簡易檢索 / 詳目顯示

回結果列表
研究生： 王昱翔
Wang, Yu-Hsiang
論文名稱： 以機器學習製程圖引導雷射箔材列印製程中Inconel 625機械性質之評估
Using Machine Learning-Based Process Map to Guide Evaluation of Inconel 625 Mechanical Properties in Laser Foil Printing
指導教授： 洪嘉宏
Hung, Chia-Hung
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： 2026
畢業學年度： 114
語文別： 英文
論文頁數： 47
中文關鍵詞： 雷射箔材列印 、機器學習 、製程圖 、英高鎳合金625
外文關鍵詞： Laser Foil Printing, Machine Learning, Process Map, Inconel 625
相關次數： 點閱：5  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

    • Inconel 625 為一種廣泛應用於航太、能源與化工產業之鎳基超合金，具有優異之高溫強度與耐腐蝕性能。然而，相較於粉末式積層製造技術，其於新興之雷射箔材列印（Laser Foil Printing, LFP）製程中的熔池行為、製程穩定性與機械性質仍缺乏系統性研究。傳統製程圖多仰賴大量試誤實驗或多項式迴歸模型，難以有效描述雷射製程中高度非線性的熱流與熔池演化行為。本研究建立一套以機器學習為基礎之製程圖譜，用以引導 Inconel 625 於雷射箔材列印製程中的參數選擇與機械性質評估。透過 32 組單道熔池實驗資料，採用梯度提升回歸（Gradient Boosting Regression, GBR）模型分別預測熔池深度與寬度，其預測決定係數（R²）分別達 0.859 與 0.793，平均絕對誤差分別為 22.25 μm 與 19.83 μm。從實驗結果可看出比起二次與三次多項式迴歸模型，基於 GBR 預測結果建立之製程圖更加的準確，可清楚區分熔融不足（lack-of-fusion）、導熱模式（conduction）與鑰孔模式（keyhole）等不同熔池行為區域。依據製程圖，選擇三組導熱模式參數，其熔池深度與箔材厚度比（D/T）分別約為 1.3、1.5 與 1.7，並搭配一組鑰孔模式參數進行五層堆疊驗證與機械性質測試。導熱模式試片展現穩定且一致之熔池形貌，層間結合良好，孔隙率均低於 0.05%。拉伸測試結果顯示，導熱模式試片於 X 與 Y 方向皆具有穩定且優異之機械性質，其極限抗拉強度介於 888–988 MPa，降伏強度為 708–759 MPa，伸長率達 35–41%，顯示在導熱模式範圍內，熔池深度變化對機械性質影響有限。相較之下，鍵孔模式試片雖因晶粒細化而維持較高強度，但因大量氣孔生成、高角度晶界比例上升及顯著動態回復效應，導致伸長率顯著下降至 32–34%，呈現明顯之強度–延性取捨行為。電子背向散射繞射（EBSD）與 X 光繞射（XRD）分析顯示，導熱模式試片具有均勻之柱狀晶結構、適中的低角度晶界比例、明顯 <001> 纖維織構及足夠之位錯密度，為其優異強延性平衡之主要原因。本研究證實以少量單道實驗資料結合梯度提升回歸模型，即可有效建立高可信度之製程圖，並快速鎖定雷射箔材列印 Inconel 625 的穩定製程窗口。此機器學習導向之製程設計流程，不僅提升參數選擇效率，亦為高性能鎳基超合金之積層製造提供一條可靠且具工程實用價值的最佳化方法。

    Inconel 625 is one of the most extensively studied nickel-based superalloys in powder-based additive manufacturing. In contrast, its processing characteristics and resulting properties in the emerging foil-feedstock based Laser Foil Printing (LFP) process remain largely unexplored. This study develops a machine learning-based process map for LFP of Inconel 625 using 32 single-track experiments. The Gradient Boosting Regression (GBR) model achieved R^2 values of 0.859 (melt pool depth) and 0.793 (melt pool width) with mean absolute errors of 22.25 μm and 19.83 μm, respectively. Compared to second- and third-order polynomial regressions, GBR demonstrated markedly superior performance in capturing nonlinear melt pool dynamics and accurately delineating lack-of-fusion, conduction, and keyhole regimes, thereby enabling a high-fidelity process map. Three conduction-mode parameter sets targeting depth-to-foil thickness (D/T) ratios of ~1.3, 1.5, and 1.7, together with one keyhole-mode set, were selected from the GBR-based process map for multi-layer validation. Conduction-mode builds from the validation experiments exhibited uniform melt pools, excellent interlayer bonding, and ultra-low porosity (<0.05%). Tensile properties were outstanding and consistent across the conduction regime: ultimate tensile strength 888-988 MPa, yield strength 708-759 