NN-ANARX model based control of liquid level using visual feedback

In this paper, the problem of liquid level control based on visual feedback is investigated in application to a real life model of an industrial plant. Visual detection of liquid level is implemented on the Raspberry Pi computer. Computational intelligence based controller uses input-output feedback linearization. Parameters of the controller are provided by the neural network ANARX structure. As communication between Raspberry Pi and control system is provided over WLAN, additional prediction module is used to overcome networking problems. Control of the SISO and MIMO systems is provided.

[1]  Xiaoming Zuo.  Liquid level control of water tank system based on improved polyclonal selection algorithm and RBF network , 2010, 2010 2nd International Conference on Computer Engineering and Technology.

[2]  Eduard Petlenkov,et al.  Gain and order scheduled fractional-order PID control of fluid level in a multi-tank system , 2014, ICFDA'14 International Conference on Fractional Differentiation and Its Applications 2014.

[3]  Ülle Kotta,et al.  On realizability of neural networks-based input-output models in the classical state-space form , 2006, Autom..

[4]  Cl. Festila,et al.  Level and pressure control in condenser of the 13C isotope separation column , 2010, 2010 IEEE International Conference on Automation, Quality and Testing, Robotics (AQTR).

[5]  Keiichi Abe,et al.  Topological structural analysis of digitized binary images by border following , 1985, Comput. Vis. Graph. Image Process..

[6]  Richard O. Duda,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972, CACM.

[7]  Klaus Mertens,et al.  Camera systems in hazardous (classified) locations to monitor and control the separation of liquid waste products in chemical plants , 2009, 2009 Record of Conference Papers - Industry Applications Society 56th Annual Petroleum and Chemical Industry Conference.

[8]  Avinash J Gaikwad,et al.  Selection of Steam Drum Level Control Method for Multiple Drum Interacting Loops Pressure Tube-Type BWR , 2011, IEEE Transactions on Nuclear Science.

[9]  E. Petlenkov.  NN-ANARX structure based dynamic output feedback linearization for control of nonlinear MIMO systems , 2007, 2007 Mediterranean Conference on Control & Automation.

[10]  Eduard Petlenkov.  Model reference control of nonlinear systems by dynamic output feedback linearization of neural network based ANARX models , 2008, ICARCV.

[11]  Li Liang.  The application of fuzzy PID controller in coupled-tank liquid-level control system , 2011, 2011 International Conference on Electronics, Communications and Control (ICECC).

[12]  P. Eserin.  Application of canonical variate analysis to the dynamical modeling and control of drum level in an industrial boiler , 1999, Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251).

[13]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.