Sequential anomalies: a study in the Railway Industry

Abstract

Concerned with predicting equipment failures, predictive maintenance has a high impact both at a technical and at a financial level. Most modern equipments have logging systems that allow us to collect a diversity of data regarding their operation and health. Using data mining models for anomaly and novelty detection enables us to explore those datasets, building predictive systems that can detect and issue an alert when a failure starts evolving, avoiding the unknown development up to breakdown. In the present case, we use a failure detection system to predict train door breakdowns before they happen using data from their logging system. We use sensor data from pneumatic valves that control the open and close cycles of a door. Still, the failure of a cycle does not necessarily indicates a breakdown. A cycle might fail due to user interaction. The goal of this study is to detect structural failures in the automatic train door system, not when there is a cycle failure, but when there are sequences of cycle failures. We study three methods for such structural failure detection: outlier detection, anomaly detection and novelty detection, using different windowing strategies. We propose a two-stage approach, where the output of a point-anomaly algorithm is post-processed by a low-pass filter to obtain a subsequence-anomaly detection. The main result of the two-level architecture is a strong impact in the false alarm rate.

CPS data streams analytics based on machine learning for Cloud and Fog Computing: A survey

“…Ref [51][103] [110] showed the consistent characteristics in these applications. The utilization of ML for mechanical fault diagnosis and prevention of cyber attacks in transport system can be more explored, as only two [94] [107] reported the benefits of ML in this area. ML is also a popular solution to configure plant/production, optimize electrical load/dispatch, and reduce road latent cost, forecast short term in electricity usage and etc.…”

Analyzing rare event, anomaly, novelty and outlier detection terms under the supervised classification framework

“…Rare event Ribeiro et al (2016) Failure of the train passenger doors is predicted in a fixed period of time. The data consist of both normal and failure temporal instances.…”

“…Numerous applications require filtering or detecting abnormal observations in data. For instance, in security, intruders are abnormalities (Ribeiro et al, 2016;Pimentel et al, 2014;Luca et al, 2016;Phua et al, 2010;Yeung and Ding, 2001); in traffic data, road accidents (Theofilatos et al, 2016); in geology, the eruption of volcanoes (Dzierma and Wehrmann, 2010); in food control, foreign objects inside food wrappers (Einarsdóttir et al, 2016); in economics, bankruptcy of a company (Fan et al, 2017); or in neuroscience, an unexperienced stimulus is considered an abnormality (Kafkas and Montaldi, 2018). In some situations, the abnormalities are called rare events, anomalies, novelties, outliers, exceptions, aberrations, surprises, peculiarities, noise or contaminants among others.…”

“…In this study, the authors refer to landslides as rare events because landslides seldom occur. In Ribeiro et al (2016) a similar problem is addressed, but with a different term. Here, a study in the railway industry is carried out.…”

“…In Campos et al (2016), an effort is made to distinguish between one class classification and outlier detection. Finally, in Ribeiro et al (2016), three methods related with outlier, anomaly and novelty detection learning scenarios are used to solve the same problem. Also, some insights are given about all these three learning scenarios.…”