MPa, and elongation 35-41%. The keyhole-mode specimen retained comparable strength but exhibited significantly reduced elongation (32-34%) due to large gas pores, increased high-angle grain boundary fraction, and excessive recovery. EBSD and XRD analyses confirmed that conduction-mode samples possessed uniform columnar grains, moderate low-angle grain boundary fractions, strong <001> fiber texture, and sufficient dislocation density, collectively delivering superior strength-ductility balance. This work demonstrates that GBR-driven process mapping using minimal single-track data enables rapid and reliable identification of robust processing windows, providing an efficient parameter optimization pathway for producing defect-free, high-performance Inconel 625 components via Laser Foil Printing.

    Abstract i 中文摘要 ii Chapter 1 Introduction 1 1.1 Background and Motivation 1 1.2 Laser Foil Printing and its Advantages 1 1.3 Challenges in Process Window Identification for LFP 2 1.4 Machine Learning -Based Process Mapping 2 1.5 Research Objectives 3 1.6 Organization of This Thesis 3 Chapter 2 Experimental Setup and Methods 5 2.1 Laser Foil Printing Process and Materials 5 2.2 Laser Foil Printing System Configuration 6 2.3 Single Track Experiments and Data Collection 8 2.4 Machine Learning Model Development and Process Map Construction 8 2.5 Multi-Layer Fabrication and Tensile Specimen Preparation 11 2.6 Microstructural and Mechanical Charactrization 12 Chapter 3 Results and Discussion 13 3.1 Performance of Machine Learning Models and Process Map Validation 13 3.2 Melt Pool Morphology and Porosity in Multi-Layer Builds 18 3.3 Mechanical Properties and Crystallographic Analysis 21 3.3.1 Tensile Properties and Anisotropy 21 3.3.2 Crystallographic Texture and Grain Boundary Characteristics 23 3.3.3 Grain Size Distribution and Strenthening Mechanisms 25 3.3.4 Phase Constitution and Lattice Defect State 27 3.4 Summary of Results and Discussion 28 Chapter 4 Conclusions and Future Work 30 4.1 Conclusions 30 4.2 Contributions of This Study 31 4.3 Future Work 31 References 33

    [1] V. Shankar, K.B.S. Rao, S.L. Mannan, Microstructure and mechanical properties of Inconel 625 superalloy, Journal of Nuclear Materials 288 (2001) 222–232. https://doi.org/10.1016/S0022-3115(00)00723-6.
    [2] C. Chen, Y. Shen, H.L. Tsai, A foil based additive manufacturing technology for metal parts, Journal of Manufacturing Science and Engineering 139 (2017) 024501. https://doi.org/10.1115/1.4034139.
    [3] J.N. Ghoussoub, S. Utada, F. Pedraza, W.J.B. Dick-Cleland, Y.T. Tang, R.C. Reed, Alloy design for additive manufacturing: Early stage oxidation of nickel-based superalloys, Metallurgical and Materials Transactions A, 54 (2023) 1721–1729. https://doi.org/10.1007/s11661-002-06860-6.
    [4] C.T. Sims, N.S. Stoloff, W.C. Hagel, The Superalloys: Fundamentals and Applications, Wiley, New York, 1987.
