With constantly changing regulations on emissions, heavy commercial vehicles manufacturers have to adapt for their products to preserve their quality while meeting these new requirements. Over the past decades, noise emissions have become a great concern and new stricter laws demand companies to decrease their vehicle pass-by noise target values. To address the requirements from different disciplines, Scania follows a simulation driven design process to develop new concept models EATS. The collaboration among engineers from different fields is thereby necessary in order to obtain higher performance silencers. However, the preprocessing step in terms of acoustic simulations is time-consuming, which can slow the concept development process. In this thesis, a new method was introduced to automate the pre-processing of silencer acoustic models and allow for design optimisation based on acoustic performance results. A common Scania product study case was provided to several theses within the NXD organisation. The collaboration among the master thesis workers aimed to demonstrate the benefits of KBE and MDO and how they can be integrated within Scania’s current concept development and product introduction processes. The performed work was divided in the following steps: data collection, method development and concluding work. The first step consisted in gathering sufficient knowledge by conducting a thorough literature review and interviews. Then, an initial method was formulated and tested on a simplified silencer model. Once approved and verified, the method was applied to the study case EATS. The study case showed that a complex product can have its acoustic pre-processing step automated by ensuring a good connectivity among the required software and a correct denomination of the geometrical objects involved in the simulations. The method investigated how morphological optimisations can be performed at both global and local levels to enhance the transmission loss of a silencer. Besides optimising the acoustic performance of the models, the method allowed the identification of correlations and inter-dependencies among their design variables and ouput parameters. / Med ständiga förändringar i lagkrav som berör utsläpp måste tillverkare av tunga fordon anpassa sina produkter för att upprätthålla kvalitén samtidigt som de möter de nya kraven. De senaste årtiondena har ljudnivåerna från fordon blivit ett orosmoment, det stiftats striktare lagar som berör den ljudnivå som tunga fordon får emittera under ett förbifartsprov. För att adressera kraven från de olika disciplinerna följer Scania en simuleringsdriven utvecklingsprocess vid utveckling av nya efterbehandlingssystem. Samarbetet mellan ingenjörer från olika fält är därför nödvändigt för att utveckla högre prestanda efterbehandlingsystem. Uppställningen utav de akustiska simuleringarna är tidskrävande, vilket kan leda till en långsam utvecklingsprocess. I detta examensarbete föreslås en ny metod för att introducera en automatiserad uppställning av akustiska simuleringar på efterbehandlingssystem som tillåter optimering av de akustiska egenskaperna. Ett gemensamt studiefall gavs av Scania till flera examensarbeten skrivna vid NXD organisationen. Samarbetet mellan de olika examensarbetena syftade på att demonstrera fördelarna med KBE och MDO och hur de kan bli integrerade i Scanias nuvarande konceptutvecklings- och produktintroduktionsprocess. Examensarbetet är uppdelat i följande steg; datainsamling, metodutveckling och avslutandearbete. Det första steget innefattade insamling av kunskap genom att genomföra en grundlig litteraturstudie och flera intervjuer. Det nästkommande steget innefattade formulering av en initial metod vilken testades på ett simplifierat efterbehandlingssystem. När detta hade verifierats och godkänts applicerades metoden på efterbehandlingssystem i fallstudien. Fallstudien visade att även för en komplex produkt kan uppställningen av de akustiska simuleringarna bli automatiserade genom att säkerställa en bra koppling mellan de olika mjukvarorna och en korrekt benämning av de geometriska objekten involverade i simuleringen. Metoden undersökte hur morfologiska optimeringar kan bli genomförda både på en vittomfattande och lokal nivå för att förbättra transmissionsförlusten i ett efterbehandlingssystem. Förutom att optimera den akustiska prestandan av modellen kunde flera korrelationer mellan de olika konstruktiosparametrar identifieras likväl kunde korrelationer mellan konstruktiosparametrar och systemegenskaperna.

