Open AccessSimplified Machine Diagnosis Techniques in Absolute Deterioration Factor by Using the 2nd Order AR Model
Author(s) -
Kazuhiro Takeyasu
Publication year - 2018
Publication title -
international journal of business administration
Language(s) - English
Resource type - Journals
eISSN - 1923-4015
pISSN - 1923-4007
DOI - 10.5430/ijba.v10n1p61
Subject(s) - bicoherence , autoregressive model , mahalanobis distance , kurtosis , autocorrelation , autoregressive–moving average model , series (stratigraphy) , computer science , algorithm , mathematics , function (biology) , nonlinear autoregressive exogenous model , statistics , bispectrum , artificial intelligence , spectral density , paleontology , evolutionary biology , biology
In order to make machine diagnosis, the method of calculating Kurtosis or Bicoherence was utilized. Calculating system parameter distance was also utilized applying time series data to Autoregressive (AR) model or Autoregressive Moving Average (ARMA) model.In this paper, simplified calculation method of autocorrelation function is introduced and it is utilized for the 2nd order AR model identification. An absolute deterioration factor such as Bicoherence is also introduced. Furthermore, Mahalanobis’ generalized distance is introduced by the relationship with system parameter distance. Three cases in which the rolling elements number is nine, twelve and sixteen are examined and compared. Machine diagnosis can be executed by this simplified calculation method of system parameter distance. Good results are obtained.