Artificial neural network models for fault detection and isolation of industrial processes

• Autorzy: Korbicz J. , Janczak A.
• Języki publikacji: EN

Abstrakty

EN

The paper focuses on using of artificial neural networks in model-based fault detection and isolation. Modelling of a system both at its normal operation conditions and in faulty states is considered and a comparative study of three different methods of system modelling that use a linear model, neural network nonlinear autoregressive with exogenous input model, and neural network Wiener model is presented. Application of these models is illustrated with an example of approximation of a dependence of the juice steam pressure in the stage two on the juice steam pressures in the stages one and three of a five stage sugar evaporator. Parameters of the linear model are estimated with the recursive pseudolinear regression method, whilst the backpropagation and truncated backpropagation through time algorithms are employed for training the neural network models. All the considered models are derived based on the experimental data recorded at the Lublin Sugar Factory.

Słowa kluczowe

EN

neural network; fault detection and isolation

PL

sieć neuronowa

• Wydawca: Instytut Podstawowych Problemów Techniki PAN
• Czasopismo: Computer Assisted Mechanics and Engineering Sciences
• Rocznik: 2002
• Tom: Vol. 9, No. 1
• Strony: 55--69
• Opis fizyczny: Bibliogr. 20 poz., rys., wykr.

Twórcy

autor

Korbicz J.

• Uniwersytet Zielonogórski, Instytut Robotyki i Inżynierii Oprogramowania, ul. Podgórna 50, 65-246 Zielona Góra

autor

Janczak A.

• Uniwersytet Zielonogórski, Instytut Robotyki i Inżynierii Oprogramowania, ul. Podgórna 50, 65-246 Zielona Góra

Bibliografia

• [1] H. Al-Duwaish. Use of feedforward neural networks in identification and control of Wiener model. EE Proc. Control Theory Appl., 143: 255-258, 1996.
• [2] A. Carlos, A.B. Corripio. Princeples and Pracitice of Automatic Control. Wiley, New York, 1985.
• [3] J. Chen, R.J. Patton. Robust Model-Based Fault Diagnosis for Dynamic Systems. Kluwer Academic Publishers, Boston, 1999.
• [4] A. Cichocki, R. Unbehauen Neural Networks for Optimization and Signal Processing. Wiley, New York, 1998.
• [5] T.L. Fine. Feedforward Neural Network Methodology. Springer, New York, 1999.
• [6] A. Janczak. Neural network apprach to identification of Wiener and Hammerstein systems. In: W. Duch, J. Korbicz, L. Rutkowski, R. Tadeusiewicz, eds., Biocybernettcs and Biomedical Engineering 2000, Vol. 6. Neural Networks (in Polish), 419-458. Akad. Ofic. Wyd. EXIT, Warsaw, 2000.
• [7] P.M. Frank. Fault diagnosis in dynamical systems using analytical and knowledge-based redundancy — A survey of some new results. Automatica, 26: 459-474, 1990.
• [8] A. Janczak. Identification of Wiener models using recurrent neural networks. Proc. 4th Int. Conf. Methods and Models in Automation and Robotics, MMAR/'97, Międzyzdroje, Poland, pp. 727-732, 1997.
• [9] A. Janczak. Recurrent neural network models tor identification of Wiener systems. Proc. CESA'98 IMACS Multiconference, Symp. Modeling, Analysis and Control, Nabeul- Hammamet, Tunisia, pp. 965-970, 1998.
• [10] A. Janczak, J. Korbicz. Neural network models of Hammerstein systems and their application to fault detection and isolation. Proc. 14th World Congress of IFAC, Beijing P.R.C. , P: 91-96, 1999.4th World Con mmerstein systems and thei icati "I
• [11] A. Janczak. Parametric and neural network models for fault detecction and isolation of industrial process submodules, Prepr. 4th IFAC – Symp. Fault Detection Supervision and Safety for Technical Processes, SAFEPROCESS ‘2000, Budapest, Hungary, pp. 203-208,2000.
• [12] A. Jankowska, M. Barty Application of Perceptron neural networks for fault detection Prepr. 4th IFAC Symp. Fault Detection Supervision and Safety for Technical Processes, SAFEPROCESS ‘2000, Budapest, Hungary, pp. 203-208, 2000.
• [13] S. Lissane Elhaq, F. Giri, H. Unbenhauen. Modelling, identification and control of sugar evaporation — theoretical design and experimental evaluation. Control Engineering Practice, 7: 931-942, 1999.
• [14] L. Ljung. System Identification. Theory for User. Prentica Hall, New York, 1999.
• [15] K.S. Narendra, K Parthasarathy Identification and control of dynamical systems using neural networks. IEEE Trans. Neural Networks, 1: 4-26, 1990.
• [16] O. Nelles. Nonlinear System Identification. Springer, Berlin, 2001.
• [17] M. Nørgaard, O. Ravn, N.K. Poulsen, L.K. Hansen. Neural Networks for Modelling and Control of Dynamic Systems. Springer, London, 2000.
• [18] R.J. Patton, M. Frank, R.N. Clark. Fault Diagnosis in Dynamic Systems. Theory and Applications. Prentice-Hall, New York, 1990. |
• [19] K. Patan, J. Korbicz. Application of dynamic neural networks in an industral plant. Prepr. 4th IFAC Symp. Fault Deteection Supervision and Safety for Technical Processes, SAFEPROCESS ‘2000, Budapest, Hungary, pp. 186-191, 2000.
• [20] N.T. Russel, H.H.C. Bakker, R.I. Chaplin. Modular neural network modelling for long range prediction of an evaporator. Control Eng. Practice, 8: 49-59, 2000.