Structural Monitoring and Maintenance Volume 5, Number 1, March 2018 , pages 51-65 DOI: https://doi.org/10.12989/smm.2018.5.1.051 |
||
Deep learning-based sensor fault detection using S-Long Short Term Memory Networks |
||
Lili Li, Gang Liu, Liangliang Zhang and Qing Li
|
||
Abstract | ||
A number of sensing techniques have been implemented for detecting defects in civil infrastructures instead of onsite human inspections in structural health monitoring. However, the issue of faults in sensors has not received much attention. This issue may lead to incorrect interpretation of data and false alarms. To overcome these challenges, this article presents a deep learning-based method with a new architecture of Stateful Long Short Term Memory Neural Networks (S-LSTM NN) for detecting sensor fault without going into details of the fault features. As LSTMs are capable of learning data features automatically, and the proposed method works without an accurate mathematical model. The detection of four types of sensor faults are studied in this paper. Non-stationary acceleration responses of a three-span continuous bridge when under operational conditions are studied. A deep network model is applied to the measured bridge data with estimation to detect the sensor fault. Another set of sensor output data is used to supervise the network parameters and backpropagation algorithm to fine tune the parameters to establish a deep self-coding network model. The response residuals between the true value and the predicted value of the deep S-LSTM network was statistically analyzed to determine the fault threshold of sensor. Experimental study with a cable-stayed bridge further indicated that the proposed method is robust in the detection of the sensor fault. | ||
Key Words | ||
structural health monitoring; sensor fault; Long Short-Term Memory Networks; fault threshold; stochastic gradient decline; deep learning | ||
Address | ||
Lili Li, Gang Liu and Liangliang Zhang: 1School of Civil Engineering, Chongqing University, Chongqing 400045, China 2The Key Laboratory of New Technology for Construction of Cities in Mountain Area of the Ministry of Education, Chongqing University, Chongqing 400030, China Qing Li: College of Computer Science, Chongqing University, Chongqing 400045, China | ||