Artificial intelligence for springback compensation with electric vehicle motor component
Source abstract
Abstract
Hairpin, which is used for a drive motor of electric vehicle, is formed from copper coil coated with very thin enamel layer to its desired shape by successive forming processes. The unavoidable springback of hairpin forming has induced critical problems in fabricating the drive motor of electric vehicle that is directly related to the product performance of the motor. In this research, a new method for the springback compensation for hairpin forming was proposed by using artificial intelligence (AI). The AI model calculates the eight springback parameters with respect to the given inputs: material properties, cross-sectional dimension, and die spotting. The training dataset for AI model is based on finite element simulation. Material properties of copper and thin enamel layer were characterized by combined methods: newly designed specimen, nanoindentation, and inverse analysis. For springback compensation, the die spotting value representing the gap between die and punch (or punch stroke) was optimized by using simplex optimization algorithm with the trained AI model. The results showed that the springback could be effectively compensated with the proposed method in a few seconds.
Source: expertdata · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Metal Forming Simulation Techniques · Metallurgy and Material Forming · Aluminum Alloy Microstructure Properties
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (34)
Show source-provided references
1. Joo G, Huh H, Kwon J (2019) Evaluation of rate-dependent hardening behaviors of AHSS sheets with novel tension and compression test devices. J Mater Process Technol 270:365–37910.1016/j.jmatprotec.2019.03.011 ↗
2. Choi HS, Yoon JW, Lee JS, Kim GH (2019) A Springback prediction of 1.5 GPa grade steel in roll forming process for automotive sill-side inner component. In: Key Engineering Materials, Trans Tech Publ, p. 267–27410.4028/www.scientific.net/KEM.794.267 ↗
3. Sumikawa S, Ishiwatari A, Hiramoto J (2017) Improvement of springback prediction accuracy by considering nonlinear elastoplastic behavior after stress reversal. J Mater Process Technol 241:46–5310.1016/j.jmatprotec.2016.11.005 ↗
4. Eggertsen P-A, Mattiasson K (2011) On the identification of kinematic hardening material parameters for accurate springback predictions. IntJ Mater Form 4:103–12010.1007/s12289-010-1014-7 ↗
5. Ghaei A, Green D, Aryanpour A (2015) Springback simulation of advanced high strength steels considering nonlinear elastic unloading–reloading behavior. Mater Des 88:461–47010.1016/j.matdes.2015.09.012 ↗
6. Taherizadeh A, Green DE, Yoon JW (2015) A non-associated plasticity model with anisotropic and nonlinear kinematic hardening for simulation of sheet metal forming. Int J Solids Struct 69:370–38210.1016/j.ijsolstr.2015.05.013 ↗
7. Yoshida F, Uemori T (2003) A model of large-strain cyclic plasticity and its application to springback simulation. Int J Mech Sci 45:1687–170210.1016/j.ijmecsci.2003.10.013 ↗
8. Barlat F, Vincze G, Grácio J, Lee MG, Rauch E, Tomé C (2014) Enhancements of homogenous anisotropic hardening model and application to mild and dual-phase steels. Int J Plast 58:201–21810.1016/j.ijplas.2013.11.002 ↗
9. Chen S, Liao J, Xiang H, Xue X, Pereira AB (2021) Pre-strain effect on twist springback of a 3D P-channel in deep drawing. J Mater Process Technol 287:11622410.1016/j.jmatprotec.2019.05.005 ↗
10. Badr OM, Rolfe B, Zhang P, Weiss M (2017) Applying a new constitutive model to analyse the springback behaviour of titanium in bending and roll forming. Int J Mech Sci 128:389–40010.1016/j.ijmecsci.2017.05.025 ↗
11. Lee JY, Lee JW, Lee MG, Barlat F (2012) An application of homogeneous anisotropic hardening to springback prediction in pre-strained U-draw/bending. Int J Solids Struct 49:3562–357210.1016/j.ijsolstr.2012.03.042 ↗
12. Karafillis A, Boyce M (1992) Tooling design accommodating springback errors. J Mater Process Technol 32:499–50810.1016/0924-0136(92)90206-8 ↗
