Font Size: a A A

Study On The System In Fault Intelligent Diagnosis Of Power Transformer

Posted on:2009-04-26Degree:MasterType:Thesis
Country:ChinaCandidate:C Y LongFull Text:PDF
GTID:2178360242990635Subject:Electronics and Communications Engineering
Abstract/Summary:PDF Full Text Request
The fault diagnosis of the analog circuits is an advanced synthesis intercrossed subject, which is an application technology absorbing the new theory,technology and method in other subjects and fields. In the past 30 years, it has developped a great deal of theory and approaches.But the approaches are limited to deal with fault diagnosis because of the variety and complexity of the nonlinear analog circuits, especially the large-scale nonlinear analog circuits with the tolerance.Artificial neural networks(ANN) which have been one of the most active research areas recently can be contributed to solve problems in various practical fields.Genetic algorithm (GA) can solve complicated problems which cannot be solved by the traditional technology and it has a function of researching all kinds of the fields.This paper located the fault diagnosis of the nonlinear analog circuits using artificial neural networks and genetic algorithm according to the screen theory and piece wise-linear.This paper mainly introduces the screen theory of single branch circuit and sub-circuit of large-scale circuit,It narrowed the scope of suspicious failure with logic tearing method and cross-torn tearing method ,and found the screen diagnosis method of nonlinear analog circuit.the faults can be located in sub-circuit with a few of tests and incentive by screen method, so it is simple and feasible.This paper presented the space characteristics of single fault of linear sub-circuit, and then it proved theoretically that the space characteristics of double-fault and triangle -fault can be accessed from the space characteristics of single fault, and the simulation requirements before test are reduced. Tolerance of circuit was analyzed and handled, and tolerance scope of circuit response can be obtained by genetic algorithm method, and then the tolerance test samples can be obtained. It is easy to find the best one. It costs less CPU time. Neural network fault diagnosis methods is especially proposed. It is respectively based on space characteristics,piece wise-linear model,space characteristics and screen technology of nonlinear circuits. We simulate the exampled circuit based on MATLAB and OrCAD. The experiment results show that the preposed methods are feasible and simple.
Keywords/Search Tags:Nonlinear analog circuit, Fault diagnosis, Neural Network, Genetic Algorithm, Screen theory
PDF Full Text Request
Related items