Simulation of aging process of lead frame copper alloy by an artificial neural network

1　INTRODUCTIONThefunctionsofleadframeinelectronicpackingareprovidingchannelsforelectronicsignalsbetweendevicesandcircuits ,andfixingdevicesoncircuitboards.Leadframealloysarerequiredtohavehighstrengthandgoodformabilityaswellashighelectri calandthermalconductivity .Cu basealloysarethemostpopularleadframealloysandareusedinplasticpackagingapplicationduetotheirhighthermalandelectricalconductivityaswellashighstrength[13] .Theaginghardening processinfabricationofleadframecopperalloymakesitpossi…     

利用神经网络建立快速凝固Cu-Cr-Zr合金时效知识库

根据人工神经网络(ANN)的BP(back propagation)算法，建立了快速凝固Cu-Cr-Zr铜合金时效温度和时间与硬度和导电率的神经网络映射模型。预测值与实际情况吻合良好，硬度和导电率最大误差分别为4．1％和1．9％。通过对样本集的学习，建立了快速凝固时效工艺知识库，对预测和控制该工艺性能非常有益。     

INTERACTION OF PRECIPITATION AND RECRYSTALLIZATION IN RAPIDLY SOLIDIFIED Cu-Cr-Zr-Mg ALLOY

1.IntroductionCu--Cr-Zr-Mgalloysarewidelyusedinvariousaspects,suchasinelectricresistanceweldingelectrode,motor--commutatorandintegratedcircuitleadframe,duetotheirgoodthermalandelectricalconductivitiesandrelativelyhigherstrength.However,itisdifficulttofurtherimprovetheirelectricalandmechanicalpropertiesunderconventionalsohltionheat--treatment(CSHT)sincethedegreeofprecipitationhardeninguponagingisrestrictedbythelimitedsolubilityofchromiumandzirconiumincopper[1--31.Thecompositionsandthepropert…     

基于人工神经网络的7055铝合金二次时效性能预测

利用人工神经网络对7055铝合金二次时效热处理工艺参数与时效性能样本集进行训练和学习,采用改进的BP网络算法Levenberg-Marquardt算法,建立7055铝合金二次时效热处理工艺BP神经网络模型。针对二次时效工艺特点,研究的工艺参数包括:预时效温度、预时效时间、二次时效温度和二次时效时间。结果表明:神经网络预测值与实验值吻合较好,说明神经网络模型具有较高的精度及良好的泛化能力,可有效地用于预测和分析二次时效工艺参数对7055铝合金时效性能的影响。     

Evolutionary artificial neural network approach for predicting properties of Cu- 15Ni-8Sn-0.4Si alloy

A novel data mining approach, based on artificial neural network（ANN） using differential evolution（DE） training algorithm, was proposed to model the non-linear relationship between parameters of aging processes and mechanical and electrical properties of Cu-15Ni-8Sn-0.4Si alloy. In order to improve predictive accuracy of ANN model, the leave-one-out-cross-validation （LOOCV） technique was adopted to automatically determine the optimal number of neurons of the hidden layer. The forecasting performance of the proposed global optimization algorithm was compared with that of local optimization algorithm. The present calculated results are consistent with the experimental values, which suggests that the proposed evolutionary artificial neural network algorithm is feasible and efficient. Moreover, the experimental results illustrate that the DE training algorithm combined with gradient-based training algorithm achieves better convergence performance and the lowest forecasting errors and is therefore considered to be a promising alternative method to forecast the hardness and electrical conductivity of Cu- 15Ni-8Sn-0.4Si alloy.     

Establishing the knowledge repository of rapidly solidified aging Cu-Cr-Zr alloy on the artificial neural-network

The non-linear relationship between parameters of rapidly solidified aging processes and mechancal and electrical properties of Cu-Cr-Zr alloy is available by using a supervised artificial neural network (ANN). A knowledge repository of rapidly solidified aging processes is established via sufficient data learning by the network. The predicted values of the neural network are in accordance with the tested data. So an effective measure for foreseeing and controlling the properties of the processing is provided.     

基于人工神经网络的A357合金力学性能预测(英文)

A357铝合金零件一般都需要经过热处理(T6状态)以获得优异的力学性能。这类零件的性能取决于固溶温度、固溶时间、人工时效温度及人工时效时间。在本研究中,建立了基于反向传播(BP)算法的人工神经网络(ANN)模型,对A357合金的力学性能进行预测,研究了热处理工艺对该合金性能的影响。结果表明,所建立的BP模型能够对A357合金的力学性能进行有效且精度高的预测。良好的神经网络预测能力能够直观地反映A357合金的热处理工艺参数对其力学性能的影响。绘制抗拉强度和伸长率的等值线图形有助于清晰地找到抗拉强度和伸长率之间的关系,可为实际生产中热处理工艺参数的选择提供技术支持。     

