Dissertation > Excellent graduate degree dissertation topics show

Research on Multi-Criteria Decision-Making Model and Application for the Oilfield Development Area

Author: WuShuLing
Tutor: XuShaoHua
School: Daqing Petroleum Institute
Course: Computer Software and Theory
Keywords: Multi - criteria decision making Fuzzy Logic Neural Networks Model Application
CLC: TP183
Type: Master's thesis
Year: 2010
Downloads: 34
Quote: 0
Read: Download Dissertation

Abstract


Multiple criteria of the issues involved in the field of oil field development , multi- objective decision making , research in artificial intelligence and decision support in the field of multi- criteria decision making theory , model and learning algorithm and fuzzy logic , neural network theory and into the multi- criteria decision-making rules typical decision-making problems involved in the oil field development process research and application . Of reservoir damage diagnosis for oilfield development process , oil and water layers discriminant and inefficient wells to improve the program of measures is a typical multi-criteria decision - making problems , research models and methods of decision-making rules and neural network combined intelligent decision based on expert knowledge , fuzzy , can deal directly with the qualitative development of knowledge and quantitative data of the oilfield development is the fuzzy neural network , fuzzy weighted reasoning network , fuzzy comprehensive evaluation model to construct the corresponding algorithm , and each model the actual application , the application of the results of verification the model and the effectiveness of the algorithm . Preferred multi - objective decision making for oil field development program , the establishment of an improved BP neural network model and learning algorithm on the basis of the basic BP network , join signal feedback and deviations unit , to facilitate the introduction of experience in the learning process knowledge instead of Sigmoid function neural network and fuzzy optimization theory model , making the excitation function of the neural network has a clearer intuitive physical significance to improve the reliability of the network description of the decision - making rules and decisions . Consider each variable in the actual the oilfield development system in different stages during operation may have a different role in the relationship and information transformation mechanism , and the various stages of the continuity of the state of the system , a number of process neural the Motoko networks constitute cascade structure to establish a system of dynamic forecast model ; same time , in order to compensate for the actual time sequence sampling data deficiencies and improve the utilization of data using phase space reconstruction theory constructed training sample set . The paper constructs a the cascade process neural network - based decision - making model and learning algorithm to oilfield development the EOR process indicators forecast , for example , the experimental results verify the validity of the model and method .

Related Dissertations

  1. Research on Magnetic Field Sensor Based on GMI Effect and Geomagnetic Matching Algorithm,P318
  2. EDM Electrode Wear Mechanism and Control Research,TG661
  3. Experimental Study on Pyrolysis and Combustion Characteristics of Paint and Tar Based Single Hazardous Wastes,X705
  4. Powered Activited Carbon-UF for Treating Micro-polluted Surface Water,X703
  5. High Speed Frequency Measurment and Non-Linearity Correction of Frequency Modulated Capacitive Displacement Sensor,TH822
  6. Design and Research on Stabilization Loop of Gyro Stabilized Pod Control System,V241.5
  7. Satellite Attitude Control Methods Using Only Magnetorquers,V448.222
  8. Investigation of Turbine S2 Stream Surface Direct Problem Aerodynamic Optimization Design,V235.11
  9. Temperature Drift Modeling and Compensation of Fiber-Optic Gyroscopes,V241.5
  10. Research on Models and Simulation of Electromagnetic Railgun Exterior Trajectory,TJ399
  11. The Technological Parameter Analysis and Influencing Factor Research on RUV4 Automobile Ignition Coils,U463.64
  12. The Study of Control Algorithm for Automotive Power Window Based on Lin Bus,U463.6
  13. The Research of Residential Community Design of Vanke Model,TU984.12
  14. The Equivalent Circuit Model of Radial Vibration Mode Piezoelectric Transformer and Its Application,TM406
  15. Research on Compensation of Hysteresis in Piezoceramic Actuators,TM282
  16. The Design and Accomplishment of Simulition Platform for Voltage Clamp Experiment Based on Cell Electrophysiological Model,R318.0
  17. A Study of the Application of TBLT to English Teaching in Rural Middle School,H319
  18. Quantitative evaluation model based on information entropy of the classroom observation,G632.4
  19. High school politics,the new curriculum reform classroom teaching model to integrate exploration,G633.2
  20. Research and Implement of SDO Model in University Enroll System Based on SOA,G647
  21. Multiple ANN/HMM Hybrid Used in Speech Recognition,TN912.34

CLC: > Industrial Technology > Automation technology,computer technology > Automated basic theory > Artificial intelligence theory > Artificial Neural Networks and Computing
© 2012 www.DissertationTopic.Net  Mobile