Research and Application of Improved FCM in Power Plant Data Analysis

FCM (Fuzzy C-means) is a common clustering algorithm in power plant data analysis that has the advantages of high search efficiency and robustness, but is still essentially a local search algorithm. The initial clustering centre is determined by the randomly generated membership matrix, and the membership matrix is sensitive to the choice of the initial value. In this paper, by studying the improved FCM, the adaptive jump probability is used instead of the random probability to adjust the population, which is more conducive to the algorithm to find the optimal, and the experimental comparisons validate the improved FCM clustering effect and accuracy as a whole is better than FCM and K-means.