    [5] T. DebRoy, H.L. Wei, J.S. Zuback, T. Mukherjee, J.W. Elmer, J.O. Milewski, A.M. Beese, A. Wilson-Heid, A. De, W. Zhang, Additive manufacturing of metallic components- process, structure, and properties, Progress in Materials Science, 92 (2018) 112-224, https://doi.org/10.1016/j.pmatsci.2017.10.001.
    [6] M. Sharifitabar, S. Khorshahian, M.S. Afarani, P. Kumar, N.K. Jain, High-temperature oxidation performance of Inconel 625 superalloy fabricated by wire arc additive manufacturing, Corrosion Science, 197 (2022) 110087, https://doi.org/10.1016/j.corsci.2022.110087.
    [7] E.R. Lewis, M.P. Taylor, B. Attard, N. Cruchley, A.P.C. Morrison, M.M. Attallah, S. Cruchley, Microstructural characterization and high-temperature oxidation of laser powder bed fusion processed Inconel 625, Material Letters, 311 (2022) 131582, https://doi.org/10.1016/j.matlet.2021.131582.
    [8] G. Hardjadinata, C.C. Doumanidis, Rapid prototyping by laser foil bonding and cutting: thermomechanical modeling and process optimization, Journal of Manufacturing Processes, 3 (2001) 108-119, https://doi.org/10.1016/S1526-6125(01)70126-0.
    [9] J. Dutkiewicz, L. Rogal, D. Kalita, K. Berent, B. Antoszewski, H. Danielewski, M.S. Weglowski, M. Lazinska, T. Durejko, T. Czujiko, Microstructure and properties of Inconel 625 fabricated using two types of laser metal deposition methods, Manufacturing Processes and Systems, 13 (2020) 5050, https://doi.org/10.3390/ma13215050.
    [10] M.A. Anam, Microstructure and mechanical properties of selective laser melted superalloy Inconel 625, Elsevier, (2018).
    [11] S.P. Kumar, S. Elangovan, R. Mohanraj, J.R. Ramakrishna, A review on properties of Inconel 625 and Inconel 718 fabricated using direct energy deposition, Materialstoday: Proceedings, 46 (2021) 7892-7906, https://doi.org/10.1016/j.matpr.2021.02.566.
    [12] Y.X. Wang, C.H. Hung, H. Pommerenke, S.H. Wu, T.Y. Liu, Fabrication of crack-free aluminum alloy 6061 parts using laser foil printing process, Rapid Prototyping Journal, 30 (2024) 722-732, https://doi.org/10.1108/RPJ-10-2023-0370.
    [13] J.P. Oliveira, A.D. LaLonde, J. Ma, Processing parameters in laser powder bed fusion metal additive manufacturing, Materials & Design, 193 (2020) 108762, https://doi.org/10.1016/j.matdes.2020.108762.
    [14] J.V. Gordon, S.P. Narra, R.W. Cunningham, H. Liu, H. Chen, R.M. Suter, J.L. Beuth, A.D. Rollett, Defect structure process maps for laser powder bed fusion additive manufacturing, 36 (2020) 101552, https://doi.org/10.1016/j.addma.2020.101552.
    [15] F. Imani, A. Gaikwad, M. Montazeri, P. Rao, H. Yang, E. Reutzel, Process mapping and in-process monitoring of porosity in laser powder bed fusion using layerwise optical imaging, 140 (2018) 101009, https://doi.org/10.1115/1.4040615.
    [16] C.H. Hung, C.W. Chu, T.L. Chang, T.C. Lin, Y.P. Chen, Effect of focal spot size on AlSi10Mg alloy parts fabricated by laser powder bed fusion: process window, mechanical properties, and microstructure, Journal of Alloys and Compounds, 977 (2024) 173338, https://doi.org/10.1016/j.jallcom.2023.173338.
    [17] H. Bikas, P. Stavropoulos, G. Chryssolouris, Additive manufacturing methods and modeling approached: a critical review, The International Journal of Advanced Manufacturing Technology, 83 (2016) 389-405, https://doi.org/10.1007/s00170-015-7576-2.
