Application Of Information Fusion Technology In The Fault Diagnosis Of Generating Units

Supplying power for residents and enterprises uninterruptedly becomes increasingly important with the electricity consumption rising up rapidly in the21century, and it is also closely related to a sound development of national economy. Although new energies has been rising up in recent years, they are sparsely scattered in a short range and not mature in technique, therefore, traditional powers, especially thermal power remains in the dominant position and how to better identify the breakdown is put highly on our agenda. While the existing methods in identifying malfunction can not well meet the ever complicated mechanism of high-rating generator, it is necessary to make a research on the application of information fusion theory in settling problems on high-rating generating units.The traditional evidence theory can’t obtain accurate diagnosis result when it’s used to deal with evidences of high conflict in the process of information fusion. To address this problem, this dissertation proposes two methods to modify combination rules to improve traditional D-S evidence theory. In the first methods,we thinks that part of conflict information is available and its availability depends on the product of evidence’s support proportion and average supported degree, the availability of which was checked by experiments. In the second methods, we thinks that conflict information is completely available and the evidence’s conflicting probability is distributed to every proposition according to its average-ratio supported degree. This method was used in the fault diagnose of generating units and has good combination results.