• Structural Engineering and Mechanics
• /
• 제85권4호
• /
• 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.

• 한국농공학회논문집
• /
• 제52권3호
• /
• pp.73-79
• /
• 2010

In the present study, the loading frequency dependencies of cyclic shear strength and elastic shear modulus of reconstituted clay were examined by performing undrained cyclic triaxial tests and undrained cyclic triaxial tests to determine deformation properties. The result of undrained cyclic triaxial test of reconstituted and saturated clay shows that a faster frequency leads to higher stress amplitude ratio, but when the frequency becomes fast up to a certain point, the stress amplitude ratio will reach its maximum limit and the frequency dependence becomes insignificant. And also, the result of undrained cyclic triaxial deformation test shows a fact that a faster loading frequency leads to higher equivalent shear modules and smaller hysteresis damping ratio, and confirms the frequency dependence of cohesive soil. Meanwhile, the result of the creep test shows that continuing creep is created in the undrained cyclic triaxial test with slow loading frequency rate, and since loading rate becomes slower at the vicinity of the maximum and the minimum deviator stress due to sine wave loading, the vicinity of the maximum and the minimum deviator stress shall be more influenced by creep.

• 한국자동차공학회논문집
• /
• 제3권1호
• /
• pp.1-12
• /
• 1995

Isothermal and thermal-mechanical fatigue characteristics of 12Cr heat resisting steel used for high temperature applications were investigated including hold time effects. Isothermal low cycle fatigue test at $600^{\circ}C$ and in-phase, out-of-phase thermal-mechanical fatigue test at 350 to $600^{\circ}C$ were conducted using smooth cylindrical hollow specimen under strain-control with total strain ranges from 0.006 to 0.015. Regardless of thermal-mechanical and isothermal fatigue tests, cyclic softening behavior was observed and much more pronounced in the thermal-mechanical fatigue tests with hold times due to the stress relaxation during the hold time. The phase difference between temperature and strain in thermal-mechanical fatigue tests resulted in significantly shorter fatigue life for out-of-phase compared to in-phase. The differences in fatigue lives were dependent upon the magnitudes of plastic strain ranges and mean stresses. During the hold time in the strain-controlled fatigue tests, the increase in the plastic strain range and the stress relaxation were observed. It appeared that the increase in plastic strain range per cycle and the introduction of creep damage made important contributions to the reduction of thermal-mechanical fatigue life with hold time, and the life reduction tendency was more remarkable in the in-phase than in the out-of-phase thermal-mechanical fatigue. Isothermal fatigue tests performed under the combination of fast and slow strain rates at $600^{\circ}C$ showed that the fatigue life decreased as the strain rate and frequency decreased,especially for the low strain ranges.

• 한국구조물진단유지관리공학회 논문집
• /
• 제27권6호
• /
• pp.22-29
• /
• 2023

재료 및 부재의 내진성능평가 실험 시 재하속도와 수직하중은 성능에 중대한 영향을 미칠 수 있다. 반복 가력 및 하이브리드 실험 시 재하속도는 입력 변위와 출력 변위 사이의 시간 지연현상으로 인해 고속으로 제어하기 어려우며 횡방향 변위에 의해 수직하중을 일정하게 유지하는 것이 어려워 일정한 수직하중이 유지되는 고속 및 실시간 실험은 거의 이루어지지 않았다. 본 연구에서는 면진받침의 속도 의존성과 수직하중의 영향을 조사하기 위해 저속 및 고속 반복 가력 실험과 실시간 하이브리드 실험을 수행하였다. 실험에서 수평 변위와 수직 하중의 실시간 제어를 위해 Adaptive Time Series(ATS) 보정 방법과 State estimator가 포함된 FLB System을 구축하였다. 고속 또는 실시간으로 재하되는 수평 변위 제어 속도와 상부구조물에 의한 수직하중은 면진받침의 강도 및 지진 시 거동에 상당한 영향을 미칠 수 있음을 확인하였으며 내진성능평가를 위한 실험 시 실제와 유사하도록 구현되어야함을 알 수 있었다. 본 연구는 내진성능평가를 위해 구축하고 사용된 시스템의 우수한 성능을 보여주며 정확하고 효율적인 내진성능평가가 가능하도록 하였다.

• 대한기계학회논문집
• /
• 제18권5호
• /
• pp.1192-1202
• /
• 1994

Fatigue behavior and life prediction were presented for thermal-mechanical and isothermal low cycle fatigue of 12Cr forged steel used for high temperature applications. In-phase and out-of-phase thermal-mechanical fatigue test at 350 to 600.deg. C and isothermal low cycle fatigue test at 600.deg. C were conducted using smooth cylindrical hollow specimen under strain-control with total strain ranges from 0.006 to 0.015. Cyclic softening behavior was observed regardless of thermal-mechanical and isothermal fatigue tests. The phase difference between temperature and strain in thermal-mechanical fatigue resulted in significantly shorter fatigue life for out-of-phase than for in-phase. The difference in fatigue lives was dependent upon the magnitudes of inelastic strain ranges and mean stresses. Increase in inelastic strain range showed a tendency of intergranular cracking and decrease in fatigue life, especially for out-of-phase thermal-mechanical fatigue. Thermal-mechanical fatigue life prediction was made by partitioning the strain ranges of the hysteresis loops and the results of isothermal low cycle fatigue tests which were performed under the combination of slow and fast strain rates. Predicted fatigue lives for out-of-phase using the strain range partitioning method showed an excellent agreement with the actual out-of-phase thermal-mechanical fatigue lives within a factor of 1.5. Conventional strain range partitioning method exhibited a poor accuracy in the prediction of in-phase thermal-mechanical fatigue lives, which was quite improved conservatively by a proposed strain range partitioning method.