Abstract
An accurate thermal simulation of direct laser deposition (DLD) provides a basis for optimizing DLD process parameters. However, the input thermal parameters that significantly affect the simulation performance are difficult to be measured directly through experimental methods. This paper proposes an inverse method to identify the heat source parameters for DLD thermal simulations using support vector regression and genetic algorithm. Firstly, forward simulation errors of a single-track deposition under different heat source parameters are obtained. Secondly, a quantitative relationship between the heat source parameters and simulation errors is established using support vector regression (SVR), and the suboptimal heat source parameters are inversely identified by genetic algorithm (GA). Finally, a closed-loop forward-inverse iteration is further developed to improve the accuracy of the identified heat source parameters. The results indicate that the proposed inverse identification method gives a good agreement between the predicted and measured temperatures during DLD, and is an efficient method to accurately extract unknown input parameters.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Debroy, T., Wei, H.L., Zuback, J.S.: Additive manufacturing of metallic components—process, structure and properties. Prog. Mater Sci. 92(1), 112–224 (2018)
Graf, B., Ammer, S., Gumenyuk, A., et al.: Design of experiments for laser metal deposition in maintenance, repair and overhaul applications. Procedia CIRP 11(1), 245–248 (2013)
Niz’ev, V.G., Khomenko, M.D., Mirzade, F.K.: Process planning and optimisation of laser cladding considering hydrodynamics and heat dissipation geometry of parts. Quantum Electron. 48(8), 743–748 (2018)
Li, C., Liu, C., Li, S.: Numerical simulation of thermal evolution and solidification behavior of laser cladding AlSiTiNi Composite Coatings. Coatings 9(6), 391–409 (2019)
Fabrizia, C., Vittorio, A.: Simulation of laser-assisted directed energy deposition of aluminum powder: prediction of geometry and temperature evolution. Materials 12(13), 2100–2121 (2019)
Felipe, V., Jorge, A.R.-G., Magdalena, W.: Multiphysics simulation of laser-material interaction during laser powder disposition. Int. J. Adv. Manuf. Technol. 59(1), 1037–1045 (2012)
Bai, X.W., Zhang, H.O., Wang, G.L.: Improving prediction accuracy of thermal analysis for weld-based additive manufacturing by calibrating input parameters using IR imaging. Int. J. Adv. Manuf. Technol. 69(1), 1087–1095 (2013)
Iñigo, H., Alfredo, R.M., Magdalena, C.: Inconel 718 laser welding simulation tool based on a moving heat source and phase change. Procedia CIRP 74(1), 674–678 (2018)
Min, R.Y., Gaoyang, M., Jun, X.J.: Laser penetration welding of ship steel EH36: A new heat source and application to predict residual stress considering martensite phase transformation. Mar. Struct. 61(1), 256–267 (2018)
Li, P., Lu, H.: Hybrid heat source model designing and parameter prediction on tandem submerged arc welding. Int. J. Adv. Manuf. Technol. 62(5–8), 577–585 (2011)
Sun, J.M., Jakob, K., Thomas, N.: Effects of heat source geometric parameters and arc efficiency on welding temperature field, residual stress, and distortion in thin-plate full-penetration welds. Int. J. Adv. Manuf. Technol. 99(1–4), 497–515 (2018)
Song, K.J., Zhong, Z.H., Fang, K.: Analytic temperature field solution of dual laser welding heat sources and application in static recrystallization. Int. J. Adv. Manuf. Technol. 92(5–8), 1629–1641 (2017)
Imani, S.S., Zhang, Z.D., Ali, K.: Heat source model calibration for thermal analysis of laser powder-bed fusion. Int. J. Adv. Manuf. Technol. 106(7–8), 3367–3379 (2020)
Song, Y.L., Yu, C., Dai, D.G., et al.: Parameter optimization of heat source model for laser welding based on BP neural network and genetic algorithm. J. Plasticity Eng. 24(1), 218–222 (2017)
Zuo, P.F., Chen, S.Y., Wei, M.W.: Thermal behavior and grain evolution of 24CrNiMoY alloy steel prepared by pre-laid laser cladding technology. Opt. Laser Technol. 119(1), 105613–105624 (2019)
Ren, K., Chew, Y., Fuh, J.Y.H.: Thermo-mechanical analyses for optimized path planning in laser aided additive manufacturing processes. Mater. Des. 162(1), 80–93 (2019)
Cui, L.J., Zhang, S.H., Guo, S.R.: Temperature field simulation and experimental analysis of laser cladding 45 Steel. In: Proceedings of the 25th IEEE International Conference on Automation and Computing, Lancaster Univ, Lancaster, England, F. IEEE, 345 E 47th St, New York, NY 10017 USA (2019)
Goldak, J., Chakravarti, A., Bibby, M.: A new finite element model for welding heat sources. Metall. Trans. 15(1), 299–305 (1984)
Gu, W., Chen, W.P., Ko, C.-H.: Two smooth support vector machines for epsilon-insensitive regression. Comput. Optim. Appl. 70(1), 171–199 (2018)
Furui, AL-Absi, M.A., Lee, H.J.: Introduce a specific process of genetic algorithm through an example. In: Proceedings of the 10th International Conference on Information and Communication Technology Convergence Jeju, South Korea, F. IEEE, 345 E 47th St, New York, NY 10017 USA (2019)
Tian, F., Zhou, X.X., Yu, Z.H.: Power system transient stability assessment based on comprehensive SVM classification model and key sample set. Power Syst. Prot. Control 45(22), 1–8 (2017)
Chen, C.R., Lin, Y.J., Ou, H.: Study of heat source calibration and modelling for laser welding process. Int. J. Precis. Eng. Manuf. 19(8), 1239–1244 (2018)
Kong, L.W., Wang, Z.Z., Ye, C., Hou, L.: Research on developing technology of five-axis additive-subtractive hybrid machining center. Aeronaut. Manuf. Technol. 62(6), 53–59 (2019)
Acknowledgements
This project is supported by Innovation Method Program Funded by Ministry of Science and Technology of China (Grant No. 2020IM010100), National Natural Science Foundation of China (Grant No. 51905461, Grant No. 51975495).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Xu, Y. et al. (2022). Parameter Inverse Identification for Direct Laser Deposition Simulation Using Support Vector Regression and Genetic Algorithm. In: Tan, J. (eds) Advances in Mechanical Design. ICMD 2021. Mechanisms and Machine Science, vol 111. Springer, Singapore. https://doi.org/10.1007/978-981-16-7381-8_100
Download citation
DOI: https://doi.org/10.1007/978-981-16-7381-8_100
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-7380-1
Online ISBN: 978-981-16-7381-8
eBook Packages: EngineeringEngineering (R0)