检索结果-内蒙古大学图书馆

24th International ESAFORM Conference on Material forming, ESAFORM 2021

作者： Weiser, Ingo Felix Mannens, Robby Feuerhack, Andreas Bergs, Thomas Laboratory for Machine Tools and Production Engineering WZL of RWTH Aachen University Campus-Boulevard 30 AachenD-52074 Germany Fraunhofer-Institute for Production Technology IPT Steinbachstr. 17 AachenD-52074 Germany

ISBN: (纸本)9782870193020

Fine blanking is a highly productive process of industrial mass production with which high quality components in particular but not exclusively for the automotive industry are produced. The manufacturing process faces its limits at elevated tensile strengths of the materials to be processed. Consequently, high-strength steels can currently only be fine blanked to a limited extent. This can be overcome by lowering the flow stress of high-strength steels by means of inductive heating. A steel of high importance especially for industries with high hygiene standards such as medical and nutrition production is the stainless steel X5CrNi18-10 (1.4301). As a metastable austenitic steel which can initiate cutting impact on the press through martensitization, fine blanking of stainless steel is a challenge. X5CrNi18-10 is not a high-strength steel per se but becomes difficult to process due to the high hardness of the martensite phase, known as transformation-induced plasticity (TRIP) effect. Thus, in order to combine the possible advantages of the fine blanking process with inductive heating and the important properties of stainless steel, fine blanking of this steel was investigated with inductive heating prior to the fine blanking. The process forces and product quality properties such as die roll were investigated and found to be advantageous in comparison to non-heated fine blanking specimens of the same steel. The process forces and the die roll height decreased due to the heating. © ESAFORM 2021 - 24th Inter. Conf. on Mat. forming. All rights reserved.

关键词： High strength steel

来源：评论

学校读者我要写书评

暂无评论

Discomfort Detection During Automated Driving Using Temporal Transformers

SSRN

引用

SSRN 2025年

作者： Assarzadeh, Maha Hartwich, Franziska Vitay, Julien Bocklisch, Franziska Hamker, Fred H. Artificial Intelligence Computer Science Chemnitz University of Technology Chemnitz Germany Fraunhofer Institute for Machine Tools and Forming Technology Chemnitz Germany Materials and Surface Engineering Group Chemnitz University of Technology Chemnitz Germany

With the recent breakthroughs in driving automation and the development of smart vehicles, human-technology interaction issues, such as detecting comfort levels in automated driving, have been gaining increasing attention. We assessed a passenger’s discomfort level in a smart, automated vehicle using physiological, environmental, and vehicle automation features from different sensors. Given the evidence of discomfort levels being an evolving psychological state in time, the tracking of discomfort levels for passengers of an automated vehicle can be considered a time-varying phenomenon. Our approach is to dynamically predict discomfort levels using time-dependent models, particularly the Temporal Fusion Transformer (TFT), an advanced attention-based deep learning architecture providing an interpretable explanation of temporal dynamics as well as high-performance forecasting over multiple horizons. The models are trained and evaluated using a dataset of 100 participants of a simulated automated driving experiment, during which they signaled their level of discomfort using a manual device. Two TFT models, TFT-full and TFT-restricted, are investigated depending on which physiological, environmental, and vehicle automation signals are used as inputs. The results are compared with the auto-regressive model DeepAR. Different window sizes are used to analyze the impact of the window size on the model’s performance. Among the tested models, TFT-restricted with a window size of 300-time steps (about 5 seconds) demonstrates the best performance in predicting discomfort levels on our data, with a mean absolute error (MAE) of 0.037 and a root mean square error (RMSE) of 0.131. © 2025, The Authors. All rights reserved.

