Continuous welding is one of the prominent techniques used in producing seamless piping used in many applications such as the mining and the oil and gas industries. Weld defects cause significant loss of time and money in the piping production industry. Therefore, there is a need for effective online weld defects detection systems. A laser-based weld defects detection (LBWDD) system has been developed by the industrial partner. However, the current LBWDD system can only detect some geometrically based weld defects, but not material inhomogeneity such as voids, impurities, inclusions, etc. The main objective of this study is to assess the predictability of a thermal imaging-based weld defects detection system (TIBWDD) using an IR camera that can be integrated with the current LBWDD system. The aim of the integrated detection system is to be able to detect a wider range of weld defects. A test rig has been designed and used to carry out a set of emissivity (ε) calculation experiments considering three different materials – Aluminum 5154 (Al), Stainless Steel 304L (SS), and Low Carbon Steel A131 (LCS) with two surface finishes 0.25 μm (FM) and 2.5 μm (RM), which are relevant to pipe welding operations. Al showed least change in ε varying from 0.162 to 0.172 for FM samples and from 0.225 to 0.250 for RM samples from 50°C to 550°C. LCS showed highest change in ε varying from 0.257 – 0.918 for FM samples and from 0.292 to 0.948 for RM samples. SS showed a consistent increase in ε for both FM and RM samples. Experimental and numerical analysis have been carried out mimicking two sets of possible weld defects investigating defect size, Dh, and distance between effect and sample surface, δ. Results showed that the δ based defects that are located within 3 mm can be detected by the IR camera. Defects with Dh = 1. 5 mm can be detected by the IR camera with and without glass wool. Laser welding simulations using 2D and 3D Gaussian heat source models have been carried out to assess the predictability of a set of possible weld defects. The heat source models have been validated using experimental data. Three sets of defects were considered representing material-based inhomogeneity, step and inclined misalignment defects. For material-based inhomogeneity in thin plates all defects located at 1.25 mm from the surface are found detectable as ΔT (temperature difference obtained on surface) > ΔTmin (detectability limit of TIBWDD system). For inhomogeneity defects in thick plates, except defects of 2.5 mm in square size all other defects were found detectable as ΔT > ΔTmin. All step misalignment defects were detected for thin and thick plates. In the case of inclined misalignment defects, for thin plates, the misalignment error in the thin plate had to be at least 0.275 mm to be detected. In the case of thick plates, the misalignment error had be at least 0.375 mm to be detected. Overall, results of the present study confirm that thermal imaging can be successfully used in detecting material-based and geometry-based weld defects. / Thesis / Master of Applied Science (MASc)

L'arrivée de nouveaux matériaux dans les industries manufacturières engendre de nouvelles problématiques de contrôle. C'est notamment le cas pour l'entreprise SKF qui introduit dans ses roulements des rouleaux en céramique. Ces rouleaux peuvent avoir deux géométries différentes, en forme de cylindre ou de tonneau. La plupart des méthodes de Contrôle Non Destructif dédiées aux rouleaux en acier ne sont pas exploitables pour ceux en céramique, c'est pourquoi il est nécessaire de développer une nouvelle approche. Dans ces travaux, nous nous sommes intéressés à la méthode Ultrasons-Laser. L'utilisation de lasers permet de générer et de détecter des ondes ultrasonores sans contact sur des structures en acier ou en céramique. Une étude des diagrammes de directivité pour les sources les plus communes et le calcul des courbes de dispersion liées à la géométrie cylindrique ont été effectués. Ces éléments nous ont permis d'interpréter les signaux acquis expérimentalement. Nous avons alors pu montrer que la méthode était efficace pour la détection de défauts de différentes natures sur des rouleaux de forme cylindrique en acier et en céramique. Une méthode originale a été proposée et étudiée théoriquement et expérimentalement afin de réduire significativement le temps de contrôle d'un rouleau et ainsi optimiser la méthode. Cette méthode a été étendue avec succès aux rouleaux de forme "tonneau". / The development of new materials in industries creates new issues about their control. It is the case for SKF introduces ceramic rollers in its bearings. These rollers can have two different geometries, cylinder or barrel. Most methods of Non Destructive Testing developed for steel rollers analysis are not adapted for ceramic rollers. In fact, these equipments use electrical of metal materials properties to control a solid. In consequence, it is necessary to develop a new approach for ceramic structures. In this report, we are studying Ultrasonics Laser method. The use of lasers allows to generate and to detect ultrasound waves without contact on steel or ceramic media. A study of directivity patterns for the most common thermoelastic sources and calculation of dispersive curves due to cylindrical geometry have been done. The results of these studies allow us to interpret different signals obtained during ours experimentations. We have shown that the method was efficient for the detection of different types of defects present on ceramic and steel rollers. An original approach has been proposed and studied, theoretically and experimentally, to reduce significantly the time of control for a cylindrical roller. This approach have been extended to a ceramic barrel roller with success.

