Dissertation > Excellent graduate degree dissertation topics show

Fault Diagnosis of Nuclear Power Plant Based on Support Vector Machine

Author: DuXingFu
Tutor: XiaHong
School: Harbin Engineering University
Course: Nuclear Energy Science and Engineering
Keywords: Nuclear Power Plant Fault Diagnosis Support Vector machine Principal Component Analysis
CLC: TL364.1
Type: Master's thesis
Year: 2009
Downloads: 74
Quote: 0
Read: Download Dissertation

Abstract


Nuclear power plants are technology intensive, expensive, huge and complicated systems which also have potential fatalness. In order to ensure secure and reliable running of the devices, it is very essential to study its fault diagnosis system. However, in practical fault detection, the fault data used for pattern recognition and systematic are relative less, because it is difficult to collect fault data of nuclear power devices. Under the circumstances with less data, how to diagnose precisely the fault of nuclear power plants precisely is very significant.Statistical learning theory is a new theory system to aim directly at statistics problems of small sample sizes. The statistical inference rule under this system doesn’t consider only the requirement to progressive performance, but also pursuits obtaining the optimization result in the available limited information. Support vector machine (SVM) is a new machine learning method developed technically to small sample size in recent years based on the foundations of statistical learning theory. SVM adopts the structural risk minimization (SRM) principle and considers simultaneously training error and generalization ability, which has shown many special advantages in dealing with small samples and non-linear problems.In this paper, two fault diagnostic casts were constructed using SVM theory for model fault such as cracks of steam generator heat transfer tubes and small break loss of coolant accident in nuclear power plant. One fault diagnostic cast was constructed based on least squares support vector machines using C++ programming language. The other was constructed based on traditionary support vector machines using Matlab7.0 program. The results in the Simulation Test have shown that the performance of the two models based on two kinds of SVMs both depends on the choice of nuclear function model and the parameters. In this study, after the suitable choice, the same diagnostic performance was obtained using two kinds of SVMs. The fault can be diagnosed exactly during the period between the third second until shutdown. In the first three seconds, the fault data were not yet shown or the data were fluctuant. The simulation results demonstrated that the methods could diagnose the fault phenomenon accurately under the circumstances of small example sizes, and the precision was very high.

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. Research on Autamatic Music Structrue Analysis,TN912.3
  5. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  6. Fault Diagnosis Method Based on Support Vector Machine,TP18
  7. Fault Diagnosis Research on Three-Tank System,TP277
  8. Process Support Vector Machine and Its Application to Satellite Thermal Equilibrium Temperature Prediction,TP183
  9. Application of Improved Principal Component Analysis Algorithm in Course Construction,G642.4
  10. Research on the Key Technology of Waterborne Transport Security System,U698
  11. Research for Infrared Image Target Identification and Tracking Technology,TP391.41
  12. Study on the Road Condition Monitoring Based on Vehicular 3D Acceleration Sensor,TP274
  13. Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
  14. The Impact of Tourism on Typical Vegetation in Luya Mountain Nature Reserve, Shanxi Province,S759.9
  15. Macaca mulatta palm morphological study of pattern ridge count,Q954
  16. Zhaoguan Lower Coal Group water inrush prediction and control techniques,TD745
  17. Research on Cultural Industrial Competitiveness of Chong Qing,F224
  18. Amendment of Mental Health Evaluation Scale for Chinese Nuclear Power Plant Operators,B849
  19. The Research on Intrusion Detection System Based on Machine Learning,TP393.08
  20. Fault Diagnosis Method Study of Hydraulic System of Concrete Pump,TU646
  21. Preliminary Study on Neurobehavioral Evaluation of Chinese Nuclear Power Plant Operators,R131

CLC: > Industrial Technology > Nuclear technology > Engineering of Nuclear Reactors > Reactor safety and control > Reactor safety > Safety principles , safety analysis
© 2012 www.DissertationTopic.Net  Mobile