In this paper we develop a digital twin based on the new One Record linked data standard. This enables short-term workload prediction for the various partners in the air cargo supply chain without the need for multiple data exchange interfaces. To the best of our knowledge, it is the first research on the potential benefits of One Record. The concept of the digital twin allows for an overarching optimization of operations in the air cargo supply chain without the necessity of full transparency between all the partners.

Two phenomena form the basis for this thesis; bad lighting for children and our connection to nature. The former has somehow largely stayed unchanged through the years, the second one is rapidly changing for the worse. Lighting in spaces designed for children in Sweden often seem like an afterthought focusing on the quantitative aspects, ignoring the qualitative; following standards but often forgetting who the space is meant for. At the same time, cities are becoming denser, making nature something many people actively have to seek out to experience - children’s definition of nature is slowly changing.How can outdoor lighting for children become better? Using the Ringmuren preschool in Uppsala, Sweden, as a case study, this thesis proposes an alternative way of thinking when designing light for children and how it can encourage a connection to nature. The design proposal was made using interviews, site analysis, research and experiments inside a digital twin custom made for RIngmuren preschool. The direct result of this project is a digital twin and a lighting concept, but it also argues that the practicalities of analysing and designing lighting is one thing; getting the people in power to understand why good lighting is important is the first, and largest, hurdle. Producing good, affordable examples of good lighting design that can be applied to varying situations is a good place to start to at the least initiate a discussion.

[pt] Com a chegada da Industria 4.0, empresas aderiram a usar gêmeos digitais para melhorar seus processos de produção e as condições de trabalhos de seus empregados. Os gêmeos digitais são normalmente associados a modelos tridimensionais, permitindo a realização de planejamentos, extração de dados, simulação e treinamento a partir das condições reais. Infelizmente, gêmeos digitais incorretos ou desatualizados podem induzir a erros e a desencontro de informações o que retira todas as vantagens do processo de virtualização, arruinando quaisquer comparativos com a realidade. Em contrapartida, gêmeos digitais ricos em informação permitem que simulações e extrações de dados sejam mais fieis a realidade. Atualmente, as tecnologias capazes de enriquecer as informações de gêmeos digitais são escassos, pois é um procedimento que leva tempo devido a necessidade de análises de especialistas, custos, equipamentos e ferramentas específicas. Recursos como fotografias 360 graus, vídeos e modelos tridimensionais podem ser usados para realizar uma avaliação e atualização nos gêmeos digitais. Porém, diferenças temporais, condições do ambiente e erros humanos entre os recursos podem gerar confusão durante a transferência e conexão da informação. Este trabalho apresenta uma ferramenta que explora as vantagens de combinar fotografias 360 graus com modelos 3D para gerar gêmeos digitais as-built. Cada imagem pode ser ajustada a uma localização dentro do sistema de coordenadas do modelo, inclusive permitindo alterações nos eixos e no campo de visão. Durante a navegação, é possível navegar livremente pelo modelo e pelas posições de interesse criadas pelo usuário. Além da visualização, a ferramenta propõe uma interação mais eficaz para realizar anotações entre modelos e fotografias 360 graus com o propósito de verificar consistências ou agregar novas informações ao gêmeo digital. Estas interações são importantes para a inspeção e manutenção, como avaliação de peças, análise das condições atuais ou a criação de comparativos entre o planejado e o real. / [en] With the arrival of Industry 4.0, companies have adopted digital twins to improve their production processes and the working conditions of their employees. Digital twins are generally associated with three-dimensional models and allow planning, data extraction, simulation, and training based on current conditions. Unfortunately, incorrect or outdated digital twins can lead to errors and information mismatch, which takes away all the advantages of the virtualization and computerization process, ruining any comparisons with reality. In contrast, information-rich digital twins allow simulations and data extraction to be more faithful to reality. Currently, technologies capable of enriching the information of digital twins are scarce, as it is a procedure that takes time due to the need for expert analysis, costs, equipment, and specific tools. Resources such as 360 degrees photographs, videos, and 3D models can be used to perform an evaluation and update the digital twins. However, temporal differences, environmental conditions, and human errors between the images and the model can generate confusion during the transfer and connection of information. This work presents a tool that explores the advantages of combining 360 degrees photographs with 3D models to generate as-built digital twins. Each image can be adjusted to a location within the model s coordinate system, allowing changes to axes and field of view. During navigation, it is possible to navigate the model and the user-created positions of interest freely. In addition to visualization, the tool proposes a more effective interaction to annotate between models and 360 degrees photographs to verify consistency or add new information to the digital twin. These interactions are essential for inspection and maintenance, such as evaluating parts, analyzing current conditions, or creating comparisons between planned and actual.

