检索结果-内蒙古大学图书馆

AI-enhanced Identification, Inspection and Sorting for Reverse Logistics in Remanufacturing

Procedia CIRP 2021年 98卷 300-305页

作者： Marian Schlüter Hannah Lickert Katharina Schweitzer Pinar Bilge Clemens Briese Franz Dietrich Jörg Krüger Fraunhofer IPK - Institute for Production Systems and Design Technology Pascalstr. 8-9 10587 Berlin Germany Technische Universität Berlin Institute for Machine Tools and Factory Management Pascalstr. 8-9 10587 Berlin Germany acatech – Deutsche Akademie der Technikwissenschaften Karolinenplatz 4 80333 München Germany

In a circular economy for remanufacturing, after each life cycle used products are returned to a remanufacturer for identification, inspection, sorting and reprocessing. Shortcomings and requirements of the remanufacturing market are identified through expert interviews and process analysis. A concept is proposed to enable an improved identification and a more objective inspection by enhancing the working environment and processes of sorting stations. Digitization and machine learning are applied on business data, using machine vision as well as sensor and actor skills of the worker. With an experimental case study on visual object recognition a positive impact on identification and thus sorting could be demonstrated.

关键词： Circular Economy Remanufacturing Reverse Logistics Sorting Computer Vision Machine Learning Assistance System

来源：评论

学校读者我要写书评

暂无评论

Generative 3D Reconstruction of Ti-6Al-4V Basketweave Microstructures by Optimization of Differentiable Microstructural Descriptors

SSRN

引用

SSRN 2024年

作者： Blümer, Vincent Safi, Ali Reza Soyarslan, Celal Klusemann, Benjamin Boogaard, Ton van den Nonlinear Solid Mechanics University of Twente Drienerlolaan 5 Enschede7522 NB Netherlands Institute of Material and Process Design Helmholtz-Zentrum Hereon Max-Planck-Straße 1 Geesthacht21502 Germany Fraunhofer Innovation Platform Hengelosestraat 701 Enschede7521 PA Netherlands Institute for Production Technology and Systems Leuphana University Universitätsallee 1 Lüneburg21335 Germany Institute of Product and Process Innovation Section of Applied Mechanics

We present a methodology for the generative reconstruction of 3D microstructures from 2D cross-sectional electron backscatter diffraction micrographs. The method is applied to Ti-6Al-4V processed by laser powder bed fusion, where a high amount of basketweave morphology is observed, which arises from the solid-state β → α-transition upon cooling. Prior-β-grain reconstruction is performed and the out-of-plane orientation of the observed grains is obtained leveraging Burgers orientation relationship. Convolutional neural network - based microstructural descriptors are extracted from the 2D micrographs, and used for cross-section-based optimization of pixel values in a 3D volume. In order to reconstruct crystallographic orientations, the orientation distribution of the basketweave microstructure is reduced to a discrete set of characteristic orientations, which are sequentially reconstructed as separate components. Our reconstructions capture the characteristic lath morphology that is typically observed in powder bed fusion-processed Ti-6Al-4V and perform well in comparisons of chord length-, as well as grain size-, aspect ratio-, and axis orientation distributions. © 2024, The Authors. All rights reserved.

关键词： Aspect ratio

来源：评论

学校读者我要写书评

暂无评论

User centered development of a Digital Twin concept with focus on sustainability in the clothing industry

引用

Procedia CIRP 2020年 90卷 660-665页

作者： Theresa Riedelsheimer Lisa Dorfhuber Rainer Stark Fraunhofer-Institute for Production Systems and Design Technology (IPK) Pascalstrasse 8-9 10587 Berlin Germany Technical University Berlin Pascalstrasse 8-9 10587 Berlin Germany

The optimization of a product's socio-economic and environmental impact is gaining more relevance for customers and regulating institutions. Still, there is a gap between sustainable attitude and behavior. In this context, new technologies are explored to stimulate sustainable consumers' behavior. This paper aims at analyzing the concept of a Digital Twin and its sustainability impact. The authors present a user centered development of a Digital Clothing Twin with the aim to foster sustainability in the Mid-of-life and End-of-Life-phase. The sustainability impact of the Digital Twin concept as a potential solution as well as part of the problem is discussed.

关键词： Life Cycle Sustainability Assessment (LCSA) Life Cycle Assessment (LCA) Digital Twin Sustainability Smart products Use case

来源：评论

学校读者我要写书评

暂无评论

Demand-oriented barriers and potentials for remanufacturing in Vietnam

引用

International Journal of Sustainable Manufacturing 2020年第2-4期4卷 336-349页

作者： Guidat, Thomas Wewer, Aleksandra Kohl, Holger Seliger, Günther Department of Machine Tools and Factory Management Technische Universität Berlin Pascalstraße 8-9 Berlin10587 Germany Vietnamese German University Lê Lai Đinh Hoà Thů Dâu Môt Bình Dương Viet Nam Fraunhofer Institute for Production Systems and Design Technology IPK Pascalstraße 8-9 Berlin10587 Germany

