Abstract This thesis presents measuring techniques as well as measured and simulated results with the aim of helping the design of photovoltaic energy harvesting systems. Therefore, cost-effective measurement setups were developed for collecting the amount of irradiation, for both stationary and moving photovoltaic (PV) installations. The impact of the time resolution of solar radiation data on estimating the available solar energy was investigated. For moving PV installations, the dynamics and the rate of changes in the available irradiation were studied in order to analyse the effects on maximum power point tracking (MPPT) algorithms. In addition, possibilities for harvesting PV energy in indoor environments were also investigated. The main contribution of this thesis is the effective testing of PV cells and complete PV panels: instead of measuring the characteristic I-V (Current-Voltage) response under strictly controlled artificial illumination, photovoltaics are simply biased externally. Then, with the help of synchronized thermography (ST), infrared (IR) images of the PV panel self-heating are recorded. In the obtained IR-images, defected areas are seen as cold spots, since they are not biased by the external power supply. From the calculated temperature variations, the size of the defect area can be calculated and, thus, the loss in output power can be estimated. The method is shown to work both with and without glass encapsulation. / Tiivistelmä Tämä työ esittelee mittaustekniikoita ja mitattuja ja simuloituja tuloksia aurinkoenergian keruujärjestelmien suunnittelun avuksi. Työtä varten kehitettiin kustannustehokas mittausjärjestelmä, jonka avulla arvioitiin aurinkoenergian määrää sekä stationaarisen että liikkuvan valokennon tapauksissa. Näiden lisäksi tutkittiin mittaustaajuuden vaikutusta arvioitaessa saatavilla olevan aurinkoenergian määrää. Liikkuvan PV (photovoltaic)-asennuksen avulla tutkittiin saatavilla olevan aurinkoenergian vaihtelun suuruutta ja nopeutta tarkoituksena analysoida näiden vaikutuksia käytettäviin MPPT-algoritmeihin. Tämä lisäksi tutkittiin myös valoenergian keruumahdollisuuksia sisätiloissa. Työn tärkein kontribuutio on valokennojen ja kokonaisten valopaneelien toiminnallisuuden testaamisen tehostaminen. Tyypillisesti PV:n toiminnallisuus varmistetaan tarkasti määritetyssä ympäristössä suoritetun I-V -ominaiskäyrämittauksen avulla. Tämän työn menetelmä on yksinkertaisesti biasoida PV:t ulkoisesti, minkä jälkeen ST (synchronized thermpgraphy) -kuvauksen avulla määritetään PV-paneelien itselämpenemistä kuvaavat infrapunakuvat. Paneelin vioittuneet alueet erottuvat IR-kuvissa kylminä alueina ulkoisen biasoinnin puuttuessa. IR-kuvista havaituista lämpötilavaihteluista on mahdollista määrittää vioittuneen alueen koko ja siten arvioida myös menetettyä lähtötehoa. Kyseisen metodin toimivuus osoitettiin niin lasikoteloiduilla kuin ilman sitä olevilla PV-paneeleilla.

This master thesis analyses the existing methods both practically and theoretically used to detect defected surface area in solar cells. Various methods were used but by using an upgraded CMOS camera without IR filter to implement the electroluminescence method, this has proven to have a very crucial impact on the results. Given the overall results and the acquired information, a procedure with a simple parameter can be setup to carry out the measurements. In addition to this a catalog was formed showing the defects occurring in mono and polycrystalline solar cells.

The goal of this work is to bring automatic defect detection to the manufacturing process of plastic cards. A card is considered defective when it is contaminated with a dust particle or a hair. The main challenges I am facing to accomplish this task are a very few training data samples (214 images), small area of target defects in context of an entire card (average defect area is 0.0068 \% of the card) and also very complex background the detection task is performed on. In order to accomplish the task, I decided to use Mask R-CNN detection algorithm combined with augmentation techniques such as synthetic dataset generation. I trained the model on the synthetic dataset consisting of 20 000 images. This way I was able to create a model performing 0.83 AP at 0.1 IoU on the original data test set.

