Evolution of artificial neural network controller for a boost converter

EVOLUTION OF ARTIFICIAL NEURAL NETWORK CONTROLLER FOR A BOOST CONVERTER VASANTH SUBRAMANYAM (B E., Anna University, India) A THESIS SUBMITTED FOR THE DEGREE OF MASTER OF ENGINEERING DEPARTMENT OF ELECTRICAL & COMPUTER ENGINEERING NATIONAL UNIVERSITY OF SINGAPORE 2007 Acknowledgements I would like to thank all the people who have helped me during my study at the National University of Singapore First and foremost, I would like to thank my supervisors Assoc Prof Dipti Srinivasan and Assoc Prof Ramesh Oruganti They have been extremely enthusiastic and supportive regarding this research which has helped me learn many new aspects of artificial intelligence and control I appreciate both of them for their innovative ideas and profound knowledge in Artificial Intelligence and Controls Without their encouragement and support, this study would not have been possible I had the pleasure of interacting with many research students from the Power Systems Laboratory, Power Electronics Laboratory and Electrical Machines Laboratory My sincere thanks to all of them for the wonderful time we had working and helping each other in the laboratories My warmest thanks and regards to the Laboratory Officer Mr Seow Heng Cheng, for his helpful nature and dedication in making the laboratory such a nice place to work Without his support, it would have been impossible to carry out the research in the laboratory And finally, there are no words suffice to express my heart felt gratitude to my parents I would have never reached so far in life without their constant love, support and encouragement ii Contents ACKNOWLEDGEMENTS II CONTENTS III SUMMARY VII LIST OF FIGURES .XI LIST OF TABLES XVI LIST OF SYMBOLS AND ABBREVIATIONS XVII CHAPTER INTRODUCTION 1.1 M OTIVATION 1.2 THESIS OBJECTIVES AND ACHIEVEMENTS 1.3 PROBLEM S TATEMENT 1.4 STRUCTURE OF THE THESIS CHAPTER BACKGROUND 2.1 ARTIFICIAL N EURAL N ETWORKS 2.2 PARTICLE SWARM OPTIMIZATION ALGORITHM 12 2.2.1Adaptive PSO 15 2.3 G ENETIC ALGORITHMS 15 2.4 SUMMARY 18 iii CHAPTER 19 LITERATURE SURVEY 19 3.1 LITERATURE S URVEY 19 3.2 SUMMARY 24 CHAPTER 26 OVERVIEW OF A BOOST CONVERTER AND ITS CONTROL DIFFICULTIES 26 4.1 INTRODUCTION TO DC-DC POWER CONVERTERS 26 4.2 OPERATING PRINCIPLE OF A BOOST CONVERTER 27 4.2.1Continuous Conduction Mode 28 4.2.2Discontinuous Conduction Mode 30 4.2.3Limit between Continuous and Discontinuous Modes 32 4.2.4Effect of Parasitic Resistances 35 4.3 CONTROL DIFFICULTIES WITH THE BOOST CONVERTER 37 4.4 SUMMARY 38 CHAPTER 39 PROPOSED DESIGN APPROACH FOR ARTIFICIAL NEURAL NETWORK CONTROLLER 39 5.1 CONTROL SCHEME OF THE ANN CONTROLLER 40 5.2 CONFIGURATION OF N EURON AND N EURAL N ETWORK 44 5.3 M ATHEMATIC M ODELING AND STABILITY ANALYSIS OF THE FEED FORWARD ANN CONTROLLER 46 iv 5.4 NEURAL N ETWORK D ESIGN USING A D UAL LAYERED PARTICLE SWARM OPTIMIZATION ALGORITHM 49 5.4.1Principle of the Dual-Layer Particle Swarm Optimization Algorithm 50 5.4.2Implementation of the DLPSO Algorithm 51 5.5 Benchmark PI Controller Design for a Boost Converter 58 5.6 WEIGHT OPTIMIZATION USING GA AND PSO BASED H YBRID APPROACH 61 5.7 SUMMARY 64 CHAPTER 65 SIMULATION RESULTS AND ANALYSIS 65 6.1 OPTIMIZATION OF THE PARAMETERS OF THE DLPSO ALGORITHM 65 6.2 SIMULATION R ESULTS 72 6.3 TESTS CONDUCTED ON THE ANN CONTROLLER DESIGNED USING THE DLPSO ALGORITHM AT VARIOUS OPERATING POINTS 86 6.4 COMPARISON OF A B ENCHMARK PI CONTROLLER AND ANN CONTROLLER DESIGNED BY DLPSO ALGORITHM 92 6.5 COMPARISON OF THE GA USED IN THE HYBRID APPROACH AND THE PSO USED IN THE DLPSO A LGORITHM FOR LEARNING OF THE WEIGHTS OF THE ANN CONTROLLER 94 6.6 DISCUSSION ON THE PERFORMANCE OF THE PROPOSED APPROACH 98 6.7 SUMMARY 98 CHAPTER 100 CONCLUSION & FUTURE WORK 100 v 7.1 CONCLUSIONS 100 7.2 FUTURE WORK 103 BIBLIOGRAPHY 105 LIST OF PUBLICATIONS 110 CONFERENCE PAPER 110 APPENDIX 111 SOFTWARE CODES FOR THE DLPSO ALGORITHM 111 A FIRST LAYER OF PSO FOR STRUCTURAL OPTIMIZATION 111 B SECOND LAYER OF DLPSO FOR WEIGHT OPTIMIZATION 115 C FITNESS EVALUATION OF THE ANN CONTROLLER FOR THE DLPSO ALGORITHM 117 D NEURAL NETWORK ARCHITECTURE BEING CREATED IN SIMULINK 119 E NEURON CONFIGURATION IN AN ANN CONTROLLER OPTIMIZED BY DLPSO ALGORITHM 120 vi Summary In recent years, Artificial Intelligence techniques such as neural networks and biologically inspired algorithms are gaining immense popularity due to their unconventional ability to solve complex problems Utilization of such unconventional artificial intelligent techniques to solve complex control engineering problems proves to open a new dimension to Control Engineering This thesis focuses on the design of controllers, which is one such complex problem, where the application of artificial