Earthquake Ground Motion Matching on a Small Electric Shaking Table Using a Combined NN-PDFF Controller

Abstract

Replicating acceleration time histories with high accuracy on shaking table platforms is still a challenging task. The complex interference between the components of the system, the inherent nonlinearities, and the coupling effect between the specimen and the shaking table are among other reasons that most affect the control performance. In this paper, a neural network- (NN-) based controller has been developed and experimentally implemented to improve the acceleration tracking performance of an electric shaking table. The latter is a biaxial shaking table driven by linear motors and controlled by a proportional-derivative-feedforward (PDFF) controller that is very efficient in reproducing displacement waveforms on the detriment of the simulation of the prescribed acceleration ground motions. In order to bypass this shortcoming, a control scheme combining the PDFF as a basic control function with a NN controller which filters the shaking table feedback signal and acts on the drive signal by compensating for acceleration distortions is proposed in this study. Several experimental tests have been carried out to build a database for offline training, validating, and testing of the proposed NN control model. Subsequently, the well-trained NN is implemented in the inner control loop of the shaking table to compensate, in parallel with the PDFF controller, the distortions during the replication of acceleration signals. Results of tests using earthquake records showed an enhancement in signal matching when integrating the NN model for both bare and loaded conditions of the shaking table. The tracking errors, estimated using the relative root-mean-square error, between the measured and the desired signal, are significantly reduced in time and frequency domains with the additional NN online controller.

Frequency Seismic Response for EEWS Testing on Uniaxial Shaking Table

“…Global RMSEs , computed for all spectral components to be compared with other reported results, have lower values than those reported in recent papers [ 39 , 40 , 41 , 42 ]. Even if simple control algorithms have been used, the minimization of the hardware arrangement, and the low weight of the moving parts (only 390 g for the cart and accelerometer), yields very good seismic-waveform-tracking characteristics.…”

Cyclic Behaviour of Uniform Sand in Drained and Undrained Conditions at Low Confining Stress in Small-Scale Landslide Model

“…The slope material used in this research is uniform sand, which is discussed in detail later in the text. Dynamic loading that simulates the earthquake load is applied to the small-scale slope model using a Quanser STI-III seismic platform e.g., [62][63][64]. The Quanser STI-III seismic platform facility is located in the Laboratory of Structures in the Faculty of Civil Engineering, University of Rijeka, Croatia (e.g., [65,66]).…”

Decoupling Control of a Multiaxis Hydraulic Servo Shaking Table Based on Dynamic Model

“…erefore, it is extensively employed in seismic engineering [5], automobile industry [6], and structure fatigue testing [7]. For the multiaxis hydraulic servo shaking table, the number of hydraulic cylinders is greater than the number of degrees of freedom, and the complex dynamic characteristics make strong coupling effect between the different degrees of freedom, which results in deviation from the desired motion [8][9][10][11]. In addition, the nonlinearity of multiaxis hydraulic servo shaking table and the produced coupling force during the force loading process deteriorate the control performance.…”