BACKGROUND - The development of Industry 4.0 increases the opportunities to both automate and digitize processes in the manufacturing industry. The steel industry has been around for many years, which means firmly anchored operations and both manual- and automated processes. To make better decisions, identify bottlenecks, and test new functions without having to stop the production, a digital model of the process can be helpful. Furthermore, with the rapid development of technology, digital models can be further developed into digital twins. A digital twin should be able to handle the communication between the physical- and digital world automatically and analyze data to make decisions in the process. RESEARCH QUESTIONS What are the challenges of developing a digital model representing a production line within a global steel manufacturing company? What opportunities could a digital model of a production line entail, and how could Industry 4.0 technologies create opportunities to further develop the digital model into a digital twin? METHODS - In this project, both a literature- and case study have been carried out. During the literature study, techniques that can be used to develop the digital model further have been investigated. During the case study, a digital model of a Quench Line was developed to gather practical experience of what it can mean to create a digital model of a manufacturing process within a steel manufacturing company. The model has been developed in MATLAB/Simulink. RESULTS - The most significant challenges when developing digital flow simulation models identified in this project were data management/access, handling variations, verifying the model, andlack of knowledge linked to digital models in general. The opportunities identified and confirmed in this project were that the model could be used to carry out new logistics planning, bottleneck analyses, and test new machine implementations. To further develop the digital model into a digital twin, Industry 4.0 technologies will be crucial. The technologies that will be useful are the Internet of Things, Artificial Intelligence, Machine Learning, Cloud Computing, and Big Data.