intelligent techniques is justified The complexity involved in the design process of a controller comprises of the optimization of the following decision parameters: · the total number of signal processing blocks to be employed in the controller · The type of each block (e.g., lead, lag, gain, integrator, differentiator, adder, inverter, subtractor, and multiplier) · The tuning of all the parameters for all the blocks and the topological interconnections between the blocks · Whether or not to employ internal feedback (i.e., feedback inside the controller) The optimization of these decision parameters combined with the expertise and knowledge of the system to be controlled, constitutes the design of the controller The emphasis of this thesis is automation of the controller design process using artificial intelligent techniques without prior knowledge of the system to be controlled vii This thesis investigates the feasibility of applying a hybrid approach to the automated design of controllers which encapsulates the concepts associated with Artificial Neural Networks (ANN) and Swarm Intelligence The problem which needs to be addressed in order to automate the design of the ANN controller is the design of the ANN itself The designing process of the ANN constitutes the following decisions: · The structure of the ANN · The tuning of the weights of the ANN Thus, an algorithm is proposed in this thesis called the “Dual- layered Particle Swarm Optimization (DLPSO) algorithm” for effectively designing the structure and tuning the weights of the ANN This algorithm consists of two operation layers where one is used for the design of the architecture and the other for the tuning of the weights The concept of two layers is the key feature because, for every configuration developed by the algorithm, the weights are tuned to the optimum Hence, the ANN controller designed by this method can be considered to have an optimal structure for the particular application The advantage brought about by this aspect is the need of minimum amount of human intervention and least domain knowledge of the system for designing the controller Moreover, the neural network learning used here is classified as unsupervised since the outputs vary depending on the inputs and hence, there are no fixed input-output training data for training of the neural network This justifies the application of the DLPSO algorithm for designing the structure and weights of the ANN controller Thus, in this thesis, the ANN controller designed based on the above method, is tested on a classical boost converter because it’s a non- minimum phase, non-linear system which makes it difficult to control Generally, the non- minimum phase viii characteristic is solved by controlling the output voltage in an indirect way, that is, by selecting a different measure of the output voltage, to make the system a minimum phase one and commonly, the inductor current used as the measure for the minimum phase output Thus, by doing this, the dynamic response of the system is improved Dynamic response here refers to effectiveness of the actual output voltage to track the reference output voltage To improve the dynamic response and effectively stabilize and control the output voltage at different operating points, the advantages of ANNs viz., interconnectivity and learning capabilities, are used The ANN controller uses the feedback input from the output of the system and thus calculates the error between the reference input and the output, which acts as the input to the ANN The control signal to the boost converter is its duty cycle ratio By controlling the duty cycle ratio of the boost converter, the output voltage of the converter is regulated The performance of the controller is evaluated based on its input transient response The transient analysis of the boost converter is carried out by providing a step change to the reference output voltage and hence, determining the dynamic performance of the ANN controller by analyzing the actual output voltage The dynamic performance indicators used are typically, the overshoot voltages and settling times This is carried out for various values of reference voltages i.e at different operating points This performance is compared to that of a conventional PI controller which is used as a benchmark to evaluate the performance of the ANN controller Thus, in this thesis, the proposed DLPSO algorithm is benchmarked using a conventional PI controller It has been brought out from the simulation results and analysis, that the ANN controller designed outperforms the PI controller in terms of ix settling time and is better or comparable to the PI controller in terms of overshoot Hence, for this application, the dynamic performance