Dissertation > Excellent graduate degree dissertation topics show

Applications of SVM to Predict Silicon Content in Hot Metal

Author: JianLing
Tutor: LiuXiangGuan
School: Zhejiang University
Course: Operational Research and Cybernetics
Keywords: Blast furnace ironmaking Silicon content in hot metal Statistical Learning Theory Support Vector Machine Classification Forecast
CLC: TF54
Type: Master's thesis
Year: 2006
Downloads: 245
Quote: 13
Read: Download Dissertation

Abstract


Blast furnace ironmaking is the the upstream main process of the iron and steel industry, as an important part of the pillar industries of the national economy, have played an important role in its development of the iron and steel industry and energy saving. The blast furnace process is a highly complex process, and its operating mechanism is often nonlinear, time delay, high-dimensional, large noise distribution parameters and other characteristics. Problem as well as the actual ironmaking blast furnace ironmaking process furnace mathematical model prediction and control, both iron-making automation of the production foreman and the director are very concerned about the issue. The accurate prediction of the furnace, will help the foreman improve the operating level, so as to achieve the purpose of improving utilization factor and lower coke rate. Support vector machine is based on a machine learning algorithm developed from statistical learning theory, it can be used to solve the practical problems of nonlinear, high-dimensional, small sample size, the local minimum points. Currently, has been widely used in pattern recognition, function approximation, data mining and other fields. Papers selected Laiwu Steel's No. 1 blast furnace (750m ~ 3) 1000 furnace data collected online analysis of blast furnace smelting process state variables (feed speed, the permeability, the amount of iron) and the control variables (pulverized coal injection, air flow through the calculation of the correlation coefficient , air temperature) and hot metal silicon content [Si] (the blast furnace hot metal silicon content reflects chemical heat, can be used to the furnace), on this basis, the establishment of the hot metal silicon based on support vector machine The content of numerical prediction models and silicon content multi-class classification model. The thesis includes the following four aspects: overview of blast furnace ironmaking blast furnace expert system and furnace temperature forecast; analysis of blast furnace smelting process state parameters and control parameters; statistical learning theory and support vector machines; molten iron based on support vector machine numerical prediction model of silicon content and silicon content multi-class classification model. The papers selected the 50 sets of test data were applied to the time sequence of the AR model and support vector machine model to predict, and the predicted results were compared. The results show that: Compared with the AR model, the prediction model based on support vector machine significantly improve the prediction hit rate of silicon content in hot metal. The paper improved M-ary classification method, based on the 1000 furnace hot metal silicon content online collection of Laiwu Steel's No. 1 blast furnace (750m ~ 3) [Si] time series clustering analysis using C-means algorithm, to achieve

Related Dissertations

  1. K Company’s Improving Planning and Forecasting for the Reasonable Allocation of Inventory,F224
  2. Research on Automatic Detection Algorithm for Substructure Distress of Highway Pavement Based on SVM,U418.6
  3. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  4. Research on Text Classification Based on Biomimetic Pattern Recongnition,TP391.1
  5. Fault Diagnosis Method Based on Support Vector Machine,TP18
  6. Process Support Vector Machine and Its Application to Satellite Thermal Equilibrium Temperature Prediction,TP183
  7. Uptake and Accumulation of Heavy Metals of Pistia Stratiotes and Eicharnia Crassipes under Combinated Pollution Condition,X173
  8. Research on Nondestructive Detection Technology for External Qualities of Papayas Based-on Vision,S667.9
  9. Research on the Evaluation of Straw Resource and the Development of Scale-Up Straw Energy Utilization in Jiangsu Province,S38
  10. The Research of Prediction of Lean Yield with CSB Image-Meater and Pork Carcass Grading System,S828
  11. Shanghai Public Security Authorities of the Police Job Classification,D631.1
  12. Research for Infrared Image Target Identification and Tracking Technology,TP391.41
  13. Research on Talents Team in Hefei-Wuhu-Bengbu Based on Independent Innovation,C964.2
  14. Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
  15. The Feasibility of the Immunohistochemistry Classification to Predicting Prognosis in Breast Cancer,R737.9
  16. \u00C2\u00BF \u00BE ??C ?? CY \u00BF??\u00A5\u00A5 C?? \u00AF \u0153\u00E6 ?? '\u00E6 ? ?? ?? S11 \u301C,TD745
  17. Research on Whispered Speaker Identification in Channel Mismatch Conditions,TN912.34
  18. Study on the Birds Word Poem in Song Dynasty,I207.22
  19. Research on Ontology-based Scientific Papers of Chinese Classification,TP391.1
  20. Chinese Keyword Extraction Method Based on Word Span and Its Application in Text Classification,TP391.1
  21. Integration of multi-granularity Chinese sentences subjectivity and emotion classification method,TP391.1

CLC: > Industrial Technology > Metallurgical Industry > Ironmaking > Blast furnace operation
© 2012 www.DissertationTopic.Net  Mobile