Dissertation > Excellent graduate degree dissertation topics show

Study of Orthogonal Recurrent Neural Network and Its Application in Industrial Control

Author: ZhuYong
Tutor: QianJiXin
School: Zhejiang University
Course: Industrial automation
Keywords: Forward neural network Orthogonal basis Genetic Algorithms Dynamic Neural Network Orthogonal polynomials Regression neural network Learning rule Doctoral Dissertation Network structure Nonlinear systems
CLC: TP311.52
Type: PhD thesis
Year: 1998
Downloads: 234
Quote: 0
Read: Download Dissertation

Abstract


Society developments are increasing the complexity of many real tasks, which makes the traditional control theories limited. It is no doubt that more and more appearances of advanced tools such as neural networks, genetic algorithm and fuzzy logic can cause development of control theories. To overcome the drawback of existing neural network models in control and modeling of dynamic nonlinear systems, a novel neural network model known as Dynamic Orthogonal Polynomial Basis Neural Network (DOPBNN) is presented in this thesis. The modeling and control strategies and methodologies based on the DOPBNN are discussed in this thesis.The main contributions of this thesis are as follows:1) Up to date methods, applications, researches and drawbacks of existing neural networks in the cybernetics are summarized firstly. It becomes a good starting point of following research work.2) Based on the combination of orthogonal polynomial theory and the existent recurrent neural network structure, a novel neural network model DOPBNN is proposed. It is proved that given enough number of neuron in the middle layer, a DOPBNN can approximate any dynamical system to any degree of accuracy.3) Some important inequalities about Legendre polynomial are proposed and proved. Based on these inequalities, the sufficientconditions of globally exponential stability criteria is proposed4) The application of DOPBNN to modeling dynamic nonlinear systems is researched in detail. The update laws of weights of DOPBNN derived from the Lyapunov method ensure the convergency of the identification error and weights. By using the singular perturbation method, it is proved that if singular perturbation satisfies some conditions the convergency is ensured even there exist

Related Dissertations

  1. Yunnan Province, human capital, the network structure of critical efficiency factor,F249.27
  2. Development of the on-line Training and Examination System of Army,TP311.52
  3. Designs and Applications of Fuzzy Synthetic Evaluation Models Based on Parallel Algorithms,TP18
  4. The Research on Structure Model and Operation Mechanism of University-Enterprise Cooperative Innovation Network,F273.1
  5. Based on Genetic Algorithm Pishihang irrigation canal water allocation marshalling model of,S274
  6. Genetic Algorithm in logistics and warehousing Optimization Research,F259.2
  7. Mining resources based on genetic algorithm optimization model of,O224
  8. Research on NO-reference Image Quality Assessment Based on HVS,TP391.41
  9. The Research and Application of Modified Algorithms About Fuzzy Predictive Functional Control,TP273
  10. Optimal Control of Emulsion System in Cold Rolling,TP273
  11. Research on the Marshalling-scheduling Model and Algorithms of Freight Trains Based on Game Theory,O225
  12. Multi-directional Mutation Genetic Algorithm and Research on Neural Network Optimization,TP18
  13. The Application of Using Genetic Algorithms on Universities Course-arranging System,TP18
  14. Research on Mobile Robot Path Planning and Simulation Realization,TP242
  15. Research on Routing Algorithmin Sensor Networks Based on Cluster with Mobile Sink,TP212.9
  16. Research and Implement of the Theme Crawler for Automotive Industry,TP391.3
  17. The Research and Implement on Camera Calibration Technology Based on Trifocal Tensor,TP391.41
  18. Decision Support System of Vehicle Scheduling in Double Level Garage,TP242
  19. The Studies on Some Improvements of the GA and Their Applications in SVM,TP18
  20. A Reduction Method for Artificial Neural Network Inputs Based on An Improved Genetic Algorithm,TP18
  21. Optimal Riser Design of Steel Casting Based on CAE Analysis,TG260

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer software > Program design,software engineering > Software Engineering > Software Development
© 2012 www.DissertationTopic.Net  Mobile