To realize key business capabilities and secure long-term growth, Volvo Construction Equipment (Volvo CE) set out to define a vision for digital transformation. The latest trends in AI-powered smart electronics open up endless opportunities to help Volvo CE's operators use Wheel Loaders – Construction machines to increase productivity. To ensure operators are working in a way that delivers optimum fuel efficiency and productivity to achieve optimum results on-site, the company aspires to create visual tools to keep track of operator behavior in the operator environment. Monitor operator behavior with key indicators then visualized to inform how this affects important results for the customers and for Volvo CE. The audience is operators themselves, and internal staff like UX engineers and Product owners. Data-driven concept design (DDCD) is a decision-making approach that heavily relies on collected data and highlights the need to proactively plan and design. It is a popular approach to capturing tacit customer needs and makes a great contribution to data visualization design. Also, an emerging concept like the digital twin provides inspired ideas in data visualization conceptual design. However, little research is on the DDCD for data visualization. Thus, this work aims to explore appropriate data visualization techniques under the DDCD framework. The result is to help Volvo CE, primarily via data visualization, keep track of operator behaviors, and how these affect wheel loader productivity and energy efficiency data on different levels and in a wider context. To carry out, A series of DDCD cases for the improvement of wheel loader operator behaviors are researched and designed, to present data in a clear and concise visual way for both internal audience and operator training. As the result, a prototype containing a series of visualization techniques is proposed for two target groups and corresponding application scenarios including coaching and aid decision-making. Created a series of dashboards with expected functionalities based on understanding the current machine. The prototype for the internal audience has functionality: site and time selection, weekly overview window, phase selection, cycle thread trace, insight window, data presentation, and toolbox. The prototype for operator training has functionality: site and time selection, opponent selection, phase selection, cycle thread trace, external data window, individual comparison section, and insights block. / För att förverkliga viktiga affärsmöjligheter och säkra långsiktig tillväxt har Volvo Construction Equipment (Volvo CE) tagit fram en vision för digital omvandling. De senaste trenderna inom AIdriven smart elektronik öppnar oändliga möjligheter att hjälpa Volvo CE:s operatörer att använda hjullastare - anläggningsmaskiner för att öka produktiviteten. För att säkerställa att förarna arbetar på ett sätt som ger optimal bränsleeffektivitet och produktivitet för att uppnå optimala resultat på plats strävar företaget efter att skapa visuella verktyg för att hålla koll på förarens beteende i förarmiljön. Övervaka operatörens beteende med nyckelindikatorer som sedan visualiseras för att informera om hur detta påverkar viktiga resultat för kunderna och för Volvo CE. Målgruppen är operatörerna själva och intern personal som UX-ingenjörer och produktägare. Datadriven konceptdesign (DDCD) är en beslutsmetod som i hög grad bygger på insamlade data och belyser behovet av proaktiv planering och design. Det är ett populärt tillvägagångssätt för att fånga upp tysta kundbehov och ger ett stort bidrag till design av datavisualisering. Dessutom ger ett framväxande koncept som den digitala tvillingen inspirerande idéer för konceptuell utformning av datavisualisering. Det finns dock lite forskning om DDCD för datavisualisering. Det här arbetet syftar därför till att utforska lämpliga datavisualiseringstekniker inom ramen för DDCD. Resultatet är att hjälpa Volvo CE, främst via datavisualisering, att hålla koll på förarnas beteenden och hur dessa påverkar data om hjullastares produktivitet och energieffektivitet på olika nivåer och i ett större sammanhang. För att genomföra, En serie DDCD-fall för förbättring av beteenden hos hjullastarförare undersöks och utformas, för att presentera data på ett tydligt och kortfattat visuellt sätt för både intern publik och förarutbildning. Som resultat föreslås en prototyp som innehåller en serie visualiseringstekniker för två målgrupper och motsvarande tillämpningsscenarier, inklusive coaching och stöd för beslutsfattande. Skapade en serie instrumentpaneler med förväntade funktioner baserat på förståelse av den nuvarande maskinen. Prototypen för den interna målgruppen har följande funktioner: val av plats och tid, fönster för veckoöversikt, val av fas, spårning av cykeltråd, insiktsfönster, datapresentation och verktygslåda. Prototypen för operatörsutbildning har följande funktioner: val av plats och tid, val av motståndare, val av fas, spårning av cykeltråd, fönster för externa data, avsnitt för individuella jämförelser och block för insikter.

