F-1-3 Judgment of Distribution Equipment Movement Using Statistical Characterictics of Acceleration

Abstract

This paper presents an algorithm to judge multiple statuses of distribution equipment fヒ om conlinuous vibration measuremen し The algorism finds the acceleration threshold of moving and staying statuses as cluster boundaries of acceleration lcvel distributions ． In the method ， first the measured acceleration data are divided into multiple clusters using tentative boundarにs ． Then acceieration data are re − classifjed as one of clusters using k − nearest neighbor algorithm and Mahalanobis distances ． Validity of the mcthod is confirmed by the simulation with simply distributed samp 且 es and by an experiment with measured acceleration data of an automobi ！ e ． For the case of 〔 》verlapped boundaries ， which is caused by inappropriate numbers of tentative beundaries ， the algorism to find appropriate cluster number is proposed and confirmed by the simu 正 ation and