| 研究生: |
范凱德 Ganesan, Venkatesh |
|---|---|
| 論文名稱: |
利用資料探勘技術獲得3D積層製造之過程參數優化 Optimal Process Parameters in 3D Additive Manufacturing by Data Mining |
| 指導教授: |
羅裕龍
Lo, Yu-Lung |
| 學位類別: |
碩士 Master |
| 系所名稱: |
工學院 - 機械工程學系 Department of Mechanical Engineering |
| 論文出版年: | 2018 |
| 畢業學年度: | 106 |
| 語文別: | 英文 |
| 論文頁數: | 74 |
| 中文關鍵詞: | 選擇性雷射燒熔 、最佳化 、替代系統 、資料探勘 、神經網路 |
| 外文關鍵詞: | Selective laser melting, Optimization, Surrogate model, Data mining, Neural network |
| 相關次數: | 點閱:211 下載:0 |
| 分享至: |
| 查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
選擇性雷射燒熔(SLM)是一種加法製造(AM)技術,用來逐層建立復雜的三維零件,使用雷射光束將金屬粉末熔合在一起。目前SLM面臨的最大挑戰之一是找到製造3D複雜零件的最佳加工參數。在這項研究中,將計算機模擬和統計技術結合起來,進而找出製造高密度/較少微裂痕/較低表面粗糙度的簡單三維零件的最佳參數。首先,建立復雜的模擬設計,為了使模擬尺寸達到最小,然後根據粉末粒度分佈建立模擬模型,提取所有熔池特徵。然後建立一個複雜的數據驅動模型(神經網絡)來預測不同參數下的熔池特徵,並建立代替模型來減少電腦模擬的運行時間。某些新的標準被提出,如利用表面粗糙度和溫度梯度來獲得最佳區域。最後得到利用SLM方式製造出密度為99.97%,材料為SS 316L的立方體。此外,利用我們所提出的方法,可以不用切開任何斷面來看熔池深度,而熔池深度就能被預測。因為我們發現熔池深度預測與實驗數據誤差小於3%。
Selective laser melting (SLM) is an additive manufacturing (AM) process that builds complex three-dimensional parts, layer by layer, using a laser beam to fuse fine metal powder together. Current one of the biggest challenges in SLM is to find the optimal process parameters for manufacturing the 3D complex parts. In this study, the method of integrating the computer simulation and statistical techniques to find the optimal process parameters for manufacturing the simple 3D parts with high density/less microcrack/less surface roughness would be proposed. At first, the complex simulation design is constructed to minimize the simulation size and then simulation model will be set up based on powder size distribution, laser power, scanning speed, layer thickness and etc. Finally, the melt pool characteristics like depth and peak temperature in this study will be extracted. And then build up a complex data-driven model (neural network) to predict all the melt pool characteristics with different parameters, and also by establishing the surrogate model in reducing the running time in a computer is implemented in this study. Some new criteria like surface roughness and temperature gradient are proposed to approach the optimal zone. As a result, the density of 99.97% of SS 316L in a cube made by SLM system is obtained. Additionally, based upon the proposed methodology the melt pool depth would be predicted without cutting any cross-section of the melt pool in experiments. It is found that the error between prediction and experimental data in melt pool depth is less than 3%.
Bourell, D. L., Leu, M. C., and Rosen, D. W., Roadmap for additive manufacturing - Identifying the future of freeform processing, The University of Texas at Austin, 2009.
Brierley, P. and Batty, P., "Data mining with neural networks - an applied example in understanding electricity consumption patterns" in Knowledge Discovery and Data Mining (ed Max Bramer), chapter 12, pp.240-303, IEE, ISBN 0 85296 767 5, 1999.
Chandrika, K., "Data mining and statistical inference in selective laser melting," The International Journal of Advanced Manufacturing Technology, vol. 86.5-8, pp.1659-1677, 2016.
