Abstract:

The feed water pump system is an important auxiliary equipment of the power plant system, so an effective evaluation of its state is helpful to the safe and reliable operation of the power plant. Based on the historical health data of the feed pump system, the fuzzy c-means clustering algorithm is adopted to build the state score model which can automatically predict the equipment state score in real time. The experiment is carried out on the real data of the power plant. The results show that the predicted scores are in line with the actual situation and can effectively characterize the equipment state.

Key words: feed water pump system, state score, clustering algorithm