A multi-objective optimization based on machine learning for dimension precision of wax pattern in turbine blade manufacturing

Abstract

Wax pattern fabrication in the investment casting of hollow turbine blades directly determines the dimension accuracy of subsequent casting, and therefore significantly affects the quality of final product. In this work, we develop a machine learning-based multi-objective optimization framework for improving dimension accuracy of wax pattern by optimizing its process parameters. We consider two optimization objectives on the dimension of wax pattern, i.e., the surface warpage and core offset. An active learning of Bayesian optimization is employed in data sampling to determine process parameters, and a validated numerical model of injection molding is used to compute objective results of dimension under varied process parameters. The collected dataset is then leveraged to train different machine learning models, and it turns out that the Gaussian process regression model performs best in prediction accuracy, which is then used as the surrogate model in the optimization framework. A genetic algorithm is employed to produce a non-dominated Pareto front using the surrogate model in searching, followed by an entropy weight method to select the most optimal solution from the Pareto front. The optimized set of process parameters is then compared to empirical parameters obtained from previous trial-and-error experiments, and it turns out that the maximum and average warpage results of the optimized solution decrease 26.0% and 20.2%, and the maximum and average errors of wall thickness compared to standard part decrease from 0.22 mm and 0.051 7 mm using empirical parameters to 0.10 mm and 0.035 6 mm using optimized parameters, respectively. This framework is demonstrated capable of addressing the challenge of dimension control arising in the wax pattern production, and it can be reliably deployed in varied types of turbine blades to significantly reduce the manufacturing cost of turbine blades.

Keywords

Hollow turbine blade / Wax pattern fabrication / Dimension control / Multi-objective optimization / Machine learning / Numerical simulation

References

[1] Zhang X, Bu K. B-spline contour curve approximation and deformation analysis of complex ceramic core. Proc I Mech E Part B J Eng Manuf, 2018, 233(6): 1663-1673.

[2] Lu Z, et al. Review of main manufacturing processes of complex hollow turbine blades. Virtual Phys Prototy, 2013, 8(2): 87-95.

[3] Petes F, Voigt R, Blair M (1996) Dimensional repeatabililty of investment castings. In: 9th world conference on investment casting. San Francisco

[4] Jiang S, Zhang D, Wang W, et al. Estimation of displacement field for turbine blade profile based on reverse engineering in investment casting. Spec Cast Nonferrous Alloys, 2009, 29(1): 13-15.

[5] Wiens K, Eng P (2013) Airfoil thickness as a life limiting factor of gas turbine blades. In: 20th symposium of the industrial application of gas turbines committee. Banff, Alberta, Canada. pp 1–14

[6] Chauhan AS, Pradyumna R (2015) Shrinkage evaluation in a stepped wax pattern—a simulation approach. In: International conference on mechanical engineering design and analysis. Doha, Qatar

[7] Yi CC, Yui JL, Shi CT, et al. Core deflection in plastics injection molding. Polym-Plast Technol Eng, 2011, 50(9): 863-872.

[8] Zhang DH, Cheng YY, Jiang RS, et al. Deformation simulation of investment casting and die cavity optimization of turbine blade. turbine blade investment casting die technology, 2018, Berlin, Heidelberg: Springer p105-171.

[9] Cui K, Wang W, Jiang R, et al. A wall-thickness compensation strategy for wax pattern of hollow turbine blade. Chin J Aeronaut, 2019, 32(8): 1982-1993.

[10] Zhang J, Wang S, Zhou H, et al. Manufacturable casting parts design with topology optimization of structural assemblies. Proc I Mech E Part B J Eng Manuf, 2022, 236(4): 401-412.

[11] Mondal NR, Rafiquzzaman M, Siddique MA, et al. Optimization of investment casting parameters to improve the mechanical properties by Taguchi method. Am J Mech Ind Eng, 2020, 5(5): 64-70.

[12] Vladimír K, Pavel N, Antonín Z, et al. Requirements for hybrid technology enabling the production of high-precision thin-wall castings. Materials, 2022, 15(11): 3805.

[13] Vdovin RA, Smelov VG, Sufiiarov VS, et al. Designing of the digital casting process for the gas turbine engine blades with a single-crystal structure. IOP Conf Ser Mater Sci Eng, 2018, 441(1): 012058.

[14] Torres-Carrillo S, Siller HR, Vila CC, et al. Environmental analysis of selective laser melting in the manufacturing of aeronautical turbine blades. J Clean Prod, 2020, 246(10): 119068.

