No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

Infrastructures like bridges and tunnels are significant for the economy and growth of countries, however, the risk of failure increases as they getting aged. Therefore, a systematic monitoring scheme is necessary to check the integrity regularly. Among all the defects, cracks are the most common ones that can be observed directly by camera or mapping system. Meanwhile, cracks are capable and reliable indicators. As a result, crack detection is one of the most broadly researched topic. As the limitation of computing resource vanishing, deep learning methods are developing rapidly and used widely. U-net is one of the latest deep learning methods for image classification and has shown overwhelming adaptability and performance in medical images. It is promising to be capable for crack detection.  In this thesis project, a U-net approach is used to automatically detect road and tunnel cracks. An open-source crack detection dataset is used for training. The model is improved by new parameter settings and fine-tuning and transformed onto the data acquired by the mobile mapping system of TACK team. Image processing techniques such as class imbalance handling and center line are also used for improvement. At last, qualitative and quantitative statistics are used to illustrate superiority of the methods.  This thesis project is a sub-project of project TACK, which is an ongoing research project carried out by KTH - Royal Institute of Technology, Sapienza University of Rome and WSP Sweden company under the InfraSweden2030 program funded by Vinnova. The main objective of TACK is developing a methodology for automatic detection and measurement of cracks on tunnel linings or other infrastructures.

The aim of this research is to calibrate conductive polymer nanocomposite materials for large strain sensing and develop a structural health monitoring algorithm for gossamer structures by using nanocomposites as strain sensors. Any health monitoring system works on the principle of sensing the response (strain, acceleration etc.) of the structure to an external excitation and analyzing the response to find out the location and the extent of the damage in the structure. A sensor network, a mathematical model of the structure, and a damage detection algorithm are necessary components of a structural health monitoring system. In normal operating conditions, a gossamer structure can experience normal strain as high as 50%. But presently available sensors can measure strain up to 10% only, as traditional strain sensor materials do not show low elastic modulus and high electrical conductivity simultaneously. Conductive polymer nanocomposite which can be stretched like rubber (up to 200%) and has high electrical conductivity (sheet resistance 100 Ohm/sq.) can be a possible large strain sensor material. But these materials show hysteresis and relaxation in the variation of electrical properties with mechanical strain. It makes the calibration of these materials difficult. We have carried out experiments on conductive polymer nanocomposite sensors to study the variation of electrical resistance with time dependent strain. Two mathematical models, based on the modified fractional calculus and the Preisach approaches, have been developed to model the variation of electrical resistance with strain in a conductive polymer. After that, a compensator based on a modified Preisach model has been developed. The compensator removes the effect of hysteresis and relaxation from the output (electrical resistance) obtained from the conductive polymer nanocomposite sensor. This helps in calibrating the material for its use in large strain sensing. Efficiency of both the mathematical models and the compensator has been shown by comparison of their results with the experimental data. A prestressed square membrane has been considered as an example structure for structural health monitoring. Finite element analysis using ABAQUS has been carried out to determine the response of the membrane to an uniform transverse dynamic pressure for different damage conditions. A neuro-fuzzy system has been designed to solve the inverse problem of detecting damages in the structure from the strain history sensed at different points of the structure by a sensor that may have a significant hysteresis. Damage feature index vector determined by wavelet analysis of the strain history at different points of the structure are taken by the neuro-fuzzy system as input. The neuro-fuzzy system detects the location and extent of the damage from the damage feature index vector by using some fuzzy rules. Rules associated with the fuzzy system are determined by a neural network training algorithm using a training dataset, containing a set of known input and output (damage feature index vectors, location and extent of damage for different damage conditions). This model is validated by using the sets of input-output other than those which were used to train the neural network. / Ph. D.

