Fraunhofer-Institut für Produktionsanlagen und Konstruktionstechnik IPK

Filters
Reset filters

Settings
Now showing 1 - 10 of 63
  • Publication
    An Ensemble Learning based Hierarchical Multi-label Classification Approach to Identify Impacts of Engineering Changes
    ( 2020)
    Pan, Y.
    ;
    Stark, R.
    In the process of complex products development, design decisions of products are constantly changed to improve quality or functionality, reduce costs, respond to statutory constraints or implement wishes from customers, with respect to new functionality. The changes on already released design decisions are known as Engineering Changes (EC). Due to interdependency, changes on one component may cause changes on another, and this will spread along the product structure. Therefore, to completely identify the affected components of engineering changes is a major challenge. This paper presents a novel approach to use properties of components as target variables and applying the predicted properties to locate the EC affected components in product structure. We create a hierarchy of the properties and divide the label space into separate communities. A stacked multi-label classifier is trained in each community, the result is obtained by union of assigned labels from different communities. Finally, the predicted labels are adjusted by incorporating the hierarchical relation. Experiments conducted on real-world industrial EC dataset with mixed data types. Results demonstrated that, the ensemble framework in our approach is more efficient and effective than our baseline models and has achieved superior performance on real industrial engineering change data.
  • Publication
    Integration of automated structure mechanic analyses into production process simulation
    ( 2019)
    Schmitz, M.B.
    ;
    Stark, R.
    To produce individual variants of a given product, each variant has to be assessed with respect to their mechanical integrity. This is usually done in the course of product design by assessing all required variants. However, during the lifetime of a product several changes of the existing variants occur or new variants will be created. In this paper a method is described how to integrate and automate the assessment of the mechanical integrity of the product variants directly into the production process by exploiting modern computer methods and automated set-up of state-of-the-art CAE methods. We show this on a demonstrator of a smart factory, that produces disks which can be customized to a large extend. The disks undergo a milling process, which alters the structural properties of the disks. Generally, it cannot be guaranteed upfront that a variant that can be produced is also strong enough to withstand the loads in the application. Therefore, the integrated FEM analyses are computing and assessing the load cases deduced from the use cases of the disks and the loads that occur during milling and handling in the factory. The assessment of the results is done automatically and if positive the production process is started.
  • Publication
    Neural Network Hyperparameter Optimization for the Assisted Selection of Assembly Equipment
    ( 2019)
    Hagemann, S.
    ;
    Sünnetcioglu, A.
    ;
    Fahse, T.
    ;
    Stark, R.
    The design of assembly systems has been mainly a manual task including activities such as gathering and analyzing product data, deriving the production process and assigning suitable manufacturing resources. Especially in the early phases of assembly system design in automotive industry, the complexity reaches a substantial level, caused by the increasing number of product variants and the decreased time to market. In order to mitigate the arising challenges, researchers are continuously developing novel methods to support the design of assembly systems. This paper presents an artificial intelligence system for assisting production engineers in the selection of suitable equipment for highly automated assembly systems.
  • Publication
    Application of industrial methods in engineering education
    ( 2019)
    Kind, S.
    ;
    Dybov, A.
    ;
    Buchholz, C.
    ;
    Stark, R.
    Modern trends and challenges like an increased level of product complexity and reduced time for development require new, improved skills for future employees. Potential industrial methods based on early project planning, interdisciplinary product solutions and a systematic preparation for production are researched and presented within this paper. Future employees need to understand the processes and methods of product implementation and production. Especially the last stages of product development require additional attention, since these are the most challenging phases regarding integration and implementation starting from initial prototyping up to a functional product. Industrial feedback proves, that these skills are not taught in an appropriate extend by todays academic education, concluding that todays' graduates are not well prepared for tomorrow's job challenges. Following the gaps in today's education a student project lecture was developed, that teaches and applies industry-related development methods addressing advanced master students. Focus of the related student project includes a constant review of project management practices in industrial design reviews, as well as the gathering and definition of requirements. In addition to this, development methods for functional prototypes are taught and applied. Especially the actual creation of prototypes is addressing the product integration and testing phase. To present the above-mentioned methods and an innovative testing environment, two successfully applied use cases are described within this paper. These are covering the entire development process starting from early requirements gathering, accompanied by model-based system engineering.
  • Publication
    Semantic Assistance System for Providing Smart Services and Reasoning in Aero-Engine Manufacturing
    ( 2019)
    Gogineni, S.
    ;
    Exner, K.
    ;
    Stark, R.
    ;
    Nickel, J.
    ;
    Oeler, M.
    ;
    Witte, H.