Denna projektrapport beskriver arbetet för en kvalitativ produktutveckling av ett åkdon som ska brukas i Persåsens anläggning för kälkåkning. Syftet med projektet var att bredda kunskapen och förståelsen om vad som bidrar till en hållfast, bekväm och säker kälke. Kälken ska naturligt uppmuntra till en aktiv körställning. Detta genom att undersöka och utvärdera vilka möjliga lösningar det finns för ramkonstruktion, skidor och knästöd. Projektets resultat skulle i framtiden bidra till att kälkåkningen utvecklas till en säkrare, bekvämare aktivitet som är anpassad för en bredare kategori av användare. Projektets mål är att leverera ett förslag på en ramkonstruktion i form av en 3D-modell som uppfyller samtliga krav från upprättad kravspecifikation. FEM-analyser som redovisar att ramkonstruktionen klarar av lasten som dubbla maximala rekommenderad vikt på användare genererar på 3 kritiska punkter. Projektet skall även resultera i en 3D-modell som visar på ett designförslag av knästöd samt skidor. Utöver detta konceptförslag innehåller resultatet från det här projektet en konkurrensanalys, prototypbygge och experimentella data från ett användartest. Sistnämnda tre punkters resultat har legat som underlag för konstruktion- och designförslag. / This project report describes the work for a qualitative product development of a vehicle to be used in Persåsen's sledding facility. The purpose of the project was to broaden the knowledge and understanding of what contributes to a strong, comfortable and safe sled. The sledge should naturally encourage an active driving position. This is done by investigating and evaluating the possible solutions for frame construction, skis and knee supports. The results of the project would in the future contribute to the sledge riding being developed into a safer, more comfortable activity that is adapted for a wider category of users. The project's goal is to deliver a suggestion for a frame construction in the form of a 3D model as a complete criterion from established requirements specification. FEM analyzes that report that the frame construction can handle the load as double the maximum recommended weight of what a user generates at 3 critical points. The project will also result in a 3D model that shows a design suggestion of knee supports and skis. In addition to this concept suggestion the results from this project contains market analysis, prototype construction and experimental data from a user test. The latter three points' results have been the basis for construction and design suggestions. / <p>2022-07-01</p>

Målet med detta examensarbete var att ta fram ett koncept på möbelset som passar in i framtidens förskolor, samt att leverera CAD-modeller och tillverkningsunderlag. Detta möbelset skall enligt en kvantitativ definition kunna främja för lärandeförmågan hos användaren, med tanke på funktion, säkerhet, och tillgänglighet. Uppgiften startades med Furneas initiativ att ta sig in på möbelmarknaden i Mellansverige och Stockholmsområdet med en ny produkt som kan möta de behov som kännetecknas av framtidens hållbara förskolor. Arbetet gjordes i fyra olika faser; planering, faktainsamling, genomförande, och analys. I planeringsfasen fastställdes strukturering och metodik av hela arbetet. I faktainsamlingsfasen gjordes litteraturstudier med avseende på pedagogiska inriktningar, miljö, säkerhet, ergonomi, och material. Det gjordes även intervjuer av förskolepedagoger angående nuvarande användning av bord i förskolan, och på företag rörande möbeltillverkning och förskolor. Genomförandefasen använder den insamlade datan för att skapa en funktionsanalys och kravspecifikation på möbelns design, och sedan komma fram med koncept på möbelsetet. I fasen ingår även att konstruera koncepten med CAD och 3D-printing. Analyser användes för att få fram konceptet som bäst möter användarens behov och modifiera konceptet till det slutgiltiga resultatet. För detta används sållningsmatriser, simuleringsprogram för att göra hållfasthetsberäkningar, samt DFMEA, en felorsaksanalys för produktutveckling. Resultatet av detta arbete presenteras med figurer och beskrivningar av möbelsetet. / The aim of this thesis was to develop a concept for a furniture-set that fits in with the preschools of the future, as well as to deliver CAD models and manufacturing documentation. According to a quantitative definition, this furniture should be able to promote the learning ability of the user, regarding function, safety, and accessibility. The task was started at Furnea's initiative to enter the furniture market in central Sweden and the Stockholm area with a new product that can meet the needs that are characterized by future sustainable preschools. The work was done in four different phases; planning, fact collection, implementation, and analysis. During the planning phase, structuring and methodology of the entire work was established. In the fact-finding phase, literature studies were conducted regarding educational orientations, environment, safety, ergonomics, and materials. Interviews of pre-school educators regarding the current use of tables in the preschool, and on companies concerning furniture manufacturing and preschools, were also conducted. The implementation phase uses the collected data to create a functional analysis and requirement specification for the furniture design, and then come up with a concept on the furniture. The phase also includes constructing the concepts with CAD and 3D printing. Analyses were used to bring out the concept that best meets the user's needs and modify the concept to the result. For this purpose, screening matrices, simulation programs for making strength calculations, and DFMEA, an error cause analysis for product development, were used. The result of this work is presented with figures and descriptions of the furniture.