[15] Chauhan AS, Anirudh B, Satyanarayana A, et al. FEA optimization of injection parameters in ceramic core development for investment casting of a gas turbine blade. Mater Today Proc, 2020, 26: 2190-2199.

[16] BakharevA FZ, Costa F, et al. Prediction of core shift effects using mold filling simulation. ANTEC-Conf Proc, 2004, 1: 621-625.

[17] Chauhan AS, Walale A, Satyanarayana A, et al. Analysis of shrinkage & warpage in ceramic injection molding of HPT vane leading edge core of a gas turbine casting. Mater Today Proc, 2018, 5(9): 19471-19479.

[18] He B, Wang DH, Li F, et al. Simulation study on wax injection for investment casting. Adv Mater Res, 2014, 834: 1575-1579.

[19] Oktem H, Erzurumlu T, Uzman I, et al. Application of Taguchi optimization technique in determining plastic injection molding process parameters for a thin-shell part. Mater Des, 2007, 28(4): 1271-1278.

[20] Cerda-Flores SC, Rojas-Punzo AA, Nápoles-Rivera F, et al. Applications of multi-objective optimization to industrial processes: a literature review. Processes, 2022, 10(1): 133.

[21] Samson C, Murugan K, Abhra R, et al. Optimization of process parameters using response surface methodology: a review. Mater Today Proc, 2021, 37: 1301-1304.

[22] Schmidt J, Marques M, Botti S, et al. Recent advances and applications of machine learning in solid-state materials science. NPJ Comput Mater, 2019, 5(1): 83.

[23] Xu J, Tan W, Li T. Predicting fan blade icing by using particle swarm optimization and support vector machine algorithm. Comput Electr Eng, 2020, 87: 106751.

[24] Shi D, Sun L, Xie Y. Off-design performance prediction of a S-CO₂ turbine based on field reconstruction using deep-learning approach. Appl Sci, 2020, 10(14): 4999.

[25] Jamil TAMT, Roslan SAH, Rasid ZA, et al. Experimental and simulation of aerodynamic performance of the small-scale wind turbine blades for usage in Malaysia. IOP Conf Ser Mater Sci Eng, 2021, 1092(1): 012023.

[26] Akolekar HD, Waschkowski F, Zhao Y, et al. Transition modeling for low pressure turbines using computational fluid dynamics driven machine learning. Energies, 2021, 14(15): 4680.

[27] Hamedi M, Farzaneh A. Optimization of dimensional deviations in wax patterns for investment casting. J Comput Appl Mech, 2014, 45(1): 23-28.

[28] Shahane S, Aluru N, Ferreira P, et al. Optimization of solidification in die casting using numerical simulations and machine learning. J Manuf Proc, 2020, 51: 130-141.

[29] Ezhilsabareesh K, Rhee SH, Samad A. Shape optimization of a bidirectional impulse turbine via surrogate models. Eng Appl Comput Fluid Mech, 2018, 12(1): 1-12.

[30] Herman A, Kubelková I, Vrátn O. New use of instruments for more accurate wax pattern blade segment production. Arch Foundry Eng, 2019, 19(2): 101.

[31] Zhang XH, Gao HS, Yu KH, et al. Crystal orientation effect and multi-fidelity optimization of a solid single crystal superalloy turbine blade. Comp Mater Sci, 2018, 149: 84-90.

[32] Li C, de Celis Leal DR, Rana S, et al. Rapid Bayesian optimisation for synthesis of short polymer fiber materials. Sci Rep, 2017, 7(1): 1-10.

[33] Kikuchi S, Oda H, Kiyohara S, et al. Bayesian optimization for efficient determination of metal oxide grain boundary structures. Phys B Condens Matter, 2018, 532: 24-28.

[34] Xue D, Balachandran PV, Hogden J, et al. Accelerated search for materials with targeted properties by adaptive design. Nat Commun, 2016, 7(1): 1-9.

[35] Vahid A, Rana S, Gupta S, et al. New bayesian-optimization-based design of high-strength 7xxx-series alloys from recycled aluminum. JOM, 2018, 70(11): 2704-2709.

[36] Herbol HC, Hu W, Frazier P, et al. Efficient search of compositional space for hybrid organic–inorganic perovskites via Bayesian optimization. NPJ Comput Mater, 2018, 4(1): 51.

[37] Herbol HC, Poloczek M, Clancy P, et al. Cost-effective materials discovery: Bayesian optimization across multiple information sources. Mater Horiz, 2020, 7(8): 2113-2123.

Funding

National Key Research and Development Program of China(2019YFA0705302)

National Science and Technology Major Project “Aeroengine and Gas Turbine” of China(2017-VII-0008-0102)