Green light optimal speed advisory (GLOSA) systems require reliable estimates of signal switching times to improve vehicle energy/fuel efficiency. Deployment of successful infrastructure to vehicle communication requires Signal Phase and Timing (SPaT) messages to be populated with most likely estimates of switching times and confidence levels in these estimates. Obtaining these estimates is difficult for actuated signals where the length of each green indication changes to accommodate varying traffic conditions and pedestrian requests. This dissertation explores the different ways in which predictions can be made for the most likely switching times. Data are gathered from six intersections along the Gallows Road corridor in Northern Virginia. The application of long-short term memory neural networks for obtaining predictions is explored for one of the intersections. Different loss functions are tried for the purpose of prediction and a new loss function is devised. Mean absolute percentage error is found to be the best loss function in the short-term predictions. Mean squared error is the best for long-term predictions and the proposed loss function balances both well. The amount of historical data needed to make a single accurate prediction is assessed. The assessment concludes that the short-term prediction is accurate with only a 3 to 10 second time window in the past as long as the training dataset is large enough. Long term prediction, however, is better with a larger past time window. The robustness of LSTM models to different demand levels is then assessed utilizing the unique scenario created by the COVID-19 pandemic stay-at-home order. The study shows that the models are robust to the changing demands and while regularization does not really affect their robustness, L1 and L2 regularization can improve the overall prediction performance. An ensemble approach is used considering the use of transformers for SPaT prediction for the first time across the six intersections. Transformers are shown to outperform other models including LSTM. The ensemble provides a valuable metric to show the certainty level in each of the predictions through the level of consensus of the models. Finally, a hybrid approach integrating deep learning and controller logic is proposed by predicting actuations separately and using a digital twin to replicate SPaT information. The approach is proven to be the best approach with 58% less mean absolute error than other approaches. Overall, this dissertation provides a holistic methodology for predicting SPaT and the certainty level associated with it tailored to the existing technology and communication needs. / Doctor of Philosophy / Automated and connected vehicles waste a lot of fuel and energy to stop and go at traffic signals. The ideal case is for them to be able to know when the traffic signal turns green ahead of time and plan to reach the intersection by the time it is green, so they do not have to stop. Not having to stop can save up to 40 percent of the gas used at the intersection. This is a difficult task because the green time is not fixed. It has a minimum and maximum setting, and it keeps extending the green every time a new vehicle arrives. While this is good for adapting to traffic, it makes it difficult to know exactly when the traffic signal turns green to reach the intersection at that time. In this dissertation, different models to know ahead of time when the traffic signal will change are used. A model is chosen known as long-short term memory neural network (LSTM), which is a way to recognize how the traffic signal is expected to behave in the future from its past behavior. The point is to reduce the errors in the predictions. The first thing is to look at the loss function, which is how the model deals with error. It is found that the best thing is to take the average of the absolute value of the error as a percentage of the prediction if the prediction is that traffic signal will change soon. If it is a longer time until the traffic signal changes, the best way is to take the average of the square of the error. Finally, another function is introduced to balance between both. The second thing explored is how far back in time data was needed to be given to the model to predict accurately. For predictions of less than 20 seconds in the future, only 3 to 10 seconds in the past are needed. For predictions further in the future, looking further back can be useful. The third thing explored was how these models would do after rare events like COVID-19 pandemic. It was found that even though much fewer cars were passing through the intersections, the models still had low errors. Techniques were used to reduce the model reliance on specific data known as regularization techniques. This did not help the models to do better after COVID, but two techniques known as L1 and L2 regularization improved overall performance. The study was then expanded to include 6 intersections and used three additional models in addition to LSTM. One of these models, known as transformers, has never been used before for this problem and was shown to make better predictions than other models. The consensus between the models, which is how many of the models agree on the prediction, was used as a measure for certainty in the prediction. It was proven to be a good indicator. An approach is then introduced that combines the knowledge of the traffic signal controller logic with the powerful predictions of machine learning models. This is done by making a computer program that replicates the logic of the traffic signal controller known as a digital twin. Machine learning models are then used to predict vehicle arrivals. The program is then run using the predicted arrivals to provide a replication of the signal timing. This approach is found to be the best approach with 58 percent less error than the other approaches. Overall, this dissertation provides an end-to-end solution that uses real data generated from intersections to predict the time to green and estimate the certainty in prediction that can help automated and connected vehicles be more fuel efficient.

Cooperative driving in a connected vehicle (CV) environment has received increasing attention over the years due to its ability to enhance driving safety and efficiency. Despite many efforts that have been made in this field, the role of human drivers and pedestrians is frequently omitted. It is important to consider them to develop cooperative driving algorithms that are intelligent and robust to incorporate any uncertainty brought by humans. In this dissertation, a framework of a multi-driver in-the-loop driving simulator and a pedestrian in-the-loop digital twin system is introduced. Three important topics in cooperative driving were investigated using the developed framework: the effects of human-machine interface (HMI) design for cooperative driving, vehicle-pedestrian interaction under occlusion scenarios, and multi-vehicle decision-making at weaving segments. In the first topic, three HMIs were designed for collaborative speed adaptation following the skills, rules, and knowledge (SRK) taxonomy. The HMI designs were tested using a multi-driver simulator, and the results showed that the graphic-based HMI improved cooperative driving performance and was preferred by the participants. In the second task, a Digital Twin framework for CV and pedestrian in-the-loop simulation was proposed based on Carla-Sumo Co-simulation and Cave automatic virtual environment (CAVE). The effects of Vehicle-Pedestrian (V2P) warning systems under occlusion scenarios were investigated for different connectivity and vehicle automation levels. In the third task, an edge-enhanced graph attention deep reinforcement learning algorithm was developed to aid autonomous vehicles in diverging at weaving segments. The results showed that the proposed algorithms outperformed existing models and performed well in real-world driving scenarios. The dissertation provides insights into developing safe and efficient cooperative driving algorithms and applying advanced simulation technologies to human-in-the-loop cooperative driving testing.

