Open Access
Subscription Access
Application of Radial Basis Function Neural Networks in Modeling of Nonlinear Systems with Deadband
Presence of dead-band in engineering process decreases the system performance. Modeling of systems with such nonlinear properties is a key factor in model-based control and in fact a challenging task by conventional mathematic methods. In this paper, application of radial basis neural networks in such systems is investigated. The nonlinear static part of the system can be decoupled first from linear dynamic part and then modeled using Radial Basis Function (RBF) network; the dynamic linear part of the system can be identified using linear models. Results show that RBF can capture well, the key model of the systems with dead band.
Keywords
Radial Basis Function, Deadband, Modeling, Static, Dynamic
User
Information
- Haykin S (1994). Neural Networks: A Comprehensive Foundation, Chapter 2, Pearson Eduvation Publication, 72–133.
- Wang H, Oh Y et al. (1998). Strategies for modeling and control of nonlinear chemical processes using neural networks, Computers & Chemical Engineering, vol 22(Sup 1), S823–S826.
- Han X, Xie W et al. (2011). Nonlinear systems identification using dynamic multi-time scale neural networks, Neurocomputing, vol 74(17), 3428–3439.
- Stenman A, Gustafsson F et al. (2003). A segmentation-based method for detection of stiction in control valves, International Journal of Adaptive Control and Signal Processing, vol 17(7–9), 625–634.
- Yamashita Y (2006). An automatic method for detection of valve stiction in process control loops, Control Engineering Practice, vol 14(5), 503–510.
- Fruzzetti K, Palazoğlu A et al. (1997). Nolinear model predictive control using Hammerstein models, Journal of Process Control, vol 7(1), 31–41.
- Srinivasan R, and Rengaswamy R (2005). Control Loop Performance Assessment. 2. Hammerstein Model Approach for Stiction Diagnosis, Industrial & Engineering & Chemistry Research, vol 44(17), 6719–6728.
- Bai E-W (2004). Decopling the linear and nonlinear parts in hammerstein model identification, Automatica, vol 40(4), 671–676.
- Broomhead D S, and Lowe D (1988). Multivariable functional interpolation and adaptive networks, Complex Systems, vol 2(2), 321–355.
- Krzyzak A, Linder T et al. (1996). Nonparametric estimation and classification using radial basis function nets and empirical risk minimization, IEEE Transactions on Neural Networks, vol 7(2), 475–487.
- Mali K, and Mitra S (2005). Symbolic classification, clustering and fuzzy radial basis function network, Fuzzy Sets and Systems, vol 152(3), 553–564.
- Hou M, and Han X (2010). Constructive approximation to multivariate function by decay RBF neural network, IEEE Transactions on Neural Networks, vol 21(9), 1517–1523.
- Shen C, Cao G-Y et al. (2002). Nonlinear modeling and adaptive fuzzy control of MCFC stack, Journal of Process Control, vol 12(8), 831–839.
- Bahita M, and Belarbi K (2012). Radial basis function controller of a class of nonlinear systems using mamdani type as a fuzzy estimator, International Symposium on Robotics and Intelligent Sensors Procedia Engineering, vol 41, 501–509.
- Qiao J-F, and Han H-G (2012). Identification and modeling of nonlinear dynamical systems using a novel self-organizing RBF-based approach, Automatica, vol 48(8), 1729–734.
- Warwick K (1996). An introduction to radial basis functions for system identification: a comparison with other neural networks methods, Proceedings of the 35th Conference on Decision and Control, Kobe, Japan, vol 1, 464–469.
- Ljung L (1999). System Identification: Theory for the User, 2nd Edn., Chapter 4, Prentice Hall PTR, New Jersey, 69–115.
- Sut H-T, and McAvoy T I (1993). Neural model predictive control of nonlinear chemical processes, IEEE International Symposium On Intelligent Control, Chicago, USA, 358–363.
Abstract Views: 434
PDF Views: 0