Dissertation > Excellent graduate degree dissertation topics show

An Application Research on Industrial Process Fault Diagnosis Method Based on KPCA and SVM

Author: ZhaoJinLi
Tutor: LiuJianChang
School: Northeastern University
Course: Control Theory and Control Engineering
Keywords: Fault Diagnosis Principal Component Analysis Kernel Principal Component Analysis Support Vector Machine Tennessee - Eastman
CLC: TH165.3
Type: Master's thesis
Year: 2008
Downloads: 151
Quote: 0
Read: Download Dissertation

Abstract


Online monitoring of the production process in order to ensure the security of the industrial process , the stability of the product quality , timely and accurate fault diagnosis has become an important research direction in the field of process control . Particularly those based on various statistical methods for data having a large number of easy to obtain the process data of the reason , since it does not rely on the mathematical model and the industrial field and more practical . This method requires the collection under normal operating conditions , and the historical data in the various fault condition . The diagnostic steps including fault detection and fault identification two steps . This paper describes a fault diagnosis method commonly used in the industrial process , and analyze their strengths and weaknesses . Tennessee - Eastman Chemical industrial processes (Tennessee-Eastman Process, TEP) as the background , a detailed analysis of the industrial process . Introduces the principal component analysis (Principle Component Analysis, PCA) and kernel principal component analysis (KernelPrinciple Component Analysis, KPCA) principle and multivariate statistical fault monitoring methods in TE . KPCA introduced the concept of the kernel function , the original space are mapped to high dimensional feature space , principal component analysis in high - dimensional space , good separability of the input data . The two detection methods used in the TE process come multivariate statistical fault detection method based on KPCA outperforms the PCA . Classification support vector machines (Support Vector Machine, SVM) method has complete global optimization theory and good generalization performance . The traditional SVM improvement , more one-on-one SVM construct multi - value classification of the SVM . And PCA, KPCA feature extraction method with SVM combination will drop the dimension main linear and nonlinear principal training and recognition as SVM input . And KPCA-SVM with TE process , come to have good diagnostic capabilities .

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. The Research on Intrusion Detection System Based on Machine Learning,TP393.08
  19. Research on Improved K Neighbor Support Vector Machine Algorithm Faced Text Classification,TP391.1
  20. The Research of Prairie Road Light Environment Effects on Physiological Indicators of Drivers,U491.254
  21. Research on Face Recognition Based on AdaBoost Algorithm,TP391.41

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