The overall goal of this work is to create an open-source digital twin of the wire arc directed energy deposition process using robot operating system 2 for interpass temperature regulation of a maraging steel alloy. This framework takes a novel approach to regulating the interpass temperatures by using in-situational infrared camera data and a closed loop feedback control that is enabled by robot operating system 2. This is the first implementation of robot operating system 2 for wire arc directed energy deposition and this framework outlines a sensor and machine agnostic approach for creating a digital twin of this additive manufacturing process. In-situ control of the welding process is conducted on a maraging steel alloy demonstrating interpass temperature regulation leads to improved as-built surface roughness and more consistent as-built hardness. An evaluation of three distinct weld modes: Pulsed MIG, CMT MIX, and CMT Universal and two primary process parameters: travel speed and wire feed speed was conducted to identify suitable process windows for welding the maraging alloy. Single track welds for each parameter and weld mode combination were produced and evaluated against current weld bead metrics in the literature. Non destructive profilometry and destructive characterization were performed on the single track welds to evaluate geometric features like wetting angle, dilution percentage, and cross sectional area. In addition, the role of material feed rate on heat input and the cross sectional area was examined in relation to the as-built hardness. The robot operating system 2 digital twin provides a visualization environment to monitor and record real time data from a variety of sensors including robot position, weld data, and thermal camera images. Point cloud data is visualized, in real time, to provide insight to the captured weld meta data. Capturing in-situ data from the wire arc directed energy deposition process is critical to establishing an improved understanding of the process for parameter optimization, tool path planning, with both required to build repeatable, quality components. This work presents an open-source method to capture multi-modal data into a shared environment for improved data capture, data sharing, data synchronization, and data visualization. This digital twin provides users enhanced process control capabilities and greater flexibility by utilizing the robot operating system 2 as a middleware to provide interoperability between sensors and machines.

This dissertation aims to provide critical methodological advancements for sensor fusion and physics-informed machine learning in metal additive manufacturing (MAM) to assist practitioners in detecting quality control structural anomalies. In MAM, there is an urgent need to improve knowledge of the internal layer fusion process and geometric variation occurring during the directed energy deposition processes. A core challenge lies in the cyclic heating process, which results in various structural abnormalities and deficiencies, reducing the reproducibility of manufactured components. Structural abnormalities include microstructural heterogeneities, porosity, deformation and distortion, and residual stresses. Data-driven monitoring in MAM is needed to capture process variability, but challenges arise due to the inability to capture the thermal history distribution process and structural changes below the surface due to limitations in in-situ data collection capabilities, physical domain knowledge integration, and multi-data and multi-physical data fusion. The research gaps in developing system-based generalizable artificial intelligence (AI) and machine learning (ML) to detect abnormalities are threefold. (1) Limited fusion of various types of sensor data without handcrafted selection of features. (2) There is a lack of physical domain knowledge integration for various systems, geometries, and materials. (3) It is essential to develop sensor and system integration platforms to enable a holistic view to make quality control predictions in the additive manufacturing process. In this dissertation, three studies utilize various data types and ML methodologies for predicting in-process anomalies. First, a complementary sensor fusion methodology joins thermal and ultrasonic image data capturing layer fusion and structural knowledge for layer-wise porosity segmentation. Secondly, a physics-informed data-driven methodology for joining thermal infrared image data with Goldak heat flux improves thermal history simulation and deformation detection. Lastly, a physics-informed machine learning methodology constrained by thermal physical functions utilizes in-process multi-modal monitoring data from a digital twin environment to predict distortion in the weld bead. This dissertation provides current practitioners with data-driven and physics-based interpolation methods, multi-modal sensor fusion, and anomaly detection insights trained and validated with three case studies.

