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.

Polymerbasierte Leichtbaumaterialien (LMs) werden zunehmend als Konstruktionswerkstoffe im Transportwesen (Automobilbau, Luft- und Schifffahrt, Schienenverkehr), in der zivilen Infrastruktur, im Bauwesen und in der Energietechnik eingesetzt, um Energie, Gewicht und Ressourcen einzusparen, sowie den Ausstoß klimaschädlicher Treibhausgase zu reduzieren. Sie besitzen eine hohe Festigkeit, Stabilität, Zuverlässigkeit, Langlebigkeit und können energie-, kosten- und ressourceneffizient hergestellt werden. Stoffliche Änderungen können irreversible Schäden am LM hervorrufen und zum frühzeitigen Materialversagen führen. Daher ist eine Materialüberwachung sinnvoll. Die vorliegende Arbeit untersucht einen neuartigen Sensoransatz zur Zustandsüberwachung von LMs mittels passiver und strukturintegrierter elektromagnetischer Resonatorarrays (RAs). Sie zeichnen sich durch regelmäßig zueinander angeordnete Subwellenlängenresonatoren aus, die in Drucktechnologie umgesetzt und mittels Spritzgieß- oder Vakuum-Infusionstechnologie in die LMs integriert werden. Stoffliche Veränderungen bewirken ein verändertes elektromagnetisches Resonanzverhalten der RAs, dass per Reflexionsmessung kontaktlos ausgewertet werden kann. Es werden reflexionsbasierte Sensorkonzepte durch den Einsatz mehrlagiger RAs erarbeitet und das Reflexionsverhalten numerisch mittels der Finiten-Elemente-Methode analysiert und die betrachteten RAs exemplarisch umgesetzt, integriert und hinsichtlich ihrer Sensorfunktion bewertet.:1 Einleitung 2 Elektromagnetische Felder, Wellen und deren Wechselwirkung mit Materie 3 Entwicklung von Subwellenlängen Resonatorarrays 4 Realisierung eines Messverfahrens zur Bewertung der Eigenschaften der entwickelten Resonatorarrays 5 Applikationsszenarien 6 Ergebnisbewertung und Auswertung Anhang

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.

A piezoelectric impedance-based structural health monitoring technique was developed at the Center for Intelligent Material Systems and Structures. It has been successfully implemented on several complex structures to detect incipient-type damage such as small cracks or loose connections. However, there are still some problems to be solved before full scale development and commercialization can take place. These include: i) the damage assessment is influenced by ambient temperature change; ii) the sensing area is small; and iii) the ability to identify the damage location is poor. The objective of this research is to solve these problems in order to apply the impedance-based structural health monitoring technique to real structures. First, an empirical compensation technique to minimize the temperature effect on the damage assessment has been developed. The compensation technique utilizes the fact that the temperature change causes vertical and horizontal shifts of the signature pattern in the impedance versus frequency plot, while damage causes somewhat irregular changes. Second, a new impedance-based technique that uses multiple piezoelectric sensor-actuators has been developed which extends the sensing area. The new technique relies on the measurement of electrical transfer admittance, which gives us mutual information between multiple piezoelectric sensor-actuators. We found that this technique increases the sensing region by at least an order of magnitude. Third, a time domain technique to identify the damage location has been proposed. This technique also uses multiple piezoelectric sensors and actuators. The basic idea utilizes the pulse-echo method often used in ultrasonic testing, together with wavelet decomposition to extract traveling pulses from a noisy signal. The results for a one-dimensional structure show that we can determine the damage location to within a spatial resolution determined by the temporal resolution of the data acquisition. The validity of all these techniques has been verified by proof-of-concept experiments. These techniques help bring conventional impedance-based structural health monitoring closer to full scale development and commercialization. / Master of Science

