Dissertation > Excellent graduate degree dissertation topics show

Modeling and Control of Neural Network for Cupola

Author: HuDongGang
Tutor: SunZhiYi
School: Taiyuan University of Science and Technology
Course: Control Theory and Control Engineering
Keywords: Cupola Artificial Neural Networks Adaptive control
CLC: TP183
Type: Master's thesis
Year: 2008
Downloads: 64
Quote: 3
Read: Download Dissertation

Abstract


Artificial Neural Network (Artificial Neural Network, for short ANN) is a network interconnect widely made by a large number of processing units, it is proposed on the basis of the results of modern neuroscience. The neural network-based, large-scale simulation of parallel processing has strong robustness, fault tolerance and self-learning ability. Neural networks of arbitrary nonlinear function with arbitrary approximation and learning abilities, the neural network has a good effect on the control of nonlinear systems and difficult modeling system, and it is in solving highly nonlinear and serious uncertainty system The control has great potential. The application of neural network has penetrated into all aspects of the field of automatic control, system identification, system control, optimizing the calculation and control system fault diagnosis and fault-tolerant control. The cupola is the most basic smelting equipment melting molten iron casting production. Cupola melting process has not only non-linear, strong disturbance, such as large time delay characteristics exist bottom three complex process of coke combustion, heat transfer and metallurgical reaction is a typical complex industrial process. Therefore, using traditional modeling methods is very difficult to achieve the modeling of the cupola. See from the control point of view, the cupola melting as a production process, the control requirements are relatively high. Given its complexity, people with early classical and modern control theory control cupola thought the cupola has not been before fundamental improvements and smelting of standardization has not been able to achieve the desired effect. This paper first introduces the research background and significance of the topic; Research cupola melting control technology, and a brief introduction of artificial neural network development process; expounded the basic characteristics of the artificial neural network, learning styles and learning rules, study two feedforward neural networks: the BP neural network and RBF neural network, as well as their learning algorithm. Then use neural network the cupola modeling and MATLAB simulation of the actual data of the cupola. Finally cupola complex nonlinear systems, adaptive neural network control method to control the temperature of the liquid iron cupola using BP neural network identification (NNI) and controller (NNC), First NNI offline training, when the NNI training to achieve the desired effect, and then the NNC learning, the use of the deviation from the NNI, NNC can quickly to keep up with the changes in the system, so that the control quickly achieve the desired requirements. MATLAB simulation results show that this control scheme is feasible, and laid the foundation for its actual production.

Related Dissertations

  1. High Speed Frequency Measurment and Non-Linearity Correction of Frequency Modulated Capacitive Displacement Sensor,TH822
  2. Design and Research on Stabilization Loop of Gyro Stabilized Pod Control System,V241.5
  3. Robust Adaptive Control Algorithms Research for the System of Spacecraft Attitude Dynamics,V448.22
  4. Optimal Synchronization Control of a Class of Underactuated Lagrangian Systems,TP13
  5. Adaptive Control of Post-Boost Vehicle Using Multiple Models,TP273.2
  6. Study on Adaptive Fuzzy Control Algorithm and Its Implementation,TP273.4
  7. Research on Adaptive Control of Recovery of UUV with Near Wall Constraint,TP273
  8. Spectrum Variation of Vegetation in Yanzhou Coal Mine Area and Heavy Metal Stress Characteristic,X173
  9. Algorithm Research for Robot Trajectory Tracking Control,TP242
  10. Research of Adaptive Active Noise Control Based on Neural Network,TP183
  11. Researches on the Application of the Neuron-MOS in the Neural Network,TP183
  12. The Modified Harmony Search Algorithm with Control Parameters Co-evolution and Its Application,TP391.3
  13. Research on Evaluating the Feature Fatigue’s Effect on Customer Equip,F224
  14. One kind of structure in the depth of learning prototype classification method,TP18
  15. The Design of Identification System for Power Marketing Services,TP391.41
  16. Real-time feedback Adaptive Signal Control System,U491.54
  17. The Index System of Risk Warning and Evealuation for Zhangshang Enterprise,F279.27
  18. Simulation Based on Artificial Neural Network for SBBR Shortcut Nitrification Treatment,X703
  19. Theoretical and Experimental Studies on the Measurement of COD in Water Using Ultraviolet Spectrum Method,X832
  20. Pb- Al composite electrode materials preparation technology and performance,TB331
  21. Inverse model based on artificial neural networks in the production of hot-rolled strip,TG334.9

CLC: > Industrial Technology > Automation technology,computer technology > Automated basic theory > Artificial intelligence theory > Artificial Neural Networks and Computing
© 2012 www.DissertationTopic.Net  Mobile