检索结果-内蒙古大学图书馆

Integrating deep learning and rule-based systems into a smart devices decision support system for visual inspection in production

引用

Procedia CIRP 2022年 109卷 305-310页

作者： Hendrik Mende Alexander Peters Faruk Ibrahim Robert H. Schmitt Fraunhofer Institute for Production Technology IPT Steinbachstraße 17 52074 Aachen Germany Laboratory for Machine Tools and Production Engineering WZL of RWTH University Campus-Boulevard 30 52074 Aachen Germany University of Applied Sciences Düsseldorf Faculty of Mechanical and Process Engineering Münsterstraße 156 40476 Düsseldorf Germany

Due to the increasing implementation of cyber physical systems and the internet of things in industry, there is a trend towards flexible, multi-variant production with a very high degree of automation to strengthen the resilience of the company. Each variant is subject to high quality requirements that must be checked to ensure quality. A common means for this is quality assurance through visual inspections, which are carried out manually. Visual inspections are time-consuming yet prone to wrong decisions, since they are subjective, inconsistent, and susceptible to uncertainties. The quality of the inspection relies heavily on the experience of the personnel. This work addresses this issue through the concept and design of a system for objective decision making in visual inspection by integrating Deep Learning (DL) models with a Belief Rule Based Expert System (BRBES) inside a smart devices application. Smart devices like tablets and smartphones serve to generate information by recording and evaluating image material of the components being inspected. Based on this data, DL models are trained and used to classify defects on new image material to automate part of the inspection process. Furthermore, smart devices serve to provide context-dependent decision recommendations in the visual inspection process, which were calculated by the BRBES with the inclusion of uncertainties. The knowledge base of the BRBES is fed by the expert knowledge of experienced visual inspectors using knowledge elicitation techniques. In this way, the system can enable optimized and objectified visual inspection based on the data-driven and knowledge-driven approaches used. This paper outlines the concept of integrating DL and BRBES into a smart devices decision support system.

关键词： deep learning belief rule-based expert system rule-based system visual inspection decision support smart devices production quality assurance

来源：评论

学校读者我要写书评

暂无评论

Prediction of temperature distribution in diamond cutting tools during machining Ti-6Al-4V

引用

Procedia CIRP 2021年 102卷 37-42页

作者： E. Uhlmann D. Schröter V.H. Wohlfahrt Technische Universität Berlin Institute for Machine Tools and Factory Management (IWF) Pascalstr. 8-9 10587 Berlin Germany Fraunhofer Institute for Production Systems and Design Technology (IPK) Pascalstr. 8-9 10587 Berlin Germany

The high thermal conductivity and wear resistance of CVD diamond provide potential for the machining of Ti-6Al-4V. By predicting thermomechanical loads, simulations can provide information about the usability of these cutting materials. However, the occurring shear chip formation within the cutting process leads to unsteady contact conditions. Therefore, a computationally intensive long-term transient simulation is necessary for precise prediction of tool temperatures. In this respect, a user-subroutine has been developed, allowing a high-resolution long-term simulation with acceptable computing time. By experimental investigations and validation of simulated results, a modelling of temperature distribution within the cutting tool is possible, providing valuable information regarding the contact temperatures.

关键词： titanium diamond tool turning temperature

来源：评论

学校读者我要写书评

暂无评论

Micro-texture trajectory dependent pressure distribution of CVD diamond thick film cutting tools during turning of Ti-6Al-4V

引用

Procedia CIRP 2021年 102卷 49-54页

作者： E. Uhlmann D. Schröter Technische Universität Berlin Institute for Machine Tools and Factory Management (IWF) Pascalstr. 8-9 10587 Berlin Germany Fraunhofer Institute for Production Systems and Design Technology (IPK) Pascalstr. 8-9 10587 Berlin Germany

To counteract the high thermomechanical load during turning Ti-6Al-4V, an advancement of tool geometries is necessary. Based on simulative and empirical analysis, the present study investigates the process behaviour of micro-textured CVD diamond cutting tools. Different micro-texture trajectories determine influence of the microstructure on the stress levels, pressure distributions and adhesive wear. Compared to non-textured cutting tools, a cutting force reduction of 12.8 % determined empirically and 19.5 % determined simulatively with simultaneous displacement of the principal stress results using micro-textures. Based on simulatively calculated process forces and pressure distributions an evaluation of tool stability and adhesion tendency is possible.