This dissertation presents an approach to reconstruct degenerate near-planar road surface in three-dimensional (3D) while automatically detect road defects. Three techniques are developed in this dissertation to establish the proposed approach. The first technique is proposed to reconstruct the degenerate near-planar road surface into 3D from one camera. Unlike the traditional Structure from Motion (SfM) technique which has the degeneracy issue for near-planar object 3D reconstruction, the uniqueness of the proposed technique lies in the use of near-planar characteristics of surfaces in the 3D reconstruction process, which solves the degenerate road surface reconstruction problem using only two images. Following the accuracy-enhanced 3D reconstructed road surface, the second technique automatically detects and estimates road surface defects. As the 3D surface is inversely solved from 2D road images, the detection is achieved by jointly identifying irregularities from the 3D road surfaces and the corresponding image information, while clustering road defects and obstacles using a mean-shift algorithm with flat kernel to estimate the depth, size, and location of the defects. To enhance the physics-driven automatic detection reliability, the third technique proposes and incorporates a self-supervised learning structure with data-driven Convolutional Neural Networks (CNN). Different from supervised learning approaches which need labeled training images, the road anomaly detection network is trained by road surface images that are automatically labeled based on the reconstructed 3D surface information. In order to collect clear road surface images on the public road, a road surface monitoring system is designed and integrated for the road surface image capturing and visualization. The proposed approach is evaluated in both simulated environment and through real-world experiments. The parametric study of the proposed approach shows the small error of the 3D road surface reconstruction influenced by different variables such as the image noise, camera orientation, and the vertical movement of the camera in a controlled simulation environment. The comparison with traditional SfM technique and the numerical results of the proposed reconstruction using real-world road surface images then indicate that the proposed approach effectively reconstructs high quality near-planar road surface while automatically detects road defects with high precision, accuracy, and recall rates without the degenerate issue. / Doctor of Philosophy / Road is one of the key infrastructures for ground transportation. A good road surface condition can benefit mainly on three aspects: 1. Avoiding the potential traffic accident caused by road surface defects, such as potholes. 2. Reducing the damage to the vehicle initiated by the bad road surface condition. 3. Improving the driving and riding comfort on a healthy road surface. With all the benefits mentioned above, it is important to examine and check the road surface quality frequently and efficiently to make sure that the road surface is in a healthy condition. In order to detect any road surface defects on public road in time, this dissertation proposes three techniques to tackle the road surface defects detection problem: First, a near-planar road surface three-dimensional (3D) reconstruction technique is proposed. Unlike traditional 3D reconstruction technique, the proposed technique solves the degenerate issue for road surface 3D reconstruction from two images. The degenerate issue appears when the object reconstructed has near-planar surfaces. Second, after getting the accuracy-enhanced 3D road surface reconstruction, this dissertation proposes an automatic defects detection technique using both the 3D reconstructed road surface and the road surface image information. Although physics-based detection using 3D reconstruction and 2D images are reliable and explainable, it needs more time to process these data. To speed up the road surface defects detection task, the third contribution is a technique that proposes a self-supervised learning structure with data-driven Convolutional Neural Networks (CNN). Different from traditional neural network-based detection techniques, the proposed combines the 3D road information with the CNN output to jointly determine the road surface defects region. All the proposed techniques are evaluated using both the simulation and real-world experiments. Results show the efficacy and efficiency of the proposed techniques in this dissertation.