Prediction and analysis of the aging properties of rapidly solidified Cu-Cr-Sn-Zn alloy through neural network

It is known that the strength of a metal can be successfully improved by rapid solidification. The hardness of the rapidly solidified Cu-Cr-Sn-Zn alloy is much higher than that of the solution heat-treated and aged alloy. In this study, multiple-layer, feed-forward, artificial neural network (ANN) modeling has been used to study the hardness and electrical conductivity behavior of a rapidly solidified Cu-Cr-Sn-Zn alloy. The ANN model shows how the aging parameters influence the hardness and electrical conductivity of a rapidly solidified Cu-Cr-Sn-Zn alloy. The ANN modeling also provides encouraging predictions for information not included in the trained set samples, indicating that a backpropagation network is a very useful and accurate tool for property analysis and prediction.     

基于人工神经网络的冷挤压工艺设计系统的知识自动获取研究

提出了用人工神经网络补充和修改冷挤压工艺设计系统知识库内容的模型框架,根据人工神经网络映射的特征编码提出并实现了一种专家系统自动获取冷挤压零件特征的方法,并详细讨论了算法过程,最后结合典型实例给出了知识自动获取的过程。所提出的知识自动获取方法的优点在于不仅可以通过人工神经网络把冷挤压零件的成形过程整体地存入知识库中,而且由于所选用的人工神经网络映射模式是集中反馈式、分工序循环进行的。因此,通过该方法还可以获取冷挤压成形过程中每步工序半成品件的特征,然后存入冷挤压工艺设计系统的知识库。     

基于人工神经网络与遗传算法的Al-Mg-Si系合金抗拉强度预测模型

为了研究Al-Mg-Si系合金热处理制度和合金成分对力学性能的影响规律,采用人工神经网络（artificial neural network, ANN）和遗传算法（genetic algorithm, GA）相结合的方法,构建了Al-Mg-Si系合金强度预测模型（ANN-GA模型）。通过单因素和双因素分析,研究了合金元素含量和热处理工艺参数对铝合金抗拉强度的影响规律。结果表明,随着Si含量的增加,铝合金的抗拉强度呈现先降低后升高的趋势;随着Mg含量的增加、Cu含量的增加或者Fe含量的减少,铝合金的抗拉强度整体上呈现升高的趋势。双因素分析更能反映输入参数对铝合金抗拉强度的影响。Mg/Si比、Mg+Si总量和时效时间对Al-Mg-Si系合金力学性能的影响显著。铝合金的硬度随时间的变化趋势与ANN-GA模型的计算结果一致,峰值时效时间为29 h,相对误差为11.86%。     

热轧生产工艺对C70250合金力学性能和导电性能的影响

在模拟工业化生产条件下研究C70250合金的热轧、固溶及时效处理工艺,对比C70250合金板坯的热轧、热轧+时效、热轧+冷轧+时效后合金的力学性能与导电性能,同时研究空冷与水冷对材料力学性能的影响.结果表明:时效析出为C70250合金的主要强化手段,时效前的塑性加工能使合金强度提高4%～5%.XRD分析表明:C70250合金铸锭经热轧开坯,在575～725 ℃之间保温1 h,析出相以Ni_2Si为主;合金开轧与终轧温度应控制在(900±50)～725 ℃之间,热轧板冷却速度不小于2.5 ℃/s;固溶处理制度为(900±50) ℃、1～3 h;时效工艺为400～ 450 ℃、4～6 h,该工艺制备的C70250合金抗拉强度不小于644 MPa,电导率IACS为40%,伸长率为8%.     

基于人工神经网络的铜合金时效性能研究

利用神经网络对Cu-Cr-Zr合金时效温度、时间与硬度和电导率样本集进行学习，采用改进的BP网络算法—Levenberg-Marquardt算法，建立了时效强化工艺BP神经网络模型。预测结果表明：该BP神经网络可以充分挖掘样本蕴含的领域知识，可以对材料性能进行有效预测和分析。     

ANN预测铀钛合金贮存后的力学性能

建立了预测铀钛合金在不同氮气氛和不同相对湿度下贮存后力学性能变化的人工神经网络模型,并用两组已知数据对人工神经网络垢预测效果进行了验证。     

MICROSTRUCTURE AND MECHANICAL PROPERTIES OF 8090 Al-Li ALLOY

The change of mechanical properties of the 8090 Al-Li alloy influenced by aging is attributedto the change of δ′-phase particle size and the precipitation of S′-phase.The δ′-phase mayeasily precipitate and rapidly grow,but the S′-phase can only precipitate with a longer stageof incubation.The precipitation of S′-phase would be promoted by cold working prior to ag-ing.The co-precipitation of δ′- and S′-phase could improve the strength and plastieity of thealloy,for which aging at 190℃.for 20—30 h seems to be optimal.In addition,the precipitatefree zone( PFZ)can form at high angle grain boundary and its width is over 200 nm in peakaging condition.But at sub-grain boundary,the formation of PFZ is difficult.     

