M
Mahdi Shadabfar
Researcher at Sharif University of Technology
Publications - 29
Citations - 376
Mahdi Shadabfar is an academic researcher from Sharif University of Technology. The author has contributed to research in topics: Monte Carlo method & Computer science. The author has an hindex of 6, co-authored 19 publications receiving 122 citations. Previous affiliations of Mahdi Shadabfar include Tongji University.
Papers
More filters
Journal ArticleDOI
Beam Damage Detection Under a Moving Load Using Random Decrement Technique and Savitzky- Golay Filter.
TL;DR: The results show that the proposed method can accurately estimate the damage location/quantification from the acceleration data without any prior knowledge of either input load or damage characteristics.
Journal ArticleDOI
Deep learning-based automatic recognition of water leakage area in shield tunnel lining
TL;DR: Data augmentation to increase the number of positive samples, transfer learning to improve the robustness of convolutional layers, and cascade strategy to enhance the quality of samples were adopted to achieve high precision pixel segmentation of water leakage.
Journal ArticleDOI
Rock fragmentation induced by a TBM disc-cutter considering the effects of joints: A numerical simulation by DEM
TL;DR: In this paper, a 3D discrete element model of rock-cutting using a disc-cutter was established via the high-performance MatDEM software, and the influence of different joint parameters (e.g., joint inclination, orientation, spacing, etc.) on cutting force and rock fragmentation volume was examined.
Journal ArticleDOI
Meta-modelling of coupled thermo-hydro-mechanical behaviour of hydrate reservoir
TL;DR: In this article, a meta-model is proposed to predict the response of hydrate reservoir during gas production via depressurization by utilizing an artificial neural network (ANN) algorithm, and the results are in good agreement with those from the fully-coupled simulator.
Journal ArticleDOI
Deep learning-based classification and instance segmentation of leakage-area and scaling images of shield tunnel linings
TL;DR: By using the proposed approach, the leakage‐area and scaling defects can be automatically classified and quantified with an overall accuracy of 89.3%, which is quite promising compared to the inherent uncertainty in geotechnical engineering.