For the purpose of an future machine vision system development in Tyco Electronics Czech s.r.o. I have developed Cognex Designer template. Template will serve as a flexible basis for further development of camera applications on the Cognex VC5 industrial computer. The functionality of the program template has been successfully verified by modifying it to a particular application of the laboratory manual station used to measure the parameters of the manufactured connectors. A camera with lens and lightning was chosen and installed on the station. DIO communication was put into operation between VC5 and PLC system. The application has been calibrated and verified as a measurement system using MSA Type I and Capability study standard methods.

Tato práce se zabývá návrhem a implementací dvou konkrétních softwarových modulů, které jsou částí distribuovaného řídícího systému CoSMic. Tento systém je určen pro řízení speciálního zařízení pro charakterizaci papírových vláken. Prvním vyvinutým modulem je HapticFiber, ten má poskytovat rozhraní mezi řídícím systémem a speciálním vstupním zařízením - haptic device. Druhým modulem je ViCo, jehož účelem je poskytnout softwarovou obálku pro uživatelem definovaný algoritmus zpracovaní obrazu. Tento modul musí být připraven splnit určitá časová omezení, proto je nutné, aby běžel v rámci operačním systému reálného času.

This thesis describes the design and workflow of creating an image processing application in Android system, and what are the possibilities in choosing development environment and how to implement them. Then I am writing about my solutions of creating applications, graphical user interface and an interface for Android. I am describing my approach in the design and functionality of the application, communication with the camera, storing and retrieving data. Further I explain which algorithms were implemented for image processing and image evaluation. Product of this thesis is a functioning application that allows to its user to capture images and video stream. The algorithm evaluates the entering data and shows the location of the number plate. The application also allows recognizing texts and numbers from images. There are other various practical features and options implemented within the application.

Dot peen markings are used by Scania Ferruform to maintain a traceability of their products throughout the manufacturing. Quality inspection of the markings are performed to ensure that they are added correctly and readable. This is, however, done manually by workers, which they are looking to change. Machine vision, in combination with machine learning, could prove helpful in automating this process, which is where this thesis comes in. Images of two types of dot peen markings were gathered using different experimental setups and equipment. Amazon Rekognition and MVTec Halcon were both used to predict the characters of the images, in order to determine if the two systems could be used to demonstrate that the quality inspection can be automated. To improve the result, the images were also processed with varied techniques. The pretrained version of Amazon Rekognition and MVTec Halcon, with unprocessed image, performed the best. They both predicted all the characters correctly, and showed a high confidence in their predictions, with an average confidence of 96.41% and 99.87% respectively. When processing the images before predicting the confidence of the systems decreased and predictions were also made incorrectly. Custom training a model also showed a poor result, with the best combination of average precision and overall recall being at 0.733 and 0.561 respectively.

Volvo Construction Equipment (CE) are facing the challenge of vibrations in their wheel loaders that generate disruptive noise and impact the driver's experience. These vibrations have been linked to the contact surface between the crown wheel and pinion gear in the vehicles drive-axles. In response, this thesis was created to develop an Artificial Intelligence (AI) system, which can identify outliers in a dataset containing images of the contact surfaces between the crown wheel and pinion gear. However, the dataset exhibits variations in image sharpness, exposure and centering of the crown wheel, which hinders its suitability for machine vision tasks. The varying quality of the images poses the challenge of accurately extracting relevant features required to analyze the images through machine learning algorithms. This research aims to address these challenges by investigating two research questions. (1) what method can be employed to extract the Region of Interest (ROI) in images of crown wheels? And (2) which method is suitable for detection of outliers within the ROI? To find answers to these questions, a literature study was conducted leading up to the implementation of two architectures: You Only Look Once (YOLO) v5 Oriented Bounding Boxes (OBB) and a Hybrid Autoencoder (BAE). Visual evaluation of the results showed promising outcomes particularly for the extraction of ROIs, where the relevant areas were accurately identified despite the large variations in image quality. The BAE successfully identified outliers that deviated from the majority, however, the results of the model were influenced by the differences in image quality, rather than the geometrical shape of the contact patterns. These findings suggest that using the same feature extraction method on a higher-quality dataset or employing a more robust segmentation method, could increase the likelihood of identifying the contact patterns responsible for the vibrations.

