Research output: Contribution to journal › Conference article › peer-review
Combustion anomalies detection for a thermal furnace based on Recurrent Neural Networks. / Abdurakipov, Sergey; Butakov, Evgenii.
In: Journal of Physics: Conference Series, Vol. 1105, No. 1, 012043, 28.11.2018.Research output: Contribution to journal › Conference article › peer-review
}
TY - JOUR
T1 - Combustion anomalies detection for a thermal furnace based on Recurrent Neural Networks
AU - Abdurakipov, Sergey
AU - Butakov, Evgenii
N1 - Publisher Copyright: © Published under licence by IOP Publishing Ltd.
PY - 2018/11/28
Y1 - 2018/11/28
N2 - This paper describes the application of Recurrent Neural Networks (RNN) for effectively detecting anomalies in time series data obtained from experimental study of the combustion and gasification of mechanically activated coal fuel in a thermal furnace. We train Recurrent Neural Networks (RNN) with Long Short-Term Memory (LSTM) units to learn the normal time series patterns and predict anomaly values. The resulting prediction errors between real and expected values are analyzed to give anomaly scores. To investigate the most suitable configuration of RNN and evaluate the effectiveness of the anomaly detection model, we used three datasets of real-world data that contain several types of anomalies. The developed RNN algorithm detected 9 out the 9 collective anomalies in the hold-out sample with one false positive anomaly event.
AB - This paper describes the application of Recurrent Neural Networks (RNN) for effectively detecting anomalies in time series data obtained from experimental study of the combustion and gasification of mechanically activated coal fuel in a thermal furnace. We train Recurrent Neural Networks (RNN) with Long Short-Term Memory (LSTM) units to learn the normal time series patterns and predict anomaly values. The resulting prediction errors between real and expected values are analyzed to give anomaly scores. To investigate the most suitable configuration of RNN and evaluate the effectiveness of the anomaly detection model, we used three datasets of real-world data that contain several types of anomalies. The developed RNN algorithm detected 9 out the 9 collective anomalies in the hold-out sample with one false positive anomaly event.
KW - ACTIVATION
UR - http://www.scopus.com/inward/record.url?scp=85058245061&partnerID=8YFLogxK
U2 - 10.1088/1742-6596/1105/1/012043
DO - 10.1088/1742-6596/1105/1/012043
M3 - Conference article
AN - SCOPUS:85058245061
VL - 1105
JO - Journal of Physics: Conference Series
JF - Journal of Physics: Conference Series
SN - 1742-6588
IS - 1
M1 - 012043
T2 - 34th Siberian Thermophysical Seminar Dedicated to the 85th Anniversary of Academician A. K. Rebrov, STS 2018
Y2 - 27 August 2018 through 30 August 2018
ER -
ID: 17853207