关键词： diamond tool texture finite element method (FEM) titanium turning

来源：评论

学校读者我要写书评

暂无评论

Influence of a Hydrostatic Pressure Shift on the Flow Stress in Sheet Metal

引用

Procedia Manufacturing 2020年 47卷 1245-1249页

作者： Sam Coppieters Mathias Jackel Christian Kraus Toshihiko Kuwabara Frederic Barlat KU Leuven Technology Campus Ghent Ghent Belgium Fraunhofer Institute for Machine Tools and Forming Technology IWU Dresden Germany Tokyo University of Agriculture and Technology Tokyo Japan GIFT-POSTECH Pohang Republic of Korea

The stack compression test (SCT) and the strain-rate controlled hydraulic bulge test (HBT) enable to determine the large strain flow curve of sheet metal under an identical deformation mode and balanced biaxial tension. This equivalence should lead to identical flow behavior if plastic yielding is independent of the hydrostatic stress. However, a discrepancy is observed in the flow curves of DP600 steel sheet determined by the SCT and the HBT. In order to avoid uncertainty with respect to dissimilar test conditions, the average strain-rate in both material tests is carefully controlled. Additionally, evidence is provided that friction can be sufficiently minimized yielding a homogeneous SCT up to a true plastic strain of 0.3. Assuming reliable experimental data, the hypothesis that the hydrostatic pressure shift between the stress states in the SCT and the HBT causes the observed difference in flow behavior is scrutinized. Theoretical considerations regarding the effect of a superimposed hydrostatic pressure (i.e. putting a material under a pressure environment for a certain stress state) on the flow stress, as suggested by Spitzig et al. [1] and Spitzig and Richmond [2], are used to understand the effect of a pressure shift between two stress states on the flow stress. Finally, the theoretical considerations are experimentally validated using the discrepancy in flow behavior of DP600 measured by the SCT and the HBT.

关键词： sheet metal stack compression test hydraulic bulge test pressure dependency

来源：评论

学校读者我要写书评

暂无评论

Improvement of Charpy impact toughness by using an AC magnet backing system for laser hybrid welding of thick S690QL steels

引用

Procedia CIRP 2022年 111卷 462-465页

作者： Ömer Üstündag Nasim Bakir Andrey Gumenyuk Michael Rethmeier Bundesanstalt für Materialforschung und -prüfung (BAM) Unter den Eichen 87 12205 Berlin Germany Fraunhofer Institute for Production Systems and Design Technology Pascalstraße 8-9 10587 Berlin Germany Institute of Machine Tools and Factory Management Technische Universität Berlin Pascalstraße 8-9 10587 Berlin Germany

The study deals with the influence of the heat input and the resulting cooling times on the microstructure and Charpy impact toughness of single-pass laser hybrid welded 20-mm thick high-strength steel S690QL. The main focus is on the change of the mechanical properties over the entire seam thickness. The cooling times were measured in-situ using a pyrometer and an optical fibre in three different depths of the seam where Charpy impact test specimens were also later taken. Thereby, three different heat inputs from 1.3 kJ/mm to 2 kJ/mm were investigated. Despite the observed decreased values of both t 8/5 -cooling time and the Charpy impact toughness in the root part of the seam, the required impact toughness of 38 J/cm 2 could be reached in dependance on applied heat input, especially at the heat input of 1.6 kJ/mm.

关键词： laser hybrid welding AC magnet backing Charpy impact toughness high-strength steel S690QL

来源：评论

学校读者我要写书评

暂无评论

DEMONSTRATING DATA-TO-KNOWLEDGE PIPELINES FOR CONNECTING PRODUCTION SITES IN THE WORLD WIDE LAB A PREPRINT

arXiv

引用

arXiv 2024年

作者： Gorisen, Leon Schneider, Jan-Niklas Behery, Mohamed Brauner, Philipp Lennartz, Moritz Kotter, David Kaster, Thomas Petrovic, Oliver Hinke, Christian Gries, Thomas Lakemeyer, Gerhard Ziefle, Martina Brecher, Christian Hafner, Constantin Chair for Laser Technology RWTH Aachen University Aachen52074 Germany Knowledge Based Systems Group RWTH Aachen University Aachen52074 Germany Communication Science RWTH Aachen University Aachen52074 Germany Chair of Textile Technology RWTH Aachen University Aachen52074 Germany Laboratory for Machine Tools and Production Engineering RWTH Aachen University Aachen52074 Germany Human Computer Interaction Center RWTH Aachen University Aachen52074 Germany Fraunhofer Institute for Laser Technology Aachen52074 Germany

The digital transformation of production requires new methods of data integration and storage, as well as decision making and support systems that work vertically and horizontally throughout the development, production, and use cycle. In this paper, we propose Data-to-Knowledge (and Knowledge-to-Data) pipelines for production as a universal concept building on a network of Digital Shadows (a concept augmenting Digital Twins). We show a proof of concept that builds on and bridges existing infrastructure to 1) capture and semantically annotates trajectory data from multiple similar but independent robots in different organisations and use cases in a data lakehouse and 2) an independent process that dynamically queries matching data for training an inverse dynamics foundation model for robotic control. The article discusses the challenges and benefits of this approach and how Data-to-Knowledge pipelines contribute efficiency gains and industrial scalability in a World Wide Lab as a research outlook. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Digital service application for the recalibration of a machine tool through Augmented Reality-supported data acquisition

引用

IOP Conference Series: Materials Science and Engineering 2022年第1期1235卷

作者： F Arnold G Lemme M Hess S Witt S Ihlenfeldt Institute of Mechatronic Engineering Chair of Machine Tools Development and Adaptive Controls TU Dresden Germany Fraunhofer Institute for Machine Tools and Forming Technology (IWU) Dresden Germany Software AG Darmstadt Germany METROM Mechatronische Maschinen GmbH Hartmannsdorf Germany

