Dissertation > Excellent graduate degree dissertation topics show

The Study on Embedded Condition Detection and Fault Diagnosis Technology for Chassis of Self-propelled Gun

Author: LiWei
Tutor: ZhangXiaoZu
School: Jiangsu University
Course: Vehicle Engineering
Keywords: State detection Fault Diagnosis Self-propelled artillery chassis Embedded systems Wireless distributed network Support Vector Machine
CLC: TJ818
Type: Master's thesis
Year: 2009
Downloads: 46
Quote: 0
Read: Download Dissertation

Abstract


Self-propelled artillery system includes a power unit chassis, transmission and mobile devices, and its performance directly affects the the artillery dynamic performance and mobility. High-density chassis systems, multi-functional, integrated technical characteristics, making the difficulty of maintenance and support. Traditional detection method for self-propelled artillery chassis systems online without disassembly detect its drawbacks chassis system components can only be detected in the no-load state conditions. The absence of the corresponding dynamic load, the various components of the test chassis system dynamic response signal, useful failure information is often drowned out by the noise signal, sometimes even unable to accurately capture the fault information, resulting in lower accuracy of fault location. And fault diagnosis method, a small sample of the data characteristics, but also makes the neural network fault diagnosis method based on traditional statistical theory learning and recognition of the failure categories prone to learning, generalization ability, to fall into local minimum problem. Design embedded wireless distributed network-based detection system, avoiding online without disassembly the connection detection problem, chassis makes it possible to detect the load conditions. In the artillery during use, the the chassis system state information acquired by a sensor embedded detection system acquisition, conversion and storage, and real-time to the information processing center through wireless distributed network. Engine cylinder head vibration signal feature extraction, on the one hand, the use of the hardware resources of the microcontroller in the detection subsystem to extract a vibration signal, the dimensionless amplitude domain indexes, the characterization of the feature quantity of the vibration signal as a radio transmission, on the other hand the original vibration signals of wavelet packet decomposition, wavelet coefficients characterize the signal energy to take Adaptive method based on sub-band energy to eliminate noise interference, as the feature vectors of each sub-band energy statistics. Will be introduced based on the small sample statistical learning theory support vector machine fault diagnosis, the use of fuzzy theory to improve the performance of the support vector machine multiple fault classifier and improve the fault classification accuracy and generalization performance of the fault diagnosis model. ART2 neural network to cover the support vector machine fault classifier unknown failure mode can not be identified and learning defects, and the ART2 network learning algorithm has been improved.

Related Dissertations

  1. Design and Development of Application Programme for Fault Analyzer Based on Wince Platform,TP311.52
  2. Research on Automatic Detection Algorithm for Substructure Distress of Highway Pavement Based on SVM,U418.6
  3. Research on Autamatic Music Structrue Analysis,TN912.3
  4. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  5. Process Support Vector Machine and Its Application to Satellite Thermal Equilibrium Temperature Prediction,TP183
  6. Research for Infrared Image Target Identification and Tracking Technology,TP391.41
  7. Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
  8. Research on Subimage Selection and Mathching Method for Synthetic Aperture Radar(SAR) Target Recognition,TN957.52
  9. The Studies on Some Improvements of the GA and Their Applications in SVM,TP18
  10. Study on Instrument Calibrator for Diesel Engines and Its Integrated Information Management System,TK426
  11. Design and Implementation of a Three-dimensional Widget Set,TP391.41
  12. Research of Automatic Code Generation Technique for Embedded System Graphic User Interface,TP368.1
  13. The Research and Implementation of the Fault Management System for Triple Play,TP315
  14. Interactive Design and implementation of real-time classroom,TP311.52
  15. Unbalanced data set classification method and its application in the telecommunications industry,TP311.13
  16. Automatic Target Recognition fluorescent magnetic particle inspection image processing techniques,TP391.41
  17. Based on support vector machine textile and apparel Safety Risk Assessment Model,TS941.1
  18. Based on Information Fusion roads and obstacle detection method,TP242
  19. Based on SVM-RFE potential biomarker selection algorithm,TP311.13
  20. Research on Recognizing and Locating Tomatoes Base on Binocular Stereo Vision Technology,TP391.41
  21. Trucks bearing acoustic emission signal feature extraction and intelligent diagnosis,U270.7

CLC: > Industrial Technology > Arms industry > Tanks, warships, aircraft, aerospace,weapons > Chariot > Self-propelled artillery
© 2012 www.DissertationTopic.Net  Mobile