Maintaining quality outcomes is an essential task for any manufacturing organization. Visual inspections have long been an avenue to detect defects in manufactured products, and recent advances within the field of deep learning has led to a surge of research in how technologies like convolutional neural networks can be used to perform these quality inspections automatically. An alternative to these often large and deep network structures is the modular neural network, which can instead divide a classification task into several sub-tasks to decrease the overall complexity of a problem. To investigate how these two approaches to image classification compare in a quality inspection task, a case study was performed at AR Packaging, a manufacturer of food containers. The many different colors, prints and geometries present in the AR Packaging product family served as a natural occurrence of complexity for the quality classification task. A modular network was designed, being formed by one routing module to classify variant type which is subsequently used to delegate the quality classification to an expert module trained for that specific variant. An image dataset was manually generated from within the production environment portraying a range of product variants in both defective and non-defective form. An image processing algorithm was developed to minimize image background and align the products in the pictures. To evaluate the adaptability of the two approaches, the networks were initially trained on same data from five variants, and then retrained with added data from a sixth variant. The modular networks were found to be overall less accurate and slower in their classification than the conventional single networks were. However, the modular networks were more than six times smaller and required less time to train initially, though the retraining times were roughly equivalent in both approaches. The retraining of the single network did also cause some fluctuation in the predictive accuracy, something which was not noted in the modular network. / <p>Det finns övrigt digitalt material (t.ex. film-, bild- eller ljudfiler) eller modeller/artefakter tillhörande examensarbetet som ska skickas till arkivet.</p>

Crack, a typical term most people know, is a common form of distress or damage in road pavements and railway sleepers. It poses significant challenges to their structural integrity, safety, and longevity. Over the years, researchers have developed various data-driven technologies for image-based crack detection in road and sleeper applications. The image-based crack detection has become a promising field.  Many researchers use ensemble learning to win the Road Damage Detection Challenge. The challenge provides a street view dataset from several countries from different perspectives. The version of the dataset is 2020, which contains images from Japan, India, and Czech. Thus, the dataset inherits a domain shift problem. Current solutions use ensemble learning to deal with such a problem. Those solutions require much computational power and challenge adaptability in real-time applications. To mitigate the problem, the thesis experiments with various data augmentation techniques that could improve the base model performance. The main focuses are erasing a crack from an image using generative AI (Erase), implementing road segmentation by using the Panoptic Segmentation (RS) and injecting a perspective-aware synthetic crack (InjectPa) into the segmented road surface in the image. The results show that compared to the base model, the Erase + RS techniques improve the model's F1 score when trained only on Japan in the dataset rather than when trained on three countries simultaneously. Moreover, the InjectPa technique does not help improve the base model in both scenarios. Then, the experiment moved to the SBB dataset containing close-up images of sleepers from cameras mounted in front of the diagnostic vehicle. This section follows the same techniques but changes the segmentation model to the Segment Anything Model (SAM) because the previous segmentation model was trained on a street view dataset, making it vulnerable to close-up images. The Erase + SAM techniques show improvement in bbox/AP and validation loss. Nevertheless, it does not improve the F1 score significantly compared to the base model.  This thesis also applies the explainable AI name D-RISE to determine which feature most influences the model decision. D-RISE shows that the augmentation model can pay attention to the damage type pothole for road pavements and defect type spalling for sleepers than other types. Finally, the thesis discusses the results and suggests a strategy for future study. / Sprickor, en typisk term som de flesta känner till, är en vänlig form av skador i vägbeläggningar och järnvägsslipers. Det innebär betydande utmaningar för strukturella integritet, säkerhet och livslängd. Under årens lopp har olika datadrivna tekniker utvecklats för bildbaserade sprickdetektering i vägbeläggningar och järnvägsslipers applikationer. Den bildbaserade sprickdetekteringen har blivit ett lovande område. Många forskare använder ensembleinlärningsmodeller för att vinna den Road Damage Detection Challenge (Vägbeläggningar Detektering Utmaning). Utmaningen ger en Gatuvy dataset från flera länder från olika perspektiv. Versionen av datasetet är 2020 som innehåller bilder från Japan, Indien och Tjeckien. Därför ärver datasetet  ett domänskiftproblem. Nuvarande lösningar använder ensembleinlärning för att hantera ett sådant problem. Dessa lösningar kräver mycket datorkraft och utmanar anpassningsförmågan i realtidsapplikationer. För att mildra problemet, denna avhandling prover många tekniker för dataökningar som kan förbättra basmodellens prestanda. Huvudfokusen är att radera en spricka från en bild via en generativ AI (Erase), implementera vägyta segmentering via den Panoptic Segmentation (RS), lägga en persective-aware syntetik spricka (InjectPa) till segmenterade vögytan in bilden. Resultaten visar att den Erase + RS ökningsteknikerna förbättrar modellens F1 score när den tränas på Japan i datasetet i stället för att tränas alla länder samtidigt. Dessutom förbättrar den InjectPa tekniken inte basmodellen på båda fallen.  Därefter flyttades experimentet till SBB-datasetet som innehåller närbilder av järnvägsslipers från kameror monterades framför ett diagnosfordon. Denna section följer de samma teknikerna men ändra segmentering modellen till den Segment Anything Model (SAM) eftersom förra segmentering modellen tränades på en Gatuvy dataset vilket gör den sårbar för närbilder. Den Erase + SAM ökningsteknikerna visar förbättringar på bbox/AP och validering. Ändå förbättrade den inte F1 score avsevört jämfört med basmodellen.  Denna avhandling tillämpar också Förklarbar AI-namnet D-RISE för att avgöra vilken funktion som mest påverkar modellbeslutet. D-RISE visar att modellen som har dataökning kan uppmärksamma skadetypen potthål för vägbeläggningar och defekttypen spjälkning för järnvägsslipers än andra typer. Slutligen diskuterar avhandlingen resultaten och föreslår en strategi för framtida arbetsinsatser.

