TY - JOUR
T1 - Anomaly detection of sensor faults and extreme events based on support vector data description
AU - Zhang, Yuxuan
AU - Wang, Xiaoyou
AU - Ding, Zhenghao
AU - Du, Yao
AU - Xia, Yong
N1 - Funding Information:
The authors wish to acknowledge the support of The Hong Kong Polytechnic University Project (Grant Number: 1‐ZVFH). The authors would like to thank the committee of 1st International Project Competition for Structural Health Monitoring for providing acceleration data of a long‐span bridge.
Publisher Copyright:
© 2022 John Wiley & Sons Ltd.
PY - 2022/10
Y1 - 2022/10
N2 - Structural health monitoring (SHM) systems generate a massive amount of sensing data. On one hand, sensor faults may cause the measurement data to have low fidelity. On the other hand, extreme events, such as typhoons or earthquakes, may cause the monitoring data look “abnormal.” These abnormal data, however, are closely related to the structural safety condition and require special attention. This study proposes an automatic and efficient anomaly detection methodology based on support vector data description (SVDD) to simultaneously detect anomalies caused by sensor faults and extreme events. The SVDD trained by a single pattern can divide the feature space into one-versus-the rest. Several decision boundaries are defined to enclose normal data and common sensor fault patterns, forming an equivalent multi-class classifier to classify common sensor fault types and detect unknown patterns. Next, multiple sensor faults and extreme events are separated from the unknown patterns. Multi-label data are detected based on the local features, while extreme events are recognized by the correlation of different sensors. The proposed method is finally applied to datasets collected from two SHM systems. Results show that the sensor anomalies in the systems are detected with high efficiency and accuracy, and extreme events are separated as a special pattern from the normal, common abnormal, and unknown patterns.
AB - Structural health monitoring (SHM) systems generate a massive amount of sensing data. On one hand, sensor faults may cause the measurement data to have low fidelity. On the other hand, extreme events, such as typhoons or earthquakes, may cause the monitoring data look “abnormal.” These abnormal data, however, are closely related to the structural safety condition and require special attention. This study proposes an automatic and efficient anomaly detection methodology based on support vector data description (SVDD) to simultaneously detect anomalies caused by sensor faults and extreme events. The SVDD trained by a single pattern can divide the feature space into one-versus-the rest. Several decision boundaries are defined to enclose normal data and common sensor fault patterns, forming an equivalent multi-class classifier to classify common sensor fault types and detect unknown patterns. Next, multiple sensor faults and extreme events are separated from the unknown patterns. Multi-label data are detected based on the local features, while extreme events are recognized by the correlation of different sensors. The proposed method is finally applied to datasets collected from two SHM systems. Results show that the sensor anomalies in the systems are detected with high efficiency and accuracy, and extreme events are separated as a special pattern from the normal, common abnormal, and unknown patterns.
KW - data anomaly detection
KW - multi-label classification
KW - one-class classification
KW - structural health monitoring
KW - support vector data description
UR - http://www.scopus.com/inward/record.url?scp=85134023322&partnerID=8YFLogxK
U2 - 10.1002/stc.3047
DO - 10.1002/stc.3047
M3 - Journal article
AN - SCOPUS:85134023322
SN - 1545-2255
VL - 29
JO - Structural Control and Health Monitoring
JF - Structural Control and Health Monitoring
IS - 10
M1 - e3047
ER -