检索结果-内蒙古大学图书馆

19th IMEKO TC10 Conference on MACRO meets NANO in Measurement for Diagnostics, Optimization and Control

作者： Heymann, Henrik Hellmich, Jan Hendrik Frye, Maik Grunert, Dennis Schmitt, Robert H. Fraunhofer Institute for Production Technology IPT Steinbachstraße 17 Aachen52074 Germany Laboratory for Machine Tools and Production Engineering WZL RWTH Aachen University Campus-Boulevard 30 Aachen52074 Germany

ISBN: (纸本)9781713884125

Artificial Intelligence (AI) projects in production often end in proof-of-concepts with AI solutions not being continuously maintained along their life cycle. Only by managing multiple AI use cases simultaneously and systematically, companies can achieve an industrial level of usage in their production environment and fully benefit from the technology’s potential. For that purpose, an AI management model is proposed that serves as a framework to capture, design, and optimize AI activities to continuously improve the quality of the AI solutions and the satisfaction of involved stakeholders. Relevant related concepts from quality management (QM) are employed during the creation of the management model distinguishing three categories of processes: management, core, and support. For each category, corresponding processes and sub-processes are provided and explained for orientation in the implementation in specific scenarios. The proposed management model is validated with AI, QM, and production domain experts on a conceptual level. Furthermore, it is applied operationally in the implementation of real-life use cases from production. © 2023 19th IMEKO TC10 Conference "MACRO meets NANO in Measurement for Diagnostics, Optimization and Control".

关键词： Artificial Intelligence Management Model Production Quality Management

来源：评论

学校读者我要写书评

暂无评论

Fast, semi-automated geometric and functional characterization of miniaturized lenses using optical coherence tomography-based systems and wavefront sensors 10

Fast, semi-automated geometric and functional characterizati...

引用

10th European Seminar on Precision Optics Manufacturing

作者： Iturbide, Alfredo Velazquez Schmitt, Robert Fraunhofer Institute for Production Technology IPT Steinbachstr. 17 Aachen52074 Germany Laboratory for Machine Tools and Production Engineering WZL of RWTH Aachen University Campus-Boulevard 30 Aachen52074 Germany

ISBN: (数字)9781510667594

ISBN: (纸本)9781510667587

Miniaturized lenses are increasingly utilized in a range of applications, including medical devices, optical communication, and imaging systems. The characterization of these lenses is crucial as their performance is highly dependent on their geometrical and functional properties. However, the small size of these lenses coupled with the required short measurement times, presents a significant challenge for conventional measurement techniques. Recent advances in optical coherence tomography (OCT) and Shack Hartmann wavefront sensors (SHWS) have enabled rapid, semi-automated geometric and functional characterization of miniaturized lenses when appropriate hardware, software, and algorithms are integrated. OCT is a non-invasive imaging technique that can provide high-resolution cross-sectional images of the lens, allowing the accurate measurement of its central thickness, curvature, and other geometric parameters of both surfaces. Moreover, SHWS can be used to measure the transmitted wavefront error of the lens, which is directly related to its optical performance. In this paper, we demonstrate the use of OCT and SHWS to characterize polymer and glass lenses with diameters and thicknesses of a few millimeters with spherical and aspherical shapes. Our results show that OCT is capable of accurately measuring the central thickness and surface profile of the lenses, while SHWS provides information on their wavefront aberrations. By combining these two techniques, we were able to obtain a com-prehensive characterization of the lenses' geometrical and functional properties. © 2023 SPIE.

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

Assessment Framework for Deployability of machine Learning Models in Production 16

Assessment Framework for Deployability of Machine Learning M...

