Dissertation > Excellent graduate degree dissertation topics show

Investigation of Control Methodology for Magnetically Controlled Shape Memory Alloy Actuators

Author: GaoLinLin
Tutor: GaoWei
School: Jilin University
Course: Pattern Recognition and Intelligent Systems
Keywords: Controlled shape memory alloy Hysteresis nonlinear Neural Networks PI model Reinforcement learning
CLC: TP273
Type: Master's thesis
Year: 2011
Downloads: 103
Quote: 0
Read: Download Dissertation

Abstract


Magnetic shape memory alloy is a development of the relatively short history of functional materials, but because of its both piezoelectric ceramic materials and magnetostrictive material frequency fast response, high control accuracy advantages, at the same time be able to overcome the two material deformation rate is small and can not meet the large stroke actuators shortcomings. Further, because the material is a material, of a magnetron-type is easy to control the significant advantages compared to the alloy material has a thermostat type. Therefore, the controlled shape memory alloy materials received extensive attention. However, current research status, one of the kinds of material deformation mechanism, affecting factors of deformation the alloy material applications is not enough, especially in the controlled shape memory alloy actuators control method the research, almost still blank. Therefore, this article attempts to control method for magnetically controlled shape memory alloy actuators experimental studies, and lay a foundation for the further application of future controlled shape memory alloy actuators. First, the background of magnetically controlled shape memory alloy introduction, and for the the actuator deformation mechanism, static characteristics, dynamic characteristics to make analysis introduced MSMA actuator is established on the basis of the power school model, and lay the foundation for the study of the control method. Analysis of the external characteristics of magnetically controlled shape memory alloy actuators learned multifunctions hysteresis nonlinear relationship between the input and output of the actuator, for this hysteresis nonlinear relationship, consider establish actuator hysteresis model, using the model compensation method to control it. Modeling, the use of controlled shape memory alloy actuators significant superiority of the neural network function approximation using two pan Sigmoid (S) function as the activation function to solve the neural network can not achieve one-to-many mapping problem, and the successful establishment of controlled shape memory alloy actuators inverse model and inverse model of the open-loop control of the actuator, and finally using the open-loop controller with a neural network controller constitute ago feed plus feedback composite control, simulation results show the effectiveness of the control method, and can obtain better accuracy. Subsequently, the PI hysteresis model is based on the use of the Play operator to establish positive model of the MSMA actuators. Play count the promoter and Stop operator for a group of complementary operator theory Stop operator to establish MSMA actuator inverse model and inverse model of the actuator open-loop control, and finally also take advantage of the open-loop control with a neural network controller constitute a feedforward plus feedback composite control, simulation results show the effectiveness of the control method and good accuracy. Finally, the use of the theory of fuzzy control, reinforcement learning learning for MSMA actuator design a reinforcement learning fuzzy neural network controller to control the actuator. Simulation experiments for the design of the controller, the experimental results show that the controller can achieve a better control effect.

Related Dissertations

  1. High Speed Frequency Measurment and Non-Linearity Correction of Frequency Modulated Capacitive Displacement Sensor,TH822
  2. Research on Cooperative Orbit Determination in Satellite Network Based on Multi-Agent System Theory,V474
  3. Research on Anti-periodic Solutions of Delayed Cellular Neural Networks without Assuming Global Lipschitz Conditions,TP183
  4. Designs and Applications of Fuzzy Synthetic Evaluation Models Based on Parallel Algorithms,TP18
  5. Spectrum Variation of Vegetation in Yanzhou Coal Mine Area and Heavy Metal Stress Characteristic,X173
  6. Multi- license plate location method based on CNN's Intelligent Transportation Systems Research,TP391.41
  7. Research on the Models of GPS Height Fitting Based on BP Neural Network and Their Applications,P228.4
  8. Research of QoS Optimization Based on Neural Network Prediction for Ethernet Passive Optical Network,TN929.1
  9. Sensitivity Study and Application of Complex Variabal Weight Function Neural Network,TP183
  10. Researches on the Application of the Neuron-MOS in the Neural Network,TP183
  11. A Reduction Method for Artificial Neural Network Inputs Based on An Improved Genetic Algorithm,TP18
  12. On-line Monitoring of Tool Wear for Mass Production,TG71
  13. Modeling of Photovoltaic Cells and Its Application in Energy Prediction,TM914.4
  14. Research on Evaluating the Feature Fatigue’s Effect on Customer Equip,F224
  15. Delay Neutral System Stability Analysis of Neural Networks,O175.13
  16. One kind of structure in the depth of learning prototype classification method,TP18
  17. The Design of Identification System for Power Marketing Services,TP391.41
  18. The Study of Intelligent Intrusion Detection System Based on Neural Network in Linux,TP393.08
  19. RFID Information Sharing in Supply Chain and Business Valuation Research,F224
  20. Slurry pipeline transportation system, process monitoring and fault diagnosis,F426.1
  21. Consider short-term load forecasting PV,TM715

CLC: > Industrial Technology > Automation technology,computer technology > Automation technology and equipment > Automation systems > Automatic control,automatic control system
© 2012 www.DissertationTopic.Net  Mobile