    [18] N. Baldi, A. Giorgetti, A. Polidoro, M. Palladino, I. Giovannetti, G. Arcidiacono, P. Citti, A supervised machine learning model for regression to predict melt pool formation and morphology in laser powder bed fusion, Applied Science, 14 (2024) 328, https://doi.org/10.3390/app14010328.
    [19] P. Akbari, F. Ogoke, N.Y. Kao, K. Meidani, C.Y. Yeh, W. Lee, A.B. Farimani, MeltpoolNet: melt pool characteristics prediction in metal additive manufacturing using machine learning, Additive Manufacturing, 55 (2022) 102817, https://doi.org/10.1016/j.addma.2022.102817.
    [20] I. Baturynska, K. Martinsen, Prediction of geometry deviations in additive manufactured parts: comparison of linear regression with machine learning algorithms, Journal of Intelligent Manufacturing, 32 (2021) 179-200, https://doi.org/10.1007/s10845-020-01567-0.
    [21] T. Turk, M.C. Leu, Experimental study for improving the productivity of laser foil printing, The International Journal of Advanced Manufacturing Technology, 125 (2023) 5149-5162, https://doi.org/10.1007/s00170-023-11076-y.
    [22] L. Wang, Y. Zhang, H.Y. Chia, W. Yan, Mechanism of keyhole pore formation in metal additive manufacturing, Computational Materials, 8 (2022), https://doi.org/10.1038/s41524-022-00699-6.
    [23] S.A. Khairallah, A.T. Anderson, A. Rubenchik, W.E. King, Laser powder-bed fusion additive manufacturing technology: physics of complex melt pool and formation mechanisms of pores, spatter, and denudation zone, Acta Materialia, 108 (2016) 36-45, https://doi.org/10.1016/j.actamat.2016.02.014.
    [24] J.H. Friedman, Greedy function approximation: a gradient boosting machine, The Annals of Statistics, 29 (2001) 1189-1232, https://www.jstor.org/stable/2699986.
    [25] J.H. Friedman, Stochastic gradient boosting, Computational Statistics & Data Analysis, 38 (2002) 367-378, https://doi.org/10.1016/S0167-9473(01)00065-2.
    [26] X. Zhu, F. Jiang, C. Guo, Z. Wang, T. Dong, H. Li, Prediction of melt pool shape in additive manufacturing based on machine learning methods, Optics & Laser Technology, 159 (2023) 108964, https://doi.org/10.1016/j.optlastec.2022.108964.
    [27] C.H. Hung, W.T. Chen, M.H. Sehhat, M.C. Leu, The effect of laser welding modes on mechanical properties and microstructures of 304L stainless steel parts fabricated by laser-foil-printing additive manufacturing, The International Journal of Advanced Manufacturing Technology, 112 (2021) 867-877, https://doi.org/10.1007/s00170-020-06402-7.
    [28] H. Liu, C.K.I. Tan, Y. Wei, S.H. Lim, C.J.J. Lee, Laser-cladding and interface evolutions of Inconel 625 alloy on low alloy steel substrate upon heat and chemical treatments, Surface and Coatings Technology, 404 (2020) 126607, https://doi.org/10.1016/j.surfcoat.2020.126607.
    [29] C. Li, R. White, X.Y. Fang, M. Weaver Y.B. Guo, Microstructure evaluation characteristics of Inconel 625 alloy from selective laser melting to heat treatment, Materials Science and Engineering: A, 705 (2017) 20-31, https://doi.org/10.1016/j.msea.2017.08.058.
    [30] F. Chen, Q. Wang, C. Zhang, Z. Huang, M. Jia, Q. Shen, Microstructures and mechanical behaviors of additive manufactured Inconel 625 alloys via selective laser melting and laser engineered net shaping, Journal of Alloys and Compounds, 917 (2022), 165572, https://doi.org/10.1016/j.jallcom.2022.165572.