This thesis aims to create a system using colour markings for Volvo’s autonomous wheel loaders which determines their restricted area and operation using sensors available on the machine. The wheel loader shall be able to interpret and distinguish different colours of spray paint, and depending on the colour, act accordingly. Six different colours are evaluated across two different colour types to find the most suitable ones for the system. Multiple tests are presented throughout the thesis to find the approach with the most optimal performance that meets the system's requirements. The system is evaluated in various weather conditions to determine how the weather affects the performance of the system. The thesis also compares two different line-following approaches, where one is based on edge detection using Canny Edge and Hough transform, and the other uses histogram analysis and sliding window search, to distinguish and track the colour markings. While the wheel loader is in operation, it collects GPS coordinates to create a map of the path taken by the wheel loader and the location of various tasks. The evaluation shows that red, green and blue in fluorescent colour type are the most suitable colours for such a system. The line-following algorithm that utilises perspective warp, histogram and a sliding window search was the most prominent for accurate line detection and tracking. Furthermore, the evaluation showed that the performance of the system was affected depending on the weather condition.

No description available.

The volume of data acquired in production systems continues to expand. Emerging imaging technologies, such as machine vision systems (MVSs) and 3D surface scanners, diversify the types of data being collected, further pushing data collection beyond discrete dimensional data. These large and diverse datasets increase the challenge of extracting useful information. Unfortunately, industry still relies heavily on traditional quality methods that are limited to fault detection, which fails to consider important diagnostic information needed for process recovery. Modern measurement technologies should spur the transformation of statistical process control (SPC) to provide practitioners with additional diagnostic information. This dissertation focuses on how MVSs and 3D laser scanners can be further utilized to meet that goal. More specifically, this work: 1) reviews image-based control charts while highlighting their advantages and disadvantages; 2) integrates spatiotemporal methods with digital image processing to detect process faults and estimate their location, size, and time of occurrence; and 3) shows how point cloud data (3D laser scans) can be used to detect and locate unknown faults in complex geometries. Overall, the research goal is to create new quality control tools that utilize high density data available in manufacturing environments to generate knowledge that supports decision-making beyond just indicating the existence of a process issue. This allows industrial practitioners to have a rapid process recovery once a process issue has been detected, and consequently reduce the associated downtime. / Ph. D.

With the advancement of sensor technology and data processing capacities, various types of high volume data are available for process monitoring and prognostics in manufacturing systems. In a broaching process, a multi-toothed broaching tool removes material from the workpiece by sequential engagement and disengagement of multiple cutting edges. The quality of the final part, including the geometric integrity and surface finish, is highly dependent upon the broaching tool condition. Though there has been a considerable amount of research on tool condition monitoring and prognostics for various machining processes, the broaching process is unique in the following aspects: 1) a broaching process involves multiple cutting edges, which jointly contribute to the final part quality; 2) the resharpening and any other process adjustments to the tool can only be performed with the whole broaching tool or at least a whole segment of the tool replaced. The overarching goal of this research is to explore how engineering knowledge can be used to improve process monitoring and prognostics for a complex manufacturing process like broaching. This dissertation addresses the needs for developing new monitoring and prognostics approaches based on various types of data. Specifically, the research effort focuses on 1) the use of in-situ force profile data for real-time process monitoring and fault diagnosis, 2) degradation characterization for broaching processes on an individual component level based on image processing; and 3) system-level degradation modeling and remaining useful life prediction for broaching processes based on multiple images. / Ph. D. / Big data have been providing both opportunities and challenges for product quality assurance and improvement in modern manufacturing systems. In aerospace industry, broaching processes are one of the most important manufacturing processes as they are used to produce the turbine discs in the jet engine. Nonconforming turbine disc quality, either in terms of compromised surface finish or geometry accuracy, will lead to malfunction or even catastrophic failures in the aircraft engines. One of the major sources that lead to nonconforming product quality is excessive tool wear accumulation and other abrupt malfunctions of the broaching tools. In broaching processes, multiple cutting edges are sequentially pushed or pulled through the workpiece, and each cutting edge is responsible to shape the workpiece into a specific intermediate shaped contour. Therefore, a broaching process can be regarded as a multistage manufacturing process with variation propagating through the multiple cutting edges. The overarching goal of this dissertation is to explore how process knowledge can be used to improve process monitoring and prognostics for a complex manufacturing process like broaching. This dissertation focuses on the quality assurance and improvement for broaching processes which includes: 1) timely abrupt process fault detection; 2) tool performance degradation quantification; and 3) remaining tool life prediction, which contributes to both methodological development and practical applications in advanced sensing analytics in manufacturing systems.

