| Abstrakt: |
Deep neural networks (DNNs) have recently become one of the most often used soft computational tools for numerical analysis. The huge success of DNNs in the field of image processing is associated with the use of convolutional neural networks (CNNs). CNNs, thanks to their characteristic structure, allow for the effective extraction of multi-layer features. In this paper, the application of CNNs to one of the important soil-structure interaction (SSI) problems, i.e., the analysis of vibrations transmission from the free-field next to a building to the building foundation, is presented in the case of mine-induced vibrations. To achieve this, the dataset from in-situ experimental measurements, containing 1D ground acceleration records, was converted into 2D spectrogram images using either Fourier transform or continuous wavelet transform. Next, these images were used as input for a pre-trained CNN. The output is a ratio of maximal vibration values recorded simultaneously on the building foundation and on the ground. Therefore, the last layer of the CNN had to be changed from a classification to a regression one. The obtained results indicate the suitability of CNN for the analyzed problem. [ABSTRACT FROM AUTHOR] |
