AN OPEN ACCESS JOURNAL
 JJCE Submission Home


Sensor Fault Detection Based on Particle Filter and Mahalanobis Distance

Submitted2020-01-05
Last Update2020-01-05
TitleSensor Fault Detection Based on Particle Filter and Mahalanobis Distance
Author(s)Author #1
Name: Tianzhi Li
Org: Master Student, School of Civil Engineering, Chongqing University, No.174 Shazhengjie, Shapingba, Chongqing, 400044, China
Country:
Email: litz@cqu.edu.cn

Author #2
Name: Gang Liu
Org: Professor, School of Civil Engineering, Chongqing University, No.174 Shazhengjie, Shapingba, Chongqing, 400044, China
Country:
Email: gliu@cqu.edu.cn

Author #3
Name: Liangliang Zhang
Org: Professor, School of Civil Engineering, Chongqing University, No.174 Shazhengjie, Shapingba, Chongqing, 400044, China
Country:
Email: zll200510@126.com

Other Author(s)
Contact AuthorAuthor #1
Alt Email: litz@cqu.edu.cn
Telephone:
KeywordsStructural health monitoring, Sensor fault detection, Particle filter, Mahalanobis distance, System identification
AbstractIt is essential to evaluate the health condition of structure and sensors in structural health monitoring (SHM) systems. Compared with the identification of structural damage, only a few papers nvestigated sensor fault detection in civil engineering. This paper presents a model-based sensor fault detection approach utilizing particle filter (PF) and Mahalanobis distance (MD). The discrete state-space model is constructed by a system identification algorithm named N4SID instead of physical principles. A sensor fault is determined if Mahalanobis distance between test state and training state is above the threshold. The experimental study demonstrates the accuracy and efficiency of the proposed method.
Topics• str
• str. dyn.
• con.mat..
• tra.-traf.
• surv.
• tra.-pav.
• wat. Res.
Comments
Paper 4831.pdf (1170KB)
 

http://www.just.edu.jo