Research On Power System Fault Diagnosis New Method Based On Rough Sets Theory

While the complex fault occurs in the power system or uncertain factors appear, such as mal-operation,non-operation and missing messages on account of channel disturbance, it will make system response complex and fault diagnosis more difficult . If dispatchers make misjudgment or leaky judgment for this kind of faults, maybe it will bring out serious aftereffects such as accident spread, etc. Thus, it is necessary to develop a fault diagnosis method with strong robustness to suit all kinds of disadvantaged instances, and assist dispatchers to identify faults quickly for guarantying power system's safe and stable running.Rough Sets theory, an intelligent method for mining and processing imprecise and uncertain knowledge, has got great improvement. Power system fault diagnosis can be described as a mode classified problem, and it is quite fit to apply the decision table method of rough sets theory.Therefore, based on formers' research and recurring to the rather strong ability of holding mistakes possessed by rough set theory, This paper present a new attribute reduction arithmetic as well as an improved value reduction arithmetic based on the combination of rough set theory and duality Boolean calculation, and use it to handle the reduction progress of the decision table including all kinds of fault cases which is established by considering the signals of protection relays and circuit breakers, then form the general mixed knowledge model and bring up an idea about automatic production of decision table . Finally, we realize the reduction of fault diagnosis decision-table and mixed knowledge model by the program using VC++, and use Delphi to establish the windowinterface. The example proves that the new fault diagnosis method is available in power system fault diagnosis.