abstract: Thousands of high-resolution images are generated each day. Segmenting, classifying, and analyzing the contents of these images are the key steps in image understanding. This thesis focuses on image segmentation and classification and its applications in synthetic, texture, natural, biomedical, and industrial images. A robust level-set-based multi-region and texture image segmentation approach is proposed in this thesis to tackle most of the challenges in the existing multi-region segmentation methods, including computational complexity and sensitivity to initialization. Medical image analysis helps in understanding biological processes and disease pathologies. In this thesis, two cell evolution analysis schemes are proposed for cell cluster extraction in order to analyze cell migration, cell proliferation, and cell dispersion in different cancer cell images. The proposed schemes accurately segment both the cell cluster area and the individual cells inside and outside the cell cluster area. The method is currently used by different cell biology labs to study the behavior of cancer cells, which helps in drug discovery. Defects can cause failure to motherboards, processors, and semiconductor units. An automatic defect detection and classification methodology is very desirable in many industrial applications. This helps in producing consistent results, facilitating the processing, speeding up the processing time, and reducing the cost. In this thesis, three defect detection and classification schemes are proposed to automatically detect and classify different defects related to semiconductor unit images. The first proposed defect detection scheme is used to detect and classify the solder balls in the processor sockets as either defective (Non-Wet) or non-defective. The method produces a 96% classification rate and saves 89% of the time used by the operator. The second proposed defect detection scheme is used for detecting and measuring voids inside solder balls of different boards and products. The third proposed defect detection scheme is used to detect different defects in the die area of semiconductor unit images such as cracks, scratches, foreign materials, fingerprints, and stains. The three proposed defect detection schemes give high accuracy and are inexpensive to implement compared to the existing high cost state-of-the-art machines. / Dissertation/Thesis / Ph.D. Electrical Engineering 2010

The goal of this thesis is to create overall, automatic and non-contact quality control of a pellet. The issue is divided into two separate parts. The first part deals with precise dimensional measuring of pellet - its length and head diameter so that it is precise and reasonably fast. Precise measuring is achieved with help of algorithms which achieve the sub-pixel precision by polynomial approximation of the edges extracted from the image gradients. The second part deals with the defects of a pellet. Detecting defects like longitudinal furrows or skirt cuts is achieved with convolutional neural networks. The measurement modules work with the resulting precision up to 0.025 mm in case of length measuring and up to 0.01 mm in case of head diameter measuring. In case of defect detections, neural network shows very high classification success rate. The contribution of this thesis is a presentation of innovative approaches in automatic quality control of pellets with use of neural networks and a demonstration of its usage in real manufacturing process.

This thesis deals with the design and subsequent implementation of a unit inspecting a printed logos on the pen surface. A line-scan camera is used to capture the object. Whole the unit including acquited data processing is controlled by Raspberry Pi 4 platform extended by perifery board. The control of the hardware parts is implemented in C++, the detection algorithms in Python using OpenCV and TensorFlow libraries. The unit has a graphical user interface for control of the inspection process. In the end of the thesis test of the unit reliability is shown.

In this master thesis is described how to design and implement classifier of defects detected during the final stage of production nonwovens. The beginning of the thesis is devoted to the analysis of options for image processing and classification. Followed by the part, where is described process of image segmentation and extraction of feature vector. Description of classifier implementation and table of achieved results of classification on real images of detected defects.

This thesis deals with diagnostics of photovoltaic panels especially with infrared diagnostics. There are described defects which we can examine using thermovision and also this thesis explains the cause of their formation. Practical part deals with the design of the program that automatically detects defects on infrared images.

<p>Validerat; 20140619 (global_studentproject_submitter)</p>