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-3A1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.
参考文献
| [1] | 赵永庆.高温钛合金研究[J].钛工业进展,2001(01):33-39. |
| [2] | Froes F H;Laplan I L.Titanium Science and Technology[M].San Diego:TMS Minerals,Metals,Materials Press,1992:77-88. |
| [3] | Evans WJ. .Optimising mechanical properties in alpha+beta titanium alloys[J].Materials Science & Engineering, A. Structural Materials: Properties, Misrostructure and Processing,1998(1/2):89-96. |
| [4] | Ankem;Greene C A .[J].Materials Science and Engineering,1999,A63:127-131. |
| [5] | 姚泽坤,郭鸿镇,苏祖武,孙开本,徐永超,曹晓卿.热力参数对α+β两相钛合金再结晶百分数和力学性能的影响[J].稀有金属材料与工程,2000(05):340-343. |
| [6] | 朱知寿,钟鸣,储俊鹏,王庆如,全桂彝,王韦琪.β-21S钛合金薄板材的热处理工艺和冷成形性能研究[J].稀有金属材料与工程,2000(01):46-49. |
| [7] | 焦李成.神经网络系统理论[M].西安:西安电子科技大学出版社,1995:79. |
| [8] | Jan K;Roman K .[J].Journal of Materials Processing Technology,2002,127:115-121. |
| [9] | Calcaterra S;Campana G;Tomesani L .[J].Journal of Materials Processing Technology,2000,104:74-80. |
| [10] | Song R G;Zhang Q Z .[J].Materials Science and Engineering,2001,C17:133-137. |
| [11] | Abhijit M;Sudip N B .[J].Nuclear Engineering and Design,1997,178:1-11. |
| [12] | Liu Z Y;Wang W D;Gao W .[J].Journal of Materials Processing Technology,1996,57:332-336. |
| [13] | Malinov S;Sha W;Mckeown J J .[J].COMPUTATIONAL MATERIALS SCIENCE,2001,21:375-394. |
| [14] | Seibi A;Alawi S M Owan .[J].Engineering Fracture Mechanics,1997,56(03):311-319. |
| [15] | Song R G;Zhang Q Z .[J].Journal of Materials Processing Technology,2001,117(1-2):84-88. |
| [16] | Chung J S;Huang S M.[J].Journal of Materials Processing Technology,1998:136-143. |
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%