Indirect Adaptive Control of nonlinear Systems Based on Bilinear Neuro-Fuzzy Approximation

In this paper, we investigate the indirect adaptive regulation problem of unknown affine in the control nonlinear systems. The proposed approach consists of choosing an appropriate system approximation model and a proper control law, which will regulate the system under the certainty equivalence principle. The main difference from other relevant works of the literature lies in the proposal of a potent approximation model that is bilinear with respect to the tunable parameters. To deploy the bilinear model, the components of the nonlinear plant are initially approximated by Fuzzy subsystems. Then, using appropriately defined fuzzy rule indicator functions, the initial dynamical fuzzy system is translated to a dynamical neuro-fuzzy model, where the indicator functions are replaced by High Order Neural Networks (HONNS), trained by sampled system data. The fuzzy output partitions of the initial fuzzy components are also estimated based on sampled data. This way, the parameters to be estimated are the weights of the HONNs and the centers of the output partitions, both arranged in matrices of appropriate dimensions and leading to a matrix to matrix bilinear parametric model. Based on the bilinear parametric model and the design of appropriate control law we use a Lyapunov stability analysis to obtain parameter adaptation laws and to regulate the states of the system. The weight updating laws guarantee that both the identification error and the system states reach zero exponentially fast, while keeping all signals in the closed loop bounded. Moreover, introducing a method of "concurrent" parameter hopping, the updating laws are modified so that the existence of the control signal is always assured. The main characteristic of the proposed approach is that the a priori experts information required by the identification scheme is extremely low, limited to the knowledge of the signs of the centers of the fuzzy output partitions. Therefore, the proposed scheme is not vulnerable to initial design assumptions. Simulations on selected examples of well-known benchmarks illustrate the potency of the method.

[1]  Mohammad R. Mosavi,et al.  Gps Receivers Timing Data Processing Using Neural Networks: Optimal Estimation and Errors Modeling , 2007, Int. J. Neural Syst..

[2]  Meng Joo Er,et al.  Dynamic fuzzy neural networks-a novel approach to function approximation , 2000, IEEE Trans. Syst. Man Cybern. Part B.

[3]  Emil Levi,et al.  Identification of complex systems based on neural and Takagi-Sugeno fuzzy model , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[4]  Uwe Reuter,et al.  Artificial Neural Networks for Forecasting of Fuzzy Time Series , 2010, Comput. Aided Civ. Infrastructure Eng..

[5]  Wei Wu,et al.  LP Approximation Capabilities of Sum-of-Product and Sigma-pi-Sigma Neural Networks , 2007, Int. J. Neural Syst..

[6]  Wolfgang Graf,et al.  Recurrent Neural Networks for Uncertain Time‐Dependent Structural Behavior , 2010, Comput. Aided Civ. Infrastructure Eng..

[7]  Chin-Teng Lin,et al.  An On-Line Self-Constructing Neural Fuzzy Inference Network and Its Applications , 1998 .

[8]  Aminah Robinson Fayek,et al.  A multi-criteria optimization framework for industrial shop scheduling using fuzzy set theory , 2010, Integr. Comput. Aided Eng..

[9]  Dimitris C. Theodoridis,et al.  Direct adaptive neuro‐fuzzy trajectory tracking of uncertain nonlinear systems , 2012 .

[10]  Hojjat Adeli,et al.  A neural dynamics model for structural optimization—Theory , 1995 .

[11]  Hojjat Adeli,et al.  Machine Learning: Neural Networks, Genetic Algorithms, and Fuzzy Systems , 1994 .

[12]  Hojjat Adeli,et al.  WAVELET-HYBRID FEEDBACK-LEAST MEAN SQUARE ALGORITHM FOR ROBUST CONTROL OF STRUCTURES , 2004 .

[13]  Héctor Pomares,et al.  Generating Balanced Learning and Test Sets for Function Approximation Problems , 2011, Int. J. Neural Syst..

[14]  Zoe Doulgeri,et al.  Loss minimization in DC drives , 1991 .

[15]  A Samant,et al.  ENHANCING NEURAL NETWORK INCIDENT DETECTION ALGORITHMS USING WAVELETS , 2001 .

[16]  Hyo Seon Park,et al.  COUNTERPROPAGATION NEURAL NETWORKS IN STRUCTURAL ENGINEERING , 1995 .

[17]  Hojjat Adeli,et al.  Fuzzy clustering approach for accurate embedding dimension identification in chaotic time series , 2003, Integr. Comput. Aided Eng..

