Dissertation > Excellent graduate degree dissertation topics show

Research on Modeling and Optimization of Anticorrosion Injection Agent in Oil Distillation

Author: ZhangJieLu
Tutor: ZhouZuo
School: Northeastern University
Course: Control Theory and Control Engineering
Keywords: Refining production Note ammonia Note inhibitor Support Vector Machine 0-1 integer programming
CLC: TE6264
Type: Master's thesis
Year: 2008
Downloads: 77
Quote: 0
Read: Download Dissertation

Abstract


With the rapid development of China's national economy, the growing demand for petroleum products, domestic crude oil can no longer meet the needs of economic development. Continue to increase the amount of imported crude oil, crude oil quality varied, acid value and sulfur content is generally higher, many enterprises are facing new equipment corrosion problems. Refinery production, de-Note \determination stays expertise. Note the number of doses as well as the injection dose and the process parameters (the crude acid value A, the pH of the sulfur S and drainage, the concentration of iron ions Fe2 / 3) the relationship between, are problems to be solved. Refinery distillation unit injection dose from the two aspects of the theory and practice of in-depth study to identify the optimal injection dose of the distillation column in the refinery production equipment corrosion. The frequent replacement of the current refinery oil collected at the scene of the injection amount of ammonia, the pH value and the concentration of iron ion in the inhibitor amount Note, the the crude acid value A, the sulfur content S and drainage Fe2 / 3 process data such as larger changes more caused by the characteristics of the sample data property. Directly with this data applications support vector machines to build predictive models, will increase the amount of computation, reduce training speed and forecast accuracy. In this paper, based on the fuzzy data classification method to solve this problem, the fuzzy math, fuzzy reasoning method based Fuzzy classification process of distillation plant site collected data to establish the fuzzy rules. For further analysis and optimization of data provided favorable support for enterprise equipment resistant to the corrosive nature of the difference, the article also adopted other rules, data classification. Is a new kind of learning method based on statistical learning theory, support vector machine, in compliance with the structural risk minimization principle. In this paper, based on the analysis of the the experts experience of data, application support vector machine method to establish Note dose with crude oil acid value, sulfur content and drainage of the pH, the concentration of iron ions relational model, has been the injection dose and crude oil acid value of different types of sulfur content and drainage pH values, the relationship between the input and output of the iron ion concentration data; Note the amount of ammonia and the use of support vector machines created Note the the inhibitor amount forecast model were compared with BP neural network prediction. Simulation results show that support vector machines to overcome some of the inherent shortcomings of the neural networks and other methods, to improve the generalization ability of the model, has a special advantage in small sample modeling. Fuzzy classification method based on data collected at the scene to process data classification using support vector machine to establish the relationship of the agent injection process data model clear relationship between the data, macro Injecting process to reflect the general law, but can not be given all kinds of crude oil production, the optimal amount of note the amount of ammonia and Note inhibitor. Note ammonia Note corrosion inhibitors 0-1 integer programming model and application binary particle swarm algorithm in refinery production, Note doses of crude oil acid value, sulfur content and drainage pH value, the concentration of iron ions in optimal results under different conditions (such as satisfaction, etc.). Particle swarm algorithm for solving the optimal solution to meet the technical requirements and satisfaction premise, so moderate Note dose, both to achieve the purpose of the equipment corrosion, but also to avoid the anti-corrosion and excessive put, to cause wasting a lot of phenomena. Finally, the full text summary of the next stage injection dose study prospect.

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. The Research and Implementation of the Fault Management System for Triple Play,TP315
  14. Modulation Classification Algorithms of Digital Communication Signals,TN914.3
  15. Application of QSAR and Molcular Docking Studies in Medicinal Analytical Chemistry,R917
  16. Weighted posterior support vector and the listed company financial credit evaluation of the application,F224
  17. Method Research of Typhoon Cloud Recognition and Its Center Location Based on Doppler Weather Radar Image,P444
  18. Study on the Determination of Trace Metal Elements in Tobaccos and Pattern Recognition,TS47
  19. Improved SVM and Its Applications in Prediction of Silicon Content in Hot Metal,TF325.69
  20. Integrated Measurement for Density and Viscosity of Heavy Medium Suspension Based on Differential Pressure,TD94
  21. Short - term load forecasting , energy management system based on support vector machines,TM715

CLC: > Industrial Technology > Oil and gas industry > Oil, natural gas processing industry > Petroleum refining > Petroleum products
© 2012 www.DissertationTopic.Net  Mobile