Aus der Einleitung: "Im Modell und Formenbau des Maschinenbaus beschreibt Reverse Engineering den Prozess der 3D-Erfassung eines Objektes, die Aufbereitung der Digitalisierungsdaten zu CAD-Modellen und die weitere Nutzung dieser Daten in einer CAD/CAM-Umgebung. Ziel dieser Arbeiten ist es dann weiterführend, physische Objekte durch CNC-Fräsen oder mittels Generativer Fertigungsverfahren herzustellen. Die Maßkontrolle der gefertigten Produkte gegenüber dem CAD ist ebenfalls eine Aufgabestellung des Reverse Engineering (Schöne 2009, Wang 2011)."

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.

[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] 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.

Maitriser le triptyque coût-qualité-délai lors des différentes phases du Processus de Développement d’un Produit (PDP) dans un environnement de plus en plus concurrentiel est un enjeu majeur pour l’industrie. Le développement de nouvelles méthodes et de nouveaux outils pour adapter une représentation du produit à une activité du PDP est l’une des nombreuses pistes d’amélioration du processus et certainement l’une des plus prometteuses. Cela est particulièrement vrai dans le domaine du transfert de modèles de Conception Assistée par Ordinateur (CAO) vers des activités de simulations numériques. Actuellement, les méthodes et outils de préparation d’un modèle CAO original vers un modèle dédié à une activité existent. Cependant, ces processus de préparation sont des tâches complexes qui reposent souvent sur les connaissances des experts et sont peu formalisés, en particulier lorsque l’on considère des maquettes numériques riches comprenant plusieurs centaines de milliers de pièces. Pouvoir estimer a priori l’impact de la préparation de la maquette numérique sur le résultat de la simulation permettrait d’identifier dès le début le meilleur processus et assurerait une meilleure maitrise des processus et des coûts de préparation. Cette thèse a pour objectif de relever ce défi en utilisant des techniques d’intelligence artificielles capables d'imiter et de prévoir un comportement à partir d'exemples judicieusement choisis. L’idée principale est d’utiliser des exemples de préparation de maquettes numériques comme entrées d’algorithmes d’apprentissage pour configurer des estimateurs de la performance d’un processus. Lorsqu’un nouveau cas se présente, ces estimateurs pourront alors prédire a priori l’impact de la préparation sur le résultat de l’analyse sans avoir à la réaliser. Afin d'atteindre cet objectif, une méthode a été développée pour construire une base d’exemples représentatifs, identifier les variables d’entrée et de sortie déterminantes et configurer des modèles d’apprentissage. La performance d’un processus de préparation sera évaluée à l’aide de critères tels que des coûts de préparation, des coûts de simulation et des erreurs sur le résultat de l’analyse dues à la simplification des modèles CAO. Ces critères seront les données de sortie des algorithmes d’apprentissage. Le premier challenge de l’approche proposée est d’extraire les données des modèles 3D complétées par des données relatives au cas de simulation qui caractérisent au mieux un processus de préparation , puis d’identifier les variables explicatives les plus déterminantes. Un autre challenge est de configurer des modèles d’apprentissage capables d’évaluer avec une bonne précision la qualité d’un processus malgré un nombre limité d’exemples de processus de préparation et de données disponibles (seules les données relatives aux modèles CAO originaux, aux cas de simulation sont connues pour un nouveau cas). Au final, l’estimateur de la performance d’un processus aidera les analystes dans le choix d'opérations de préparation de modèles CAO. Cela ne les dispensera pas de la simulation mais permettra d'obtenir plus rapidement un modèle préparé de meilleure qualité. Les techniques d’intelligence artificielles utilisées seront des classifieurs de type réseaux de neurones ou arbres de décision. L’approche proposée sera appliquée à la préparation de modèles CAO riches pour l’analyse CFD. / Controlling the well-known triptych costs, quality and time during the different phases of the Product Development Process (PDP) is an everlasting challenge for the industry. Among the numerous issues that are to be addressed, the development of new methods and tools to adapt to the various needs the models used all along the PDP is certainly one of the most challenging and promising improvement area. This is particularly true for the adaptation of CAD (Computer-Aided Design) models to CAE (Computer-Aided Engineering) applications. Today, even if methods and tools exist, such a preparation phase still requires a deep knowledge and a huge amount of time when considering Digital Mock-Up (DMU) composed of several hundreds of thousands of parts. Thus, being able to estimate a priori the impact of DMU preparation process on the simulation results would help identifying the best process right from the beginning, and this will ensure a better control of processes and preparation costs. This thesis addresses such a difficult problem and uses Artificial Intelligence (AI) techniques to learn and accurately predict behaviors from carefully selected examples. The main idea is to identify rules from these examples used as inputs of learning algorithms. Once those rules obtained, they can be used as estimators to be applied a priori on new cases for which the impact of a preparation process can be estimated without having to perform it. To reach this objective, a method to build a representative database of examples has been developed, the right input and output variables have been identified, then the learning model and its associated control parameters have been tuned. The performance of a preparation process is assessed by criteria like preparation costs, analysis costs and the errors induced by the simplifications on the analysis results. The first challenge of the proposed approach is to extract and select most relevant input variables from the original and 3D prepared models, which are completed with data characterizing the preparation processes. Another challenge is to configure learning models able to assess with good accuracy the quality of a process, despite a limited number of examples of preparation processes and data available (the only data known to a new case are the data that characterize the original CAD models and simulation case). In the end, the estimator of the process’ performance will help analysts in the selection of CAD model preparation operations. This does not exempt the analysts to make the numerical simulation. However, this will get faster a simplified model of best quality. The rules linking the output variables to the input ones are obtained using AI techniques such as well-known neural networks and decision trees. The proposed approach is illustrated and validated on industrial examples in the context of CFD simulations.