Microstructure based on selective laser melting and mechanical properties prediction through artificial neural net

被引：0
作者：
Yang T. [1 ]
Zhang P. [1 ]
Yin Y. [1 ]
Liu W. [1 ]
Zhang R. [2 ,3 ]
机构：
[1] State Key Laboratory of Advanced Processing and Recycling of Nonferrous Metals, Lanzhou University of Technology, Lanzhou
[2] China Iron & Steel Research Institute Group, Beijing
[3] Hardware Knife Cut Industrial Technology Research Institute Yangjiang, Yangjiang
来源：
Hanjie Xuebao/Transactions of the China Welding Institution | 2019年 / 40卷 / 06期
关键词：
18Ni300; Artificial network; Microstructure; Selective laser melting;
D O I：
10.12073/j.hjxb.2019400162
中图分类号：
学科分类号：
摘要：
Selective laser melting has been applied to fabricate 18Ni300. SEM is used to observe dendritic growth orientation and solidification structure. Artificial neural network is applied to rank the respective importance of laser power, scanning speed and scanning space for mechanical properties, while BP neural net with improved weight by genetic algorithm is applied to the prediction of tensile property. Results show that the main structure of the specimen is columnar dendritic crystals with significant epitaxial growth. The orientation of the growth is determined by the solidification condition at the bottom of the molten pool. CET can easily take place on the top of the melting pool. Meanwhile, there is transition zone in other places contributed by the thermo capillary convection. The result of the importance prediction by artificial neural network shows: They order from high to low is laser power, scanning speed and scanning space.Since the prediction results agree with the actual ones, BP neural net can effectively predict actual results. The determination coefficient R2 = 0.73. © 2019, Editorial Board of Transactions of the China Welding Institution, Magazine Agency Welding. All right reserved.
引用
收藏
页码：100 / 106
页数：6
相关论文
共 16 条
  • [1] Yin H., Bai P., Liu B., Et al., The research status and development trend of selective laser melting, Hot Working Technology, 39, 1, pp. 140-144, (2010)
  • [2] Shen Y., Wu P., Gu D., Et al., Laser sinter experiment using Ni-CuSn mixed powder, Transactions of the China Welding Institution, 26, 2, pp. 73-76, (2005)
  • [3] Suryawanshi J., Prashanth K.G., Scudino S., Et al., Simultaneous enhancements of strength and toughness in an Al-12Si alloy synthesized using selective laser melting, Acta Materialia, 115, pp. 285-294, (2016)
  • [4] Sander J., Hufenbach J., Giebeler L., Et al., Microstructure and properties of FeCrMoVC tool steel produced by selective laser melting, Materials & Design, 89, pp. 335-341, (2016)
  • [5] Raghavan N., Dehoff R., Pannala S., Et al., Numerical modeling of heat-transfer and the influence of process parameters on tailoring the grain morphology of IN718 in electron beam additive manufacturing, Acta Materialia, 112, pp. 303-314, (2016)
  • [6] Wang D., Yang Y., Wu W., Selective fiber laser melting parameter optimization using 316L powder, Chinese Journal of Lasers, 36, 12, pp. 3233-3239, (2009)
  • [7] Yan C., Yang L., Dai W., Et al., The parameter influence on surface quality of selective laser melting using 316L powder, Hot Working Technology, 20, pp. 170-174, (2017)
  • [8] Zhang A., Gao F., Niu X., Et al., Rail way flash welding joint grey spot area prediction using BP neural network, Transactions of the China Welding Institution, 37, 11, pp. 11-14, (2016)
  • [9] Zhou J., Xu Y., Cao J., Et al., Optimization design of high pulse power supply using BP neural network and genetic algorithm, Transactions of the China Welding Institution, 37, 4, pp. 9-13, (2016)
  • [10] Wang C., Hu B., 18Ni300 endurance property prediction using genetic algorithm, Tool Technology, 50, 4, pp. 61-64, (2016)
12