Dissertation > Excellent graduate degree dissertation topics show

The Study of Forecasting Models on Electric Characteristics about Crystallization Process of Cu-Zr-Al Amorphous Alloys

Author: KangLei
Tutor: WangXiaoLan
School: Lanzhou University of Technology
Course: Detection technology and automation devices
Keywords: Time series prediction Neural Network Model Support Vector Machine Least squares support vector machine Incremental algorithm
CLC: TG139.8
Type: Master's thesis
Year: 2009
Downloads: 21
Quote: 0
Read: Download Dissertation

Abstract


Material forming process is an extremely complex dynamic process , its mechanism modeling time-consuming and difficult to guarantee the accuracy of the Materials Science and Engineering and Computer Science , the material evolution of the external characteristics of the process as a non - stationary process , dynamic crystallization process of amorphous Cu - Zr - Al material departure from the observed data to form the complex dynamics of the process modeling and prediction . In order to make the least squares support vector machine is more suitable for online applications , the proposed algorithm, the concept of fuzzy membership to the introduction of incremental support vector machine , reducing the sensitivity of the regression function of isolated points , to improve the prediction accuracy . The simulation can be seen the incremental fuzzy least squares support vector machine algorithm is more accurate , faster , plus its own recursive features , easier to practical application . For non-stationary time series prediction , in addition to the choice of the model depends critically on how to extract the low-frequency and high-frequency components in the time series and modeling , as well as how to avoid over-fitting the high-frequency information , taking into account the binary is the cross wavelet decomposition of non-stationary time series adaptability , low frequency separation of wavelet transform is applied to the time series prediction , a non-stationary time series prediction scheme based on wavelet transform and the BP - ILSSVM method . The first to use the the Mallat algorithm on the non-stationary time series decomposition and reconstruction , isolated low-frequency and high-frequency information in the non-stationary time series , and then the BP neural network model built on the high-frequency information , while the low-frequency information online minimum squares fitting support vector machine , and finally superimposed on the prediction results of each model , thereby obtaining the prediction value of the original sequence . Simulation results show that this method not only be able to fully fit the low-frequency information , but also to avoid over-fitting , high-frequency information of non-stationary time series prediction method .

Related Dissertations

  1. Research on Automatic Detection Algorithm for Substructure Distress of Highway Pavement Based on SVM,U418.6
  2. Research on Autamatic Music Structrue Analysis,TN912.3
  3. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  4. Fault Diagnosis Method Based on Support Vector Machine,TP18
  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. Study on the Road Condition Monitoring Based on Vehicular 3D Acceleration Sensor,TP274
  8. Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
  9. The Research on Intrusion Detection System Based on Machine Learning,TP393.08
  10. Research on Improved K Neighbor Support Vector Machine Algorithm Faced Text Classification,TP391.1
  11. Research on Face Recognition Based on AdaBoost Algorithm,TP391.41
  12. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  13. Study on the Buildings Deformation Around Expansive Soil Foundation Pit,TU443
  14. Research on Subimage Selection and Mathching Method for Synthetic Aperture Radar(SAR) Target Recognition,TN957.52
  15. Research of Facial Expression Recognition Algorithm,TP391.41
  16. Fundus Image Segmentation Based on SVM and Template Matching,TP391.41
  17. Research and Realization of License Plate Character Recognition Algorithm Based on SVM,TP391.41
  18. Cloud Classification Based on Geostationary Meteorological Satellite Imagery,TP391.41
  19. The Studies on Some Improvements of the GA and Their Applications in SVM,TP18
  20. The Research and Implementation of the Fault Management System for Triple Play,TP315
  21. Modulation Classification Algorithms of Digital Communication Signals,TN914.3

CLC: > Industrial Technology > Metallurgy and Metal Craft > Metallurgy and Heat Treatment > The alloy learn with a variety of properties of alloys > Other special nature of the alloy > Amorphous alloy
© 2012 www.DissertationTopic.Net  Mobile