[18]  Petros A. Ioannou,et al.  Adaptive control tutorial , 2006, Advances in design and control.

[19]  Derong Liu,et al.  Nonlinear Torque and Air-to-Fuel Ratio Control of SPARK Ignition Engines Using Neuro-Sliding Mode Techniques , 2011, Int. J. Neural Syst..

[20]  Hojjat Adeli,et al.  Enhanced probabilistic neural network with local decision circles: A robust classifier , 2010, Integr. Comput. Aided Eng..

[21]  Wided Ben Tagherouit,et al.  A Fuzzy Expert System for Prioritizing Rehabilitation of Sewer Networks , 2011, Comput. Aided Civ. Infrastructure Eng..

[22]  Hojjat Adeli,et al.  Pseudospectra, MUSIC, and dynamic wavelet neural network for damage detection of highrise buildings , 2007 .

[23]  Hojjat Adeli,et al.  Hybrid control of irregular steel highrise building structures under seismic excitations , 2005 .

[24]  Xiaoou Li,et al.  Automated Nonlinear System Modeling with Multiple Fuzzy Neural Networks and Kernel Smoothing , 2010, Int. J. Neural Syst..

[25]  Hojjat Adeli,et al.  An Adaptive Conjugate Gradient Neural Network–Wavelet Model for Traffic Incident Detection , 2000 .

[26]  Hojjat Adeli,et al.  RADIAL BASIS FUNCTION NEURAL NETWORK FOR WORK ZONE CAPACITY AND QUEUE ESTIMATION , 2003 .

[27]  Qiang Li,et al.  Pavement Smoothness Prediction Based on Fuzzy and Gray Theories , 2009, Comput. Aided Civ. Infrastructure Eng..

[28]  Manolis A. Christodoulou,et al.  Adaptive Control with Recurrent High-order Neural Networks , 2000, Advances in Industrial Control.

[29]  Reza Langari,et al.  Model‐Based Multi‐input, Multi‐output Supervisory Semi‐active Nonlinear Fuzzy Controller , 2010, Comput. Aided Civ. Infrastructure Eng..

[30]  Chin-Teng Lin,et al.  A recurrent self-organizing neural fuzzy inference network , 1999, IEEE Trans. Neural Networks.

[31]  Kazuyuki Murase,et al.  Faster Training Using Fusion of Activation Functions for Feed Forward Neural Networks , 2009, Int. J. Neural Syst..

[32]  Rudolf Kruse,et al.  DESIGNING NEURO-FUZZY SYSTEMS THROUGH BACKPROPAGATION , 1996 .

[33]  Dimitris C. Theodoridis,et al.  Direct adaptive regulation of unknownnonlinear systems with analysis of themodel order problem , 2011, Journal of Zhejiang University SCIENCE C.

[34]  X Li,et al.  Fuzzy Regression Modeling for Tool Performance Prediction and Degradation Detection , 2010, Int. J. Neural Syst..

[35]  Sung-Suk Kim,et al.  Development of Quantum-Based Adaptive Neuro-Fuzzy Networks , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[36]  Hojjat Adeli,et al.  Hybrid Control of Smart Structures Using a Novel Wavelet‐Based Algorithm , 2005 .

[37]  Nazmul Siddique,et al.  Computational Intelligence: Synergies of Fuzzy Logic, Neural Networks and Evolutionary Computing , 2013 .

[38]  Wolfgang Graf,et al.  Recurrent neural networks for fuzzy data , 2011, Integr. Comput. Aided Eng..

[39]  Alexandru Stancu,et al.  Nonlinear System Identification Based on Internal Recurrent Neural Networks , 2009, Int. J. Neural Syst..

[40]  Danilo P. Mandic,et al.  Recurrent Neural Networks for Prediction , 2001 .

[41]  E. H. Mamdani,et al.  Advances in the linguistic synthesis of fuzzy controllers , 1976 .

[42]  Hojjat Adeli,et al.  Resource Scheduling Using Neural Dynamics Model of Adeli and Park , 2001 .

[43]  Hojjat Adeli,et al.  WIND-INDUCED MOTION CONTROL OF 76-STORY BENCHMARK BUILDING USING THE HYBRID DAMPER-TLCD SYSTEM , 2005 .

[44]  René V. Mayorga,et al.  Non-Linear Global Optimization via Parameterization and Inverse Function Approximation: an Artificial Neural Networks Approach , 2007, Int. J. Neural Syst..

