Abstract
Knowledge-Based Neural Network model is known as one of the most useful methods which can predict every single variability to create the process parameters for the data on Roll Forming process. To get the best quality of product and process parameters in roll forming, the Knowledge-Based Neural Network has to be trained with high reliability. To obtain the target aimed, this paper proposes a new novel of the optimal algorithm for training in the Knowledge-Based Neural Network model with the integration between Genetic Algorithm and Hill Climbing Algorithm. Initially, a global optimization method is carried out to find the global optimum area by using Genetic Algorithm, and then the Hill climbing Algorithm will effectively detect the positions of that local optimal region with high accuracy in the training of the Knowledge-Based Neural Network model. Additionally, to obtain the trained data set of the Knowledge-Based Neural Network model, the Finite Element Analysis result of the high fidelity Finite Element Model is used. From the results of simulation, we can find out that the efficiency of the proposed method is higher than the conventional methods in optimization of the roll forming process.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Abbreviations
- d:
-
inner distance between roll stands (mm)
- ω :
-
rotation velocity of rolls (rad/s)
- f:
-
friction coefficient
- r:
-
ratio between the roll gap and sheet thickness
- D:
-
damage variable
- α :
-
spring back angle
References
Lindgren, M., “Experimental and Computational Investigation of the Roll Forming Process,” Division of Material Mechanics, Luleå University of Technology, 2009.
Zeng, G., Li, S. H., Yu, Z. Q., and Lai, X. M., “Optimization Design of Roll Profiles for Cold Roll Forming Based on Response Surface Method,” Materials & Design, Vol. 30, No. 6, pp. 1930–1938, 2009.
Paralikas, J., Salonitis, K., and Chryssolouris, G., “Optimization of Roll Forming Process Parameters — A Semi-Empirical Approach,” The International Journal of Advanced Manufacturing Technology, Vol. 47, No. 9–12, pp. 1041–1052, 2010.
Chen, D.-C. and Chen, C.-F., “Use of Taguchi Method To Study a Robust Design for the Sectioned Beams Curvature During Rolling,” Journal of Materials Processing Technology, Vol. 190, No. 1–3, pp. 130–137, 2007.
Shahani, A. R., Setayeshi, S., Nodamaie, S. A., Asadi, M. A., and Rezaie, S., “Prediction of Influence Parameters on the Hot Rolling Process Using Finite Element Method and Neural Network,” Journal of Materials Processing Technology, Vol. 209, No. 4, pp. 1920–1935, 2009.
Pal, S., Pal, S. K., and Samantaray, A. K., “Artificial Neural Network Modeling of Weld Joint Strength Prediction of a Pulsed Metal Inert Gas Welding Process Using Arc Signals,” Journal of Materials Processing Technology, Vol. 202, No. 1–3, pp. 464–474, 2008.
Harkouss, Y., Rousset, J., Chehade, H., Ngoya, E., Barataud, D., and Teyssier, J., “The Use of Artificial Neural Networks in Nonlinear Microwave Devices and Circuits Modeling: An Application to Telecommunication System Design (Invited Article),” International Journal of RF and Microwave ComputerAided Engineering, Vol. 9, No. 3, pp. 198–215, 1999.
Devabhaktuni, V. K., Xi, C., and Zhang, Q. J., “A Neural Network Approach to the Modeling of Heterojunction Bipolar Transistors from S-Parameter Data,” Proc. of A Neural Network Approach to the Modeling of Heterojunction Bipolar Transistors from S-Parameter Data, Vol. 1, pp. 306–311, 1998.
Rajagopalan, R. and Rajagopalan, P., “Applications of Neural Network in Manufacturing,” Proc. of Applications of neural network in manufacturing, Vol. 2, pp. 447–453, 1996.
Wang, F. and Qi Jun, Z., “Knowledge-Based Neural Models for Microwave Design,” Microwave Theory and Techniques, IEEE Transactions on, Vol. 45, No. 12, pp. 2333–2343, 1997.
Park, H. S. and Dang, X. P., “Optimization of Conformal Cooling Channels with Array of Baffles for Plastic Injection Mold,” Int. J. Precis. Eng. Manuf., Vol. 11, No. 6, pp. 879–890, 2010.
Kim, H. S., Koç, M., and Ni, J., “A Hybrid Multi-Fidelity Approach to the Optimal Design of Warm Forming Processes Using a Knowledge-Based Artificial Neural Network,” International Journal of Machine Tools and Manufacture, Vol. 47, No. 2, pp. 211–222, 2007.
Abdelbar, A. and Tagliarini, G., “HONEST: A New High Order Feedforward Neural Network,” Proc. of HONEST: A New High Order Feedforward Neural Network, Vol. 2, pp. 1257–1262, 1996.
Zhang, Q. J. and Gupta, K. C., “Neural Networks for RF and Microwave Design,” Artech House, Inc., 2000.
Hagan, M. T. and Menhaj, M. B., “Training Feedforward Networks with the Marquardt Algorithm,” Neural Networks, IEEE Transactions on, Vol. 5, No. 6, pp. 989–993, 1994.
Farzin, M., Salmani Tehrani, M., and Shameli, E., “Determination of Buckling Limit of Strain in Cold Roll Forming by the Finite Element Analysis,” Journal of Materials Processing Technology, Vol. 125–126, pp. 626–632, 2002.
Salmani Tehrani, M., Moslemi Naeini, H., Hartley, P., and Khademizadeh, H., “Localized Edge Buckling in Cold Roll-Forming of Circular Tube Section,” Journal of Materials Processing Technology, Vol. 177, No. 1–3, pp. 617–620, 2006.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Park, H.S., Nguyen, T.T. Optimization of roll forming process with evolutionary algorithm for green product. Int. J. Precis. Eng. Manuf. 14, 2127–2135 (2013). https://doi.org/10.1007/s12541-013-0288-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12541-013-0288-3