Indoor environment modeling has become a relevant topic in several applications fields including Augmented, Virtual and Mixed Reality. Furthermore, with the Digital Transformation, many industries have moved toward this technology trying to generate detailed models of an environment allowing the viewers to navigate through it or mapping surfaces to insert virtual elements in a real scene. Therefore, this Thesis project has been conducted with the purpose to review well- established deterministic methods for 3D scene reconstruction and researching the state- of- the- art, such as machine learning- based approaches, and a possible implementation on mobile devices. Initially, we focused on the well- established methods such as Structure from Motion (SfM) that use photogrammetry to estimate camera poses and depth using only RGB images. Lastly, the research has been centered on the most innovative methods that make use of machine learning to predict depth maps and camera poses from a video stream. Most of the methods reviewed are completely unsupervised and are based on a combination of two subnetwork, the disparity network (DispNet) for the depth estimation and pose network (PoseNet) for camera pose estimation. Despite the fact that the results in outdoor application show high quality depth map and and reliable odometry, there are still some limitations for the deployment of this technology in indoor environment. Overall, the results are promising. / Modellering av inomhusmiljö har blivit ett relevant ämne inom flera applikationsområden, inklusive Augmented, Virtual och Mixed Reality. Dessutom, med den digitala transformationen, har många branscher gått mot denna teknik som försöker generera detaljerade modeller av en miljö som gör det möjligt för tittarna att navigera genom den eller kartlägga ytor för att infoga virtuella element i en riktig scen. Därför har detta avhandlingsprojekt genomförts med syftet att granska väletablerade deterministiska metoder för 3Dscenrekonstruktion och undersöka det senaste inom teknik, såsom maskininlärningsbaserade metoder och en möjlig implementering på mobil. Inledningsvis fokuserade vi på de väletablerade metoderna som Structure From Motion (SfM) som använder fotogrammetri för att uppskatta kameraställningar och djup med endast RGBbilder. Slutligen har forskningen varit inriktad på de mest innovativa metoderna som använder maskininlärning för att förutsäga djupkartor och kameraposer från en videoström. De flesta av de granskade metoderna är helt utan tillsyn och baseras på en kombination av två undernätverk, skillnadsnätverket (DispNet) för djupuppskattning och posenätverk (PoseNet) för kameraposestimering. Trots att resultaten i utomhusanvändning visar djupkarta av hög kvalitet och tillförlitlig vägmätning, finns det fortfarande vissa begränsningar för användningen av denna teknik i inomhusmiljön, men ändå är resultaten lovande.

Purpose – The purpose of this study is to enhance the understanding of how to successfully collaborate on digital platforms in the manufacturing industry by developing a contingency framework. To fulfill this purpose, the following research questions were derived: RQ1: Which challenges arise when collaborating on digital platforms in the manufacturing industry? and RQ2: How can collaboration challenges on digital platforms in the manufacturing industry be managed? Method – The study was conducted as an explorative, inductive single case study of a digital platform. More specifically, the study examined the development process of a digital twin platform created by a large high-technological company and its collaborative actors. In total, 21 interviews were conducted at eight different companies. The respondents all had experience of digital twin platforms, where some were working with digital twins sporadically and others on a daily basis. The data were analyzed through a thematic analysis. Findings – The analysis reveals that actors on digital platforms can face five types of challenges that hinder a successful collaboration: disadvantages of dependency, uncertainty regarding data management, varying customer needs, insufficient work methods, and unsuitable payment models. The analysis also reveals four strategies that can be used to address the challenges: transparency strategy, incentive model strategy, servitization strategy, and control strategy. Moreover, these findings are summarized in a contingency framework that explains which types of challenges that can be addressed with which strategies based on the specific prerequisites of each collaboration. Theoretical and practical implications – The study extends the digital platform literature by providing empirical evidence for several collaboration challenges among the actors on a digital platform, which has previously bee not been studied. Additionally, the study provides evidence of how these challenges can be addressed. Our framework helps manufacturing companies to successfully adopt digital platforms by providing managers with the tools to handle the required collaboration. Limitations and further research – The study is limited by a single case study of a specific digital platform. Thus, to extend the findings, further research that examines other contexts are recommended. Moreover, the establishment of the studied platform is currently in an early phase which limits the study to hypothetical challenges and management methods. To validate the findings, further research that examines a fully developed and implemented platform is recommended.

For each generation of electronic equipment there is a trend towards higher power den-sities. Increased heat generation is an undesired consequence that the thermal design unit in a company must handle. The goal of thermal design engineer/unit is to utilizethe same volume to more efficiently transfer more heat from the equipment. This can bedone by exploring more complex and advanced heat sink geometries, optimizing the finshapes and so on. The new prototypes developed will be tested for their reliability and endurance in special chambers called climate chambers, that simulate desired environ-ments. The measurements by thermal design teams in these kind of climate chambers are mainly of outdoor products, whose cooling is based on natural convection. Forcedcooling using fans is optional for these outdoor products. The climate chambers in general provides temperature measurement as the outputto the analysis, though there are other important parameters that define the operationalfunctionality of an equipment. The ability to visualize the flow characteristics duringthe process of testing is a valuable aid in the design process. A virtual/CFD form of thephysical climate chamber (CC) would empower the design process, while alleviating theusage of the climate chambers for such analyses. CFD offers a wide range of capabilitiesthat lets the user change the boundary conditions with great ease compared to that ofthe experimental setup. The numerical model developed in this thesis project provides results, that help inunderstanding the physics involved in fluid flow inside the physical climate chamber.Turbulence quantification of the flow is the main aim of this thesis project, which wouldbe resourceful in future works. Experiments are conducted inside the climate chamber, in order to aid the construction of numerical model as well as serve as source of vali-dation for the numerical results. Laminar transient case simulations are preferred over use of any turbulence models, to limit any kind of predictions made by these turbulencemodels. Integral length scales and turbulence intensities are compared and reason fordiscrepancies are addressed. The results from the comparisons show that, the numerical model emulates physicsof actual flow inside the climate chamber. However, there are many factors that directlyaffect the results, making it difficult to precisely quantify the error, within the time periodof this thesis project.

