Janko Logar

Modelling soil behaviour in uniaxial strain conditions by neural networks

Abstract The feed-forward neural network was used to simulate the behaviour of soil samples in uniaxial strain conditions, i.e. to predict the oedometer test results only on the basis of the basic soil properties. Artificial neural network was trained using the database of 217 samples of different cohesive soils from various locations in Slovenia. Good agreement between neural network predictions and laboratory test results was observed for the test samples. This study confirms the link between basic soil properties and stress–strain soil behaviour and demonstrates that artificial neural network successfully predicts soil stiffness in uniaxial strain conditions. The comparison between the neural network prediction and empirical formulae shows that the neural network gives more accurate as well as more general solution of the problem.

Use of Automatic Target Recognition System for the Displacement Measurements in a Small Diameter Tunnel Ahead of the Face of the Motorway Tunnel During Excavation

During construction of the Šentvid tunnel a unique opportunity arose to measure the 3D displacements ahead of the motorway tunnel excavation face, since the exploratory tunnel was already constructed in the axis of the main tunnel. According to reviewed literature such measurements had not been performed yet and several problems regarding equipment and complete scheme of the experiment needed to be overcome. The paper gives a brief description of the Šentvid tunnel project, presents significant factors that affected the choice of the geodetic equipment and describes the scheme of the experiment. A special attention is focused on the problems relating to the operation of the instrument in demanding environmental conditions (water, dust).

Mechanisms of Landslides and Creep in Over-Consolidated Clays and Flysch (WCoE 2014–2017)Open image in new window

The Faculty of Civil and Geodetic Engineering of the University of Ljubljana (UL FGG), Slovenia, Europe, was voted in 2014 at the 3rd World Landslide Forum in Beijing, China to be one of the 15 new World Centres of Excellence (WCoE) in Landslide Disaster Reduction for the period 2014–2017. This successful nomination followed the period 2011–2014, in which UL FGG successfully fulfilled the role as one of the WCoEs for the second time. The title of the activities of the WCoE in this third term was slightly modified to be “Mechanisms of Landslides and Creep in Over-Consolidated Clays and Flysch”. We can divide the activities of the WCoE at UL FGG into international and national research activities. The international ones consisted of the ICL related activities with the main task of being the main organizer of this 4th World Landslide Forum 2017, international cooperation, European research activities, and bilateral cooperation. The national ones consisted of the national projects and the national research program “Water Science and Technology, and Geotechnics”. In the paper, these activities of the WCoE at UL FGG are elaborated in more detail, with a comprehensive list of publications to show the dissemination and capacity building efforts.

Introduction: Landslide Mitigation, Remediation and Stabilization

Open image in new window The Session Landslide Mitigation, Remediation and Stabilization: Landslide Protection Works, Landslide Stabilization and Remediation, and Landslide Non-structural Measures, as a part of WLF4 Volume 3 Advances in Landslide Technology, contains the contributions with the aims to present different approaches and measures used in landslide mitigation, remediation and stabilization including structural and non-structural measures with a general purpose to ensure stability of a slope against current and reasonably possible conditions in the slope.