Abstract
Measuring displacement response is essential in the field of structural health monitoring and seismic engineering. Numerical integration of the acceleration signal is a common measurement method of displacement data. However, due to the circumstances of ground tilt, low-frequency noise caused by instruments, hysteresis of the transducer, etc., it would generate a baseline drift phenomenon in acceleration integration, failing to obtain an actual displacement response. The improved traditional baseline correction methods still have some problems, such as high baseline correction error, poor adaptability, and narrow application scope. This paper proposes a deep neural network model based on empirical mode decomposition (EMD–DNN) to solve baseline correction by removing the drifting trend. The feature of multiple time sequences that EMD obtains is extracted via DNN, achieving the real displacement time history of prediction. In order to verify the effectiveness of the proposed method, two natural waves (EL centro wave, Taft wave) and one Artificial wave are selected to test in a shaking table test. Comparing the traditional methods such as the least squares method, EMD, and DNN method, EMD–DNN has the best baseline correction effect in terms of the evaluation indexes: Mean Absolute Error (MAE), Mean Square Error (MSE), Root Mean Square Error (RMSE), and degree of fit (R-Square).
Highlights
Published: 19 September 2021For civil structures, the damage of a structure under earthquake or strong wind can be judged and the seismic or wind resistance of the structure can be evaluated by displacement responses [1,2]
In order to improve the accuracy of baseline correction and establish a widely applicable method to eliminate baseline drift, this paper proposes a deep neural network model based on empirical mode decomposition (EMD–Deep Neural Network (DNN)) to correct the baseline of acceleration records
Considering that Empirical Mode Decomposition (EMD) can obtain more modal characteristics of data and DNN has an excellent performance in time series data modeling, this paper proposes an EMD–DNN prediction model
Summary
Published: 19 September 2021For civil structures, the damage of a structure under earthquake or strong wind can be judged and the seismic or wind resistance of the structure can be evaluated by displacement responses [1,2]. Displacement is an important design control parameter, and an important working condition index; displacement measurement is an indispensable part of structural seismic design in the field of earthquake engineering, and an important part of structural health monitoring. In the field of earthquake engineering, on the one hand, the shaking table laboratory can obtain the real seismic response of the structure. The dynamic testing instruments widely used in shaking table tests are acceleration sensors and pull-wire displacement sensors. Numerical integration of acceleration data is the main method to obtain structural displacement response. Strong vibration acceleration records provide valuable basic information for seismologists and engineers to study the mechanism of focal rupture in large earthquakes and the failure mechanism of engineering structures, in which displacement data need to be obtained by numerical integration of acceleration records.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