Projektet gick ut på att utveckla ett antal koncept för att automatisera limningen av ett kullager som monteras i underdelen med hjälp av en kollaborativ robot. De ser detta som vägen framåt mot en mer effektiv produktion. Målet var att ta fram tre koncept för hur detta kan ske samtidigt som kraven upprätthålls. Projektet handlade endast om limningen av lagret och inte andra delar av sammanställningen av underdelen. Robotens gripdon som används vid sammanställningen fick dock inte modifieras på ett sätt som påverkar andra steg i processen. Underdelen är den komponent som fäster mätinstrumentet vid ett stativ. Den består av två huvuddelar som monteras vid varandra via ett lagerpar för att minimera oönskat spel. Utrymmet som finns tillgängligt begränsas huvudsakligen av robotens räckvidd och de andra stationerna i produktionslinan som roboten arbetar i. Tester av robotens förmåga att utföra de nödvändiga stegen genomfördes genom att stegvis testa dess egenskaper. Resultatet av dessa tester visade att roboten kunde utföra de nödvändiga stegen. De tre koncepten som togs fram byggde på varandras styrkor och svagheter med olika filosofier som grund. När dessa koncept var färdigställda utvärderades de och ställdes mot varandra i en beslutsmatris där det vinnande konceptet vidareutvecklades i CAD. Denna CAD-sammanställning omvandlades sedan med hjälp av 3D-utskrifter i PETG till en 1:1-skalig modell. Det koncept som valdes för vidareutveckling var det som bygger på att använda robotens rotationsförmåga och på så vis inte behöva några extra motorer. Resultatet blev då en station som uppfyller målen och går att använda för utveckling av produktionslinan. / The project aimed to develop several concepts for automating the bonding of a ball bearing that is mounted in the adapter housing with the help of a collaborative robot. They see this as the way forward to a more efficient production. The goal was to develop three concepts for how this can be done while maintaining the requirements. The project only dealt with the bonding of the ball bearing and not other parts of the assembly of the lower part. However, the robot's tongs used in the assembly could not be modified in a way that affects other steps in the process. The adapter housing is the component that attaches the measuring instrument to a tripod. It consists of two main parts that are mounted together through a pair of ball bearings to minimize unwanted play in the construction. The space available is mainly limited by the robot's reach and the other stations in the production line where the robot acts. Tests of the robot's ability to perform the necessary steps were carried out by systematically testing its features. The results of these tests showed that the robot could perform the necessary steps. Three concepts were developed that built on each other's strengths and weaknesses with different philosophies as a basis. When these concepts were completed, they were evaluated and compared in a decision matrix, where the winning concept was further developed in CAD. This CAD assembly was then converted using 3D printing in PETG to a 1:1 scale model. The concept chosen for further development was the one based on utilizing the robot's rotational capability, thus eliminating the need for any additional motors. The result was a station that meets the objectives and can be used for the development of the production line.

The oar has historically played a significant role for Sweden as a lake andcostal dominated country. For many years small boats called “snipa” wereused to gather fish by people living along the coastlines or alongside lakes.Oars was then the only option for conveying the boat forward. In today’ssociety, oar-propelled boats don’t have the same importance for people toacquire food. However, there are still reasons for a continued use of oars inactivities such as private fishing, competitive rowing or outdoor pursuits.The consumer market today is largely focused on mass production ofproducts, which often results in a reduced availability of custom-made ones.Being able to “engineer to order” is sometimes preferable due to the fact thathigh-quality and robust designs are, in certain respects, essential.Linnaeus University is conducting a research project that has vitalized atraditional Sami hunting and fishing gig boat, designed to be conveyed byoars and requires specially adapted oars for two different types of waterconditions. Currently, private consumers have limited options, for productsthat is designed for this, on the market.The purpose of this work is to describe how the established and well-knownmethodology of Systems Engineering, more specific “Design For SixSigma” (DMADOV), can be used to design and construct oars for use in twodifferent water conditions.

