2019 3rd International conference on Electronics, Communication and Aerospace Technology (ICECA) · 2019 · 18 citations · 5 references
ComputingIndustrial EngineeringSystems EngineeringMaintenance EngineeringReal-time SystemsTime Series AnalysisCondition MonitoringFault DetectionPredictive MaintenanceTime Series ForecastingTime Series ModelingTime Series PredictionArima ModelsOnline MonitoringPredictionReal-time Data AnalysisReal-time Data CaptureReal-time MonitoringReal-time ProcessingTime Series Trend Analysis
In recent times, the working of trains can be improved by incorporating the real time data capture capability and trend analysis. The current scenario is that only the fault values are stored, and these values can only be accessed by manufacturers during the maintenance in depot. It is not available in real time. The aim of the proposed framework is to collect the real time sensor values and make it available in online to the manufacturers so that they can constantly check the healthy status of the train. Also do an analysis on fault trend. This will help in knowing where and when this fault occurs so that they can take necessary steps to overcome this situation and thus reduces the stress of an expensive task. The data send to the train MPU is then sent to the cloud of the processing unit where further analysis and prediction task carry on. ARIMA model is used for trend analysis and prediction processes. The prediction helps in predicting when the train should undergo maintenance in advance so that it will help to do maintenance before the train undergoes adverse conditions.
5
Failure prediction on railway turnouts using time delay neural networks
Halis Yılboga, Omer F. Eker, Adem Guclu et al. · 2010 · 44 citations
A new qualitative trend analysis algorithm based on global polynomial fit
Bo Zhou, Hao Ye, Haifeng Zhang et al. · AIChE Journal · 2017 · 34 citations