[45]  Uwe Reuter.  A fuzzy approach for modelling non-stochastic heterogeneous data in engineering based on cluster analysis , 2011, Integr. Comput. Aided Eng..

[46]  Edgar N. Sánchez,et al.  Blood glucose Level Neural Model for Type 1 Diabetes Mellitus Patients , 2011, Int. J. Neural Syst..

[47]  H. Adeli,et al.  Dynamic Fuzzy Wavelet Neural Network Model for Structural System Identification , 2006 .

[48]  Dimitris C. Theodoridis,et al.  Dynamical Recurrent Neuro-Fuzzy Identification Schemes Employing Switching parameter Hopping , 2012, Int. J. Neural Syst..

[49]  Paola Bandini,et al.  Prediction of Pavement Performance through Neuro‐Fuzzy Reasoning , 2010, Comput. Aided Civ. Infrastructure Eng..

[50]  H Adeli,et al.  WAVELET HYBRID FEEDBACK-LMS ALGORITHM FOR ROBUST CONTROL OF CABLE-STAYED BRIDGES , 2005 .

[51]  Hojjat Adeli,et al.  Object-oriented backpropagation and its application to structural design , 1994, Neurocomputing.

[52]  Hojjat Adeli,et al.  An adaptive conjugate gradient learning algorithm for efficient training of neural networks , 1994 .

[53]  Hojjat Adeli,et al.  Dynamic fuzzy wavelet neuroemulator for non‐linear control of irregular building structures , 2008 .

[54]  Wellington Pinheiro dos Santos,et al.  An adaptive fuzzy-based system to simulate, quantify and compensate color blindness , 2017, Integr. Comput. Aided Eng..

[55]  Dimitris C. Theodoridis,et al.  A New Neuro-FDS Definition for Indirect Adaptive Control of Unknown Nonlinear Systems Using a Method of Parameter Hopping , 2009, IEEE Transactions on Neural Networks.

[56]  Hojjat Adeli,et al.  Parallel backpropagation learning algorithms on CRAY Y-MP8/864 supercomputer , 1993, Neurocomputing.

[57]  Wolfgang Graf,et al.  Structural Analysis with Fuzzy Data and Neural Network Based Material Description , 2012, Comput. Aided Civ. Infrastructure Eng..

[58]  Hojjat Adeli,et al.  Scheduling/Cost Optimization and Neural Dynamics Model for Construction , 1997 .

[59]  Hojjat Adeli,et al.  Distributed neural dynamics algorithms for optimization of large steel structures , 1997 .

[60]  Hojjat Adeli,et al.  Comparison of fuzzy-wavelet radial basis function neural network freeway incident detection model with California algorithm , 2002 .

[61]  Wen Yu,et al.  Nonlinear system identification with recurrent neural networks and dead-zone Kalman filter algorithm , 2007, Neurocomputing.

[62]  Hojjat Adeli,et al.  Neural Network-Wavelet Microsimulation Model for Delay and Queue Length Estimation at Freeway Work Zones , 2006 .

[63]  Li-Xin Wang,et al.  Adaptive fuzzy systems and control - design and stability analysis , 1994 .

[64]  Li-Xin Wang,et al.  Adaptive fuzzy systems and control , 1994 .

[65]  Nong Zhang,et al.  Application of evolving Takagi-Sugeno fuzzy model to nonlinear system identification , 2008, Appl. Soft Comput..

[66]  Hojjat Adeli,et al.  Spiking Neural Networks , 2009, Int. J. Neural Syst..

[67]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[68]  Werner Leonhard,et al.  Control of Electrical Drives , 1990 .

[69]  Meng Joo Er,et al.  A Novel Efficient Learning Algorithm for Self-Generating Fuzzy Neural Network with Applications , 2012, Int. J. Neural Syst..

[70]  Hans-Georg Zimmermann,et al.  Recurrent Neural Networks Are Universal Approximators , 2006, ICANN.

[71]  Hojjat Adeli,et al.  Enhancing Neural Network Traffic Incident‐Detection Algorithms Using Wavelets , 2001 .

[72]  Dimitris C. Theodoridis,et al.  A New Direct Adaptive regulator with Robustness Analysis of Systems in Brunovsky Form , 2010, Int. J. Neural Syst..

[73]  Asim Karim,et al.  Neural Network Model for Optimization of Cold-Formed Steel Beams , 1997 .