By structural health monitoring (SHM) of composite structures, their sustainability, safety and economics can be improved. On one hand, it enables using components to their full life or having them replaced early before otherwise unforeseen failure. On the other hand, it may make structures lighter as designs with smaller safety margins would be possible. Cryogenic liquid hydrogen tanks for aircraft would need to become lighter to enable such fossil-free aviation, which could require SHM. Vertically aligned carbon nanotubes (VACNT) have been used as embedded sensors in composites for temperature and strain sensing while other architectures of nanotubes have been used to detect fatigue damage. In this work, VACNT embedded in carbon fibre/epoxy composites are cycled both thermally and mechanically to investigate their suitability to detect damage in composite cryogenic tanks. It was found VACNT retain their strain sensing ability after cycling to cryogenic temperatures and that a relationship of increasing electrical resistance to increased cycling and damage is possible. That indicates VACNT are suitable for SHM of cryogenic tanks, but more testing and better electrical insulation of the VACNT is needed to confirm this. / Genom att övervaka kompositstrukturers livslängd med structural health monitoring (SHM), kan miljöhållbarheten, säkerheten och ekonomin i att använda dem förbättras. Å ena sidan möjliggör det att komponenter används sin fulla livslängd eller ersätts innan annars oförutsedda skador leder till kollaps. Å andra sidan kan det göra strukturer lättare eftersom designer med mindre säkerhetsmarginaler vore möjliga. Kryotankar för flytande väte i flygplan behöver bli lättare för att möjliggöra sådant fossilfritt flygande, vilket skulle kunna kräva SHM. Vertikalt riktade kolnanorör (vertically aligned carbon nanotubes, VACNT) har använts som inbäddade temperatur- och töjningssensorer i kompositer och andra kolnanorörsmaterial har använts för att detektera utmattningsskador. I detta arbetet har VACNT inbäddat i kolfiber och epoxi cyklats både termiskt och mekaniskt för att undersöka dess lämplighet som sensorer för skadedetektering i kryotankar. Det konstaterades att VACNT behåller sin töjningsdetekteringsförmåga efter termisk cykling till kryotemperatur och att det är möjligt att ett förhållande om ökande resistans med ökande cykling och skada kan finnas. Det indikerar att VACNT vore lämpliga för SHM i kryotankar, men mer provning och bättre elektrisk isolering av VACNT behövs för att bekräfta det.

In this study a software package for easily creating and embedding structural health monitoring (SHM) data interrogation processes in remote hardware is presented. The software described herein is comprised of two pieces. The first is a client to allow graphical construction of data interrogation processes. The second is node software for remote execution of processes on remote sensing and monitoring hardware. The client software is created around a catalog of data interrogation algorithms compiled over several years of research at Los Alamos National Laboratory known as DIAMOND II. This study also includes encapsulating the DIAMOND II algorithms into independent interchangeable functions and expanding the catalog with work in feature extraction and statistical discrimination. The client software also includes methods for interfacing with the node software over an Internet connection. Once connected, the client software can upload a developed process to the integrated sensing and processing node. The node software has the ability to run the processes and return results. This software creates a distributed SHM network without individual nodes relying on each other or a centralized server to monitor a structure. For the demonstration summarized in this study, the client software is used to create data collection, feature extraction, and statistical modeling processes. Data are collected from monitoring hardware connected to the client by a local area network. A structural health monitoring process is created on the client and uploaded to the node software residing on the monitoring hardware. The node software runs the process and monitors a test structure for induced damage, returning the current structural-state indicator in near real time to the client. Current integrated health monitoring systems rely on processes statically loaded onto the monitoring node before the node is deployed in the field. The primary new contribution of this study is a software paradigm that allows processes to be created remotely and uploaded to the node in a dynamic fashion over the life of the monitoring node without taking the node out of service. / Master of Science

