This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Using Neural Network for Springback Minimization in a Channel Forming Process
Annotation ability available
Sector:
Language:
English
Abstract
Springback, the geometric difference between the loaded and unloaded configurations, is affected by many factors, such as material properties, sheet thickness, lubrication conditions, tooling geometry and process parameters. It is extremely difficult to develop an analytical model for springback control including all of these factors. The proposed neural network model is an attempt to deal with such a complicated non-linear system in a predictive way. For demonstration, an aluminum channel forming process is considered in this work. Our previous research [1] has shown that a variable binder force history during the forming operation can reduce the springback amount significantly while maintaining a relatively low maximum strain if an initial low binder force was used followed by a higher binder force. However, when and how much of the increase depends on the forming conditions of the current process. Here, several numerical simulations using Finite Element Method (FEM) were performed to obtain the teaching data required for training the neural network by means of the back-propagation algorithm. In the pre-dictive mode, different process inputs from the ones used in the previous stage were considered. For each case, the displacement where binder force increases and the level of the high binder force were predicted by the learned neural network and were numerically tested. Consistent low springback angle (< 0.5°) and moderate stretching amount (< 16%) were obtained even in the cases where the process parameters were varied as much as ±25% of the friction coefficient and sheet thickness or ±10% of the material's mechanical properties. The neural network can be easily implemented in experiments and/or in real production to resolve the uncertainty of springback amount due to the variations in material parameters and friction conditions.
Authors
Topic
Citation
Ruffini, R. and Cao, J., "Using Neural Network for Springback Minimization in a Channel Forming Process," SAE Technical Paper 980082, 1998, https://doi.org/10.4271/980082.Also In
References
- Sunseri, M. Cao, J. Karafillis, A. P. Boyce, M. C. 1995 “Accommodation of Springback Error in Channel Forming Using Active Binder Force Control: Numerical Simulations and Results” J. Eng. Mat. And Techn. 426 435
- Karafillis, A. P. Boyce, M. C. 1992 “Tooling Design in Sheet Metal Forming Using Springback Calculations” Int. J. Mech. Sci. 34 113
- Karafillis, A. P. Boyce, M. C. 1996 “Tooling and Binder Design for Sheet Metal Forming Compensating Springback Error” Int. Jnl. Machine Tools and Manufacture 36 503
- Ayres, R.A. 1984 “SHAPESET: a Process to Reduce Sidewall Curl Springback in High-strength Steel Rails” J. Appl. Metalworking 3 127
- Rosenblatt, R. 1959 “Principles of Neurodynamics” New York Spartan Books
- Widroff, B. Hoff, M. E. 1960 “Adaptive Switching Circuits” 1960 IRE WESCON Conv. Record 96 104
- Nguyen, D. Widrow, B. 1989 “The Truck Backer-upper: An Example of Self-learning in Neural Networks,” Proc. Intl. Joint Conf. on Neural Networks Washington, DC 2 357 363
- Sejnowski, T. J. Rosenberg, C. R. 1986 “Nettalk: A Parallel Network that Learns to Read Aloud,” Tech. Rep. JHU/EECS-86/01 John Hopkins University
- Bounds, D. G. Lloyd, P. J. Matthew, B. Waddel, G. 1988 “A Multilayer Perceptron Network for the Diagnosis of Low Back Pain,” Proc. 2d IEEE Intl. Conf. on Neural Networks San Diego, CA 2 481 489
- Bradshaw, G. Fozzard, R. Ceci, L. 1989 “A Connectionist Expert System that Actually Works,” Advances in Neural Network Information Processing Systems I Touretzky D. S. San Mateo, CA Morgan Kaufmann 248 255
- Elkins, K. L. 1994 “On-Line Angle Control for Small Radius Air Bending,” Carnegie Mellon University 19 25 90 95
- Yang M. Shima, S. Watanabe, T. 1992 “Development of Control System Using Neural Network Combined with Deformation Model for an Intelligent V-Bending Process of Sheet Metals,” Proc. Japan/USA Symposium on Flexible Automation ASME 2 1485 1490
- Forcellese, A. Gabrielli F. Ruffini, R 1997 “Spring-back Control in a Air Bending Process by Neural Network,” Proc. III Convegno AITEM
- Rumelhart, D.E. Mc Clelland, J.L. 1986 “Learning Internal Representation by Error Propagation,” Parallel Distributed Processing Cambridge, MA, MIT Press 1
- Widrow, B. Lher, M.A. 1990 “30 Years of Adaptive Neural Networks: Perceptron, Madaline and Backpropagation,” Proc. of the IEEE 78 9
- Stinchombe, M. White, H. 1989 “Universal Approximation using Feedforward Networks with Non-Sigmoid Hidden Layer Activation Functions,” Proc. Int. Joint Conf. on Neural Networks Washington, DC 1 613 617
- Cybenko, G. 1988 “Continuous Valued Neural Networks With Two Hidden Layers Are Sufficient,” Technical Report, Dep. of Computer Science Tufts University
- Graf, A. Hosford, W. 1993 “Plane-strain Tension Test of AL 2008-T4 Sheets” Proc. SAE Congress Symposium on Sheet Forming Detroit, MI
- Jalkh, P. Cao, J. Hardt, D. Boyce, M. C. 1993 “Optimal forming of Aluminium 2008-T4 Conical Cups Using Force Trajectory Control,” Proc. SAE Congress Symposium on Sheet Forming Detroit, MI
- Stelson, K. A. 1983 “Real Time Identification of Work-piece Material Characteristic from Measurements During Brakeforming,” ASME J. of Engineering for Industry 105 45 53
- Stelson, K. A. 1986 “An Adaptive Pressbrake Control for Strain Hardening Materials” ASME J. of Engineering for Industry 108 127 132
- Stelson K. A. Peterson, T. Y. 1989 “The Area-Coarea Method for the Estimation of Power-Law Constitutive Parameters” ASME J. of Engineering for Industry 111 295 297