This paper concerns itself with object detection as a possible solution to Valmet’s quest for a visual-feedback system that can help operators and other personnel to more easily interact with their machines and equipment. New advancements in deep learning, specifically CNN models, have been exploring neural networks with detection-capabilities. Object detection has historically been mostly inaccessible to the industry due the complex solutions involving various tricky image processing algorithms. In that regard, deep learning offers a more easily accessible way to create scalable object detection solutions. This study has therefore chosen to review recent literature detailing detection models with a selective focus on factors making them realizable on ARM hardware and in turn mobile devices like phones. An attempt was made to single out the most lightweight and hardware efficient model and implement it as a prototype in order to help Valmet in their decision process around future object detection products. The survey led to the choice of a SSD-MobileNetsV2 detection architecture due to promising characteristics making it suitable for performance-constrained smartphones. This CNN model was implemented on Valmet’s phone of choice, Samsung Galaxy S8, and it successfully achieved object detection functionality. Evaluation shows a mean average precision of 60 % in detecting objects and a 4.7 FPS performance on the chosen phone model. TensorFlow was used for developing, training and evaluating the model. The report concludes with recommending Valmet to pursue solutions built on-top of these kinds of models and further wishes to express an optimistic outlook on this type of technology for the future. Realizing performance of this magnitude on a mid-tier phone using deep learning (which historically is very computationally intensive) sets us up for great strides with this type of technology in the future; and along with better smartphones, great benefits are expected to both industry and consumers. / Den här rapporten behandlar objekt detektering som en möjlig lösning på Valmets efterfrågan av ett visuellt återkopplingssystem som kan hjälpa operatörer och annan personal att lättare interagera med maskiner och utrustning. Nya framsteg inom djupinlärning har dem senaste åren möjliggjort framtagande av neurala nätverksarkitekturer med detekteringsförmågor. Då industrisektorn svårare tar till sig högst specialiserade algoritmer och komplexa bildbehandlingsmetoder (som tidigare varit fallet med objekt detektering) så ger djupinlärningsmetoder istället upphov till att skapa självlärande system som är återanpassningsbara och närmast intuitiva i dem fall där sådan teknologi åberopas. Den här studien har därför valt att studera ett par sådana teknologier för att hitta möjliga implementeringar som kan realiseras på något så enkelt som en mobiltelefon. Urvalet har därför bestått i att hitta detekteringsmodeller som är hårdvarumässigt resurssnåla och implementera ett sådant system för att agera prototyp och underlag till Valmets vidare diskussioner kring objekt-detekteringsslösningar. Studien valde att implementera en SSD-MobileNetsV2 modellarkitektur då den uppvisade lovande egenskaper kring hårdvarukraven. Modellen implementerades och utvärderades på Valmets mest förekommande telefon Samsung Galaxy S8 och resultatet visade på en god förmåga för modellen att detektera objekt. Den valda modellen gav 60 % precision på utvärderingsbilderna och lyckades nå 4.7 FPS på den implementerade telefonen. TensorFlow användes för programmering och som stödjande mjukvaruverktyg för träning, utvärdering samt vidare implementering. Studien påpekar optimistiska förväntningar av denna typ av teknologi; kombinerat med bättre smarttelefoner i framtiden kan det leda till revolutionerande lösningar för både industri och konsumenter.