为建立BT20钛合金(Ti6Al2Zr1Mo1V)的流动应力预测模型,通过热压缩试验获得其流动应力曲线,并对BP神经网络的算法进行改进,实现BT20钛合金的流动应力的准确预测.研究表明:采用人工神经网络(ANNs)预测流动应力不需要考虑材料特性,有效地避免了传统经验或回归本构模型由于假设和简化带来的误差,并且神经网络具有很强的非线性离散数据处理能力,选取合适的网络模型(主要是隐层数及隐层单元数),输入足够的样本数据对神经网络进行训练即可获得令人满意的预测精度;采用含两个中间层,网络结构为3×16×14×1的改进BP神经网络模型能够较为准确的预测BT20钛合金的流动应力,计算效率较高,该预测模型可作为其塑性成形过程有限元模拟的本构关系.
参考文献
| [1] | E. S. Puchi .Constitutive equations for commercial-purity aluminum deformed under hot-working conditions[J].Journal of engineering materials and technology,1995(1):20-27. |
| [2] | J. Y. Sheikh-Ahmad;J. A. Bailey .A constitutive model for commercially pure titanium[J].Journal of engineering materials and technology,1995(2):139-144. |
| [3] | 王少林;阮雪榆;俞新陆 等.金属高温本构方程的研究[J].上海交通大学学报,1996,30(08):20-24. |
| [4] | Gronostajski Z.; .The constitutive equations for FEM analysis[J].Journal of Materials Processing Technology,2000(1/3):40-44. |
| [5] | Liang Riqiang;Khan Akhtar S .A critical review of experimental results and constitutive models for BCC and FCC metals over a wide range of strain rates and temperatures[J].Inter J Plastic,1999,15:963-980. |
| [6] | McQueen HJ.;Ryan ND. .Constitutive analysis in hot working[J].Materials Science & Engineering, A. Structural Materials: Properties, Misrostructure and Processing,2002(1-2 Special Issue SI):43-63. |
| [7] | Rao K P;Prasad Y K D V .Neural network approach to flow stress evaluation in hot deformation[J].Journal of Materials Processing Technology,1995,53:552-566. |
| [8] | Liu Qingbin;Ji Zhong;Liu Maobao et al.Acquiring the constitutive relationship for a thermal viscoplastic material using an artificial neural network[J].Journal of Materials Processing Technology,1996,62:206-210. |
| [9] | R. H. Wu;J. T. Liu;H. B. Chang;T. Y. Hsu;X. Y. Ruan .Prediction of the flow stress of 0.4C-1.9Cr-1.5Mn-1.0Ni-0.2Mo steel during hot deformation[J].Journal of Materials Processing Technology,2001(2/3):211-218. |
| [10] | 洪权,张振祺.Ti-6Al-2Zr-1M0-1V合金的热变形行为[J].航空材料学报,2001(01):10-12. |
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%