Dissertation > Excellent graduate degree dissertation topics show

Neural Network Inverse Model Identify and Adaptive Inverse Control Study

Author: WangYaJing
Tutor: WuShiChang；LiuFuCai
School: Yanshan University
Course: Control Theory and Control Engineering
Keywords: Adaptive Inverse Control Disturbance canceler Neural network inverse model Nonlinear systems
CLC: TP273.2
Type: Master's thesis
Year: 2010
Downloads: 172
Quote: 0
Read: Download Dissertation

Abstract


Adaptive inverse control design method as a novel controller and regulator , causing extensive research interest in the domestic and foreign scholars . The development of modern neural network technology to create conditions for nonlinear adaptive inverse control and reasonable exploration and design dynamic neural network architecture and algorithms , to build a more effective system architecture has become nonlinear adaptive inverse control the focus of the study . This paper studies the structure and algorithm of the neural network , and the inverse model of the neural network - based nonlinear adaptive control system , the main contents are as follows : First, the system analysis of several existing RBF network algorithm to determine the cluster center : K- means clustering method , gradient descent method , orthogonal least squares method and dynamic clustering method . Dynamic clustering method distance threshold is fixed this shortcoming , an improved dynamic clustering method based on sample density to adjust the distance threshold by the identification of simulation data on the gas stove , to verify the effectiveness of the algorithm and fast . Second, RBF and BP neural network is applied to the adaptive inverse control system , the the order inertia simulation results show that the generalization ability of RBF network affect the accuracy of the system 's control . BP network based adaptive inverse noise elimination method applied to the the roll eccentricity thickness control in simulation results show that this method can eliminate the strip thickness deviation indicators are better than PID control , roll eccentricity thickness control provides a new solution . Finally, based on BP network adaptive inverse noise eliminating method applied to a nonlinear system control , system control error and standard deviation were less than other methods , to verify the effectiveness of the control algorithm for nonlinear systems .

Related Dissertations

  1. The Research and Application of Modified Algorithms About Fuzzy Predictive Functional Control,TP273
  2. Research on Adaptive Inverse Control for the Hysteresis and Creep Characteristics of IPMC,TP273.2
  3. A class of semi- strict-feedback nonlinear parametric Adaptive Control Method,TP13
  4. Study on Fault-tolerant Guaranteed Cost Control for Nonlinear Systems,TP13
  5. Research on Multi-hierarchical Model Predictive Control of Nonlinear System,TP273
  6. Greenhouse environmental parameters control,S316
  7. Multiscale information fusion algorithm,TP202
  8. Maglev system H_ ∞ Control,TH-39
  9. The Study on Control Method for Nonlinear Systems Based on Element Models,TP13
  10. Two-Stage Identification Methods Based on Data Filtering,TP13
  11. Chaotic System Control Via Self-constructing Neural Network,TP183
  12. Preliminary Study on Law Dimension and Visualization of Nonlinear System,TP391.41
  13. Studies on Experimental Modeling and Frequency Domain Identification of Nonlinear Systems,O322
  14. Adaptive Regulation of Uncertain Nonlinear Systems,O231.2
  15. Estimating Domains of Attraction of Autonomous Nonlinear Systems,O224
  16. Researches on Fractional-Order PI~λD~μ Excitation Controller of Micro Gas Turbine,TM921.5
  17. H_∞ Control for Nonlinear Systems Based on Neural Networks,TP13
  18. Optimal Control for Networked Control Systems with Data Packet Dropout,TP273
  19. The cue balance system control method,TP273
  20. Iterative Learning Control Design of Multiple Time-Delay Systems,TP13
  21. The Researchs for Fault Diagnosis Algorithm and Simulation Based on Sliding Mode Observer,TP277

CLC: > Industrial Technology > Automation technology,computer technology > Automation technology and equipment > Automation systems > Automatic control,automatic control system > Adaptive ( self- tuning ) control,adaptive control ( self-tuning ) system
© 2012 www.DissertationTopic.Net  Mobile