Since the liberalisation of its economy, Vietnam has emerged as a key location for investment in workforce-intensive assembly processes operation, through an available and cheap workforce. Soaring national consumption levels for goods and services generate in turn unprecedented quantities of waste to be treated locally. In 2015, governmental decision 16/2015/QĐ-TTg set a basis for a national waste legislation for mechanical and electronic equipment goods. Remanufacturing is a non-destructive, industrial reuse strategy which aims at restoring products to original specifications by reusing a maximum number of original components in their current form. It has potential to provide Vietnam with an alternative to low value-added repair activities. As Vietnam is the fourth market for motorcycles in the world, this paper presents a case study about barriers and potentials for remanufacturing from the market and customer perspective. Potential solutions for supporting industrial development are suggested. © 2020 Inderscience Enterprises Ltd.

关键词： Motorcycles

来源：评论

学校读者我要写书评

暂无评论

Fully coupled wet cylindrical turning simulation using the Finite-Pointset-Method

引用

Procedia CIRP 2021年 102卷 43-48页

作者： Eckart Uhlmann Enrico Barth Alexander Quellhorst Tobias Seifarth Jörg Kuhnert Kaissar Nabbout Martin Sommerfeld Technische Universität Berlin Institute for Machine Tools and Factory Management (IWF) Chair of Machine Tools and Manufacturing Technology Pascalstr. 8-9 10587 Berlin Germany Fraunhofer Institute for Production Systems and Design Technology (IPK) Pascalstr. 8-9 10587 Berlin Germany Fraunhofer Institute for Industrial Mathematics ITWM Fraunhofer-Platz 1 67663 Kaiserslautern Germany Otto von Guericke University Magdeburg Institute of Process Engineering Universitaetsplatz 2 39106 Magdeburg Germany

In industrial machining operations, many turning processes are carried out under wet conditions. In contrast, most simulation tools are only suitable for dry cutting processes due to challenges of modeling fluid-structure-interactions (FSI). In this paper, a wet, fully coupled cutting simulation using the Finite-Pointset-Method (FPM) is presented and validated for industrially relevant cylindrical turning. To facilitate the required reduction of the calculation effort, different routines like adaptive numerical discretization are applied. The results indicate different cutting fluid effects like evaporation areas around the chip.

关键词： Turning Cutting fluid Simulation

来源：评论

学校读者我要写书评

暂无评论

Data augmentation for inertial sensor based human action recognition using deep learning

引用

AIP Conference Proceedings 2024年第1期2989卷

作者： Jan Kuschan Hristo Filaretov Jörg Krüger Process Automation and Robotics Fraunhofer Institute for Production Systems and Design Technology IPK Pascalstr. 8-9 10587 Berlin Germany Industrial Automation Technology Institute of Machine Tools and Factory Management Technical University Berlin Pascalstr. 8-9 10587 Berlin Germany

Human Activity Recognition (HAR) approaches are predominantly based on supervised deep learning and benefit from large amounts of labeled data—an expensive resource. Data augmentation enriches labeled datasets by adding synthetic data, which is substantially cheaper, and often results in improved model performance, but is very rarely used for sensor data. This work explores data augmentation for inertial-sensor-based HAR by transforming the data through physically interpretable operations. The main studies were conducted on the Opportunity and the Overhead Car Assembly (OCA) datasets. For these experiments, only 20% of the available training data were used, and the experiments were conducted in an 8-fold cross-validation procedure over different subsets of the training *** results show that simple geometric augmentations can be beneficial in many cases. Timewarping proved to offer the most reliable single augmentation, improving the average F1 score of Opportunity from 0.570 to 0.597 and of OCA Mixed from 0.884 to 0.906. Combining augmentations improved the accuracy in almost all scenarios but to a degree comparable to timewarping. Applying augmentations on all the available training data improved the F1 score compared to the base case with no augmentations, although this effect is more pronounced for datasets with more similar training and test data: for the OCA Mixed variant, the average F1 score improved from 0.917 to 0.933, while for the OCA Leave-One-Out (LOT) variant, the average F1 score did not significantly change. For Opportunity, which similarly to OCA LOT uses a participant-based training-test split, the F1 score improved from 0.684 to 0.697.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Trochoid milling with industrial robots

引用

Procedia Manufacturing 2020年 43卷 447-454页

作者： E. Uhlmann S. Reinkober M. Hoffmann P. Käpernick Fraunhofer Institute for Production Systems and Design Technology Pascalstraße 8-9 10587 Berlin Germany

The highly dynamic production puts the versatility of production systems in the center of industrial interests. Due to their flexibility and low energy consumption industrial robots are a big part of this development. They have been used as handling systems for decades and are already state of the art in this regard. This is not the case for other surrounding tasks such as milling. These systems have in comparison to conventional machine tools a relatively low stiffness c, which allows only low cutting forces F c and therefore low feed rates f z and speeds v c . This leads to higher processing times and therefore to a higher energy consumption. A highly dynamic milling strategy, which results in significantly lower cutting forces F c than in conventional milling and which at the same time has high cutting rates is trochoid milling. This paper shows the basic usability of this milling strategy on standard industrial robots. Furthermore, the challenges of the near future will be shown.