关键词： Physiological models

来源：评论

学校读者我要写书评

暂无评论

Residual stress assessment during cutting tool lifetime of CVD-diamond coated indexable inserts

引用

Procedia CIRP 2022年 108卷 799-804页

作者： E. Uhlmann D. Hinzmann 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

Insufficient coating adhesion limits reproducibility regarding tool lifetime as well as workpiece quality during the application of CVD-diamond coated cutting tools. Depending on the combination of tungsten carbide substrate material, coating thickness as well as coating morphology, individual residual stress conditions exist within CVD-diamond coated cutting tool specifications. The application of these tools is accompanied by coating delamination as primary cutting tool failure. The tool lifetime of the respective cutting tool composition depends on the corresponding residual stress condition until crack development within the CVD-diamond coating initiates tool failure. During external cylindrical turning of hypereutectic aluminium silicon alloy AlSi17Cu4Mg-T6 the residual stress condition of a CVD-diamond coated cutting tool is assessed along the cutting edge, the rake face as well as flank face throughout the respective tool lifetime. Consequently, the progression of the residual stress condition until cutting tool failure regarding coating delamination is observed. During the tool lifetime of the investigated CVD-diamond cutting tools, compressive residual stress ∆σ R,c shifts to tensile residual stress ∆σ R , t underneath the cutting edge corner. The approximated residual stress difference of ∆σ R ≈ 5 GPa indicates stress peak relaxation processes, such as crack initiation, within the CVD-diamond coating.

关键词： diamond tool residual stress aluminum turning

来源：评论

学校读者我要写书评

暂无评论

Experimental investigations of the workpiece-media-interaction and the surface topography formation in centrifugal disc finishing

引用

Procedia CIRP 2022年 115卷 24-29页

作者： Marco Kopp Eckart Uhlmann Christian Kneider 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

In this study the workpiece-media-interaction in centrifugal disc finishing is investigated using a miniaturised free movable force measuring system. Characteristics of the workpiece-media-interaction are derived and correlated with the surface topography formation of Ti-6Al-4V workpieces. As a result, it was found that characteristics of the workpiece-media-interaction such as the contact force between the media and the workpiece, the contact duration and the contact frequency are dependent on the type of media as well as the rotational speed of the disc. Consequently, both, the type of media as well as the rotational speed of the disc have an influence on the resulting surface roughness.

关键词： centrifugal disc finishing contact forces topography formation

来源：评论

学校读者我要写书评

暂无评论

Decision Approach for the Design and Sensor Integration of an LPBF Manufactured Gripper End Effector 54

Decision Approach for the Design and Sensor Integration of a...

引用

54th CIRP Conference on Manufacturing Ssystems, CMS 2021

作者： Schuh, Günther Bergweiler, Georg Zäpfel, Martin Salian, Anurag Bickendorf, Philipp Fraunhofer Institute for Casting Composite and Processing Technology IGCV Am Technologiezentrum 10 Augsburg86159 Germany Laboratory for Machine Tools and Production Engineering WZL RWTH Aachen University Campus-Boulevard 30 Aachen52074 Germany

In the context of increasing digitalisation of production, more and more data is required, while demands on the handling of production resources e.g. gripper for industrial robots are increasing. Currently, the potential of captured data is not being exploited and hardly any data is used with the help of production resources. In this paper, a decision process for the integration of a temperature sensor in Laser Powder Bed Fusion (LPBF) printed end effectors which considers all steps of the design is presented. The result is a 3D-printed adapted design of an end effector which is optimised regarding the requirement profile. © 2021 Elsevier B.V.. All rights reserved.

关键词： Grippers

来源：评论

学校读者我要写书评

暂无评论

Development of a New Self-flaring Rivet Geometry Using Finite Element Method and Design of Experiments

引用

Procedia Manufacturing 2020年 47卷 383-388页

作者： Christian Kraus Tobias Falk Reinhard Mauermann Welf-Guntram Drossel Fraunhofer Institute for Machine Tools and Forming Technology IWU Nöthnitzer Straße 44 Dresden 01187 Germany

The paper presents a new joining process for mixed joints of metallic and non-metallic materials. The process bases on a self-flaring rivet, which lances the joining partners and, due to its geometry, produces an interlock. In contrast to conventional self-piercing processes such as self-pierce riveting with semi-tubular rivets (SPR), the new process does not require a special shaped die as counter tool. The development of the rivet geometry is carried out with the aid of FEM analyses in SFTC Deform-3D. Design of experiments (DoE) is used to find a suitable rivet geometry that is stable enough to lance high-strength steel. However, the rivet element must be flaring to produce an interlock. The challenges and solution approaches associated with the modelling of material damage and separation in the three-dimensional calculation models of the riveting process are presented. The consideration of macromechanical and geometrical criteria for element deletion is important in order to obtain robust models with useful results. The validation of the model is done by comparing the simulation results with experimental data.