[pt] O monitoramento da integridade estrutural aumenta de importância dentro do campo de estudo de engenharia civil. Grande parte das cidades dependem de elementos de sua infraestrutura como pontes, barragens e prédios para prover uma série de benefícios para a sociedade moderna. Por outro lado, mesmo o projeto mais conservador não resiste aos efeitos do tempo. Uma boa rotina de manutenção preventiva não exime a necessidade de se ter uma constante verificação e busca de falhas pois em alguns casos isto poderia permitir em catástrofes de grande escala envolvendo grande perda material e até mesmo vidas. Graças ao desenvolvimento tecnológico das últimas décadas foi possível pesquisar e criar ferramentas poderosas que podem ajudar problemas deste tipo. O objetivo desta dissertação é avaliar a aplicação de métodos de Inteligência Artificial na detecção de danos em vigas. A metodologia utiliza parâmetros modais de elementos estruturais para verificar a presença de danos relacionados a redução de rigidez de uma seção transversal. Mais especificamente, os métodos apresentados neste estudo são orientados por dados, então primeiramente o banco de dados para treino e validação dos métodos de IA foi gerado por um programa em Python dentro do software de elementos finitos Abaqus. Os parâmetrosd modais analisados foram as cinco primeiras frequências naturais das vigas. Foi possível avaliar a performance dos métodos de IA para classificação da presença ou não de danos em diferentes métricas de análise. Por fim, uma comparação paramétrica foi feita entre os modelos de Inteligência Artificial. / [en] Monitoring structural integrity has become increasingly important in the field of civil engineering. A huge part of cities depend of civil engineer infrastructures such as bridges, dams and buildings to provide several benefits to modern society. On the other hand, even the most conservative design cannot resist the power of time. A good preventive maintenance routine don’t let go of the need in constant verification for faults because in some cases that could lead to large scale catastrophes involving big material and life costs. Thanks to technology development over the last decades it was possible to search and create many powerful tools that could help those kind of problems. The objective of this thesis is to assess on the application of Artificial Intelligence Methods to detect damage on beams. The formulation uses modal parameters of a structure to verify the presence of damage related to the reduction of stiffness of a section. More specifically, the methods presented on this study are data-driven, so first a database for training and validating the AI methods were generated in a Python program within the finite element software Abaqus. The modal parameters analyzed were the first five natural frequencies of a beam. It was possible to evaluate the performance of the AI methods when classifying a beam with or without damage on different metrics. Finally, a parametric comparison was made between the Artificial Intelligence methods.

Dehnungssensoren werden zur Überwachung von sicherheitsrelevanten Bauteilen, besonders in Bauteilen aus faserverstärkten Polymermatrixverbundwerkstoffen eingesetzt. Durch deren Integration in das Bauteilinnere werden sie vor schädigenden mechanischen sowie korrosiven Einwirkungen geschützt. Dies gewährleistet eine zuverlässige sowie dauerhafte Funktion. Verschiedene Ansätze zur Weiterentwicklung integrierbarer Dehnungssensoren werden international untersucht. Die Verringerung des Sensordurchmessers auf Abmaße im Bereich des Durchmessers von Verstärkungsfasern ist dabei ein bedeutendes Entwicklungsziel. Insbesondere bei der Integration in Bauteile aus faserverstärkten Kunststoffen sorgen zum Durchmesser von Fasern vergleichbare Sensordurchmesser für eine optimale Sensoranbindung. Die Bildung von Harznestern sowie schwächender Unstetigkeiten kann mittels dünner Sensoren verhindert werden. Dies gewährleistet eine artefaktefreie Dehnungsmessung. Drei verschiedene Ansätze für neuartige Dehnungssensoren mit kleinem Querschnitt wurden in dieser Arbeit untersucht. / Strain sensors are used for structural health monitoring issues, certainly in parts with high safety requirements made of fibre-reinforced plastic composites. The integration of these sensors inside the parts protects them against any mechanical and corrosive impact. The sensor functionality can be enhanced by integration. There is a lot of international research effort to further develop integratable strain sensors. Different approaches are currently pursued. This thesis presents the results of investigations on three different approaches for novel strain sensors. The main goal of these investigations was to minimise the sensor diameter down to the diameter of reinforcing fibres. The small diameter allows for an optimum and artefact free integration of the sensors. The formation of resin nests and notches to the material structure can be prevented by integrating sensor with a smaller diameter. The strain measurement and monitoring is enhanced and more reliable then.