Prediction of Contact Fatigue Life of Alloy Cast Steel Rolls Using Back-Propagation Neural Network

In this study, an artificial neural network (ANN) was employed to predict the contact fatigue life of alloy cast steel rolls (ACSRs) as a function of alloy composition, heat treatment parameters, and contact stress by utilizing the back-propagation algorithm. The ANN was trained and tested using experimental data and a very good performance of the neural network was achieved. The well-trained neural network was then adopted to predict the contact fatigue life of chromium alloyed cast steel rolls with different alloy compositions and heat treatment processes. The prediction results showed that the maximum value of contact fatigue life was obtained with quenching at 960 °C, tempering at 520 °C, and under the contact stress of 2355 MPa. The optimal alloy composition was C-0.54, Si-0.66, Mn-0.67, Cr-4.74, Mo-0.46, V-0.13, Ni-0.34, and Fe-balance (wt.%). Some explanations of the predicted results from the metallurgical viewpoints are given. A convenient and powerful method of optimizing alloy composition and heat treatment parameters of ACSRs has been developed.     

人工神经网络在钛合金领域的应用

概括了人工神经网络的学习机理以及运用较多的BP神经网络模型的BP算法原理,进一步综述了人工神经网络在钛合金材料高温变形行为研究、力学性能预测和相变规律等方面的应用情况。认为将人工神经网络技术应用于钛合金材料领域中,可以明显地提高工艺设计效率,缩短实验周期,对钛合金材料的研究具有很高的应用价值和深远的指导意义。     

应用人工神经网络模型预测Ti＋10V-2Fe-3A合金的力学性能

采用人工神经网络方法建立了Ti-10V-2Fe-3Al合金机械性能预测的神经网络模型。模型的输入参数包括变形温度、变形程度、固溶温度、时效温度等热加工工艺参数和热处理制度。模型的输出为钛合金最重要的5个机械性能指标，即抗拉强度、屈服强度、延伸率、断面收缩率和断裂韧性。与传统回归拟合公式相比，该模型具有容错性好、通用性强等优点。该模型可以预测Ti-10V-2Fe-3Al合金在不同热加工工艺参数和热处理制度下的机械性能，也可以用于优化热加工参数和热处理制度。     

INFLUENCE OF HEAT TREATMENT PROCESSES ON MECHANICAL PROPERTIES OF ACu－Ni－AI－Ti ALLOY

ＩＮＦＬＵＥＮＣＥＯＦＨＥＡＴＴＲＥＡＴＭＥＮＴＰＲＯＣＥＳＳＥＳＯＮＭＥＣＨＡＮＩＣＡＬＰＲＯＰＥＲＴＩＥＳＯＦＡＣｕ－Ｎｉ－ＡＩ－ＴｉＡＬＬＯＹＩＮＦＬＵＥＮＣＥＯＦＨＥＡＴＴＲＥＡＴＭＥＮＴＰＲＯＣＥＳＳＥＳＯＮＭＥＣＨＡＮＩＣＡＬＰＲＯＰＥＲ...     

Possibility of grain size prediction in AA5754 aluminium ingots using neural networks

Abstract

The approach to the grain size prediction in AA5754 Al alloy ingots based on artificial neural networks (ANN) has been used in the present study. The ANN has been trained on data that was measured in the real industrial conditions during the process of direct chill Al ingots casting. A very complex relation between the numerous casting parameters and the microstructure of the ingots justifies the application of neural networks, which are known for mapping complex and non-linear systems. A feed forward ANN model with the resilient back-propagation learning algorithm and weight decay regularisation has been developed to relate the grain size to casting rate, meniscus level, casting temperature, water flow for the metal mould cooling and speed of wire for master alloy addition. The results obtained from the ANN are found to be consistent with the theoretical researches and experience from the foundry.     

A hybrid approach for processing parameters optimization of Ti-22Al-25Nb alloy during hot deformation using artificial neural network and genetic algorithm

In the present investigation, isothermal compression tests of Ti-22Al-25Nb alloy were carried out under various hot deformation conditions, including the deformation temperature range of 940–1060 °C and the strain rate range of 0.01–10 s^?1. The constitutive relationship of Ti-22Al-25Nb alloy was developed using artificial neural network (ANN). During training process, standard error back-propagation algorithm was employed in the network model using experimental data sets. Based on the fitness function obtained from established ANN model, the optimization model of hot processing parameters for Ti-22Al-25Nb alloy was successfully created using genetic algorithm (GA). The optimal results achieved from the integrated ANN and GA optimization model were tested by using processing map. Consequently, it can be suggested that the combined approach of ANN and GA provides a novel way with respect to the optimization of processing parameters in the field of materials science.