[pt] Os modelos CAD de plantas industriais desempenham um papel importante no gerenciamento de projetos de engenharia. Apesar dos avanços do poder computacional nas últimas décadas, a renderização destes modelos continua sendo um desafio devido à sua complexidade e ao grande volume de dados. Diferentes áreas da computação obtiveram êxito ao adotar serviços na nuvem para processar dados massivos. Contudo, quando se trata de rendering na nuvem, ainda há uma deficiência destes serviços para modelos CAD. Neste trabalho, propomos uma arquitetura de rendering híbrido na nuvem para modelos CAD, dividindo a tarefa de renderização entre o cliente e servidor. Além da diminuição da sobrecarga do servidor, esta abordagem garante ao sistema maior resiliência a variações de latência da rede. Neste trabalho também é introduzido um algoritmo de seleção de carga de trabalho baseada em metaheurística para determinar o conjunto de objetos a ser desenhado no lado do cliente. Nossos resultados demonstram que a metodologia proposta permite a visualização eficiente de modelos CAD massivos mesmo em condições adversas, como clientes com dispositivos limitados e latência alta na conexão. Por fim, discutimos as oportunidades de pesquisa restantes para renderização em nuvem, abrindo caminhos para melhorias futuras. / [en] Industrial-plant CAD models play an important role in engineering project management. Despite the advances in computing power in past decades, rendering these models remains challenging due to their complexity and large data volume. Different areas of computing have succeeded in adopting cloud services to process massive data. However, when it comes to cloud rendering, there is still a lack of cloud rendering services for CAD models. In this paper, we propose a hybrid cloud rendering architecture for CAD models, dividing the rendering task between client and server. In addition to reducing server overhead, this approach affords greater resilience to the system against variations of network latency. Finally, this work also introduces a metaheuristic-based workload selection algorithm to determine the set of objects to be drawn on the client side. Our results demonstrate that the proposed methodology allows efficient visualization of massive CAD models even under adverse conditions such as clients with limited devices and high connection latency. Lastly, we discuss remaining research opportunities for cloud rendering, opening avenues for future improvements.

[pt] À medida que o processo de digitalização avança em diversos setores, a criação de modelos digitais 3D torna-se cada vez mais necessária. Normalmente, esses modelos são construídos por designers 3D, exigindo um esforço manual considerável quando o objeto modelado é complexo. Além disso, como o designer não tem uma referência precisa na maioria dos casos, o modelo resultante está sujeito a erros de medição. No entanto, é possível minimizar o esforço de construção e o erro de medição usando técnicas de aquisição 3D e modelos CAD previamente construídos. A saída típica de uma técnica de aquisição 3D é uma nuvem de pontos 3D bruta, que precisa de processamento para reduzir o ruído inerente e a falta de informações topológicas. Os modelos CAD são normalmente usados para documentar um processo de projeto de engenharia, apresentando alta complexidade e muitos detalhes irrelevantes para muitos processos de visualização. Portanto, dependendo da aplicação, devemos simplificar bastante o modelo CAD para atender aos seus requisitos. Nesta tese, nos concentramos na construção de modelos digitais 3D a partir dessas fontes. Mais precisamente, apresentamos um conjunto de algoritmos de processamento de geometria para automatizar diferentes etapas de um fluxo de trabalho típico usado para esta construção. Primeiro, apresentamos um algoritmo de redução de ruído de nuvem de pontos que visa preservar as feições nítidas da superfície subjacente. Este algoritmo inclui soluções para a estimativa normal e problemas de detecção de feições nítidas. Em segundo lugar, apresentamos uma extensão do algoritmo de redução de ruído de nuvem de pontos para processar malhas triangulares, onde tiramos proveito da topologia explícita definida pela malha. Por fim, apresentamos um algoritmo para a simplificação extrema de modelos CAD complexos, que tendem a se aproximar da superfície externa do objeto modelado. Os algoritmos propostos são comparados com métodos de última geração, apresentando resultados competitivos e superando-os na maioria dos casos de teste. / [en] As the digitalization process advances in several industries, the creation of 3D digital models is becoming more and more required. Commonly, these models are constructed by 3D designers, requiring considerable manual effort when the modeled object is complex. In addition, since the designer does not have an accurate reference in most cases, the resulting model is prone to measurement errors. However, it is possible to minimize the construction effort and the measurement error by using 3D acquisition techniques and previously constructed CAD models. The typical output of a 3D acquisition technique is a raw 3D point cloud, which needs processing to reduce the inherent noise and lack of topological information. CAD models are typically used to document an engineering design process, presenting high complexity and too many details irrelevant to many visualization processes. So, depending on the application, we must severely simplify the CAD model to meet its requirements. In this thesis, we focus on the construction of 3D digital models from these sources. More precisely, we present a set of geometry processing algorithms to automatize different stages of a typical workflow used for this construction. First, we present a point cloud denoising algorithm that seeks to preserve the sharp features of the underlying surface. This algorithm includes solutions for the normal estimation and sharp feature detection problems. Second, we present an extension of the point cloud denoising algorithm to process triangle meshes, where we take advantage of the explicit topology defined by the mesh. Finally, we present an algorithm for the extreme simplification of complex CAD models, which tends to approximate the outer surface of the modeled object. The proposed algorithms are compared with state-of-the-art methods, showing competitive results and outperforming them in most test cases.

