Optimization of variable blank holder force in deep drawing based on support vector regression model and trust region
- 43 Downloads
Blank holder force (BHF) is one of the important process parameters for successful sheet metal forming. Variable blank holder force (VBHF) that the BHF varies through the forming process is recognized as one of the advanced manufacturing technologies. Therefore, optimization of VBHF trajectory is a crucial issue in industries. One of the effective approaches to determine the VBHF trajectory is to use the surrogate modeling techniques. However, it is very inaccurate and time-consuming to determine the VBHF trajectory for successful sheet forming through surrogate-based optimization methods. Therefore, this paper proposes an improved surrogate-based optimization method by integration of support vector regression (SVR) and trust region strategy to optimize VBHF in deep drawing. First, a random sampling test of VBHF in deep drawing is designed and a SVR approximate model of VBHF under random sampling is developed. Then, a trust region algorithm is adopted to predict and control the accuracy of the SVR approximate model of VBHF. Response surface is repeatedly constructed and optimized that is adopted to identify the Pareto-frontier of VBHF. The validity of the proposed approach is examined through the comparison of numerical and experimental results. The results of this research provide a reliable reference for future efforts to optimize VBHF in deep drawing.
KeywordsDeep drawing Variable blank holder force Support vector regression model Trust region
Sincere appreciation is extended to the reviewers of this paper for their helpful comments.
This work was supported by Zhejiang Provincial Natural Science Foundation of China (No. LZ18E050001) and the National Natural Science Foundation of China (No. 51775489).
- 8.Kotkunde N., Deole A. D., Gupta A. K., Singh S. K. 2014 Effect of process parameters on deep drawing of Ti-6Al-4V alloy using finite element analysis. NUMISHEET: The 9th International Conference and Workshop on Numerical Simulation of 3D Sheet Metal Forming Processes: Part A Benchmark Problems and Results and Part B General Papers. American Institute of Physics.Google Scholar
- 11.Ma GY, Huang BB (2014) Optimization of process parameters of stamping forming of the automotive lower floor board. J Appl Math 2014:1–9Google Scholar
- 20.Kakandikar G. M., Nandedkar V. M. 2005 Optimization of forming load and variables in deep drawing process for automotive cup using Genetic Algorithm. IISc Centenary-International Conference on Advances in Mechanical Engineering ICICAME, Bangalore Google Scholar.Google Scholar
- 22.Tian Y, Xie YM, Sun XQ, He YJ (2014) Process parameters optimization of deep drawing based on fish RBF neural network and improved ant colony algorithm. Forg Stamp Technol 39(12):129–136Google Scholar
- 26.Feng YX, Zhou MC, Tian GD, Li ZW, Zhang ZF, Zhang Q, Tan JR (2018) Target disassembly sequencing and scheme evaluation for CNC machine tools using improved multiobjective ant colony algorithm and fuzzy integral. IEEE Trans Syst Man Cybern Syst. https://doi.org/10.1109/TSMC.2018.2847448 CrossRefGoogle Scholar