Fault detection and explanation through big data analysis on sensor streams

作者：

Highlights：

• Analysis of event-based monitoring of complex systems for predictive maintenance.

• An unsupervised technique for early detection of faults from diagnostic data.

• A method for characterizing failures and distinguish them from normal behavior.

摘要

•Analysis of event-based monitoring of complex systems for predictive maintenance.•An unsupervised technique for early detection of faults from diagnostic data.•A method for characterizing failures and distinguish them from normal behavior.

论文关键词：Fault detection,Anomaly detection,Outlier explanation,Big data,Sensor data

论文评审过程：Received 17 October 2016, Revised 31 May 2017, Accepted 31 May 2017, Available online 13 June 2017, Version of Record 16 June 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.05.079