%0 Journal Article
%T Multivariate Analyses for Finding Significant Track Irregularities to Generate an Optimal Track Maintenance Schedule
%A Mami Matsumoto
%A Masashi Miwa
%A Tatsuo Oyama
%J American Journal of Operations Research
%P 261-292
%@ 2160-8849
%D 2022
%I Scientific Research Publishing
%R 10.4236/ajor.2022.126015
%X We first discuss the relationship between the optimal track maintenance</span><span style=\"font-family:'Minion Pro Capt';\">&nbsp;scheduling model and an efficient detection method for abnormal track irregularities given by the longitudinal level irregularity displacement (LLID). The results of applying the cluster analysis technique to the sampling data showed </span><span style=\"font-family:'Minion Pro Capt';\">that maintenance operation is required for approximately 10% of the total lots, and these lots were further classified into three groups according to the</span><span style=\"font-family:'Minion Pro Capt';\">&nbsp;degree of maintenance need. To analyze the background factors for detecting abnormal LLID lots, a principal component analysis was performed; the re</span><span style=\"font-family:'Minion Pro Capt';\">sults showed that the first principal component represents LLIDs from the </span><span style=\"font-family:'Minion Pro Capt';\">viewpoints of the rail structure, equipment, and operating conditions. Bi</span><span style=\"font-family:'Minion Pro Capt';\">nomial and ordinal logit regression models (LRMs) were used to quantitatively in</span><span style=\"font-family:'Minion Pro Capt';\">vestigate the determinants of abnormal LLIDs. Binomial LRM was used to</span><span style=\"font-family:'Minion Pro Capt';\">&nbsp;characterize the abnormal LLIDs, whereas ordinal LRM was used to distinguish </span><span style=\"font-family:'Minion Pro Capt';\">the degree of influence of factors that are considered to have a significant</span><span style=\"font-family:'Minion Pro Capt';\">&nbsp;impact on LLIDs.
%K Multivariate Analysis
%K Track Maintenance Scheduling
%K Track Irregularity
%K Longitudinal Level Irregularity Displacement
%K Cluster Analysis
%K Principal Component Analysis
%K Binomial Logit Regression Model
%K Ordinal Logit Regression Model
%U http://www.scirp.org/journal/PaperInformation.aspx?PaperID=121501