[74]  Tet Hin Yeap,et al.  Feedback control of chaotic systems , 1994 .

[75]  Chia-Feng Juang,et al.  A TSK-type recurrent fuzzy network for dynamic systems processing by neural network and genetic algorithms , 2002, IEEE Trans. Fuzzy Syst..

[76]  Hojjat Adeli,et al.  Wavelet-Hybrid Feedback Linear Mean Squared Algorithm for Robust Control of Cable-Stayed Bridges , 2005 .

[77]  ASHIF PANAKKAT,et al.  Neural Network Models for Earthquake Magnitude Prediction Using Multiple seismicity Indicators , 2007, Int. J. Neural Syst..

[78]  Bart Kosko,et al.  Fuzzy Engineering , 1996 .

[79]  Chih-Min Lin,et al.  Adaptive Control for MIMO uncertain nonlinear Systems Using Recurrent Wavelet Neural Network , 2012, Int. J. Neural Syst..

[80]  Paris A. Mastorocostas,et al.  A recurrent fuzzy-neural model for dynamic system identification , 2002, IEEE Trans. Syst. Man Cybern. Part B.

[81]  Chin-Teng Lin,et al.  A neural fuzzy control system with structure and parameter learning , 1995 .

[82]  Alexander G. Loukianov,et al.  Real-Time Discrete Neural Block Control Using Sliding Modes for Electric Induction Motors , 2010, IEEE Transactions on Control Systems Technology.

[83]  Witold Pedrycz,et al.  Fuzzy Monte Carlo Simulation and Risk Assessment in Construction , 2010, Comput. Aided Civ. Infrastructure Eng..

[84]  Bogdan Codres,et al.  Nonlinear System Identification and Control Based on Modular Neural Networks , 2011, Int. J. Neural Syst..

[85]  Manolis A. Christodoulou,et al.  Collision Avoidance in Commercial Aircraft Free Flight via Neural Networks and Non-Linear Programming , 2008, Int. J. Neural Syst..

[86]  Hongjin Kim,et al.  HYBRID FEEDBACK-LEAST MEAN SQUARE ALGORITHM FOR STRUCTURAL CONTROL , 2004 .

[87]  Edgar N. Sánchez,et al.  Discrete-Time Reduced Order Neural Observers for Uncertain Nonlinear Systems , 2010, Int. J. Neural Syst..

[88]  A Karim,et al.  COMPARISON OF THE FUZZY–WAVELET RBFNN FREEWAY INCIDENT DETECTION MODEL WITH THE CALIFORNIA ALGORITHM , 2002 .

[89]  H Adeli,et al.  Optimal Control of Adaptive/Smart Bridge Structures , 1997 .

[90]  Hojjat Adeli,et al.  NEURO-FUZZY LOGIC MODEL FOR FREEWAY WORK ZONE CAPACITY ESTIMATION , 2003 .

[91]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[92]  Marios M. Polycarpou,et al.  High-order neural network structures for identification of dynamical systems , 1995, IEEE Trans. Neural Networks.

[93]  Shih-Hsu Wang,et al.  Neuro‐Fuzzy Cost Estimation Model Enhanced by Fast Messy Genetic Algorithms for Semiconductor Hookup Construction , 2012, Comput. Aided Civ. Infrastructure Eng..

[94]  Dimitris C. Theodoridis,et al.  Indirect Adaptive Control of Unknown Multi Variable nonlinear Systems with Parametric and Dynamic Uncertainties Using a New Neuro-Fuzzy System Description , 2010, Int. J. Neural Syst..

[95]  Frank L. Lewis,et al.  Neural Network Control Of Robot Manipulators And Non-Linear Systems , 1998 .

[96]  Hans-Georg Zimmermann,et al.  Recurrent Neural Networks are Universal approximators , 2007, Int. J. Neural Syst..

[97]  PETIA KOPRINKOVA-HRISTOVA,et al.  Backpropagation through Time Training of a Neuro-Fuzzy Controller , 2010, Int. J. Neural Syst..

[98]  Stephen Yurkovich,et al.  Fuzzy Control , 1997 .

[99]  Alexander G. Loukianov,et al.  Real-Time Recurrent Neural State Estimation , 2011, IEEE Transactions on Neural Networks.

[100]  Ch. Venkateswarlu,et al.  Modeling and Optimization of a Pharmaceutical Formulation System Using Radial Basis Function Network , 2009, Int. J. Neural Syst..