13. Karafillis AP, Boyce MC (1996) Tooling and binder design for sheet metal forming processes compensating springback error. Int J Mach Tools Manuf 36:503–52610.1016/0890-6955(95)00023-2 ↗
14. Gan W, Wagoner R (2004) Die design method for sheet springback. Int J Mech Sci 46:1097–111310.1016/j.ijmecsci.2004.06.006 ↗
15. Lingbeek R, Huetink J, Ohnimus S, Petzoldt M, Weiher J (2005) The development of a finite elements based springback compensation tool for sheet metal products. J Mater Process Technol 169:115–12510.1016/j.jmatprotec.2005.04.027 ↗
16. Yang XA, Ruan F (2011) A die design method for springback compensation based on displacement adjustment. Int J Mech Sci 53:399–40610.1016/j.ijmecsci.2011.03.002 ↗
17. Mole N, Cafuta G, Štok B (2014) A 3D forming tool optimisation method considering springback and thinning compensation. J Mater Process Technol 214:1673–168510.1016/j.jmatprotec.2014.03.017 ↗
18. Komgrit L, Hamasaki H, Hino R, Yoshida F (2016) Elimination of springback of high-strength steel sheet by using additional bending with counter punch. J Mater Process Technol 229:199–20610.1016/j.jmatprotec.2015.08.029 ↗
19. Palaniswamy H, Ngaile G, Altan T (2004) Optimization of blank dimensions to reduce springback in the flexforming process. J Mater Process Technol 146:28–3410.1016/S0924-0136(03)00841-0 ↗
20. Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2:359–36610.1016/0893-6080(89)90020-8 ↗
21. Viswanathan V, Kinsey B, Cao J (2003) Experimental implementation of neural network springback control for sheet metal forming. J Eng Mater Technol 125:141–14710.1115/1.1555652 ↗
22. Zhao J, Wang F (2005) Parameter identification by neural network for intelligent deep drawing of axisymmetric workpieces. J Mater Process Technol 166:387–39110.1016/j.jmatprotec.2004.08.020 ↗
23. Li HY, Hu JD, Wei DD, Wang XF, Li YH (2012) Artificial neural network and constitutive equations to predict the hot deformation behavior of modified 2.25 Cr–1Mo steel. Mater Des 42:192–19710.1016/j.matdes.2012.05.056 ↗
24. Li X, Roth CC, Mohr D (2019) Machine-learning based temperature-and rate-dependent plasticity model: Application to analysis of fracture experiments on DP steel. Int J Plast 118:320–34410.1016/j.ijplas.2019.02.012 ↗
25. Ghaboussi J, Garrett J Jr, Wu X (1991) Knowledge-based modeling of material behavior with neural networks. J Eng Mech 117:132–15310.1061/(ASCE)0733-9399(1991)117:1(132) ↗
26. Palau T, Kuhn A, Nogales S, Böhm H, Rauh A, Ag MB (2012) A neural network based elasto-plasticity material model. In: 6th European Congress on Computational Methods in Applied Sciences and Engineering
27. Jang DP, Fazily P, Yoon JW (2021) Machine learning-based constitutive model for J2-plasticity. Int J Plastic 138:10291910.1016/j.ijplas.2020.102919 ↗
28. Huang Y, Yuan Y, Yang L, Wu D, Chen S (2020) Real-time monitoring and control of porosity defects during arc welding of aluminum alloys. J Mater Process Technol 286:11683210.1016/j.jmatprotec.2020.116832 ↗
29. Ji X, Yan Q, Huang D, Wu B, Xu X, Zhang A, Liao G, Zhou J, Wu M (2021) Filtered selective search and evenly distributed convolutional neural networks for casting defects recognition. J Mater Process Technol 292:11706410.1016/j.jmatprotec.2021.117064 ↗
30. Nguyen NV, Kim JJ, Kim SE (2019) Methodology to extract constitutive equation at a strain rate level from indentation curves. Int J Mech Sci 152:363–37710.1016/j.ijmecsci.2018.12.023 ↗
31. Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: Proceedings of the fourteenth international conference on artificial intelligence and statistics, JMLR Workshop and Conference Proceedings, p. 315–323
32. Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint, arXiv:1412.6980
33. Rasmussen CE, Williams CK (2006) Gaussian processes for machine learning. Massachusetts, MIT Press10.7551/mitpress/3206.001.0001 ↗
34. He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. Proceedings of the IEEE international conference on computer vision, pp 1026–103410.1109/ICCV.2015.123 ↗