Dissertation > Excellent graduate degree dissertation topics show

Research on Fault Diagnosis Methods for Gear Box Based on Empirical Mode Decomposition and Support Vector Machine

Author: ZhangBin
Tutor: ChengZuo
School: Taiyuan University of Technology
Course: Mechanical and Electronic Engineering
Keywords: Gearbox Fault Diagnosis Empirical Mode Decomposition (EMD) Support Vector Machine (SVM) Feature Extraction State recognition
CLC: TH165.3
Type: Master's thesis
Year: 2009
Downloads: 125
Quote: 0
Read: Download Dissertation

Abstract


Machinery and equipment, diagnostic procedures, including diagnostic information access, fault feature extraction and state identification of three parts. Fault feature extraction and state identification, fault diagnosis is the key. In this paper, the time-frequency analysis of empirical mode decomposition (EMD) and state recognition of the support vector machine (SVM) combined diagnosis applied to a gearbox failure. EMD method is based on the time scale of the local signal characteristics, can a complex function of signal is decomposed into a finite number of intrinsic mode functions (IMF), and each of the IMF said the original signal a natural vibration modes, they reflect the local characteristics of the signal. Further, since a frequency component contained in each IMF is not only associated with the sampling frequency, and it changes as the signal itself changes, the EMD method is an adaptive time-frequency localization analysis method is very suitable for non-stationary nonlinear signal processing. Gearbox fault vibration signal non-stationary characteristics of the EMD method introduced gearbox fault feature extraction which, its basic theoretical research to achieve the characteristics of the EMD method to extract the signal failure. And its end effect generated distortion problem, proposed a new solution, and enhance the accuracy of EMD. The support vector machine has the characteristics of small sample size, good generalization capability, global optimal solution, exhibit excellent characteristics in the field of state recognition. For mechanical fault diagnosis is difficult to obtain the large number of failures typical sample of the actual situation, this article on the basis of the theory based on support vector machine to carry out the work on the gearbox state and fault type classification and identification of research and research results with into the experiment, from the results of the analysis of the data showed that the EMD and SVM combination can be effectively used in gearbox fault diagnosis. The main work of this paper include: 1) from the common form of failure of the gearbox components, the three aspects of the typical faults of the gear system vibration mechanism and gearbox vibration signal characteristics discussed the basic knowledge on gearbox fault diagnosis. 2) starting from the basic theory of the method of analysis of EMD, EMD fault feature extraction method study. Which focuses on analysis of the impact of the end effect of EMD proposed a new method for processing end effect, to solve the EMD decomposition process produces distortion. 3) starting from the statistical learning theory, based on the theoretical basis of support vector machine to carry out the study established state recognition classifier and classifier algorithm to verify the effectiveness of the algorithm. 4) common gearbox failure, fault simulation, and application of EMD to extract the the fault signal characteristics, SVM classifier gearbox state and fault type classification, identification, and get better results.

Related Dissertations

  1. Design and Development of Application Programme for Fault Analyzer Based on Wince Platform,TP311.52
  2. Research on the 6-Dof Fault Tolerant Control of the Vibration Isolation Platform with Eight Actuators,TB535.1
  3. Research on Automatic Detection Algorithm for Substructure Distress of Highway Pavement Based on SVM,U418.6
  4. ISAR Imaging Simulation of Space Targets and Target Recognition Based on ISAR Images,TN957.52
  5. Research on Autamatic Music Structrue Analysis,TN912.3
  6. Research on Feature Extraction and Classification of Pulse Waveform for Cholecystitis and Nephrotic Syndrome Diagnosis,TP391.41
  7. Application of Q-Learning in the Content-Based Image Retrieval Technology,TP391.41
  8. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  9. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  10. Research on Visual Measurement for Spacecraft Rendezvous and Approach,TP391.41
  11. Research on the Image Real-Time Acquisition, Storage and Image Processing System,TP391.41
  12. Feature Extraction, Selection and Combination in Lipreading,TP391.41
  13. Multi-currency Notes Technology Research and Implementation,TP391.41
  14. The Research on Paper Currency Classification Method Based on Harr-Like Feature and Minimal Ball Including Samples,TP391.41
  15. Pavement Distress Recognition Based on Image,TP391.41
  16. Research on Visual Detection and Tracking of Mobile Robots,TP242.62
  17. Research on Fusion Algorithm of Hyper Spectral and High Spatial Resolution Remote Sensing Image,TP751
  18. Fault Diagnosis Method Based on Support Vector Machine,TP18
  19. Fault Diagnosis Research on Three-Tank System,TP277
  20. An Approach for Identifying a Plant Resistance Gene Based on the Random Forest,Q943
  21. Research on the Key Technology of Waterborne Transport Security System,U698

CLC: > Industrial Technology > Machinery and Instrument Industry > Machinery Manufacturing Technology > Flexible manufacturing systems and flexible manufacturing cell > Fault diagnosis and maintenance
© 2012 www.DissertationTopic.Net  Mobile