引用

16th CIRP Conference on Intelligent Computation in Manufacturing Engineering, CIRP ICME 2022

作者： Heymann, Henrik Mende, Hendrik Frye, Maik Schmitt, Robert H. Fraunhofer Institute for Production Technology IPT Steinbachstr. 17 Aachen52074 Germany Laboratory for Machine Tools and Production Engineering WZL RWTH Aachen University Campus-Boulevard 30 Aachen52074 Germany

Deploying machine learning (ML) models in production environments comes with challenges such as the model's integration into live production and the missing trust of process experts in new technologies. These challenges must be addressed already in phases ahead of the deployment. Therefore, this paper aims to clarify how to ensure the deployability of methods used during model development. For this purpose, criteria for measuring and evaluating deployability in manufacturing environments are defined. A subsequent analysis of existing data preprocessing methods and ML algorithms regarding deployability as well as deployment options serves to counteract deployment issues early on in an ML project. © 2023 Elsevier B.V.. All rights reserved.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Efficient data acquisition for traceability and analytics

引用

Procedia CIRP 2024年 122卷 73-78页

作者： Heiner Reinhardt Mahtab Mahdaviasl Bastian Prell Anton Mauersberger Philipp Klimant Jörg Reiff-Stephan Steffen Ihlenfeldt Fraunhofer Institute for Machine Tools and Forming Technology IWU Reichenhainer Straße 88 09126 Chemnitz Germany Technical University of Applied Sciences Wildau Hochschulring 1 15745 Wildau Germany Professorship Virtual Technologies Hochschule Mittweida - University of Applied Sciences Technikumplatz 17 09648 Mittweida Germany Institute of Machine Tools and Control Engineering Technische Universität Dresden 01062 Dresden Germany

Implementing processes for traceability is required in various industries to assure product quality during manufacturing, provide evidence on required processing conditions or facilitate product recalls. Commonly, radio-frequency identification (RFID) or code recognition techniques (e.g. Data Matrix) are applied to track the flow of workpieces through a manufacturing system and link processing data accordingly. Although the analysis of tracking data is well-examined, we still see a gap in the research on the trade-off between data acquisition, data analytics and data quality. Here, we present a framework to increase the value of existing data by enabling data analytics while addressing common pitfalls and reducing the costs of data management.

关键词： Identification Knowledge management Manufacturing system Process control Quality assurance Sustainable development Decision making Complexity Analysis Design

来源：评论

学校读者我要写书评

暂无评论

Influence Estimation In Multi-Step Process Chains Using Quantum Bayesian Networks

Influence Estimation In Multi-Step Process Chains Using Quan...

引用

2022 Informatik in den Naturwissenschaften, INFORMATIK 2022 - 2022 Computer Science in the Natural Sciences, INFORMATIK 2022

作者： Selch, Maximilian Müssig, Daniel Hänel, Albrecht Lässig, Jörg Ihlenfeldt, Steffen Fraunhofer Institute for Machine Tools and Forming Technology IWU Department Digital Production Twin Nöthnitzer Straße 44 Dresden01187 Germany Fraunhofer IOSB Branch Advanced System Technologies IOSB-AST Cognitive Energy Systems Wilhelmsplatz 11 Görlitz02826 Germany

ISBN: (纸本)9783885797203

Digital representatives of physical assets and process steps play a decisive role in analysing properties and evaluating the quality of the process. So-called digital twins acquire all relevant planning and process data, which provide the basis, for example, to investigate path accuracies in manufacturing. Each single process step aims to perform an ideal machining after the specification of a target geometry. However, the practical implementation of a step usually shows deviations from the targeted shape. The machine-learning based method of probabilistic Bayesian networks enables the quality estimation of the holistic process chain as well as improvements by targeted considerations of single steps and influence factors. However, the handling of large-scale Bayesian networks requires a high computational effort, whereas the processing with quantum algorithms holds potential improvements in storage and performance. Based on the issue of path accuracy, this paper considers the modelling and influence estimation for a milling operation including experiments on superconducting quantum hardware. © 2022 Gesellschaft fur Informatik (GI). All rights reserved.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Force-controlled burnishing process for high surface integrity on additive manufactured parts

