Dissertation > Excellent graduate degree dissertation topics show

A Power Network Fault Diagnosis Method Based on Association Rules and Augmented Naive Bayes

Author: NieZuoZuo
Tutor: HeZhengYou
School: Southwest Jiaotong University
Course: Proceedings of the
Keywords: Fault Diagnosis Data Mining Association rules Reduction Bayesian networks
CLC: TM711
Type: Master's thesis
Year: 2010
Downloads: 247
Quote: 2
Read: Download Dissertation

Abstract


The power grid fault diagnosis system-level fault diagnosis dispatch center. Infer the possible location of the fault and the fault type is based on circuit breaker operation and electrical protective devices at all levels, measurement analysis of information protection action logic and operating personnel experience. The research power grid fault diagnosis method for Network Fault Diagnosis tasks will need to be done manually to the computer to assist in the completion of failure in the power grid, fast and accurate diagnostic results and make a reasonable run decision-making so that the auxiliary dispatcher. Contact strengthen grid scale grid also greatly increased the amount of information transmission grid failure, this gives the power grid dispatching operating personnel required for processing massive fault information, certain difficulties caused by fast artificial identify the fault signal . When the grid complex fault occurs, the switch to protect the existence of malfunction, refuse to move because of interference led to the loss of information, and many uncertainties, the power system response will complicate cause more difficulties to the grid fault diagnosis. Therefore necessary to develop a method with consideration at the early stage of the massive fault information to remove redundant, while improving the the diagnostic fault tolerance fault information contains errors, and missing uncertainties, and to assist in scheduling staff to quickly identify the fault to ensure that the power system safe operation. To solve the above problem, this paper grid fault diagnosis method using association rules attribute reduction and Bayesian networks combined. Condition attributes of protection, circuit breaker, examine various fault conditions to establish the original decision table, and then use the interactive mining association rules, extracting key attributes, and 2 - frequently concentrated each frequent itemset pick on plain Bayesian networks improve, tectonic extension Bayesian network model and its parent node, the child node training, and fault diagnosis. On this basis, in order to further validate the diagnostic effect, a large-scale urban grid, for example, the use of software based on association rules attribute reduction algorithms and Bayesian network written in C # program, and apply it to the grid model , the result of the operation with some other artificial intelligence methods such as Naive Bayesian networks, neural networks and other methods to get the data, a comprehensive comparative analysis. The experimental results show that this method has higher accuracy and fault tolerance, effective analysis and diagnosis can be carried out on a large grid model has high theoretical and practical value.

Related Dissertations

  1. Design and Development of Application Programme for Fault Analyzer Based on Wince Platform,TP311.52
  2. Experimental Research on Influence of Coal Reburning Reaction Conditions on NO_x Reduction by Non-Catalytic Reduction of Ammonia,X701
  3. Research on the 6-Dof Fault Tolerant Control of the Vibration Isolation Platform with Eight Actuators,TB535.1
  4. Experimentation Research for Deoxidize Reaction Process of NO_X Adopt Different Reburnning Fuels,TK227.1
  5. Study of Tin Alloy Carbon Composite Used for Lithium Ion Battery,TM912.9
  6. Fault Diagnosis Method Based on Support Vector Machine,TP18
  7. Fault Diagnosis Research on Three-Tank System,TP277
  8. Research on Key Technologies of Automatic Steel Wire Galvanizing Production Line Based on Gas Reduction Method,TQ153.15
  9. Yellow phosphorus storage tank area of Safety Evaluation,TQ126.317
  10. A Study on Healthcare Product Marketing Based on Data Mining Technology,F426.72
  11. Gao Zhong-ying academic thought and experience and use of Bufei Decoction treatment of common diseases of the respiratory system drug law,R249.2
  12. Bing- thick academic thought and clinical experience and empirical studies apply to turtle soups treatment of chronic kidney disease,R249.2
  13. Research and Implementation of the Conflict Resolution in Process Modeling of Magic Platform,TP311.5
  14. Research on the Key Technology of Waterborne Transport Security System,U698
  15. Study on the Synthesis of the Polypyrrole-Cobalt Oxides and Their Catalytic Behavior for the Electroreduction of H2O2,O643.32
  16. Research on Toxicity Identification and Reduction Technology for Petrochemical Industrial Drainage,X742
  17. Theory of China’s Carbon Emissions and Strategy Research in Service Outsourcing,X321
  18. The Design and Implementation of Bicluster Data Analyzing Software,TP311.52
  19. Research on Clustering Algorithm Based on Mutation Particle Swarm Optimization,TP18
  20. Research on Fuzzy C-Mean Clustering Algorithm Based on Particle Swarm Optimization and Shuffled Frog Leaping Algorithm,TP18
  21. Research on Clustering Algorithm Based on Genetic Algorithm and Rough Set Theory,TP18

CLC: > Industrial Technology > Electrotechnical > Transmission and distribution engineering, power network and power system > Theory and Analysis > Network analysis,power system analysis
© 2012 www.DissertationTopic.Net  Mobile