Process Parameter Prediction of Differential Pressure Vacuum Casting Based on Support Vector Machine

Abstract:

To reduce warpage deformation of the differential pressure vacuum casting (DPVC) products and to improve product quality, One prediction method for process parameters based on support vector machine (SVM) and artificial fish-swarm algorithm (AFSA) is proposed.Firstly sample test data is abtained by using orthogonal experimental design and numerical simulation to construct models to forecast warpage of DPVC product based on SVM. Simultaneously to improve the predictive accuracy of the model, AFSA is introduced to optimize the SVM model. And then using this model recommends and adjusts the DPVC process in order to achieve quality control. Finally , through the analysis of a mouse shell , the validity of the method proposed is verified, providing a feasible method for DPVC product quality control

• Periodical: Key Engineering Materials (Volume 621)
• Pages: 633-638
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.621.633
• Online since: August 2014
• Authors: Xu Zhang, Hai Guang Zhang*, Zhuang Ya Zhang, Qing Xi Hu
• Keywords: Artificial Fish-Swarm Algorithm, Differential Pressure Vacuum Casting, Prediction Model, Support Vector Machine (SVM), Warpage Deformation

References

[1] R. J Zhang, F Lin and Yan Yongnian, et al: Our Country Rapid Tool Technology Development and Prospect, Chinese Journal of Mechanical Engineering metal processing, Vol. 8(2008), pp.62-64.

[2] Terry Wohlers: Wohlers Report 2012 (State of the Industry Annual Worldwide Progress Report), (2012).

[3] J Ya Lee, Member Cheng-Hsien, and Chung Yu-Ti Jhan: Mold-flow Analysis for Manufacturing FRP Structures in Vacuum Assisted Resin Transfer Molding. Conference Proceedings, Japan Society of Naval Architects and Ocean Engineers, (2006).

[4] Kurtaran H, Ozcelik B and Erzurumlu T: Warpage Optimization of a Bus Ceiling Lamp Base Using Neural Network Model and Genetic Algorithm, Journal of Materials Processing Technology , Vol. 169 (2005), pp.314-319.

DOI: 10.1016/j.jmatprotec.2005.03.013

[5] Y. H Gao, X. C Wang: Surrogate-Based Process Optimization for Reducing Warpage in Injection Molding, Journal of Materials Processing Technology, Vol. 3 (2009), No. 209. p.1302—1309.

DOI: 10.1016/j.jmatprotec.2008.03.048

[6] G. Q Xiang, Z. J Yan, D. G Huang: Genetic Optimization Design Based on Support Vector Regression Metamodeling, Journal of University of Electronic Science and Technology of China, Vols. 3 (2009) , No. 38, pp.459-462. (In Chinese).

[7] F. F LI, Y. K Zhao: The Least Squares Support Vector Machine Based on Matlab Toolbox and Its Application, Computer Applications, Vol. 12 (2006) , pp.358-360. (In Chinese).

[8] X. J Peng: On Issues and Applications for Support Vector Machine. (Ph.D., Shanghai University, China 2008), pp.31-43. (In Chinese).

[9] N. Y Deng, Y. J Tian: A Novel Method in Data Mining: Support Vector Machine (Science Press, China 2004), pp.77-86. (In Chinese).

[10] THEODORIDIS S, MAVROFORKIS M: Reduced convex hulls: a geometric approach to support vector machines, IEEE Signal Processing Magazine, Vol. 3(2007) No. 24, pp.119-122.

DOI: 10.1109/msp.2007.361610

[11] Fröhlich H, Chapelle O, Schölkopf B: Feature selection for support vector machines by means of genetical gorithms, Proceedings of 15th IEEE International Conference on Tools with Artificial Intelligence, Sacramento, California, USA, Vols. 3-5(2003).

DOI: 10.1109/tai.2003.1250182

[12] C. R Wang, C. L Zhou, J. W Ma: An Improved Artificial Fish-swarm Algorithm and its Application in Feed-forward Neural Networks, Proceedings of the Fourth International Conference on Machine Learning and Cybernetics, (2005).

DOI: 10.1109/icmlc.2005.1527436