Dissertation > Excellent graduate degree dissertation topics show

Wheel/Rail Force Analysis of Instrumented Wheelset Based on BP Neural Network

Author: ZhouYanHong
Tutor: LinJianHui
School: Southwest Jiaotong University
Course: Vehicle Operation Engineering
Keywords: Instrumented wheelset BP neural network Wheel-rail force Transverse vertical bridge
CLC: U260.33
Type: Master's thesis
Year: 2005
Downloads: 152
Quote: 5
Read: Download Dissertation

Abstract


Round, is one of the main factors that affect the safe operation of trains on the important parts of the locomotive running gear. The wheel-rail force) measurement is an important part of the theory and practice of vehicle dynamics, wheel force measuring wheel-rail force is the most direct and accurate method. Round of railway rolling stock as a force sensor to measure the interaction force between wheel and rail, all wheel-rail force method of measuring the most accurate method. Evaluating the dynamic performance of the railway rolling stock and the wheel-rail wear, the derailment experimental study, any method can not replace instrumented wheelset. This paper analyzes the instrumented wheelset on the principle of continuous measurement, the traditional solution is to group the test bridge group bridge mode the positive cosine Bridge and triangular-wave bridge. The instrumented wheelset force round, however, had the following defects: (1) test bridge composition will not easily change, therefore, it is difficult to ensure that the bridge group is optimal; (2) put into operation before first calibration test. Laboratory can accurately achieve vertical load calibration tests for lateral forces not yet in the wheel-rail tread surface to achieve accurate load, making it impossible to achieve the accurate calibration of the lateral load, its more load coupling can not be predicted. Through computer simulation method, found by calculation to the same force measuring wheel the best group bridge mode and the patch position, thereby improving the accuracy of the test. For the lateral loading problem can not be achieved in the laboratory, the use of computer simulation to get a satisfactory result. The actual wheel-rail coupling of lateral and vertical wheel-rail force decoupled, and propose a method of using BP neural network model decoupling cross vertical bridge. Dynamometer wheel loading position of the transverse vertical bridge also be taken into account, the traditional approach is to obtain the correction factor, or re the Bridge-thinking design a computational load position sensitive position. A BP network model vertical load size and load position. In addition, the use of force measuring wheel model simulation data output, were compared with the results of the traditional group bridge approach and deal with the results of the BP network model, BP neural network model simulation results can be better output waveform, at the same time to solve or reduce a series of problems that exist in the traditional group bridge process, and give full consideration to the position of the wheel-rail contact information. The results show that the proposed BP neural network analysis of the wheel-rail force method is feasible, the establishment of the network is also has application value.

Related Dissertations

  1. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  2. Research on Visual Servo System of Mechanical ARM,TP242.6
  3. Municipal tourism land use planning environmental impact assessment,X820.3
  4. Study on Taste Characteristic of Taste Peptide Enzymatic Production from Oyster Base on A Neural Network Method,TS254.4
  5. The Research on Evaluation of Living Status Systems of Expressway Relocated People,D523
  6. Mine Risk Information Integration and Intelligent Early Warning,X936
  7. Research of Orange Quality Classification Technology Based on Computer Vision,TP391.41
  8. Optimization Study on Gating System and Molding Process Parameters of Injection Mold Based on Simulation,TQ320.662
  9. Study on Fabric Defect Detection and Sutomati Grad-ing System,TP391.41
  10. Design of Positive Draw-back Motion of Wool Spinning Frame and Comparison of Prediction Models of Worsted Yarns Performances,TP183
  11. The Research of Multi-Robot Coordination Control Based on Vision,TP242
  12. The Research of Evaluation Method in Connect6 Based on BP-TD Learning,TP18
  13. Research on State Diagnosis on Fan Based on Factor Analysis and BP Neural Network,F426.61
  14. The Research and Design of Converter Steelmaking Endpoint Guiding System,TF345
  15. Research on Daily Load-forecasting for Power Grid Based on ANN,TM715
  16. 2205 hot workability and mechanical properties of stainless steel clad plate and Prediction,TG142.71
  17. Urban rail transit passenger transfer station early warning and response method,U239.5
  18. Studies of Ultrasonic Casting Power Based on the Dynamic Matching of Neural Network,TG23
  19. EMU bogie bearing reliability analysis and fault diagnosis technology research,U269
  20. Neural network based on the S transform fault of the autistic through line ranging,TM72
  21. Study on the Rural Financial Operating Risk Early Warning Model Based on BP Neural Network,F224

CLC: > Transportation > Rail transport > Locomotive works > General issues > Locomotive constructed > Traveling part
© 2012 www.DissertationTopic.Net  Mobile