Bridge inspection and infrastructure inspection are critical steps in the lifecycle of the built environment. Emerging technologies and data are driving factors which are disrupting the traditional processes for conducting these inspections. Because inspections are mainly conducted visually by human inspectors, this paper focuses on improving the visual inspection process with data-driven approaches. Data driven approaches, however, require significant data, which was sparse in the existing literature. Therefore, this research first examined the present state of the existing data in the research domain. We reviewed hundreds of image-based visual inspection papers which used machine learning to augment the inspection process and from this, we compiled a comprehensive catalog of over forty available datasets in the literature and identified promising, emerging techniques and trends in the field. Based on our findings in our review we contributed six significant datasets to target gaps in data in the field. The six datasets comprised of structural material segmentation, corrosion condition state segmentation, crack detection, structural detail detection, and bearing condition state classification. The contributed datasets used novel annotation guidelines and benefitted from a novel semi-automated annotation process for both object detection and pixel-level detection models. Using the data obtained from our collected sources, task-appropriate deep learning models were trained. From these datasets and models, we developed a change detection algorithm to monitor damage evolution between two inspection videos and trained a GAN-Inversion model which generated hyper-realistic synthetic bridge inspection image data and could forecast a future deterioration state of an existing bridge element. While the application of machine learning techniques in civil engineering is not wide-spread yet, this research provides impactful contribution which demonstrates the advantages that data driven sciences can provide to more economically and efficiently inspect structures, catalog deterioration, and forecast potential outcomes. / Doctor of Philosophy / Bridge inspection and infrastructure inspection are critical steps in the lifecycle of the built environment. Emerging technologies and data are driving factors which are disrupting the traditional processes for conducting these inspections. Because inspections are mainly conducted visually by human inspectors, this paper focuses on improving the visual inspection process with data-driven approaches. Data driven approaches, however, require significant data, which was sparse in the existing literature. Therefore, this research first examined the present state of the existing data in the research domain. We reviewed hundreds of image-based visual inspection papers which used machine learning to augment the inspection process and from this, we compiled a comprehensive catalog of over forty available datasets in the literature and identified promising, emerging techniques and trends in the field. Based on our findings in our review we contributed six significant datasets to target gaps in data in the field. The six datasets comprised of structural material detection, corrosion condition state identification, crack detection, structural detail detection, and bearing condition state classification. The contributed datasets used novel labeling guidelines and benefitted from a novel semi-automated labeling process for the artificial intelligence models. Using the data obtained from our collected sources, task-appropriate artificial intelligence models were trained. From these datasets and models, we developed a change detection algorithm to monitor damage evolution between two inspection videos and trained a generative model which generated hyper-realistic synthetic bridge inspection image data and could forecast a future deterioration state of an existing bridge element. While the application of machine learning techniques in civil engineering is not widespread yet, this research provides impactful contribution which demonstrates the advantages that data driven sciences can provide to more economically and efficiently inspect structures, catalog deterioration, and forecast potential outcomes.

The objective of this work was to employ artificial neural networks (NN) to solve inverse problems in different engineering fields, overcoming various obstacles in applying NN to different problems and benefiting from the experience of solving different types of inverse problems. The inverse problems investigated are: 1) damage detection in structures, 2) detection of an anomaly in a light-diffusive medium, such as human tissue using optical imaging, 3) structural optimization of fiber optic sensor design. All of these problems require solving highly complex inverse problems and the treatments benefit from employing neural networks which have strength in generalization, pattern recognition, and fault tolerance. Moreover, the neural networks for the three problems are similar, and a method found suitable for solving one type of problem can be applied for solving other types of problems. Solution of inverse problems using neural networks consists of two parts. The first is repeatedly solving the direct problem, obtaining the response of a system for known parameters and constructing the set of the solutions to be used as training sets for NN. The next step is training neural networks so that the trained neural networks can produce a set of parameters of interest for the response of the system. Mainly feed-forward backpropagation NN were used in this work. One of the obstacles in applying artificial neural networks is the need for solving the direct problem repeatedly and generating a large enough number of training sets. To reduce the time required in solving the direct problems of structural dynamics and photon transport in opaque tissue, the finite element method was used. To solve transient problems, which include some of the problems addressed here, and are computationally intensive, the modal superposition and the modal acceleration methods were employed. The need for generating a large enough number of training sets required by NN was fulfilled by automatically generating the training sets using a script program in the MATLAB environment. This program automatically generated finite element models with different parameters, and the program also included scripts that combined the whole solution processes in different engineering packages for the direct problem and the inverse problem using neural networks. Another obstacle in applying artificial neural networks in solving inverse problems is that the dimension and the size of the training sets required for the NN can be too large to use NN effectively with the available computational resources. To overcome this obstacle, Principal Component Analysis is used to reduce the dimension of the inputs for the NN without excessively impairing the integrity of the data. Orthogonal Arrays were also used to select a smaller number of training sets that can efficiently represent the given system. / Ph. D.