Historically, software production methods and tools have a unique goal: to produce high quality software. Since the goal of Model-Driven Development (MDD) methods is no different, MDD methods have emerged to take advantage of the benefits of using conceptual models to produce high quality software. In such MDD contexts, conceptual models are used as input to automatically generate final applications. Thus, we advocate that there is a relation between the quality of the final software product and the quality of the models used to generate it. The quality of conceptual models can be influenced by many factors. In this thesis, we focus on the accuracy of the techniques used to predict the characteristics of the development process and the generated products. In terms of the prediction techniques for software development processes, it is widely accepted that knowing the functional size of applications in order to successfully apply effort models and budget models is essential. In order to evaluate the quality of generated applications, defect detection is considered to be the most suitable technique. The research goal of this thesis is to provide an accurate measurement procedure based on COSMIC for the automatic sizing of object-oriented OO-Method MDD applications. To achieve this research goal, it is necessary to accurately measure the conceptual models used in the generation of object-oriented applications. It is also very important for these models not to have defects so that the applications to be measured are correctly represented. In this thesis, we present the OOmCFP (OO-Method COSMIC Function Points) measurement procedure. This procedure makes a twofold contribution: the accurate measurement of objectoriented applications generated in MDD environments from the conceptual models involved, and the verification of conceptual models to allow the complete generation of correct final applications from the conceptual models involved. The OOmCFP procedure has been systematically designed, applied, and automated. This measurement procedure has been validated to conform to the ISO 14143 standard, the metrology concepts defined in the ISO VIM, and the accuracy of the measurements obtained according to ISO 5725. This procedure has also been validated by performing empirical studies. The results of the empirical studies demonstrate that OOmCFP can obtain accurate measures of the functional size of applications generated in MDD environments from the corresponding conceptual models. / Marín Campusano, BM. (2011). Functional Size Measurement and Model Verification for Software Model-Driven Developments: A COSMIC-based Approach [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/11237