Chandrika, K., "On the use of data mining techniques to build high-density, additively-manufactured parts," in Information Science for Materials Discovery and Design. Springer International Publishing, pp.141-155, 2016.
Chandrika, K. and Fan, Y.J., Regression with Small Data Sets: A Case Study using Code Surrogates in Additive Manufacturing (No. LLNL-TR-729017). Lawrence Livermore National Laboratory (LLNL), Livermore, CA, 2017.
Delgado, J., Ciurana, J., and Rodriguez, C., “Influence of process parameters on part quality and mechanical properties for DMLS and SLM with iron-based materials,” Int. J. Adv. Manuf. Technol. 60, pp. 601–610, 2012.
Fang, K.T., Li, R., and Sudjianto, A., Design and modelling for computer experiments, Chapman and Hall/CRC Press, Boca Raton, 2005.
Gusarov, A. B. and Kovalev, E.P., "Model of thermal conductivity in powder beds," Physical Review B, vol. 80, p. 024202, 2009.
Hodge, N. E., Ferencz, R. M., and Solberg, J. M., “Implementation of a thermomechanical model for the simulation of selective laser melting,” Comput. Mech., 54, pp. 33–51, 2014.
King, W. E., Barth, H. D., Castillo, V. M., Gallegos, G. F., Gibbs, J. W., Hahn, D. E., Kamath, C., and Rubenchik, A. M., “Observation of keyhole-mode laser melting in laser powder-bed fusion additive manufacturing,” J. Mater. Process Technol., vol. 214, pp. 2915–2925, 2014.
Kleijnen, J. P. C., Design and Analysis of Simulation Experiments, Springer, New York, NY, 2008.
Kruth, J., Badrossamay, M., Yasa, E., Deckers, J., Thijs, L., and Van Humbeeck, J., “Part and material properties in selective laser melting of metals,” In: Proceedings of 16th international symposium on electromachining (ISEM XVI), Shanghai, 2010.
Oehlert, G. W. and Freeman, W. H., A first course in design and analysis of experiments, Available from http://users.stat.umn.edu/gary/Book.html, 2000.
Sun, Yuwen and Hao, Mingzhong, "Statistical analysis and optimization of process parameters in Ti6Al4V laser cladding using Nd: YAG laser," Optics and Lasers in Engineering, vol. 50.7, pp. 985-995, 2012.
Shi, X., Ma, S., Liu, C., & Wu, Q. "Parameter optimization for Ti-47Al-2Cr-2Nb in selective laser melting based on geometric characteristics of single scan tracks," Optics & Laser Technology, vol. 90, pp. 71-79, 2017.
Shiflet, A. B. and Shiflet, G. W., Introduction to Computational Science: Modeling and Simulation for the Sciences, Princeton University Press, Princeton, NJ, 2006.
Spierings, A. and Levy, G., “Comparison of density of stainless steel 316L parts produced with selective laser melting using different powder grades,” In: Bourell D (ed) 20th annual international solid freeform fabrication symposium, an additive manufacturing conference. University of Texas at Austin, Austin, pp. 342–353, 2009.
Tran, H. C., Lo, Y. L., and Huang, M. H., "Analysis of Scattering and Absorption Characteristics of Metal Powder Layer for Selective Laser Sintering," IEEE-ASME Transactions on Mechatronics, vol. 22, pp. 1807-1817, 2017.
Tran, H. C. and Lo, Y. L. "A Heat Transfer Simulation with New Volumetric Heat source in Selective Laser Melting," Acceped by Journals of Material Processing Technology 2017.
Verhaeghe, F., Craeghs, T., Heulens, J., and Pandalaers, L., “A pragmatic model for selective laser melting with evaporation,” Acta Mater. Vol.57, pp.6006–6012, 2009.
Yadroitsev, I., Gusarov, A., Yadroitsava, I., and Smurov, I. "Single track formation in selective laser melting of metal powders," Journal of Materials Processing Technology, vol. 210.12, pp.1624-1631, 2010.
校內:2019-07-16公開