The effort for checking and correcting the spatial movement accuracy of a processing machine with 5 axes is very high. Calibration and recalibration must be carried out directly on the machine by the machine supplier or a company specializing in this. This is associated with high personnel and long machine downtimes. These constraints can be improved by using modern methods. A consistent approach of an AR-supported measurement procedure for the preparation and execution of a required measurement run and the execution of the calibration itself as a digital service is presented. This enables rapid execution by the machine operator himself using a DoubleBallBar measurement system without the need of the presence of the machine manufacturer. The determination of the calibration parameters on the basis of the measurement data is then carried out by the machine manufacturer and provided as a service. The basis for such a secure and auditable service is a digital service platform. This serves as an intermediary between the user and the machine manufacturer and uses distributed ledger technology. The approach presented is the subject of current development work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Working Gap Analysis in Electrochemical Precision Machining of External Geometries with Ring Cathodes

引用

Procedia CIRP 2020年 95卷 662-667页

作者： Ingo Schaarschmidt Matthias Hackert-Oschätzchen Gunnar Meichsner Philipp Steinert Mike Zinecker Andreas Schubert Professorship Micromanufacturing Technology Chemnitz University of Technology 09107 Chemnitz Germany Chair of Manufacturing Technology with Focus Machining Otto von Guericke University Magdeburg 39106 Magdeburg Germany Fraunhofer Institute for Machine Tools and Forming Technology 09126 Chemnitz Germany

Pulsed electrochemical machining (PECM) with oscillating cathode is a non-conventional manufacturing technology to machine complex precision geometries independent from the mechanical properties of the workpiece material. PECM with oscillating cathode is an advanced development of conventional ECM by applying a pulsed electric current in conjunction with an oscillating movement of the cathode. Result is electrochemical precision machining with a more stable process combined with better accuracy and quality. This work focuses on the analysis of the resulting side working gap in electrochemical precision machining of external geometries by applying PECM. Therefore, the height of a ring cathode was varied to adjust the cathode inner surface. The resulting side working gap was studied through multiscale multiphysics simulation applying COMSOL Multiphysics as well as experiments applying a PEMCenter 8000. As main result, the increase of the resulting side working gap as consequence of an increasing cathode inner surface will be analysed in detail.

关键词： Pulsed electrochemical machining (PECM) Side working gap Multiscale multiphysics modelling

来源：评论

学校读者我要写书评

暂无评论

Data Mining and machine Learning Methods Applied to A Numerical Clinching Model

引用

Computer Modeling in Engineering & Sciences 2018年第12期117卷 387-423页

作者： Marco Gotz Ferenc Leichsenring Thomas Kropp Peter Müller Tobias Falk Wolfgang Graf Michael Kaliske Welf-Guntram Drossel Institute for Structural Analysis Technische UniversitatDresdenGermany Fraunhofer Institute for Machine Tools and Forming Technology DresdenGermany

Numerical mechanical models used for design of structures and processes are very complex and high-dimensionally *** understanding of the model characteristics is of interest for engineering tasks and subsequently for an efficient *** analysis methods are known and available to gain insight into existing *** this contribution,selected methods from various fields are applied to a real world mechanical engineering example of a currently developed clinching *** selection of introduced methods comprises techniques of machine learning and data mining,in which the utilization is aiming at a decreased numerical *** methods of choice are basically discussed and references are given as well as challenges in the context of meta-modelling and sensitivities are *** incremental knowledge gain is provided by a step-bystep application of the numerical methods,whereas resulting consequences for further applications are ***,a visualisation method aiming at an easy design guideline is *** visual decision maps incorporate the uncertainty coming from the reduction of dimensionality and can be applied in early stage of design.

关键词： Design data mining computational intelligence meta-modelling permissible design space sensitivity analysis self-organizing maps inverse problem early stage of design clinching

来源：评论

学校读者我要写书评

暂无评论

Holistic Concept Towards a Reference Architecture Model for Predictive Maintenance

引用

Procedia CIRP 2021年 104卷 1430-1433页

作者： Eckart Uhlmann Julian Polte Nikolaos-Stefanos Koutrakis Fraunhofer Institute for Production Systems and Design Technology IPK Pascalstraße 8-9 10587 Berlin Germany Institute for Machine Tools and Factory Management (IWF) Technische Universität Berlin Pascalstraße 8-9 Berlin 10587 Germany

In the era of digital transformation of factories, one of the most challenging applications of the Industrial Internet of Things (IIoT) is predictive maintenance. This paper presents a holistic concept for predictive maintenance together with a reference architecture that includes data acquisition on the sensor level, edge computing and digital twin applications. For that purpose, condition-based maintenance, lifecycle monitoring and digital assistance systems are integrated to develop application-specific digital twins based on the proposed architecture, integrating heterogenous data sources in order to enhance the accuracy of the machine learning models. The concept is illustrated through an experimental use case.

关键词： Analytics Reference Architecture Digital Twin Predictive Maintenance IIoT machine Learning

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：