Dissertation > Excellent graduate degree dissertation topics show

Sleeper Crack Identification Based on Mixed Texture Characteristics

Author: ZhangLi
Tutor: LiBaiLin
School: Southwest Jiaotong University
Course: Mechanical Design and Theory
Keywords: Sleeper crack Pattern recognition BP neural network textural features
CLC: TP391.41
Type: Master's thesis
Year: 2012
Downloads: 33
Quote: 0
Read: Download Dissertation

Abstract


In the high speed economic development period of our country, the transportation becomes more and more important in people’s life, people’s travel is inseparable from the traffic. Along with rapid development of railway transportation, the railway transport speed and service quality are also required higher, however the train operation mode of high speed, and overloading will affect the safety of the railway transportation,so inspection and maintenance work of railway road is a very necessary and must be paid highly valued. Due to the characteristics of great mileage and high speed railway at present, the traditional by artificial inspection and maintenance work is no longer suitable for today’s development needs, but need to develop in the direction of technology and modernize, so it is necessary to study a kind of automatic railway line defect detection system, if we once use this system,it can not only reduce the labor intensity and improve the working efficiency,but also enhance the railway safety. So this thesis has important research significance and practical value.The main works include:Research on the domestic and foreign railway road defects automatic identification technology’s development situation and other defects digital detection method. Analyse the present situation of railway road maintenance work, in view of existing problems of sleeper sleeper, to make clear the importance of sleeper crack detection.Analyse the characteristics of sleeper image, the sleeper crack types and the possible existence defect recognition problems, determine the method of sleeper crack texture feature.Build BP neural network structure base on the proposed texture feature, train samples until the training curve convergence, sample error reaches the setted expectations, and then test the sample data set.Based on the above research, the railway sleeper automatic identification system is developed, the method is tested and verified through examples. Experiments show that the method that railway sleeper crack automatic detection in this paper has an good effect,the development system has a certain application value.

Related Dissertations

  1. The Classification of High Dimsnsion Flew Field Based on Manifold Learning,V231.3
  2. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  3. Research on Text Classification Based on Biomimetic Pattern Recongnition,TP391.1
  4. Research on Visual Servo System of Mechanical ARM,TP242.6
  5. Municipal tourism land use planning environmental impact assessment,X820.3
  6. Study on Taste Characteristic of Taste Peptide Enzymatic Production from Oyster Base on A Neural Network Method,TS254.4
  7. Research on Identification System of Cashmere and Wool Fiber,TS101.921
  8. Intrusion detection based on the ultrasonic echo envelope in the military security patrols,E919
  9. The Research on Evaluation of Living Status Systems of Expressway Relocated People,D523
  10. Mine Risk Information Integration and Intelligent Early Warning,X936
  11. Research of Virus Detection Methods Based on Multiple Anti-virus Softwares Collaboration,TP309.5
  12. The Optimization Research of Feedforward Neural Network Based on Genetic Algorithms,TP183
  13. JSYJ Company Purchasing Risk Management Research,F426.92
  14. The Research on the Highway Pavement System with Neural Network and Combination Forecast,TP315
  15. Research of Orange Quality Classification Technology Based on Computer Vision,TP391.41
  16. Optimization Study on Gating System and Molding Process Parameters of Injection Mold Based on Simulation,TQ320.662
  17. A Research on Monitoring and Early Warning System of Zhejiang Marine Economy,F127
  18. Study on Fabric Defect Detection and Sutomati Grad-ing System,TP391.41
  19. SAW gas sensor array pattern recognition technology research,TP212
  20. Research on Listed Tourism Companies Financial Crisis Prewarning Model Based on the Theories of Grey Neural Network,F224
  21. Design of Positive Draw-back Motion of Wool Spinning Frame and Comparison of Prediction Models of Worsted Yarns Performances,TP183

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device
© 2012 www.DissertationTopic.Net  Mobile