of the ANN controller designed using the DLPSO algorithm is better than the conventional PI controller Moreover, the performance of the PSO algorithm for the training of the weights is shown to be better than that of a conventional genetic algorithm, where the parameters for comparison are computational time and the number of generations needed to obtain the resulting weights of the ANN A detailed analysis and simulation studies have been presented in an articulate manner to substantiate the novelty of this controller design strategy x 27 Crosby, Jack L (1973) Computer Simulation in Genetics London: John Wiley & Sons 28 Fogel, David B (editor) (1998) Evolutionary Computation: The Fossil Record New York: IEEE Press 29 Barricelli, Nils Aall (1963) "Numerical testing of evolution theories Part II Preliminary tests of performance, symbiogenesis and terrestrial life" Acta Biotheoretica (16): 99-126 30 Baudry, Benoit; Franck Fleurey, Jean-Marc Jézéquel, and Yves Le Traon (March/April 2005) " Automatic Test Case Optimization: A Bacteriologic Algorithm" IEEE Software: 76-82 31 Kjellström, G (Dec 1991) "On the Efficiency of Gaussian Adaptation" Journal of Optimization Theory and Applications (3): 589-597 32 Falkenauer, Emanuel (1997) Genetic Algorithms and Grouping Problems Chichester, England: John Wiley & Sons Ltd ISBN 978-0-471-97150-4 33 Wright, A.H.; et al (2003) "Implicit Parallelism" Proceedings of the Genetic and Evolutionary Computation Conference 34 Syswerda, G (1989) "Uniform crossover in genetic algorithms" J D Schaffer Proceedings of the Third International Conference on Genetic Algorithms, Morgan Kaufmann 35 Fogel, David B (2000) Evolutionary Computation: Towards a New Philosophy of Machine Intelligence New York: IEEE Press, 140 36 J Kennedy and R C Eberhart Swarm Intelligence Morgan Kaufmann 2001 37 M Clerc Particle Swarm Optimization ISTE, 2006 108 38 D N Wilke, S Kok, and A A Groenwold, Comparison of linear and classical velocity update rules in particle swarm optimization: notes on diversity, International Journal for Numerical Methods in Engineering, Vol 70, No 8, pp 962–984, 2007 39 A Chatterjee, P Siarry, Nonlinear inertia variation for dynamic adaptation in particle swarm optimization, Computers and Operations Research, Vol 33, No 3, pp 859– 871, 2006 40 A P Engelbrecht Fundamentals of Computational Swarm Intelligence Wiley, 2005 [1] 41 D N Wilke Analysis of the particle swarm optimization algorithm, Master's Dissertation, University of Pretoria, 2005 [2] 42 M Clerc, and J Kennedy, The Particle Swarm- Explosion, Stability, and Convergence in a Multidimensional Complex Space, IEEE Transactions on Evolutionary Computation, 2002, 6, 58-73 43 Viswanathan, K.; Oruganti, R.; Srinivasan, D.; “A novel tri-state boost converter with fast dynamics,” Power Electronics, IEEE Transactions on Volume 17, Issue 5, Sept 2002 109 List of Publications Conference Paper · Vasanth Subramanyam, Dipti Srinivasan, Senior Member, IEEE, Ramesh Oruganti, Senior Member, IEEE, “A Dual Layered PSO Algorithm for Evolving an Artificial Neural Network Controller”, Congress of Evolutionary Computation, IEEE International Conference on, Singapore, 2007 110 APPENDIX Software Codes for the DLPSO algorithm A First layer of PSO for structural optimization close all; clear all; clc; global global global global global global global global num_layer; num_neuron;% Number of inputs, layers and neurons count; weight_count; globa; glob; vref; stp; L=278e-6; C=48e-6; R=12.5; vref=25; vs=12.5; stp=2; vr=25; st=2; num_particles=10; alpha=0.9; c1=1.49; c2=1.49; % random initialisation of particles for i=1:num_particles y=randperm(4); p(i).layer=zeros(1); p(i).layer=y(1); clear y; y=randperm(20); p(i).neuron=zeros(p(i).layer); p(i).neuron=y(1:p(i).layer); clear y; % random initialisation of velocity v(i).layer=p(i).layer; 111 y=randperm(10); v(i).neuron=zeros(v(i).layer); v(i).neuron=y(1:v(i).layer); clear y; end ite=1; max_ite=20; while (ite20) p(i).neuron(k)=20; end end if (k==3)||(k==4) if (p(i).neuron(k)>10) p(i).neuron(k)=10; end end end save('work'); clear all; load('work'); end alpha=alpha-((0.9-0.4)/max_ite)*ite; c1=c1-(ite/max_ite); c2=c2+(ite/max_ite); glob(ite)=gbest.fit; ite=ite+1; save('work1'); clear all; load('work1'); end plot (glob); 114 B Second layer of DLPSO for weight optimization function [weight]=pso1(ite,i) global vr; global st; global count; global weight_count; global glob; global gbest1; global pbest1; global globa; global vref; global stp; num_particles1=20; alpha1=0.9; c11=1.49; c21=1.49; % random initialisation of particles p1=rand(num_particles1,weight_count); % random initialisation of velocity velocity1=rand(num_particles1,weight_count)/10; ite1=1; max_ite1=20; vref=vr; stp=st; while (ite1