喷射沉积坯体特征尺寸的神经网络模型建立与仿真

PDF(400 KB)

材料工程 ›› 2005, Vol. 0 ›› Issue (8) : 15-19.

扫码查看或转发全文

研究与应用

喷射沉积坯体特征尺寸的神经网络模型建立与仿真

曲迎东¹, 崔成松¹, 曹福洋¹, 陈善本², 李庆春¹

作者信息 +

Neural Network Modeling and Simulation of Characteristic Dimension of Spray Deposited Preform

QU Ying-dong¹, CUI Cheng-song¹, CAO Fu-yang¹, CHEN Shan-ben², LI Qing-chun¹

Author information +

文章历史 +

摘要

采用神经网络技术建立了沉积坯特征尺寸模型,该模型描述了喷射成形关键工艺参数对沉积坯尺寸的影响规律,模型输出的相对误差为6.58%,RMS(均方差)为0.372mm.模型的仿真结果给出了沉积坯尺寸的变化规律,其中稳态仿真结果可用于预先确定喷射实验中所采用的合适工艺参数;而动态仿真结果表明,雾化气体压力和沉积器平移速度对沉积坯几何尺寸都有较大影响,其中沉积器平移速度具有调节范围大的优点,成为调节沉积坯几何尺寸较合适的工艺参数.

Abstract

Neural network technology was applied to establish a modeling of the characteristic dimension of spray deposited preform, which described the influence of the spray forming parameters on the deposit dimension.The relative error of the modeling output was 6.58% and the RMS(root-mean-square) was 0.372mm. The relationship between deposit characteristic dimension and processing parameters was given by simulation results of the neural network modeling, and suitable parameters were defined according to simulation results of static spray forming processes; the simulation results of dynamic spray forming processes showed both atomizing gas pressure and translating speed of substrate were important factors influencing deposit characteristic dimension. Furthermore, it was preferred that the translating speed could be adjusted in a wide range, and became more suitable and effective parameter to control deposit dimension.

导出引用

曲迎东, 崔成松, 曹福洋, 陈善本, 李庆春. 喷射沉积坯体特征尺寸的神经网络模型建立与仿真[J]. 材料工程, 2005, 0(8): 15-19

QU Ying-dong, CUI Cheng-song, CAO Fu-yang, CHEN Shan-ben, LI Qing-chun. Neural Network Modeling and Simulation of Characteristic Dimension of Spray Deposited Preform[J]. Journal of Materials Engineering, 2005, 0(8): 15-19

中图分类号： TB331

参考文献

[1] XU Q, LAVERNIA E J. Spray deposition and melt atomization [C]. Bremen, Germany:SDMA, 2000. 17-36.
[2] CUI C S,LI Z Y,CAO F Y,et al. Modeling of the shape forming of composite roller [J]. Journal of Materials Science and Tech nology, 2000, 16(3):337-340.
[3] 范洪波,曹福洋,崔成松,等.喷射成形锭的三维形状模型及工艺参数预测[J].中国机械工程,1999,10(2):6-10.
[4] MUHANAD N, MEDWELL J O,GETHIN D T. Model for predicting buildup of cylindrical billets in osprey preform process [J]. Power Metallurgy, 1995, 38(3):214-220.
[5] PAYNE R D, MATTESON M A, MORAN A L. Application of neural networks in spray forming technology [J]. International Journal of Power Metallurgy, 1993, 29(4):345-351.
[6] PAYNE R D, REBIS R E, MORAN A L. Spray forming quality prediction via neural network[J]. Journal of Materials Engineeringand performance, 1993, 2(5):693-702.
[7] GHOSAL S, MEHROTRA R. Orthogonal moment operators for subpixel edge detection [J]. Pattern Recognition, 1993, 26(2):295-306.
[8] 曲迎东,崔成松,陈善本,等.一种基于Sobel-Zernike矩算子的快速亚像素边缘检测方法[J].光电工程,2003,30(5):59-61.
[9] 焦李成.神经网络理论系统[M].西安:西安电子科技大学出版社,1996.6-13.