Logo image
Identifying Failing Point Machines from Sensor-Free Train System Logs
Conference proceeding

Identifying Failing Point Machines from Sensor-Free Train System Logs

Ying Yang, Xin Lou, Binbin Chen, Marianne Winslett and Zbigniew Kalbarczyk
2020 IEEE International Conference on Big Data (Big Data), pp.1424-1429
10/12/2020

Abstract

Analytical models Cyber-physical system Data models failure identification hidden Markov model Hidden Markov models Maintenance engineering Markov processes Sensor systems Sensors survival analysis train system
A great many train systems worldwide are legacy systems, without modern sensors whose data can be mined to detect and predict failures. In this paper, we show how to support failure identification in a legacy system with no sensors, using alarm and natural-language described event logs as the only data sources. With too few failures in a mass of log data to train a traditional machine learning model, we propose a new approach called SA-HMM (Survival Analysis-Hidden Markov Model). After enriching the event logs with Word2vec, SA-HMM uses HMMs and survival analysis to identify failure trends in individual assets and failure tendencies in types of assets, respectively, then combines the two part in a weighted sum that indicates the priority of each asset for preventative maintenance. Our evaluation of SA-HMM with a large amount of urban train data shows that SA-HMM greatly outperforms naive method, HMM, and one-class SVM methods in terms of precision and recall in identifying failing assets, while also offering a tunable balance between those two aspects of performance.

Metrics

1 Record Views

Details

Logo image