关键词： robot guided machining efficient machining strategies milling production

来源：评论

学校读者我要写书评

暂无评论

Micro-cutting of a MMC-composite for enhanced injection moulds 19

Micro-cutting of a MMC-composite for enhanced injection moul...

引用

19th International Conference of the European Society for Precision Engineering and Nanotechnology, EUSPEN 2019

作者： Uhlmann, E. Polte, M. Hein, C. Polte, J. Jahnke, C. Fraunhofer Institute for Production Systems and Design Technology IPK Germany Institute for Machine Tools Factory Management IWF Technische Universität Berlin Germany

ISBN: (纸本)9780995775145

Tools for micro-injection moulding are currently made of hardened steel. These tools are exposed to high local loads, which significantly reduce the injection moulding tool life time tT. Furthermore, the occurring wear of the milling tool during machining of hardened steel leads to reduced surface roughness Ra and geometrical accuracy GF. Copper and aluminium alloys as mould materials provide an alternative to hardened steel with advantages regarding material removal rate QW and wear of the milling tool, but with a significantly reduced life time of the injection moulding tool tT. Until now, the combination of a good machinability and high wear resistance cannot be achieved. The approach, presented in this paper consists of an easy to machine material and the development of a wear resistant metal-matrix-composite (MMC) material layer with a hardness of up to 3,000 HV. Therefore, the pre-machined test specimens made of aluminium-bronze are coated by laser dispersing with wolfram-carbide-particles W2C-WC. Furthermore, for the finishing machining of the coated moulds, a cutting technology for the machining of W2C-WC-particles was developed. The verification of the developed technology was performed with an injection moulding process based on carbon-fibre reinforced thermoplastic material. By means of documented machining efforts, the quality indicators geometrical accuracy GF and surface roughness Ra as well as occurring tool wear, the feasibility of the developed technology was demonstrated. © 2019 European Society for Precision Engineering and Nanotechnology, Conference Proceedings - 19th International Conference and Exhibition, EUSPEN 2019. All rights reserved.

关键词： Injection molding

来源：评论

学校读者我要写书评

暂无评论

Cutting force predictionin micro-milling considering the cutting edge micro-geometry 19

Cutting force predictionin micro-milling considering the cut...

引用

19th International Conference of the European Society for Precision Engineering and Nanotechnology, EUSPEN 2019

作者： Uhlmann, E. Polte, J. Wiesner, H.M. Kuche, Y. Polte, M. Fraunhofer Institute for Production Systems and Design Technology IPK Germany Institute for Machine Tools Factory Management IWF Technische Universität Berlin Germany

ISBN: (纸本)9780995775145

The micro-milling process is used for a wide range of materials and enables the manufacturing of complex geometries with micro-features. One important factor for the tool life is the cutting force Fc, which depends on the applied technology, process parameters and cutting edge micro-geometry. High cutting forces Fc can lead to tool breakage in the transition between the shank and the cutting part of cemented carbide end mills. The prediction of cutting forces Fc in micro-milling processes through cutting force models could potentially decrease the hazard of tool breakage. By including the cutting edge radius rβ into the prediction model, additional correction factors can be avoided. Therefore, further knowledge about the applicability of those models for the micro-milling process with chip thickness h © 2019 European Society for Precision Engineering and Nanotechnology, Conference Proceedings - 19th International Conference and Exhibition, EUSPEN 2019. All rights reserved.

关键词： Milling (machining)

来源：评论

学校读者我要写书评

暂无评论

Manufacturing of graphite electrodes with high geometrical requirements 19

Manufacturing of graphite electrodes with high geometrical r...

引用

19th International Conference of the European Society for Precision Engineering and Nanotechnology, EUSPEN 2019

作者： Uhlmann, E. Kuche, Y. Polte, J. Polte, M. Fraunhofer Institute for Production Systems and Design Technology IPK Germany Institute for Machine Tools Factory Management IWF Technische Universität Berlin Germany

ISBN: (纸本)9780995775145

Graphite is widely used for the die-sinking electrical discharge machining (EDM) process, especially for the roughing process. For the manufacturing of graphite electrodes the milling process is mainly used. The process enables fast processing times tP and high geometrical flexibility. In consequence of the cutting behaviour of graphite micro-components with geometrical features can be manufactured. In this contribution the manufacturing of micro-pins and bridges with aspect ratios of A = 1:50 were machined with diamond coated milling tools. By variation of the depth of cut ap and the width of cut ae it can be shown that the influence of the depth of cut ap is quite bigger than the influence of the width of cut ae. This results in consequence of the higher stability of the geometrical features by improved force distribution. © 2019 European Society for Precision Engineering and Nanotechnology, Conference Proceedings - 19th International Conference and Exhibition, EUSPEN 2019. All rights reserved.

关键词： Graphite electrodes

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：