Abstract
AbstractThis paper displays the set up and simulation of a compact neuro-fuzzy adaptive scheme for the filling regulation of two coupled spherical tanks. The suggested scheme employs two compact neuro-fuzzy blocks: the first one to model the plant, and the second one for the controller implementation. In this scheme, the controller is trained employing the fuzzy model estimated with data of the system working in closed-loop. Thus, the controller optimization iteratively is performed when plant variations occur. The work also includes the deduction of the equations for training, showing the adaptive process employing neuro-fuzzy systems. Moreover, the training (optimization) process of the controller’s neuro-fuzzy system includes within the adjustment function the control action and the error signal. Various experimental cases are considered using statistical analysis to verify behaviors in the adaptive control system. In this order, the main contribution of this work consists of the adjustment (coupling) of two structures of compact neuro-fuzzy systems used for identification and control, as well as the deduction and adjustment of the training algorithms to implement the adaptive control system.
Publisher
Springer Science and Business Media LLC
Reference45 articles.
1. Niu, B., Zhao, P., Liu, J.D., Ma, H.J., Liu, Y.J.: Global adaptive control of switched uncertain nonlinear systems: an improved MDADT method. Automatica 115, 108872 (2020)
2. Feng, G., Lozano, R.: Adaptive Control Systems. Newnes, Oxford (1999)
3. Åström, K.J., Wittenmark, B.: Adaptive Control, 2nd edn. Dover Books on Electrical Engineering, Dover Publications (2013)
4. Passino, K.: Biomimicry of bacterial foraging for distributed optimization and control. IEEE Control Systems Magazine 22(3), (2002)
5. Passino, K.: Biomimicry for Optimization, Control, and Automation. Springer-Verlag, London (2005)