Repository logo
 

Search Results

Now showing 1 - 2 of 2
  • Detection of exposed steel rebars based on deep-learning techniques and unmanned aerial vehicles
    Publication . Santos, R.; Ribeiro, Diogo; Lopes, Patrícia; Cabral, R.; Calçada, R.
    In recent years deep-learning techniques have been developed and applied to inspect cracks in RC structures. The accuracy of these techniques leads to believe that they may also be applied to the identification of other pathologies. This article proposes a technique for automated detection of exposed steel rebars. The tools developed rely on convolutional neural networks (CNNs) based on transfer-learning using AlexNet. Experiments were conducted in large-scale structures to assess the efficiency of the method. To circumvent limitations on the proximity access to structures as large as the ones used in the experiments, as well as increase cost efficiency, the image capture was performed using an unmanned aerial system (UAS). The final goal of the proposed methodology is to generate orthomosaic maps of the pathologies or structure 3D models with superimposed pathologies. The results obtained are promising, confirming the high adaptability of CNN based methodologies for structural inspection.
  • Railway critical speed assessment: A simple experimental-analytical approach
    Publication . Costa, Pedro Alves; Soares, Paulo; Colaço, Aires; Lopes, Patrícia; Connolly, David
    When constructing a new railway line, its long length means there are significant financial implications associated with determining the geodynamic ground properties. Therefore, this paper presents recommendations to optimize the efficiency and depth of such a geotechnical site investigation. Firstly, a numerical analysis is performed to investigate the effect of soil layering, soil stiffness and track bending stiffness on critical velocity. It is shown that each of these variables play an important role, however for most practical cases, only the top 8 m of soil is influential. Track dynamics are rarely affected by soil properties at depths below this, meaning this is the maximum required depth of soil investigation. Using this knowledge, a hybrid experimental-analytical methodology is presented, based on a geophysical Spectral Analysis of Surface Waves (SASW) experimental setup to compute the ground dispersion curve and an analytical model to compute the track dispersion curve. The experimental and analytical results are combined directly, to accurately compute the critical velocity. This approach is attractive because: 1) SASW tests are typically accurate to ≈8 m (when using a mobile exciter) thus matching the required depth needed for critical velocity computation, 2) soil property uncertainties are inherently accounted for, 3) the uncertainties associated with SASW inversion are avoided. The approach is attractive when constructing new railway lines and upgrading the speed of existing lines because it can potentially yield site investigation cost savings. In-situ field work is performed to show the practical application of the technique.