Font Size: a A A

Study Of Fault Diagnosis System For Ferroresonance Of Power Network Combined The Expert Knowledge And Neural Network Knowledge

Posted on:2008-04-11Degree:MasterType:Thesis
Country:ChinaCandidate:F L ZhuFull Text:PDF
GTID:2178360242470300Subject:Control theory and control engineering
Abstract/Summary:PDF Full Text Request
In this paper, we mainly study resonance fault in power system. On one hand more and more complicated power network structure makes fault diagnosis more difficult, on the other hand large enterprise needs safer and safer power network with the highly development of modern social economic. It is necessary to find exact fault diagnosis method to keep network safe.This paper designs an enterprise' power network ferroresonance fault diagnostic system combined with neural network and expert system. The system adopts a way of knowledge expression based on creation way of rule. A method of knowledge acquisition based on neural network is proposed. In the part of the expert system, in the design of inference machine, display the good man-machine interactive function, using backward and forward ratiocination to infer. In the design of interpretive program, employ preset text and path tagging method to get inference result and explanation of process in detail when users demand. In the neural network, build a basic structure of BP neural network and extract rules of expert system knowledge base as the set of sample and test. After emulations of training and testing, the better valid coefficient set of significance value and threshold value can be adopted as knowledge base of neural network. In the fault diagnosis, proceeds positive-going calculation by using the created neural network structure to infer the final result.At last, the system apply the object-oriented technology to realize the system module based on the plant combined with Windows 2000Sever,Visual C++6.0 and Microsoft SQL Server2000.
Keywords/Search Tags:fault diagnosis, expert system, BP neural network, knowledge acquisition, inference machine
PDF Full Text Request
Related items