Improving rail network velocity: A machine learning approach to predictive maintenance

• Published in: Transportation research. Part C, Emerging technologies Vol. 45; pp. 17 - 26
• Main Authors: Li, Hongfei, Parikh, Dhaivat, He, Qing, Qian, Buyue, Li, Zhiguo, Fang, Dongping, Hampapur, Arun
• Format: Journal Article
• Language: English
• Published: Elsevier India Pvt Ltd 01.08.2014
• Subjects: Big data; Condition based maintenance; Detectors; Information fusion; Interruption; Machine learning; Maintenance; Mathematical models; Multiple wayside detectors; Networks; Predictive maintenance; Predictive modeling; Rail network velocity; Rails; Safety; Rail network velocity; Big data; Predictive modeling; Condition based maintenance; Multiple wayside detectors; Information fusion
• ISSN: 0968-090X; 1879-2359
• DOI: 10.1016/j.trc.2014.04.013

•Develop innovative machine-learning techniques for railway predictive maintenance.•Address big data challenges coming from large and complex multi-detector network.•Develop human-interpretable rules to facilitate railway operations.•Develop innovative prediction of alarms related to catastrophic component failure in advance. Rail network velocity is defined as system-wide average speed of line-haul movement between terminals. To accommodate increased service demand and load on rail networks, increase in network velocity, without compromising safety, is required. Among many determinants of overall network velocity, a key driver is service interruption, including lowered operating speed due to track/train condition and delays caused by derailments. Railroads have put significant infrastructure and inspection programs in place to avoid service interruptions. One of the key measures is an extensive network of wayside mechanical condition detectors (temperature, strain, vision, infrared, weight, impact, etc.) that monitor the rolling-stock as it passes by. The detectors are designed to alert for conditions that either violate regulations set by governmental rail safety agencies or deteriorating rolling-stock conditions as determined by the railroad. Using huge volumes of historical detector data, in combination with failure data, maintenance action data, inspection schedule data, train type data and weather data, we are exploring several analytical approaches including, correlation analysis, causal analysis, time series analysis and machine learning techniques to automatically learn rules and build failure prediction models. These models will be applied against both historical and real-time data to predict conditions leading to failure in the future, thus avoiding service interruptions and increasing network velocity. Additionally, the analytics and models can also be used for detecting root cause of several failure modes and wear rate of components, which, while do not directly address network velocity, can be proactively used by maintenance organizations to optimize trade-offs related to maintenance schedule, costs and shop capacity. As part of our effort, we explore several avenues to machine learning techniques including distributed learning and hierarchical analytical approaches.