Dissertation > Excellent graduate degree dissertation topics show

Nonlinear predictive control model based on LS-SVM online

Author: LuJuLiang
Tutor: XiangZuoZuo
School: Nanjing University of Technology and Engineering
Course: Control Theory and Control Engineering
Keywords: LS-SVM Online model Nonlinear model predictive control Multi-model Predictive Functional Control
CLC: TP13
Type: Master's thesis
Year: 2009
Downloads: 219
Quote: 0
Read: Download Dissertation

Abstract


With the development of modern industry and the advancement of technology , the constant pursuit of economic efficiency of production as well as industrial production process has become increasingly large , complex , large range of operating points and other reasons , linear predictive control (LMPC) method can not meet the control performance requirements . Therefore, the study of nonlinear model predictive control (NMPC) has become an important research topic in the control engineering field . Most of NMPC method is to establish control in the offline model on the basis of the system domain the migration often makes offline model is not an accurate description of the actual situation , the offline model - based predictive control can not achieve satisfactory control effect , the research for this problem nonlinear model predictive control based online LS-SVM model . On the basis of previous research work , a more in-depth study certain issues of the NMPC main contents are as follows : (1 ) the lack of robustness for LS-SVM , a weighted LS- SVM . This method takes into account the time factor and similarity factor as a weighting factor , the simulation results show the robustness of the method to be effective in improving . ( 2 ) for the NMPC lack of offline model , a model based on weighted LS-SVM online NMPC algorithm . The algorithm uses the weighted LS-SVM establish online model , as rolling optimization strategy and particle swarm optimization . The simulation results show that the online model based NMPC better than the offline model based NMPC . ( 3 ) for offline clustering modeling shortcomings , a method based on weighted LS-SVM online clustering modeling . At each sampling point for the single model - based nonlinear predictive function control nonlinear model linearized inadequate study based on weighted LS-SVM online clustering modeling of multi- model predictive function control algorithm , and multi-model predictive function control law for multi- input multi-output system derived analytical and simulation results show that better than offline single model predictive functional control based on the online clustering multi- model predictive function control effect and anti-jamming capability .

Related Dissertations

  1. The Research and Application of Modified Algorithms About Fuzzy Predictive Functional Control,TP273
  2. Research on High-precision Measurement and Modeling of High Voltage Electric Transformers,TM452
  3. Research on Multi-hierarchical Model Predictive Control of Nonlinear System,TP273
  4. Research on Power Transformer Faults Diagnosis and Prediction Based on LS-SVM,TM41
  5. Model predictive control in nuclear reactor core temperature control applied research,TL362
  6. A medium -scale multi- model ensemble forecasting system establishment and application of research,P456.7
  7. Research and Design of Power Management System for Fuel Cell Electric Bus,TM911.4
  8. Research on Networked Control System Based on Predictive Functional Control,TP273
  9. Research on the Generalization and Applications of Suport Vector Machines,TP18
  10. Fuzzy Multi-model Soft Sensor and Recursive PLS Algorithm,TB99
  11. Based on Nios Ⅱ PWM DC motor speed control system design,TM33
  12. Predictive Functional Control Based on Artificial Neural Networks and It’s Application of Thermal Power Plant,TP183
  13. The Research on Multi-model Predictive Active Fault-tolerant Control Method Based on SVM,TP273
  14. Application and Research of Collaborative Filtering on Recommendation Systems for E-Commerce,TP311.52
  15. Architecture Design and Algorithm Research of Elevator Fault Diagnosis System,TU857
  16. Study on Short-term Load Forecasting Based on Weighted LS-SVM,TM715
  17. The Research on Robustness of Predictive Functional Control Systems,TP13
  18. E. coli High -density fermentation process modeling and control,TQ920.1
  19. Beer Boiling Temperature Application of Predictive Functional Control Based on Support Vector Machine,TS262.5
  20. The Research on Active Fault-tolerant Control Based on Inverse System Method,O231.2

CLC: > Industrial Technology > Automation technology,computer technology > Automated basic theory > Automatic control theory
© 2012 www.DissertationTopic.Net  Mobile