关键词： Mechanical Joining Finite Element Method Design of Experiments

来源：评论

学校读者我要写书评

暂无评论

Integrating deep learning and rule-based systems into a smart devices decision support system for visual inspection in production 32

Integrating deep learning and rule-based systems into a smar...

引用

32nd CIRP Design Conference, CIRP Design 2022

作者： Mende, Hendrik Peters, Alexander Ibrahim, Faruk Schmitt, Robert H. Fraunhofer Institute For Production Technology Ipt Steinbachstraße 17 Aachen52074 Germany Laboratory For Machine Tools And Production Engineering Wzl Of Rwth University Campus-Boulevard 30 Aachen52074 Germany University Of Applied Sciences Düsseldorf Faculty Of Mechanical And Process Engineering Münsterstraße 156 Düsseldorf40476 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. © 2022 The Authors.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Influence of superimposed low frequency oscillations on single-pass honing of long-chipping steel

引用

Procedia CIRP 2022年 108卷 607-612页

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

Single-pass honing is used as a finishing process to meet high demands regarding form and dimensional accuracy of drilled bores. The disadvantages of single-pass honing compared to the conventional long-stroke honing are high process forces and torques as well as an increased risk of chip space clogging of the abrasive stones. A significant reduction in process forces and torques can be achieved by superimposing the axial movement with oscillations. In this work the kinematic basics of different oscillation parameters and their effects on single-pass honing of long-chipping steel are analyzed. It can be concluded that by superimposing low frequency oscillations in single-pass honing, the process forces and torques as well as the specific energy consumption can be reduced significantly without a decline in surface quality and form accuracy.

关键词： Surface Finish Honing Oscillation

来源：评论

学校读者我要写书评

暂无评论

Influence of the weld pool geometry on solidification cracking in partial penetration high power laser beam welding

引用

Procedia CIRP 2022年 111卷 397-400页

作者： Nasim Bakir Ömer Üstündag Andrey Gumenyuk Michael Rethmeier 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

Solidification cracking is still a serious problem in laser beam welding, especially in the welding of thick-walled plates. The influence of weld pool geometry on solidification cracking in partial penetration welding of thick plates is investigated within scope of this study. Therefore, a specific experimental setup of steel and quartz glass in butt configuration and on the side with high-speed camera were used to record the weld pool shape. In addition, the influence of laser inclination angle on the weld pool geometry and on solidification crack formation was investigated. The results show a bulge in the weld pool root, which is separated from an upper region by a necking region. This leads to a case where there are three different longitudinal region lengths with different solidification zones. This temporal sequence of solidification strongly promotes the formation of solidification cracks in the weld root.

关键词： Laser beam welding (LBW) solidification cracking partial penetration weld pool shape

来源：评论

学校读者我要写书评

暂无评论

Digitized, networked optics production

引用

Procedia CIRP 2022年 111卷 827-831页

作者： Jonas Dorißen Cornelia Rojacher Tim Grunwald Robert H. Schmitt Thomas Bergs Fraunhofer Institute for Production Technology IPT Steinbachstraße 17 52074 Aachen Germany Laboratory for Machine Tools and Production Engineering (WZL) of RWTH Aachen University Campus-Boulevard 30 52074 Aachen Germany

The increasing demands on the quality of high-precision optical components mean that established manufacturing processes are reaching their technical limits. While individual processes can therefore hardly be improved any more, networking production machines digitally throughout the entire process chain offers high potential for meeting the tight tolerances in the optics industry and increasing the production output. To gain these benefits, first, an infrastructure is needed, containing a flexible and module data structure to satisfy different requirements from the processes. Second, the idea of offering services such as initial data analytics, artificial intelligence (AI) and machine learning (ML) must be integrated. In this paper, we present a digital infrastructure, that contains data from the entire process chain of glass and polymer optics production including simulation, process and measurement data. Services to optimize the production process are integrated and provide an outlook on how AI/ML can be added.

关键词： digitalization production optics manufacturing AI ML

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：