TY - GEN
T1 - Fault detection based on optimal transport theory
AU - Wang, Bingsen
AU - Baraldi, Piero
AU - Lu, Xuefei
AU - Zio, Enrico
N1 - Funding Information:
Bingsen Wang gratefully acknowledges the financial support from the China Scholarship Council (No. 201801810028). The participation of Piero Baraldi and Enrico Zio has been funded by ?Smart maintenance of industrial plants and civil structures by 4.0 monitoring technologies and prognostic approaches ? mac4pro?, sponsored by the call BRIC-2018 of the National Institute for Insurance against Accidents at Work ? INAIL.
Publisher Copyright:
© ESREL2020-PSAM15 Organizers.Published by Research Publishing, Singapore.
PY - 2020/1/1
Y1 - 2020/1/1
N2 - Most of the existing methods for fault detection are residual-based, i.e., they reconstruct the expected values of the signals in normal condition by using large amounts of data collected in the past and require to formulate hypotheses on the distributions. Since in many industrial applications the available data do not cover all the possible operating conditions and data distributions are unknown, their performance can be unsatisfactory. In this work, we propose a data-driven fault detection method based on Optimal Transport (OT). The Wasserstein distance between the distribution of the signals measured under the current conditions and a baseline distribution derived from the signals measured under normal conditions is used as abnormality score, and the OT solution is computed using the Cumulative Distribution Transform (CDT). The proposed method is verified considering a real bearing dataset. The performance of the detection is evaluated in terms of missed and false alarm rates, and compared to that of other traditional fault detection methods.
AB - Most of the existing methods for fault detection are residual-based, i.e., they reconstruct the expected values of the signals in normal condition by using large amounts of data collected in the past and require to formulate hypotheses on the distributions. Since in many industrial applications the available data do not cover all the possible operating conditions and data distributions are unknown, their performance can be unsatisfactory. In this work, we propose a data-driven fault detection method based on Optimal Transport (OT). The Wasserstein distance between the distribution of the signals measured under the current conditions and a baseline distribution derived from the signals measured under normal conditions is used as abnormality score, and the OT solution is computed using the Cumulative Distribution Transform (CDT). The proposed method is verified considering a real bearing dataset. The performance of the detection is evaluated in terms of missed and false alarm rates, and compared to that of other traditional fault detection methods.
KW - abnormality score
KW - cumulative distribution transform
KW - data-driven
KW - fault detection
KW - optimal transport
KW - Wasserstein distance
UR - http://www.scopus.com/inward/record.url?scp=85107300034&partnerID=8YFLogxK
U2 - 10.3850/978-981-14-8593-0_5849-cd
DO - 10.3850/978-981-14-8593-0_5849-cd
M3 - Conference contribution
AN - SCOPUS:85107300034
SN - 9789811485930
T3 - Proceedings of the 30th European Safety and Reliability Conference and the 15th Probabilistic Safety Assessment and Management Conference
SP - 1764
EP - 1771
BT - Proceedings of the 30th European Safety and Reliability Conference and the 15th Probabilistic Safety Assessment and Management Conference
A2 - Baraldi, Piero
A2 - Di Maio, Francesco
A2 - Zio, Enrico
PB - Research Publishing, Singapore
T2 - 30th European Safety and Reliability Conference, ESREL 2020 and 15th Probabilistic Safety Assessment and Management Conference, PSAM15 2020
Y2 - 1 November 2020 through 5 November 2020
ER -