采用硬度、电导率测量和X射线物相分析技术研究了铝锌镁钪合金铸锭均匀化处理过程中组织和性能的变化规律,结果表明,铸态合金过饱和程度高,合金电导率较低而硬度较高;铸锭均匀化处理过程中,随均匀化温度升高,T相先大量析出后逐渐回溶入固溶体基体,基体固溶度先降后升,合金电导率先升后降,合金硬度则先降后升,更高温度均匀化,晶粒粗化,硬度又下降.在此基础上,运用Matlab神经网络工具箱进行BP神经网络设计,采用改进的BP网络Levenberg-Marquardt算法对权值和阈值进行训练,建立了铝锌镁钪合金均匀化工艺参数到性能预测的BP神经网络模型.实验验证结果表明,该模型计算值与实验值吻合精度高,泛化检测点电导率相对误差≤±0.23%,硬度相对误差≤±1.90%,可有效预测和分析均匀化工艺对铝锌镁钪合金性能的影响,为优化均匀化工艺、降低试验成本提供一种新方法.
参考文献
| [1] | 尹志民;潘青林;姜峰.钪和含钪合金[M].长沙:中南大学出版社,2007:421-445. |
| [2] | 刘晓涛,董杰,崔建忠,赵刚.高强铝合金均匀化热处理[J].中国有色金属学报,2003(04):909-913. |
| [3] | JOSEPH H M;HYMAN R .Influence of nonequilibrium second-phase particles formed during solidification upon the mechanical behavior of an aluminium alloy[J].Metallurgical Transactions,1971,2(02):427-432. |
| [4] | 李松瑞;周善初.金属热处理[M].长沙:中南大学出版社,2005:9-26. |
| [5] | I. A. Basheer;M. Hajmeer .Artifical neural networks: fundamentals, computing, design, and application[J].Journal of Microbiological Methods,2000(1):3-31. |
| [6] | S. Malinov;W. Sha .Software products for modelling and simulation in materials science[J].Computational Materials Science,2003(2):179-198. |
| [7] | Reddy NS;Rao AKP;Chakraborty M;Murty BS .Prediction of grain size of Al-7Si alloy by neural networks[J].Materials Science & Engineering, A. Structural Materials: Properties, Misrostructure and Processing,2005(1/2):131-140. |
| [8] | 王海涛,韩恩厚,柯伟.基于人工神经网络模型的铝合金大气腐蚀的预测[J].中国腐蚀与防护学报,2006(05):272-274,281. |
| [9] | 周古为,郑子樵,李海.基于人工神经网络的7055铝合金二次时效性能预测[J].中国有色金属学报,2006(09):1583-1588. |
| [10] | 曾可令;叶卫平.计算机在材料科学与工程中的应用[M].武汉:武汉理工大学出版社,2004:210-241. |
| [11] | KESAVRAJ R;TOCK R W;Narayan R S .A neural-network-based model approach for density of high-weight esters used as plasticizers[J].Advances in Polymer Technology,1995,14(03):215-225. |
| [12] | 童长仁,李明周,吴金财,刘道斌.基于BP网络逆映射的铝酸钠溶液软测量模型[J].中国有色金属学报,2008(05):917-922. |
| [13] | ROBERT H N.Theory of the backpropagation neura network[A].Washington DC:IEEE,1989:593-605. |
| [14] | 飞思科技产品研发中心.神经理论和MATLAB7实现[M].北京:电子工业出版社,2005:99108. |
| [15] | S. Malinov;W. Sha;J. J. McKeown .Modelling the correlation between processing parameters and properties in titanium alloys using artificial neural network[J].Computational Materials Science,2001(3):375-394. |
上一张
下一张
上一张
下一张
计量
- 下载量()
- 访问量()
文章评分
- 您的评分：
-
10%
-
20%
-
30%
-
40%
-
50%