Le Contrôle-Santé Intégré (CSI) réduit les besoins d’inspections humaines grâce à une surveillance automatisée, réduit les coûts de maintenance grâce à la détection précoce des anomalies avant qu’elles ne dégénèrent et améliore la sécurité ainsi que la fiabilité des services. L’objectif de cette thèse est de concevoir une plateforme de communication sans fil pour le CSI des structures ferroviaires. Le principe de contrôle repose sur la reconstruction des réponses impulsionnelles (fonctions de Green) par corrélation de bruit aléatoire se propageant dans le milieu. Durant ces travaux, nous avons éprouvé expérimentalement la relation entre les réponses actives expérimentales et une version post-traitée des fonctions de corrélation de bruit dans un contexte ferroviaire. Ainsi, nous avons démontré l’applicabilité des fonctions de corrélation pour la détection d’un défaut local sur un rail. Ensuite, nous avons réalisé une étude expérimentale comparative sur la caractérisation d’une transmission ZigBee en termes d’atténuation et de portée dans plusieurs environnements. Dans l’environnement ferroviaire sous test, nous avons démontré l’adéquation avec la portée d’une transmission ZigBee mono-saut (dans un rayon de 76m). Une solution de synchronisation des capteurs lors du prélèvement du signal basée sur la norme IEEE 802.15.4 a été proposée et validée par une campagne de mesures. Il a été démontré que cette approche offre une précision de l’ordre de quelques centaines de nanosecondes. Un prototype-plateforme de communication sans fil basé sur la technologie ZigBee/IEEE 802.15.4 a été mis en place et déployé sur un échantillon de rail. Cette solution a permis de valider les performances de cette plateforme, une fois les données récoltées par les transducteurs, ces informations sont transmises par un lien ZigBee vers une station de base où des algorithmes de détection leurs sont appliqués. / Structural Health Monitoring (SHM) reduces human inspection requirements through automated monitoring, reduces maintenance costs by early detection of defects before they escalate, and improves safety and reliability of services. The work presented in this thesis aims to design a wireless communication platform for railway structures health monitoring. The control principle is based on the reconstruction of impulse responses (Green’s functions) by correlation of random noise propagated in the medium. In this work, direct comparison between an active emission-reception response and the estimated noise correlation function has confirmed the validity of the equivalence relation between them. Thus, we have demonstrated the applicability of the correlation functions for local defect detection in a rail. Then, we conducted an experimental study on the characterization of a ZigBee transmission in terms of path loss and communication range in multiple environments. In the railway environment under test, we showed the adequacy with the range of a ZigBee single-hop transmission (within a radius of 76m). Furthermore, a flexible solution for sensors synchronization during the sampling process, based on IEEE 802.15.4 standard was proposed and validated by a measurement campaign. It has been demonstrated that this approach provides a precision of a few hundred nanoseconds. A wireless communication-platform prototype based on the ZigBee/IEEE 802.15.4 technology has been implemented and deployed on a rail sample. This solution enabled the validation of the platform performances, once the data collected by the transducers, the information is transmitted by a ZigBee link to a base station where detection algorithms are applied.

Until recent years, terahertz (THz) waves were an undiscovered, or most importantly, an unexploited area of electromagnetic spectrum. This was due to difficulties in generation and detection of THz waves. Recent advances in hardware technology have started to open up the field to new applications such as THz imaging. This non-destructive and non-contact imaging technique can penetrate through diverse materials such that internal structures, in some cases invisible to other imaging modalities, can be visualized. Today, there are variety of techniques available to generate and detect THz waves in both pulsed and continuous fashion in two different geometries; transition, and reflection modes. In this thesis continuous wave THz imaging was employed for higher spatial resolution. However, with any new technology comes its challenges; automated processing of THz images can be quite cumbersome. Low contrast and the presence of a widely unknown type of noise make the analysis of these images difficult. In this work, there is an attempt to detect defects in composite material via segmentation by using a Terahertz imaging system. According to our knowledge, this is the first time that this type of materials are being tested under Terahertz cameras to detect manufacturing defects in aerospace industry. In addition, segmentation accuracy of THz images have been investigated by using a phantom. Beyond the defect detection for composite materials, this can establish some general knowledge about Terahertz imaging, its capabilities and limitations. To be able to segment the THz images successfully, pre-processing techniques are inevitable. In this thesis, a variety of different image processing techniques, self-developed or available from literature, have been employed for image enhancement. These methods range from filtering to contrast adjustment to fusion of phase and amplitude images by using fuzzy set theory, to just name a few. The result of pre-procssing and segmentation methods demonstrates promising outcome for future work in this field.