    [31] J.Y. Li, J. Shen, S.Y. Dong, W. Dong, Y. Chen, Y.H. Zhao, Enhanced mechanical properties and deformation mechanisms in DED Inconel 625 via printing path switching, Materials Research Letters, 13 (2025) 523-532, https://doi.org/10.1080/21663831.2025.2476174.
    [32] Z. Tian, C. Zhang, D. Wang, W. Liu, X. Fang, D. Wellmann, Y. Zhao, Y. Tian, A review on laser powder bed fusion of Inconel 625 Nickel-based alloy, Applied Sciences, 10 (2020) 81, https://doi.org/10.3390/app10010081.
    [33] F. Lu, X. Li, Z. Li, X. Tang, H. Cui, Formation and influence mechanism of keyhole-induced porosity in deep-penetration laser welding based on 3D transient modeling, International Journal of Heat and Mass Transfer, 90 (2015) 1143-1152, https://doi.org/10.1016/j.ijheatmasstransfer.2015.07.041.
    [34] W.E. King, H.D. Barth, V.M. Castillo, G.F. Gallegos, J.W. Gibbs, D.E. Hahn, C. Kamath, A.M. Rubenchik, Observation of keyhole-mode laser melting in laser powder bed fusion additive manufacturing, Journal of Materials Processing Technology, 214 (2014) 2915-2925, https://doi.org/10.1016/j.jmatprotec.2014.06.005.
    [35] Z. An, J. Pan, Z. Han, K. Lu, J. Wang, Y. Fan, K. Zhang, H. Li, Microstructure and anisotropic mechanical properties of selective laser melted Inconel 625 with heat treatment regulation, Material Science and Engineering: A, 943 (2025) 148830, https://doi.org/10.1016/j.msea.2025.148830.
    [36] X. Zhang, Y. Liang, F. Yi, Q. Zhou, Z. Yan, J. Lin, Anisotropy in microstructure and mechanical properties of additively manufactured Ni-based GH4099 alloy, Journal of Materials Research and Technology, 26 (2023) 6552-6564, https://doi.org/10.1016/j.jmrt.2023.09.038.
    [37] Y. Chen, M. Xu, T. Zhang, J. Xie, K. Wei, S. Wang, L. Yin, P. He, Grain refinement and mechanical properties improvement of Inconel 625 alloy fabricated by directed energy deposition, Journal of Alloys and Compounds, 910 (2022) 164957, https://doi.org/10.1016/j.jallcom.2022.164957.
    [38] Y. Hu, X. Lin, Y. Li, Y. Ou, X. Gao, Q. Zhang, W. Li, W. Huang, Microstructural evolution and anisotropic mechanical properties of Inconel 625 superalloy fabricated by directed energy deposition, Journal of Alloys and Compounds, 870 (2021) 159426, https://doi.org/10.1016/j.jallcom.2021.159426.
    [39] B. Dubiel, J. Sieniawski, Precipitates in additively manufactured Inconel 625 superalloy, Materials, 12 (2019) 1144, https://doi.org/10.3390/ma12071144.
    [40] S.K. Rai, A. Kumar, V. Shankar, T. Jayakunar, K.B.S. Rao, B. Raj, Characterization of microstructures in Inconel 625 using X-ray diffraction peak broadening and lattice parameter measurements, Scripta Materialia, 51 (2004) 59-63, https://doi.org/10.1016/j.scriptamat.2004.03.017.
    [41] L. Gao, Y. Chen, X. Zhang, S.R. Agnew, A.C. Chuang, T. Sun, Evaluation of dislocations during the rapid solidification in additive manufacturing, Nature Communications, 16 (2025) 4696, https://doi.org/10.1038/s41467-025-59988-5.
    [42] A. Muiruri, M. Maringa, W. D. Preez, Evaluation of Dislocation Densities in Various Microstructures of Additively Manufactured Ti6Al4V (Eli) by the Method of X-ray Diffraction, Materials, 13(23) (2020) 5255, https://doi.org/10.3390/ma13235355

    下載圖示
    校外：立即公開
    QR CODE