In this thesis, a proof of concept of a digital twin of a type of reheating furnace, the walking beam furnace, is presented. It is created by using a machine learning concept called a neural network. The digital twin is trained using real data from a walking beam furnace located in Swerim AB, Luleå, and is taught to predict the temperature in the furnace using air, fuel and pressure as inputs. The machine learning technique used is an artifical neural network in the form of a multilayer perceptron model. The resulting model consists of 3 layers, input, hidden and output layer. The hyperparameters is decided by using grid search cross validation. The hyperparameters chosen to use in this thesis was amount of epochs, optimizer, learning rate, batch size, activation function, regularizer and amount of neurons in the hidden layer. The final settings for these can be found in table. The digital twin is then evaluated comparing predicted temperatures and actual temperatures from the measured data. The end result shows that the twin performs reasonably well. The predictions differs from measured temperature with a percentage around 0.5% to 1.5%.

Introduction The paradigm shift in manufacturing that Industry 4.0 brings forth with new advanced technologies and the rapid growth of sensing and controlling technologies enable further visualization and optimization that can contribute to achievingimproved decision-making in manufacturing. A significant new capability is the ability to construct a Digital Twinthat connects the physical and virtual space. However, there are still confusion and obscurity regarding what Digital Twinis and how it can becreated and then used to create value for the company. Therefor the purpose of the thesis is to examine how manufacturing companies can utilize the implementation of Digital Twinand assess Digital Twinin a shop-floor. ➢RQ1: How can DT be beneficial to increase business value in a manufacturing company? ➢RQ2: What changes need to be done in the shop-floor to implement Digital Twin? Methodology A literature review was conducted to provide previous researchand contextwithin the area of Digital Twin. A multiple-case studywas performed at three case companies to gain meaningful insight from a real-world perspective, semi-structured interviews, dialogs, and observations were conductedat the case companies. The analysis was then performed by examining similarities, and dissimilarities between theoretical and empirical data, as well as opportunities in theoretical findings that correspond with challenges in empirical findings. Frame of Reference The literature review increased the authors’ understanding of the research topic and gave context to the concept of Digital Twin. The review is mainly focused on the Digital Twintechnologyand how it is constructed, as well as the applicationsareas. Empirical Findings The empirical findings provide an overview of boththe current and future state of the case companies in relation to organizational, operational, and technological factors. Additionally, it provides a deeper understanding of how shop-floor management is designed at one of the case companies. Analysis The combination of the Frame of Reference and Empirical Findings contributewith important insight on the potential benefits that can be created through the utilizationof Digital Twin, as well as what is requiredin the shop-floor to enable implementation ofDigital Twin. Conclusions The value that can be created utilizing Digital Twinis outlinedand a clearer definition is proposed to avoid misunderstandings and confusion. Requirements that need to be achieved for a successful implementation arecovered as well. A future recommendation is measuring resources and effort in relation to the created value of a Digital Twin.

No description available.

The use of virtual commissioning has increased in the last years, but there are still challenges before the software code validation method is widespread in use. One of the additions to virtual commissioning is basing it on a digital twin to allow for improved accuracy. The aim of this thesis is to review existing standards and approaches to developing virtual commissioning, as well as to explore the definitions. The chosen approach to achieve the aim, is to perform a literature review of existing research papers and interviews with knowledgeable people in the industry. First, the definitions and classifications are reviewed, then the approaches for development of virtual commissioning and digital twins are explored in the literature. In three interviews with people of varying backgrounds and competences, the views of the virtual technologies are assessed to provide insight in the industry. The findings of the literature review and interviews are among others, the apparent need for standardisation in the field and that a sought-after standard in the form of ISO 23247-1 is under way. Furthermore, the digital twin is a concept with a promising future in combination with other technologies of Industry 4.0. In conclusion, this thesis provides a deep review of the challenges and possibilities of virtual commissioning and the digital twin and could be used as starting point for further research in standardisations and improvements sprung from the new standard.

No description available.

The municipalities' vision of using City Information Modeling (CIM) and Digital Twins (DT) inurban planning, requires prerequisites in place. A prerequisite is BIM, which together with GIS can create CIM.BIM implementation for a municipality involves major challenges and one such challenge is the lack of BIMmodels for existing buildings and infrastructure. However, this study is limited to planned development inconnection with land allocation. BIM implementation for the land allocation process within a medium-sizedSwedish municipality involves many involved actors and thus the need for a mobilization of the involved actorsfrom an ANT-inspired perspective. The purpose of this study is therefore to analyze how an actor network canbe mobilized to implement BIM in the land allocation process. A case study method has been chosen in thisthesis, considering that a well-defined case is identified, and the approach enables a variety of data collectionmethods that have been inspired by the autoethnographic approach because the researcher belongs to the focalactor in the process.