Projektet utfördes i samarbete med Södertälje sjukhus och målet är att komma på en tillverkningsbar ram för en flakspark cykel och postvagn. Arbetet består av 4 olika faser vilka var problemanalys, faktainsamling, konceptframtagning och sammanställning av rapporten. I problemanalys fasen utfördes ett studiebesök hos Södertälje sjukhus med syfte mot att identifiera problemet. Vidare har faktainsamling genomförts i form av besök hos olika sjukhus i Sverige för att undersöka så många lösningar som möjlig. På konceptframtagning har ett antal ingenjörsverktyg använts som olika CAD modelleringar, analyser, matriser och flera metoder för att komma till den perfekta lösningen för sjukhuset. Slutligen har hela arbetet dokumenterats och resultatet redovisats. Projektens huvudproblem var att den befintliga postvagnen var för tung och svårt att manövrera på Södertälje sjukhus. Rapporten innehåller även en hel del rekommendationer, detta för att kunna ge flera alternativ på olika framtida lösningar och som troligtvis är mer tillverkningsbara. Slutresultatet omfattar en tillverkningsbar postvagn och ram, som är mer anpassat än den befintliga. Den har lätt vikt och är lättare att manövrera. Ramen kommer att kunna monteras på den befintliga monarksflaksparkcykel. / The project was carried out in cooperation with Sodertalje Hospital, whose goal is to make a manufactural framework for a flatbed scooter and post- cart. The work consists of 4 different phases which were problem analysis, faculty gathering, conceptual design and compilation of the report. In the problem analysis phase, a study visit was conducted at Sodertalje Hospital with a view to identifying the problem. In addition, faculty gathering has been conducted in the form of visits to various hospitals in Sweden to investigate as many solutions as possible. On conceptual design, several of engineering tools have been used as CAD modeling, analysis and matrices with several methods to reach the perfect solution for the hospital. During the last phase, the entire work has been documented and a final result has been reported. The main problem of the project was that the existing post-cart was too heavy and difficult to maneuver at Sodertalje hospital The report also contains a whole lot of recommendations, this in order to provide several alternatives to different future solutions and is likely to be more manufactured. The end result includes a manufactural post-cart and frame, which is more adapted than the existing one. It has light weight and is easier to maneuver. The frame will be able to be mounted on the existing Monark flatbed scooter.

Moving from a project-based to a product-based organization comes with its own challenges, which goes for most organizations when one business model is changed to another. These changes lead to uncertainties in the work for the engineers, where lead time increases and time for the projects. This master thesis aimed to evaluate the uncertainties' characteristics and set standardizations in the work process to optimize the workflow and reduce engineering hours spent per project. The goals set for this thesis formulated three research questions: RQ1: What characterizes a reduction of engineering uncertainties through product-based structures?  RQ2: How can current layout modules be converted into standardized product-based structures? RQ3: How can standardized layout modules ensure the reduction of engineering uncertainties throughout the product-development process? By examining a case company’s journey through this transition through a quantitative methodology, three cases that each follow the product development process were conducted to answer the three research questions. The results for this thesis indicated that the implementation of standards reduced lead time and overall inconsistency, thus contributing to a more efficient modelling environment for the engineers and consistent implementation of an adaptable model for PDM integration. Implementing a design for assembly methodology proved to be a successful choice in reducing the assembly time for the engineers. An evaluation of the results indicates that only 34% of the engineering hours currently spent on conducting customer-based layout routings for the case company would be necessary when utilizing the standardized modules. / Att övergå från ett projektbaserat till ett produktbaserat bolag kan leda till vissa motgångar då övergången innebär förändringar i struktur och produktion. Dessa motgångar uppstår för en majoritet av bolag som implementerar denna övergång, där förändringar inom organisationen leder till ett antal osäkerheter i arbetet för ingenjörer som ökad ledtid och tidsåtgång för projekt. Målet med denna studie är att utvärdera vilka osäkerheter som uppstår och att standardisera arbetsprocessen för att optimera arbetsflödet och reducera tidsåtgång för ingenjörer per projekt. Målen för denna studie har genererat tre forskningsfrågor: FF1: Vad karaktäriserar en reducering av ingenjörsosäkerheter genom produktbaserade strukturer? FF2: Hur kan nuvarande layout moduler konverteras till standardiserade produktbaserade strukturer? FF3: Hur kan standardiserade layout moduler säkerställa reduktion av ingenjörsosäkerheter genom produktutvecklingsprocessen? Genom att undersöka ett fallföretags resa genom övergångsprocessen med en kvantitativ metodologi, genererades tre fall som följde produktutvecklingsprocessen för att utförligt svara på forskningsfrågorna. Resultaten för denna studie indikerar att implementeringen av standarder reducerar ledtid och övergripande inkonsekvens, vilket därmed bidrar till en mer effektiv konstruktionsmiljö för ingenjörerna, samt en mer konsistent implementering av en tillämpbar modell för PDM integrering. Implementeringen av design för sammanställnings metodologi visade sig vara ett lyckat val i att reducera sammanställningstid för ingenjörerna. En utvärdering av resultaten visar att endast 34% av den tid det tar för fallföretaget i dagsläget att utföra en fullständig ”layout routing” är nödvändig när standardiserade moduler tillämpas.

