Fatigue damage detection using sensor technology have been investigated to detect fatigue damage at an early stage. Among them, there is a method to detect the strain change due to fatigue damage. However, because the magnitude of the external force in an in-service bridge is not constant, this method alone cannot be applied to an actual in-service bridge.

In this study, we propose the fatigue damage detection system that utilizes a piezoelectric sensor and a MEMS accelerometer. The field measurement results indicate the possibility of fatigue damage detection from the response measured by the piezoelectric sensor based on the external force information obtained using MEMS accelerometer.

This paper shows the usefulness of CNN with Mel-spectrogram in the detection of wood breaking sounds occurred in a large earthquake. In this research, NN and CNN models are used to detect wood breaking sounds. The NN model is trained by using the input data of MFCC which is calculated from various time series data of 3 seconds. On the other hand, the CNN model is trained by using the spectrogram or Mel-spectrogram which are also calculated from the same time series data. Then, the accuracies are compared to each other. As a result, the both methods show excellent accuracies. Furthermore, the other sounds which are synthesized by mixing a wood breaking sound with other environmental sounds are classified using the trained model. In this case, it is confirmed that the CNN with Mel-spectrogram can be more accurate classificatory than others.

It is desirable for spherical gas holders, which require a high level of safety, to be able to retain their functions during aftershocks even when the foundation is subjected to unequal settlement due to a large-scale earthquake. For this purpose, it is necessary to develop a simple method to evaluate the seismic resistance of inclined gas holders under the assumption of maximum aftershocks, which will contribute to the decision on whether or not to use the holders after a large-scale earthquake. The analysis to evaluate each element of the holder must take into account the material and geometrical nonlinear response mechanism of the supporting structure and nonlinear dampers, and it is not realistic to conduct detailed evaluation by 3D analysis in a short period of time after an earthquake. Therefore, in this paper, the simple evaluation method using a single mass-spring analysis that reflects the nonlinear spring characteristics from the pushover analysis is proposed. This method shows good agreement with the dynamic response of a 3D framework model of an actual gas holder until the maximum response value, and after that, the response value is calculated on the safe side, which means that the aftershock seismic resistance of the holder can be evaluated.

The purpose of this paper is to clarify the running safety of railway rolling stock during earthquakes when the bearings of continuous girder bridges are seismically isolated in the direction perpendicular to the bridge axis. Dynamic interacion analyses between vehicles and structures revealed that a derailment limit input acceleration of vehicles running on a continuous bridge decreases in the center span of the continuous girder when the natural frequency of the pier is 2 Hz, whereas it tends to decreases at the structural boundary on the exit side due to the occurrence of angular rotation when the natural frequency of the pier is 0.5 Hz or the dominant frequency of the track surface decreases due to the seismic isolation. By designing seismic isolation bearings with a yield seismic intensity of 0.4 and a predominant frequency of the track surface of 0.5 Hz or less, derailment can be prevented even for the L2 seismic earthequake class. When seismic isolation bearings satisfying these conditions are implemented into continuous girder, the horizontal displacement of the track surface does not increase significantly, and the horizontal displacement of the pier top can be reduced by to 50%.

A large number of wooden houses collapsed in the 2011 off the Pacific coast of Tohoku Earthquake and Tsunami and the 2016 Kumamoto Earthquake. The large amount of debris from the collapsed houses not only blocked the roads and hindered the immediate evacuation, but also caused delays in the recovery and reconstruction due to the time and cost required to remove the debris. For example, there is a high risk of earthquakes and tsunamis of the same or greater magnitude in the Tokai and Tonankai regions, and it is important to assess in advance the total amount and spread of debris that could be generated in the event of a major earthquake, and to prepare a recovery plan for post-disaster emergencies. The ASI-Gauss Code, which is a finite element method of beam elements that can analyze the progressive collapse of a framework structure, is used to predict the damage and collapse of houses caused by earthquakes. In order to demonstrate the validity of the proposed technique, we attempted to reproduce the damage in the Furukawa area of Osaki City during the 2011 off the Pacific coast of Tohoku Earthquake, and compared the results with damage reports.