Abstract
In this paper, firstly dynamic model of pressure process system was obtained by NARX type ANN. Then validity of acquired model was proved by regression analysis (R=0,997) and mean square error (MSE=3,70.10 − 07). At this step, different ANN parameters were tested and ANN-30 model was found the good enough for modeling. Afterwards to prevent the fluctuations in the tank, a cubic trajectory function was used as an input reference signal. A cost function was designed to minimize the error along the trajectory for the GA-PID and ACO-PID controller. In order to compare results with traditional approach PID controller was also tuned Z-N methods. Outputs were evaluated by means of RMS error the respect to change of trajectory slope and reference pressure and robustness of controllers were also observed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Ünal, M., Ak, A., Topuz, V., Erdal, H. (2013). Conclusion. In: Optimization of PID Controllers Using Ant Colony and Genetic Algorithms. Studies in Computational Intelligence, vol 449. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32900-5_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-32900-5_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32899-2
Online ISBN: 978-3-642-32900-5
eBook Packages: EngineeringEngineering (R0)