Peter Drahoš
580 California St., Suite 400
San Francisco, CA, 94104
Advanced Information System for Safety-Critical Processes
2014, Comput. Informatics
Sign up for access to the world's latest research
Abstract
The paper deals with the design and implementation of an intelligent modular information system (IMIS) for modeling and predictive decision making supervisory control of some important critical processes in a nuclear power plant (nuclear reactor) using selected soft computing methods. The developed IMIS enables monitoring critical states, safety impact analysis and prediction of dangerous situations. It also recommends the operator possibilities how to proceed to ensure safety of operations and humans and environment. The proposed complex IMIS has been tested on real data from a nuclear power plant process primarily used as supervisory information for decision making support and management of critical processes. The core of the proposed IMIS is a general nonlinear neural network mathematical model. For prediction of selected process variables an artificial neural network of multilayer perceptron type (MLP) has been used. The effective Levenberg-Marquardt method was used to train the...
References (18)
- Jadlovská, A.: Modelling and Control of Dynamic Processes Using Neuron Net- works. FEI TU Košice, 2003, ISBN 80-8894122-9 (in Slovak).
- Kajan, S.-Hypiusová, M.: Application of Artificial Neural Network in Modelling and Simulation a Power Engineering Process. Control of Power and Heating Systems 2006, Zlín 2006.
- Hagan, M. T.-Menhaj, M. B.: Training Feedforward Networks with the Mar- quardt Algorithm. IEEE Transactions on Neural Networks, Vol. 5, 1994, No. 6, pp. 989-993.
- The Mathworks. Neural Network Toolbox, User's Guide, 2002.
- Hornik, M.-Stinchcombe, M.-White, H.: Multilayer Feedforward Networks Are Universal Approximators. Neural Networks, Vol. 2, 1989, No. 5, pp. 359-366.
- Lippmann, R. P.: Pattern Classification Using Neural Networks. IEEE Communi- cations Magazine, Vol. 27, 1989, pp. 47-64.
- Rumelhart, D. E.-Hinton, G. E.-Williams, R. J.: Learning Representations by Back-Propagating Errors. Nature, Vol. 323, 1986, pp. 533-536.
- Siegelmann, H. T.: Neural Networks and Analog Computation: Beyond the Turing Limit. Birkhauser, Boston 1999.
- Andersen, T. J.-Wilamowski, B. M.: A Modified Regression Algorithm for Fast One Layer Neural Network Training. World Congress of Neural Networks, Washing- ton, DC, USA, July 17-21, 1995, Vol. 1, pp. 687-690.
- Werbos, P. J.: Back-Propagation: Past and Future. Proceedings of International Conference on Neural Networks, San Diego, CA, USA, 1988, Vol. 1, pp. 343-354.
- Levenberg, K.: A Method for the Solution of Certain Problems in Least Squares. Quarterly of Applied Mathematics, Vol. 2, 1944, No. 2, pp. 164-168.
- Marquardt, D.: An Algorithm for Least-Squares Estimation of Nonlinear Param- eters. SIAM Journal on Applied Mathematics, Vol. 11, 1963, No. 2, pp. 431-441.
- Valo, R.-Kozák, Š.: Effective Application of Levenberg-Marquardt Teaching. In: Kozák, Š., Kozáková, A., Rosinová, A. (Eds.): Kybernetika a informatika. Medzinárodná konferencia SSKI SAV, STU Bratislava, 2012, pp. 107-111 (in Slo- vak).
- Ionescu, M.-Sburlan, D.: Some Applications of Spiking Neural P Systems. In Computing and Informatics, Vol. 27, 2008, No. 3, pp. 515-528.
- Korenčiak, D.-Gutten, M.: Opportunities for Integration of Modern Systems Into Control Processes in Intelligent Buildings. Przeglad Elektrotechniczny, Electrical Review, Vol. 88, 2012, No. 2, pp. 266-269, ISSN 0033-2097.
- Kashif, Z.-Rauf, A.-Rauf, B.: Multiple Route Generation Using Simulated Niche Based Particle Swarm Optimization. Computing and Informatics, Vol. 32, 2013, No. 4, pp. 697-721.
- Korošec, P.-Šilc, J.: Using Stigmergy to Solve Numerical Optimization Prob- lems. Computing and Informatics, Vol. 27, 2008, No. 3, pp. 377-402.
- Štefan Koz ak obtained his M. Sc. degree from the Slovak Uni- versity of Technology in Bratislava in 1970 and the Ph. D. degree in technical cybernetics from the Slovak Academy of Sciences in 1978. He worked at the Institute of Technical Cybernetics in the field of control algorithms design and was a leader of a research team at the Institute of Applied Cybernetics in Bratislava. Since 1984 he had been with the Department of Automatic Control Systems at the Faculty of Electrical Engineering and Informa- tion Technology in Bratislava (between 1998 and 2006 he lead the department). Currently, he is with the Institute of Automo- tive Mechatronics at the Faculty of Electrical Engineering and Information Technology, STU in Bratislava. His research interests include system theory, linear and nonlinear con- trol methods, numerical methods and software for modeling, control, signal processing and embedded intelligent systems. He published over 250 research papers in conference proceedings and international journals, and organized four IFAC events held in Slovakia. Slavomír Kajan received his diploma and Ph. D. degree in automatic control from the Faculty of Electrical Engineering and Information Technology, Slovak University of Tech- nology (FEI STU) in Bratislava, in 1997 and 2006, respectively. He is now an Assistant Professor at the Institute of Control and Industrial Informatics, FEI STU in Bratislava. His research interests include servo-systems, soft-computing control methods and robust control. Ján Cig anek received his diploma and Ph. D. degree in au- tomatic control from the Faculty of Electrical Engineering and Information Technology, Slovak University of Technology (FEI STU) in Bratislava, in 2005 and 2010, respectively. He is now an Assistant Professor at the Institute of Automotive Mecha- tronics, FEI STU in Bratislava. His research interests include optimization, robust control design, computational tools, and hybrid systems. Viktor Ferencey is now a Full Professor at the Institute of Au- tomotive Mechatronics, Faculty of Electrical Engineering and In- formation Technology in Bratislava. His research work includes optimization of energy sources and of power systems for electric drives. He conducts research in energy intensity for fuel cells in the capacity of power source for an electric vehicle. In pe- dagogical work, he focuses on teaching of mechatronics systems for engines and managing the dynamics of movement of elec- tric vehicles. In cooperation with automotive industry, he ad- dresses issues of research and development of hybrid and electric propulsion systems for different types of vehicles. He is author of three monographs, four university books, several textbooks and over 150 scientific and professional publications.