    Digitalization has led to creation and management of knowledge using information and communication technology tools (ICT) and systems. Implementing such tools and systems across the lifecycle is a tedious process and not to forget customizing them to the company's processes is an additional challenge. Hence, data in a company is spread across multiple ICT in heterogeneous data formats and are sparsely connected together. Connecting the various data sources to enable a single point of access of information in a company can improve performance, quality, reduce costs and time to market. The usage of semantic technologies enables meaningful and structured unification of these distributed data sources and therefore, is providing advantages such as reusability, interoperability, and information flow across the entire value chain. Extending these capabilities with smart services and intelligent algorithms, is advantageous for the user. The user will then receive context sensitive information and additional suggestions that increases the speed, quality and efficiency of work. This paper aims at describing the design, developing and validation of an assistance system for semantic product data, in cooperation with Rolls-Royce Deutschland, an aerospace manufacturing industry, using semantic technologies and machine learning.
  • Publication
    Automated Body-in-White Production System Design: Data-Based Generation of Production System Configurations
    ( 2018)
    Hagemann, S.
    ;
    Stark, R.
    Design processes for production systems (PS) in the automotive body-in-white (BIW) sector tie up tremendous resources. Current challenges like the continuous increase of product variants and product complexity have direct impact on the required planning effort in production system design (PSD), which is currently increasing significantly. Analysis of these design processes have revealed a high potential for process automatization. In order to achieve this, suitable methods are required as well as a data basis of reasonable quality. Both methods and data basis are deeply investigated in this paper. The investigations' results create a solid basis for further research in the young field of automated BIW PSD.
  • Publication
    Decision support tool to derive sustainable product configurations as a basis for conceptual design
    ( 2018)
    Buchert, T.
    ;
    Stark, R.
    Developing sustainable products requires a thorough understanding of the product and its environmental, economic and social impact. In particular decision-making in conceptual design has a large influence on sustainability performance of the final product but still remains widely unsupported. Hence, an Engineering Decision Support System (EDSS) and a corresponding method is proposed which assists system engineers in evaluating and comparing various product concepts in early design phases. In this paper the EDSS concept is elaborated and demonstrated on the example of a pedelec drive system.
  • Publication
    Data-driven business model a methodology to develop smart services
    ( 2018)
    Exner, K.
    ;
    Stark, R.
    ;
    Kim, J.Y.
    The appearance of Industrie 4.0 also known as cyber-physical systems and internet of things enables a continuous creation of data based on intelligent facilities. It is assumed that data will be one of the main resources in the future. Nevertheless, data need to be transformed into valuable information and further systematically integrated into a value proposition. In order to develop these smart services a data-driven business model has to be developed and evaluated. For this reason, a literature review has been conducted to identify existing business model approaches in context of Industrie 4.0 and Product-Service Systems. Based on the results of the review requirements for a new model and method have been defined and a data-driven business model including an extensive catalogue of key questions have been developed and applied with an industrial partner. The findings and results of the study are presented in this paper.
  • Publication
    Understanding PLM and PLM customizing: A theoretical fundament for a conceptual approach
    ( 2018)
    Venghaus, E.
    ;
    Stark, R.
    The continuous development of product lifecycle management (PLM) technology depicts many needs for clarification and action especially in PLM understanding and PLM implementation. The adaptation and customizing of PLM technologies become unavoidable and implicate high expenditure in form of costs, time and effort which is often underestimated by organizations. Despite of the importance of PLM adaptation and PLM customizing and its influence on the success of a PLM implementation project, there is no clear basis for an understanding of what PLM adaptation and customizing really is. Furthermore a lack of solution approaches exists that can guide companies during the process of PLM adaptation and customizing. The aim of this paper is to build a foundation for understanding PLM and the customizing of PLM. Furthermore a solution area beyond the software driven focus will be suggested.
  • Publication
    Engineering activities: Considering value creation from a holistic perspective
    ( 2018)
    Lünnemann, P.
    ;
    Stark, R.
    ;
    Wang, W.M.
    ;
    Manteca, P.I.
    Modern value creation is characterized by collaboration of large networks of specialized companies. Due to market requirements and increasing competition, concurrent or simultaneous engineering has become the standard procedure in product development. Still, product development processes often follow the traditionally linear and sequential patterns, allowing for only a narrow scope of iterations. Milestone-driven models are widely used to control and steer such processes. In this article, the authors argue that proper understanding of knowledge flows in development project is an essential aspect to be regarded in design and organization of product development processes. Therefore, a new approach is proposed in this paper which considers the product development process as a set of Engineering Activities. Such activities can be seen as instantiations of processes and are the core of any value creation processes. During an experiment a group of students carried out a simple product development project within a controlled environment. The resulting model was then re-evaluated using survey results from a further student experiment. Both results indicate that the activity model can be applied to describe development projects and that it can be used to identify knowledge flows and barriers within development teams.