引用

Procedia CIRP 2022年 108卷 642-647页

作者： Martin Dix Marco Posdzich Chemnitz University of Technology Institute for Machine Tools and Production Processes (IWP) Reichenhainer Str. 70. 09126 Chemnitz Germany Fraunhofer Institute for Machine Tools and Forming Technology (IWU) Reichenhainer Str. 88. 09126 Chemnitz Germany

Additive manufactured components provide a new level of shape flexibility. However, this process has shortcomings in surface quality and dimensional accuracy. As a result post-processing is often necessary. In this paper, a combined finishing operation of machining shaping and force-controlled burnishing is used for prismatic form elements. Therefore, a corresponding control strategy was implemented for this on a CNC machine tool. The focus lies on the process characteristics between the pre-machined surface structures and the force-controlled machining and in the resulting surface properties. The aim of the work is the investigation and application of the process combination on additive manufactured metallic structural elements.

关键词： additive manufacturing force control surface modification finishing process combination

来源：评论

学校读者我要写书评

暂无评论

Synthetically Generated Images for Industrial Anomaly Detection

Synthetically Generated Images for Industrial Anomaly Detect...

引用

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： Marco Wagenstetter Petra Gospodnetic Lovro Bosnar Juraj Fulir Donovan Kreul Holly Rushmeier Thomas Aicher Arvid Hellmich Steffen Ihlenfeldt Powertrain Production System Planning BMW Group Germany Synthetic Data Generation Fraunhofer ITWM Germany Synthetic Data Generation Yale University USA Machine tools and forming technology Fraunhofer IWU Germany

ISBN: (数字)9798350361230

ISBN: (纸本)9798350361247

Automation of inspection for quality control is needed to overcome the errors and delays inherent in manual processes. machine learning methods have the potential to greatly improve automated inspection. However, machine learning techniques require training data that are precisely labeled and reflect the distribution of defects to be detected. Physically collecting suitable training data requires significant time and prolongs the overall time for system development. To address this challenge, a new study is presented that explores synthetic data generation for a state-of-the-art anomaly detection (AD) model in the electric motor housing (EMH) surface inspection. The study successfully demonstrates using synthetic data for anomaly detection and presents a comparison of detection performance by models trained solely on synthetic data and models trained on both synthetic and real data. The study shows that real data combined with synthetic data can increase overall model performance. The study also addresses current challenges in using synthetic data and proposes directions for future work.

关键词： Training Visualization Training data machine learning Quality control Inspection Data models Anomaly detection Synthetic data Electric motors

来源：评论

学校读者我要写书评

暂无评论

Reaming of carbon fibre reinforced plastics: Influence of tool geometry on process forces and tool wear 14

Reaming of carbon fibre reinforced plastics: Influence of to...

引用

14th CIRP Conference on Intelligent Computation in Manufacturing Engineering, CIRP ICME 2020

作者： Sauer, Konstantin Putz, Matthias Chemnitz University of Technology Reichenhainer Strasse 70 Chemnitz09126 Germany Fraunhofer Institute for Machine Tools and Forming Technology Reichenhainer Strasse 88 Chemnitz09126 Germany

Due to the high abrasive wear and the tendency to workpiece damages, the manufacturing of high-quality bores in carbon fibre reinforced plastics (CFRP) is still one of the major goals in tool development. In this work, reaming tests are performed on CFRP in order to characterise the relationship between tool geometry, process forces and tool wear. After a preliminary investigation of a taper reamer, diverse carbide tools have been tested which exhibit different values of rake and clearance angle. The forces measurement took place using a rotating dynamometer, while the evaluation of the tool wear has been realised by microscopic images via structured light projection. Different forms of wear appear, while hardly any differences in the force curves can be detected when applying different angles of the cutting wedge. © 2021 The Authors. Published by Elsevier B.V.

