• Structural Engineering and Mechanics
• /
• v.85 no.4
• /
• pp.469-484
• /
• 2023

A deep recursive bidirectional Cuda Deep Neural Network Long Short Term Memory (Bi-CuDNNLSTM) layer is recruited in this paper to predict the entire force time histories, and the corresponding hysteresis and backbone curves of reinforced concrete (RC) bridge piers using experimental fast and slow cyclic tests. The proposed stacked Bi-CuDNNLSTM layers involve multiple uncertain input variables, including horizontal actuator displacements, vertical actuators axial loads, the effective height of the bridge pier, the moment of inertia, and mass. The functional application programming interface in the Keras Python library is utilized to develop a deep learning model considering all the above various input attributes. To have a robust and reliable prediction, the dataset for both the fast and slow cyclic tests is split into three mutually exclusive subsets of training, validation, and testing (unseen). The whole datasets include 17 RC bridge piers tested experimentally ten for fast and seven for slow cyclic tests. The results bring to light that the mean absolute error, as a loss function, is monotonically decreased to zero for both the training and validation datasets after 5000 epochs, and a high level of correlation is observed between the predicted and the experimentally measured values of the force time histories for all the datasets, more than 90%. It can be concluded that the maximum mean of the normalized error, obtained through Box-Whisker plot and Gaussian distribution of normalized error, associated with unseen data is about 10% and 3% for the fast and slow cyclic tests, respectively. In recapitulation, it brings to an end that the stacked Bi-CuDNNLSTM layer implemented in this study has a myriad of benefits in reducing the time and experimental costs for conducting new fast and slow cyclic tests in the future and results in a fast and accurate insight into hysteretic behavior of bridge piers.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.16 no.4
• /
• pp.737-752
• /
• 1992

Analysis of elasto-dynamic deformation of flexible linkage mechanism is conducted using the finite element method. The equations of motion of the system are derived from the static structural problem in which dynamic inertia, gravitational and driving forces are treated as external loads. Linear spring model is included in the formulation of equation of motions to represent the effects of deformation of elastic bearings of revolute joints on the system behavior. A computer program is constructed and applied to analyze a specific crank-lever 4-bar mechanism. The algorithm of the program is as follows. First, the natural frequencies and the mode shapes of the system are calculated by solving the eigenproblem of the mechanism system which can be considered as a static structure by assuming the input shaft (crank shaft) to be fixed at any given configuration of mechanism. And finally, the elasto-dynamic deformation of the whole system is obtained using mode superposition method for the case of constant input speed. The effect of geometric stiffness on the mechamism is included in the program with the axial forces of links obtained through the quasi-static displacement analysis. It is found that the geometric stiffness exerts an important effect upon the elasto-dynamic behavior of the flexible linkage mechanism. Elastic deformation of bearing lowers the natural frequencies of the system, resulting smaller elastic displacement at the mid-point of the links and bigger elestic displacement at the ends of the links than rigid bearing. The above investigation of flexible linkage mechanism shows that the effects of the elastic deformation of bearing on the mechanism should be considered to design the mechanism which satisfies more preciously the purpose and the condition of design.