Until recent years, terahertz (THz) waves were an undiscovered, or most importantly, an unexploited area of electromagnetic spectrum. This was due to difficulties in generation and detection of THz waves. Recent advances in hardware technology have started to open up the field to new applications such as THz imaging. This non-destructive and non-contact imaging technique can penetrate through diverse materials such that internal structures, in some cases invisible to other imaging modalities, can be visualized. Today, there are variety of techniques available to generate and detect THz waves in both pulsed and continuous fashion in two different geometries; transition, and reflection modes. In this thesis continuous wave THz imaging was employed for higher spatial resolution. However, with any new technology comes its challenges; automated processing of THz images can be quite cumbersome. Low contrast and the presence of a widely unknown type of noise make the analysis of these images difficult. In this work, there is an attempt to detect defects in composite material via segmentation by using a Terahertz imaging system. According to our knowledge, this is the first time that this type of materials are being tested under Terahertz cameras to detect manufacturing defects in aerospace industry. In addition, segmentation accuracy of THz images have been investigated by using a phantom. Beyond the defect detection for composite materials, this can establish some general knowledge about Terahertz imaging, its capabilities and limitations. To be able to segment the THz images successfully, pre-processing techniques are inevitable. In this thesis, a variety of different image processing techniques, self-developed or available from literature, have been employed for image enhancement. These methods range from filtering to contrast adjustment to fusion of phase and amplitude images by using fuzzy set theory, to just name a few. The result of pre-procssing and segmentation methods demonstrates promising outcome for future work in this field.

Este proyecto tiene como objetivo la implementación de algoritmos para la detección de defectos en las telas poliéster. Como sabemos, desde sus inicios la industria ha utilizado avances tecnológicos no sólo para optimizar los procesos de fabricación sino también para mejorar la calidad de los productos. Ahora, si bien, no es posible evitar las fallas que alteran la calidad de las telas poliéster, sí es posible su detección mediante una inspección visual dentro del proceso de fabricación. En el presente estudio se realizó algoritmos de procesamiento de imágenes mediante el uso de librerías del software LabView para la detección de defectos en las telas poliéster, basándonos en muestras de telas con manchas comunes (MC), manchas de aceite (MA) y puntadas erróneas (PE), las cuales nos permitieron realizar varias pruebas experimentales, utilizando un módulo de pruebas a pequeña escala el cual fue fabricado según el tamaño de las muestras de tela, con la utilización de la técnica de iluminación lateral doble, y basándonos en el análisis del histograma de la imagen original de las muestras de telas, se lograron obtener parámetros numéricos que permitieron la detección de manchas comunes, manchas de aceite y puntadas erróneas, basado en el histograma de cada imagen, el cual muestra la cantidad de píxeles (tamaño de imagen) y la intensidad que se encuentra comprendido en un rango de 0-255 (siendo 0 el valor mínimo y 255 el valor máximo), se logró parametrizar numéricamente cada rango de valores de detección para el caso de MC un rango de valores de intensidad de cada pixel, obteniendo como resultado un intervalo de detección para MC de 0-195 y para el caso de las MA obteniendo como resultado un intervalo de detección de 167-194, que ayudaron en la realización del algoritmo para cada tipo de defecto, que validaron lo planteado en un inicio en la presente investigación. This project takes the implementation of algorithms to detect faults in fabrics polyester. Now, though, it is not possible to avoid the faults that alter the quality of fabrics polyester, the detection is possible by means of a visual inspection of the product inside the manufacturing process. This study carried out algorithms of image processing through the use of libraries from LabView software for detection of defects in fabrics polyester, based on samples of fabrics with Common Stains (MC), Oil Stains (MA) and Erroneous Stitches (PE), which allowed us to carry out several experimental tests, using a module of small scale tests which was manufactured according to the size of the fabric samples , using the technique of double side lighting, and based on histogram analysis, we have managed to obtain parameters that allowed the detection of Common Stains, Oil Stains and Erroneous Stitches. In the case of common stains, was parameterized numerically every range of detection values for the case of MC a range of values of each pixel intensity, resulting in a detection interval for 0-195 MC and the case of the MA resulting in a 167-194 detection interval.