Historically, automotive body panels have been made of steel and joined by a process called resistance spot welding (RSW). However, in efforts to reduce vehicle weight to improve the energy efficiency of the vehicle, automotive manufactures have begun substituting aluminum in place of steel. While aluminum can be joined with RSW, a myriad of challenges arise from doing so. These challenges result in less consistent weld quality and accelerated electrode wear. Refill friction stir spot welding (RFSSW) is an emerging joining technology that could replace RSW as it is believed to be capable of creating superior joints in thin sheet aluminum. This research's goal is to compare RFSSW and RSW for joining aluminum automotive body panels. To accomplish this goal two studies were conducted and reported on in this thesis. The first focused on evaluating the manufacturing performance of RFSSW and RSW while the second focused on comparing the microstructure and mechanical performance of RFSSW and RSW joints. To improve the relevance of the study, a Toyota automated welding cell was used as a case study. The cell utilizes AA6061-T4 in 8 unique stack-ups to create door frames. This cell served as the base for the manufacturing performance comparison while also providing the three stack-ups used to compare microstructure and mechanical performance. The study compares manufacturing performance utilized a digital twin to compare how each technology would interact within the manufacturing cell. Parameters such as joining time and maintenance time were considered while overall output of the manufacturing cell was recorded. The results showed that RFSSW and RSW could produce the same number of parts in the given manufacturing cell. However, as modifications were made to the cell to increase output RFSSW proved to be capable of greater output due to its longer tool life. Concluding that RFSSW is a viable option from a manufacturing performance view. The second study conducted a comparison of the microstructure and mechanical properties of RFSSW and RSW. This study found that each technology created unique surface topographies and grain structures. Mechanical performance testing found that depending on the stack-up RFSSW joints were between 16% and 73% stronger than RSW joints in tensile loading conditions. RFSSW also showed improved fatigue life, in one test surviving 2600% more cycles. Concluding that RFSSW joints have superior mechanical performance over RSW joints.

The Advanced Manufacturing section at ÅF Pöyry AB is exploring the possibilities of virtual commissioning and digital twins. As part of this exploration, this thesis sets out to demonstrate a method of developing scalable, reusable and realistic digital mechatronic models – the heart of a digital twin – for the virtual environment in RobotStudio. Research has shown that one of the major obstacles to implementing virtual commissioning as a standard in industry today is the lack of scalable and reusable digital twins. This is also the experience of ÅF Pöyry AB. After reviewing existing and proposed methods for developing digital twins, this thesis explains the necessary steps for developing a SmartComponent in RobotStudio, using the programming language C#. The results show that the SmartComponent developed is scalable and thus reusable. It works with grippers with any number of fingers and allows gripping by applying pressure to the target object from both the outside and the inside. It is also realistic in the sense that the interaction between the grippers and the objects to be picked in the virtual environment behaves and looks like it does in reality. The implementation of the SmartComponent developed is much faster and less complex than the method used today at ÅF Pöyry AB. The downsides of the developed method are the added competence required of the automation engineer and the risk that the digital twin may not be future-proof. / Avdelningen Advanced Manufacturing på ÅF Pöyry AB utforskar möjligheter med ”Virtual Commissioning” och ”Digital Twins”. Som ett led i detta projekt har syftet med detta examensarbete varit att visa ett sätt att utveckla en skalbar, återanvändbar och realistisk digital mekatronisk modell för den virtuella miljön i RobotStudio. Tidigare forskning har visat, i linje med ÅF Pöyry AB:s satsning, att ett av de stora hinder för att Virtual Commissioning ska kunna implementeras som standard i industrin idag är bristen av skalbara och återanvändbara digitala tvillingar. Efter en genomgång av den befintliga och föreslagna metoden för att utveckla digitala tvillingar presenteras de nödvändiga stegen för att utveckla en SmartComponent för RobotStudio, med programmeringsspråket C#. Resultaten av utvecklingen och testen har visat att den utvecklade SmartComponent är skalbar och återanvändbar: den fungerar med gripare oavsett antal fingrar och den tillåter gripning både genom att applicera tryck på plockobjektet från utsidan och insidan. Den är också realistiskt på så vis att interaktionen mellan griparen och objekten som ska plockas i den virtuella miljön beter sig och ser ut som i verkligheten. Implementeringen av den utvecklade SmartComponent är också mycket effektivare och mindre komplex jämfört med den metod som används idag på ÅF Pöyry AB. Nackdelarna med den föreslagna metoden är de extra kompetenskraven för automationsingenjörer och risken att den digitala tvillingen inte är framtidssäker.