基于Trainrp算法建立锆基合金HANA-4(Zr- 1.5Nb-0.4Sn-0.2Fe-0.1Cr)和HANA-6(Zr-1.1Nb-0.05Cu)退火参数与硬度的BP神经网络预测模型.模型输入单元为合金成分、退火温度和退火时间,输出单元为硬度.神经网络为3-7-1结构,动量因子和学习速率均为0.6.以实验结果验证网络的可靠性.预测结果表明,相对误差为7％,相对拟合率R值为0.98534.该模型可为锆基合金退火参数的制定提供参考.网络敏感性分析表明:退火温度和退火时间对网络的精度影响很大,而合金成分则影响很小.
参考文献
| [1] | 彭德全,白新德,周庆刚,刘晓阳,余任泓,邓平晔,张岱岚.高能氪离子轰击对纯锆耐蚀性的影响[J].稀有金属材料与工程,2005(01):107-111. |
| [2] | 袁改焕,李恒羽,王德华.锆材在核电站的应用及前景[J].稀有金属快报,2007(01):14-16. |
| [3] | 胡凌;肖大武;李英雷.[J].高能量密度物理,2009(01):5. |
| [4] | Jung YangI1;Lee Myung Ho;Kim Hyun Gil et al.[J].Journal of Alloys and Compounds,2009,479:423. |
| [5] | Bahrami A;Anijdan SHM;Hosseini HRM;Shafyei A;Narimani R .Effective parameters modeling in compression of an austenitic stainless steel using artificial neural network[J].Computational Materials Science,2005(4):335-341. |
| [6] | 李国勇.神经模糊控制理论及应用[M].北京:电子工业出版社,2009:18. |
| [7] | Yazdanmehr, M;Anijdan, SHM;Bahrami, A .Using GA-ANN algorithm to optimize soft magnetic properties of nanocrystalline mechanically alloyed Fe-Si powders[J].Computational Materials Science,2009(4):1218-1221. |
| [8] | Mirzadeh H;Najafizadeh A .[J].Materials Characterization,2008,59:1650. |
| [9] | Sumantra Mandal;P. V. Sivaprasad;S. Venugopal;K. P. N. Murthy .Artificial neural network modeling to evaluate and predict the deformation behavior of stainless steel type AISI 304L during hot torsion[J].Applied Soft Computing,2009(1):237-244. |
| [10] | Mousavi Anijdan S H;Madaah-Hosseini H R;Bahrami A .[J].Materials & Design,2007,28:609. |
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%