A new auto-encoder-based dynamic threshold to reduce false alarm rate for anomaly detection of steam turbines

作者：

Highlights：

• The proposed method can model the normal data with denoising and ensemble technique.

• Dynamic threshold is newly developed to minimize false alarms in anomaly detection.

• Sensitivity is newly defined to identify condition parameters related to an anomaly.

• New metrics are defined to validate the anomaly detection performance.

摘要

•The proposed method can model the normal data with denoising and ensemble technique.•Dynamic threshold is newly developed to minimize false alarms in anomaly detection.•Sensitivity is newly defined to identify condition parameters related to an anomaly.•New metrics are defined to validate the anomaly detection performance.

论文关键词：Anomaly detection,Deep learning,Ensemble denoising auto-encoder,Dynamic threshold,Steam turbine

论文评审过程：Received 14 June 2021, Revised 6 September 2021, Accepted 13 October 2021, Available online 22 October 2021, Version of Record 30 October 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.116094