Dissertation > Excellent graduate degree dissertation topics show

Research on Genetic Programming and Its Application in Automatic Designing of Human-simulated Intelligent Controller Structrue

Author: HaoYanWei
Tutor: LiZuShu
School: Chongqing University of Technology
Course: Applied Computer Technology
Keywords: Improved genetic programming Parallel computing Double Inverted Pendulum Structure Automatic design
CLC: TP13
Type: Master's thesis
Year: 2011
Downloads: 30
Quote: 0
Read: Download Dissertation

Abstract


Evolutionary algorithm is a random search methods that mimic the process of natural evolution, initially has three branches: genetic algorithms, evolutionary programming, and evolutionary strategies. The early nineties, the American scholar Koza proposed a new structure on the basis of the genetic algorithm described in methods - genetic planning (GP: GeneticProgramming). Main differences shown on the chromosome structure and evolutionary algorithm, with a dynamic tree structure to represent the chromosomes. Aspects The hierarchical coding length dynamic variable characteristics of the GP algorithm has a description of the problem, it is widely used in artificial intelligence, machine learning, symbolic processing. Kinesthetic intelligence schema-based humanoid intelligent control theory to solve control problems shows the outstanding advantages, provides an effective way to solve complex system problems. But to complete the structural design of intelligent schema humanoid intelligent controller based on kinesthetic or excessive reliance on experts experience control problems change, the need to redesign the structure of the controller, which gives designers brought difficulties. Not yet a mature method has universal significance for the automated design of of humanoid intelligent controller structure. Genetic programming algorithm is the analog nature of biological evolution a universal ideas developed optimization method, therefore, the idea of ??this paper the use of genetic programming algorithm to solve the problem of automatic design of humanoid intelligent controller structure. Inverted pendulum is a typical application for kinesthetic intelligence schema-based humanoid intelligent control, so this paper as a test platform for a double inverted pendulum swing-up inverted, verified by the results of the simulation experiments, genetic programming to solve the above problem sex. The main contents of the thesis: (1) to improve the genetic programming algorithm. This paper introduces the basic genetic programming and its various improvements, the focus of the improved strategy, and this paper an improved genetic programming algorithm performance test, (2) improving the genetic programming algorithm on two pendulum inverted Swing-Up inverted structure of the controller automatically design. Controller structure will have a direct impact to the merits of the control target could be achieved or effect, this paper presents the details of the design process and the simulation results, and the comparative experiments, the experimental results show that the proposed improved genetic programming algorithm certain advantages. (3) Improved genetic programming algorithm and parallel computing combined with genetic programming algorithm two inverted swing-up inverted the structure of the controller automatic design, fitness evaluation is quite time-consuming, the average run time is longer, therefore, combined with parallel computing. This paper describes the MPI-based parallel genetic programming algorithm design process, and carried out the experiment. The experimental results show the effectiveness of the algorithm to improve the computing speed.

Related Dissertations

  1. Research and Design of a High-Performance Scalable Public Key Cryptographic Coprocessor,TN918.1
  2. Research on Video Compression Algorithm Based on Multi-core Computing Platform,TN919.81
  3. Research of Finite Element Method on GPU,O241.82
  4. Numerical Simulation of Radiofrequency Waves in Magnetized Plasma,TL612
  5. The Algorithm Researches of Novel Wide Area Backup Protection for Power Grid,TM774
  6. The Research on Online Adaptive Settings,TM77
  7. Fault Tolerance for MapReduce in the Cloud Environment,TP302.8
  8. High dynamic SINS navigation solution algorithm and parallelization of,TN966
  9. Image retrieval method and system for parallel computing,TP391.3
  10. GPU-accelerated particle filter PET image reconstruction algorithm,TP391.41
  11. GPU-based parallel search algorithm for time series,TP391.41
  12. CPU-based inverse algorithm source strength,TP18
  13. Parallel computing for data-intensive reconfigurable linear array processor architecture design,TP332
  14. Large-scale approximation paragraph fingerprint - based page detection algorithm research,TP393.092
  15. Parallel and Dual-systems Cooperative Co-evolutionary Differential Evolution Algorithms and Their Application,TP18
  16. Research on Fault-Tolerant Parallel Skyline Query Technology in Cloud Computing Environment,TP311.13
  17. A Study on Diagonal Computing Model for GPGPU Platform,TP391.41
  18. Algorithm Study on Accelerate CV Image Segmentation and Exterior Industrial Image Reconstruction by CUDA,TP391.41
  19. The Study on the UAV Digital Remote Sensing & Survey System Integration and Images Data Processing,P237
  20. Application of Parallel FDTD and MPSTD Algorithm in EM Scattering,O441.4
  21. A Parallel DDM Preconditioner for Solving Finite Element Discretization of Elasticity Problem in Three Dimension,O241.82

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