[pt] Modelos CAD 3D ricos em dados são essenciais durante os diferentes estágios do ciclo de vida de projetos de engenharia. Devido à recente popularização da metodologia Modelagem de Informação da Construção e do uso de Gêmeos Digitais para a manufatura inteligente, a quantidade de detalhes, o tamanho, e a complexidade desses modelos aumentaram significativamente. Apesar desses modelos serem compostos de várias geometrias repetidas, os softwares de projeto de plantas geralmente não proveem nenhuma informação de instanciação. Trabalhos anteriores demonstraram que removendo a redundância na representação dos modelos CAD 3D reduz significativamente o armazenamento e requisição de memória deles, ao passo que facilita otimizações de renderização. Este trabalho propõe um arcabouço para correspondência de formas baseado em aprendizado profundo que minimiza as informações redundantes de um modelo CAD 3D a esse respeito. Nos apoiamos nos avanços recentes no processamento profundo de nuvens de pontos, superando desvantagens de trabalhos anteriores, como a forte dependencia da ordenação dos vértices e topologia das malhas de triângulos. O arcabouço desenvolvido utiliza nuvens de pontos uniformemente amostradas para identificar similaridades entre malhas em modelos CAD 3D e computam uma matriz de transformação afim ótima para instancia-las. Resultados em modelos CAD 3D reais demonstram o valor do arcabouço proposto. O procedimento de registro de nuvem de pontos desenvolvido atinge um erro de superfície menor, ao mesmo tempo que executa mais rápido que abordagens anteriores. A abordagem supervisionada de classificação desenvolvida antinge resultados equivalentes em comparação com métodos limitados anteriores e os superou significativamente num cenário de embaralhamento de vértices. Propomos também uma abordagem auto-supervisionada que agrupa malhas semelhantes e supera a necessidade de rotular explicitamente as geometrias no modelo CAD 3D. Este método auto-supervisionado obtém resultados competitivos quando comparados às abordagens anteriores, até mesmo superando-as em determinados cenários. / [en] Data-rich 3D CAD models are essential during different life-cycle stages of engineering projects. Due to the recent popularization of Build Information Modeling methodology and the use of Digital Twins for intelligent manufacturing, the amount of detail, size, and complexity of these models have significantly increased. Although these models are composed of several repeated geometries, plant-design software usually does not provide any instancing information. Previous works have shown that removing redundancy in the representation of 3D CAD models significantly reduces their storage and memory requirements, whilst facilitating rendering optimizations. This work proposes a deep-learning-based shape-matching framework that minimizes a 3D CAD model s redundant information in this regard. We rely on recent advances in the deep processing of point clouds, overcoming drawbacks from previous work, such as heavy dependency on vertex ordering and topology of triangle meshes. The developed framework uses uniformly sampled point clouds to identify similarities among meshes in 3D CAD models and computes an optimal affine transformation matrix to instantiate them. Results on actual 3D CAD models demonstrate the value of the proposed framework. The developed point-cloud-registration procedure achieves a lower surface error while also performing faster than previous approaches. The developed supervised-classification approach achieves equivalent results compared to earlier, limited methods and significantly outperformed them in a vertex shuffling scenario. We also propose a selfsupervised approach that clusters similar meshes and overcomes the need for explicitly labeling geometries in the 3D CAD model. This self-supervised method obtains competitive results when compared to previous approaches, even outperforming them in certain scenarios.