%.在最优工艺条件基础上,获得了性能优异、孔率接近87%的基板材料.并用计算机分析和预报了各单因素的影响规律,预测结果与文献报道的实验结果一致.

关键词: 中空纤维镍基板 , 网络化ANN-GA系统 , 参数优化 , 影响因素

基于GA-ANN的不锈钢复合板剪切强度优化模型研究

邹德宁 , 王鸿波 , 陈治毓 , 韩英 , 于军辉

兵器材料科学与工程 doi:33-1331/TJ.20111103.1337.003

基于人工神经网络和遗传算法,结合177组不锈钢复合板实测数据,构建不锈钢复合板剪切强度模型.研究确定不锈钢铬当量、铬镍当量比、复合板覆层厚度以及基材厚度为网络输入量,复合板剪切强度为输出量,隐含层节点数由试探寻优法确定,优化网络结构为4-7-1；比较Levenberg-Marquardt、Quick-Propagation、Standard Back-Propagation算法的训练误差、测试误差及计算迭代步数,确定以误差最小、计算速度最快的LM算法训练网络；另外,利用提前终止法避免ANN模型产生的过拟合的问题；在此基础上,引入遗传算法进一步优化ANN网络的权值和阈值,使得复合板剪切强度预测值与实测值相关系数达到0.997;将所构建模型用于实际不锈钢复合板剪切强度的预测,与实测值相近,进一步验证预测模型的有效性和可靠性.

关键词: 不锈钢复合板 , 剪切强度 , 人工神经网络 , 遗传算法