The manufacturing process ‘long line method’ has shown many advantages when producing prestressed concrete sleepers, such as rapid production and low cost. However, there have been certain difficulties when cutting the 100 m long concrete blocks into sleepers. The sleepers tend to crack when the diamond cutting blade cuts through the last strands. Moreover, the shape and size of the cracks varies from one sleeper to another. Although these cracks may not affect the load carrying capacity, they will not be aesthetically pleasing. No earlier studies within the area have been found, i.e. diamond cutting of prestressed concrete blocks. As a result, there have been certain difficulties when approaching the problem. Finite element analysis has been proven to be a useful tool when analyzing stress variation. Throughout this project, the cutting simulation has been analyzed using the finite element analysis software ABAQUS. To summarize, stress variation has been examined during different cutting depths. The results from the FE model shows that no critical values were reached in the areas expected to have cracks. The true cause of the problem could not be specified. Therefore, further studies are needed yet this thesis could be a good foundation.

This study presents an exploration of several machine learning and image processing theories, as well as a literature review of several previous works on concrete crack detection systems. Through the literature review a system is selected and implemented with the Öresund bridge photograph collection. The selected system is a Convolutional Neural Network (CNN) using cropped (256x256x) images for input. The CNN has a total of 13 layers that were implemented as described in the paper. All parts of the implementation such as cropping, code, and testing are described in detail. This study found a final accuracy rate of 77% for the trained net. This is combined with a sliding window technique for handling larger images. An exploration of reasons for this accuracy rate is done at the end of the paper.

The aim of master thesis was design and assessment foundations of waterproof concrete. Computational software Dlubal RFEM 5.07 used to calculate internal forces. Calculation in acordance with applicable standards.

This final thesis is divided into two parts. The first, theoretic part is focused on issue about industrial concrete floors, their production and adjustment. Special attention is paid to the mineral shakes, steel fibres and concrete, which is used to these constructions. There are more information about specific standardized tests of steel fibre concrete and some damages of concrete floors in other chapters. Second part of the diploma thesis is practical. Theoretical knowledge are applied to the actual construction. Survey methodology and diagnostic work are also desribed. Data processing and evaluation with the commentary is also attached to this part. The conclusion summarizes the results and selected findings relating to the issue are also included there.