Abstract

Real processes often exhibit non-linear behavior; time variance and delay between input and output, having a vast amount of highly correlated data and this correlation need to be utilized in the design of estimator. In this work, an interacting non-linear (conical tank) is taken for study and a neural estimator is designed using Data driven approach. The neural network is developed in hardware on a customized Linux kernel and implemented using python language. The second order training algorithm is modified using a batch update strategy and this approach along with the hardware implementation reduces the estimator training period and makes it highly suited to online.

References

• Skupin, P. , Klopot, W. , Klopot, T. , "Partially Decoupled DMC System", International Journal of Systems Applications, Engineering & Development, Issue 3, Vol. 4, 2010.
• K. BarrilJawatha, "Adaptive Control Technique for Two Tanks Conical Interacting System",International Conference on Computing and Control Engineering (ICCCE'12), 12 & 13 April, 2012
• J Satheesh Kumar, P Poongodi and K. Rajasekaran, "Modelling and Implementation ofLabview Based Non-linear PI Controller for a Conical Tank", Journal of Control & Instrumentation Vol. 1, Issue 1, November, pp. 1-9, 2010.
• Prakash, J. ,Patwardhan, S. C. , Shah,S. L. , "Constrained nonlinear state estimation using ensemble kalman filters", Industrial and Engineering Chemistry Research, vol. 49, issue 5, pp. 2242 - 2253, 2010
• V. Adetola, M. Guay, "Integration of real-time optimization and model predictive control", Journal of Process Control 20 (2010) 125–133
• Static and dynamic robust parameters and PI control tuning of m model for controlling the liquid level in a single tank,SICE Annual Conference 2010, Proceedings of International Conference, 18-21 Aug. 2010, pp. 979 – 984
• Q. Hu, P. Saha, G. P. Rangaiah," Experimental evaluation of an augmented IMC for non linear systems", Control engineering Practice, Volume 8 (10) Elsevier- Oct 1, 2000,pp. 1167-1176
• George Stephanopoulos "chemical process control an introduction to Theory and practice".
• Process Identification from Closed-Loop Response Using Optimization Methods. Viswanathan, P. K. ; Rangaiah, G. P. Chemical Engineering Research and Design vol. 78 issue 4 May, 2000. p. 528-541
• J. B. Gomm, D. L. Yu and D. Williams, "A new model structure selection method for non-linear . . . 752- 757, Exeter, UK, Institution of Electrical Engineers, 1996
• Peng Jing Chaonan Tong ; Lei Xiao "Decoupling Based Decentralized Robust Control for CombinedShape and Gauge System in Tandem Cold RollingProcess" 48th IEEE Conference on Decision andControl and28th Chinese Control ConferenceShanghai, P. R. China, December 16-18, 2009
• Prakash, J. , Srinivasan, K. , " Non-linear State Estimation for Continuous Stirred Tank Reactor using Neural Network State Filter",India Conference, 2006 Annual IEEE 15-17 Sept. 2006 Page(s)1 - 4
• Ravi, V. R. Thyagarajan, T. , "A decentralized PID controller for interacting non linear systems" ,Emerging Trends in Electrical and Computer Technology (ICETECT), 2011 International Conference on 23-24 March 2011Page(s):297 - 302
• K. Suresh Manic, R. Sivakumar, V. Nerthiga, R. Akila, K. Balu, "Design of Plant Estimator Model Using Neural Network", IJCSNS International Journal of Computer Science and Network Security, VOL. 9 No. 6, June 2009.
• Martin T. Hagan, Howard B. Demuth, Mark Beale, " Neural Network Design", China Machine Press, 2002.
• R. Rojas, " Neural Networks", Springer- Verlag, Berlin, 1996
• S. L. Pinjare, Arun Kumar M, "Implementation o Neural Network Back Propagation Training Algorithm on FPGA", International Journal of Computer Applications (0975-8887) volume 52- No. 6, August 2012.