关键词： Carbon fiber reinforced plastics

来源：评论

学校读者我要写书评

暂无评论

Disassembly technologies for PEMFC stacks in heavy-duty applications 10

Disassembly technologies for PEMFC stacks in heavy-duty appl...

引用

10th CIRP Conference on Assembly technology and Systems, CATS 2024

作者： Oldewurtel, Sven Wagner, Arne Imdahl, Christoph Zellmer, Sabrina Dröder, Klaus Fraunhofer Institute for Surface Engineering and Thin Films IST Riedenkamp 2 Braunschweig38108 Germany Technische Universität Braunschweig Institute of Machine Tools and Production Technology Langer Kamp 19b Braunschweig38106 Germany Technische Universität Braunschweig Institute for Particle Technology Volkmaroder Straße 4 Braunschweig38104 Germany

Hydrogen is one of the most promising solutions for decarbonising the industrial sector, particularly the chemical and steel industries. To utilise hydrogen as a mobile energy carrier in heavy-duty applications such as transportation, it is necessary to convert the chemically bound energy into electrical energy to power electrical systems. Fuel cell technologies, in particular Proton Exchange Membrane Fuel Cells (PEMFC), are crucial in this regard, as they efficiently convert hydrogen and oxygen into electricity and water. It is expected that production capacity will continue to grow, especially in the heavy-duty sector, and that the need for development will increase significantly. As a result, larger numbers of PEMFCs will reach the end of their life cycle. Successful closed-loop production requires optimising material use, making production processes more efficient, and recovering valuable materials. In order to optimise material, use and recover valuable resources such as platinum and fluorine-containing polymers and extend the product life cycle through reuse, aspects such as disassembly, reuse, remanufacturing and recycling must be considered before mass production. This publication aims to provide an overview of disassembly strategies and technologies for PEMFC stacks used in heavy-duty applications. It analyzes the general structure and layout of PEMFC stacks, with a focus on the Bipolar Plate (BPP), the Membrane Electrode Assembly (MEA) and the gaskets or seals. Various materials and designs of these components result in a wide spectrum of requirements regarding the handling and disassembly technologies. The outcome is a matrix show casing potential disassembly technologies for common PEMFC stack layouts, along with the expected limitations arising from different component and material combinations and their characteristics. The results of these investigations enable a more efficient development of automated disassembly processes for PEMFCs by providing app

关键词： Proton exchange membrane fuel cells (PEMFC)

来源：评论

学校读者我要写书评

暂无评论

Prototype fabrication of complex cooling channels by potting, additively manufactured inserts in an electric motor

Prototype fabrication of complex cooling channels by potting...

引用

International Electric Drives Production Conference (EDPC)

作者： Leonard John Steffen Reuter Dina Becker Hans-Christian Möhring Rocco Eisseler Martin Doppelbauer Fraunhofer Institute for Chemical Technology Karlsruhe Germany Institute for Machine Tools University of Stuttgart Stuttgart Germany

Embedding additively manufactured tube structures into the resin encapsulation of high-power electrical devices promises great theoretical benefits for increasing heat dissipation and thus power density. In the considered project, channels were integrated into the potting of a slot-cooled electric motor to enable a three-dimensional coolant flow at the winding *** thin-walled insert consisting of 34 channels in a ring structure with closed endcaps was manufactured using the additive LPBF process. In this context, various support structures were tested and evaluated in advance with regard to their suitability for process-stable separation of the printed component from the build platform. The insert investigated was then printed from steel metal powder with linear support structures. The separation from the build platform took place by circular milling using a specially developed clamping system. The cooling channels were then opened by drilling through existing cooling channels in the resin. The trapped metal powder inside is removed and investigated for recyclability. The potting of the motor windings is done with a polyurethan resin with fillers to enhance the thermal conductivity. As the water-based coolant is directly in touch with the potting material, properties as the permeability to water due to cracks or gas bubbles and O-ring sealing interface behavior were considered in the material selection. The vacuum potting process was done in a throw flow potting tool.

关键词：

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：