Abstract
Typical solutions based on nonlinear constrained optimization-based strategies are hard to find and usually demand for higher level of computation. In this paper two techniques for transforming the initial nonlinear optimization into an approximate convex optimization are presented and tested for a rigid manipulator modeled with a feedforward neural network. The results have shown that the overall performance is enhanced when performing an approximate feedback linearization.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Botto, Miguel Ayala: Feedback linearization techniques applied to predictive control using neural networks. Control Laboratory, Department of Electrical Engineering, Delft University of Technology (1995) Internal Report R95.042
Braake, H.A.B. te, Botto, M. Ayala, Can, H. J. L van, Costa, J. Sá da, Verbruggen, H. B.: Constrained nonlinear model based predictive control. Submitted to 2nd Portuguese Conference on Automatic Control (1996), Oporto, Portugal
Braake, H.A.B. te, Can, H.J.L. van, Scherpen, J.M.A., Verbruggen, H. B.: Control of nonlinear chemical processes using dynamic neural models and feedback linearization. Submitted to Computers in Chemical Engineering (1995)
Del Re, L.: Hybrid MPC for minimum phase nonlinear plants. Proceedings of 3rd European Control Conference (1995), Rome, Italy, 3561–3566
Gill, P. E., Murray, W.: Numerical methods for constrained optimization. Academic Press Inc. (1974), London
Isidori, A.: Nonlinear Control Systems: An Introduction. Springer-Verlag (1985) Berlin, Germany
Saint-Donat, Jean and Bhat, Naveen and McAvoy, Thomas J.: Neural net based model predictive control. International Journal of Control (1991), vol. 6, No 54, 1453–1468
Soeterboek, Ronald: Predictive control: a unified approach. Prentice Hall International (1992), UK, Cambridge
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Botto, M.A., te Braake, H.A.B., da Costa, J.S. (1996). Solving nonlinear MBPC through convex optimization: A comparative study using neural networks. In: von der Malsburg, C., von Seelen, W., Vorbrüggen, J.C., Sendhoff, B. (eds) Artificial Neural Networks — ICANN 96. ICANN 1996. Lecture Notes in Computer Science, vol 1112. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61510-5_101
Download citation
DOI: https://doi.org/10.1007/3-540-61510-5_101
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61510-1
Online ISBN: 978-3-540-68684-2
eBook Packages: Springer Book Archive