检索结果-内蒙古大学图书馆

56th CIRP International Conference on Manufacturing Systems, CIRP CMS 2023

作者： Koch, Paul Schlüter, Marian Thill, Serge Krüger, Jörg Fraunhofer Institute for Production and System Design Technology Pascalstraße 8-9 Berlin10587 Germany Donders Institute for Brain Cognition and Behavior Radboud University Nijmegen6525 HR Netherlands Technical University Berlin Institute for Machine Tools and Factory Management Pascalstraße 8-9 Berlin10587 Germany

Recently, deep neural networks achieved state-of-the-art results in the subject of 6D object pose estimation for robot manipulation. However, those deep learning methods require expensive training data. Current methods for cost reduction use synthetic data, but rely on expert knowledge and suffer from the domain gap when shifting to the real application. Here, we present a proof of concept for a novel approach towards generating annotated training data for 6D object pose estimation. This approach is designed for learning new objects in operational environments while requiring little interaction and no expertise on the part of the user. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the 56th CIRP International Conference on Manufacturing Systems 2023.

关键词： 6D Object Pose Estimation Artificial Intelligence Data Generation Robot Cognition Robotic Grasping

来源：评论

学校读者我要写书评

暂无评论

Intuitive toolpath planning in computer-aided manufacturing systems using artificial intelligence in a virtual reality environment

引用

Procedia CIRP 2024年 126卷 354-359页

作者： Lionel Damtew Philipp Ganser Tommy Venek Thomas Bergs Fraunhofer-Institute for Production Technology IPT Steinbachstr. 17 52074 Aachen Germany Laboratory for Machine Tools and Production Engineering (WZL) of RWTH Aachen University Campus-Boulevard 30 52074 Aachen Germany

CAM systems are widely used in many key industries and are essential for many machining processes such as 5-axis milling. For toolpath planning, state-of-the-art CAM systems require the user to enter many abstract parameters, making these systems difficult to use. This paper presents a more intuitive approach to toolpath planning. The approach uses convolutional neural networks to interpret user gestures in a virtual reality environment and predicts the values of the aforementioned parameters. The results show that many of these parameters can be extracted from user gestures with high accuracy, which can be used to greatly simplify toolpath planning.

关键词： toolpath planning virtual reality artificial intelligence machine learning computer-aided manufacturing milling 5-axis

来源：评论

学校读者我要写书评

暂无评论

A Systematic Literature Review for the Derivation of a Conceptual Design Framework for Platforms

引用

Procedia CIRP 2024年 128卷 573-578页

作者： M. Riesener M. Kuhn S. Schümmelfeder G. Schuh Laboratory of Machine Tools and Production Engineering (WZL) RWTH Aachen University Campus-Boulevard 30 52074 Aachen Germany Fraunhofer Institute for Production Technology IPT Steinbachstraße 17 52074 Aachen Germany

Business ecosystems and platforms are an omnipresent phenomenon in the current economic environment. In the course of this, market and competitive structures are undergoing a profound reinterpretation. While traditional industry structures rely on value creation within the boundaries of a company, platforms utilize an ecosystem of autonomous agents to create value. Thus, the platform and different stakeholders interact in order to incubate and coordinate an ecosystem. Shared, flexible value creation instead of a monolithic, rigid value chain, arranged to become the industry-defining premise. Platforms are the main reference point of value creation and delivery in many currently successful business models. Within different research contributions, the study of their characteristics diverge significantly. Within the framework of a design science research approach and through a systematic literature review combined with the realization of a taxonomic analysis of the term “platform” this contribution develops a systematization of the research area. This contribution develops a morphology of the conceptual design components “architecture, strategy and governance” and derives connected dimensions and characteristics in order to provide an ontology of design for companies and a unified understanding for further research initiatives. In addition, further necessary research approaches are identified as limitations.

关键词： Business Ecosystem Business Model Business Strategy Platform Governance Strategy Architecture Systematization

来源：评论

学校读者我要写书评

暂无评论

Layer-based information model for 5-axis milling processes using a GraphQL schema

引用

Procedia CIRP 2024年 126卷 384-389页

作者： Viktor Rudel David Wichter Sven Schiller Georg Vinogradov Aleksandra Müller Philipp Ganser 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 view of process-related information in NC-bound manufacturing technologies can range from a perspective of a single cutter location within a considered toolpath to aggregated data which represent the whole operation sequence of a manufacturing process. Data processing pipelines are often individually programmed for the process planning or machining stage addressing an isolated database abstraction layer. This paper proposes a data modeling approach based on a GraphQL schema empowering the user to query planning and actual process data cross-linked with different aggregation layers by a single request.

关键词： Information model data model Compuer Aided Manufacturing (CAM) GraphQL digital twin blisk 5-axis milling data processing

来源：评论

学校读者我要写书评

暂无评论

Extending a factory-based discrete event simulator for parallel optimization of production and supply chain level

引用

Procedia CIRP 2025年 134卷 885-890页

作者： Omid Safari Marc Münnich Florian Zumpe Yen Mai Thi Pierre Grzona Mario Henrique Callefi Steffen Ihlenfeldt Fraunhofer Institute for Machine Tools and Forming Technology IWU Reichenhainer Strasse 88 09126 Chemnitz Germany University of Applied Sciences Zwickau Faculty of Economics Kornmarkt 1 08056 Zwickau Germany Chemnitz University of Technology Professorship of Factory Planning and Intralogistics Str. der Nationen 62 09111 Chemnitz Germany Dresden University of Technology Institute of Mechatronic Engineering Helmholtzstraße 7a 01069 Dresden Germany

Factory-based discrete event simulation (FB-DES) tools are primarily used to model production systems at the factory level. However, integrating factory activities with supply network optimization has been challenging due to data barriers, leaving the application of FB-DES tools in supply chain (SC) contexts underexplored. This study addresses this limitation by enhancing the capabilities of FB-DES tools to integrate network and factory simulations within a single framework. By incorporating genetic algorithms (GAs) into the simulation model we present an approach to optimize production and supply networks based on key performance metrics such as production cost, time, and resource efficiency. The model features an automated scenario generation system using SimTalk methods and Python scripts to simulate and test potential production scenarios continuously. Additionally, Google Cloud Services (Google Maps API) are utilized for more accurate transportation time calculations, further improving network planning capabilities. This comprehensive simulation framework bridges the gap between factory and SC simulation methods, enhancing performance at both levels. This paper highlights the transformative potential of DES tools augmented with GAs and real-time data, paving the way for more resilient supply and production networks.

关键词： Discrete event simulation Optimization Genetic algorithm Supply chain Siemens Tecnomatix Plant Simulation Automated simulation process

来源：评论

学校读者我要写书评

暂无评论

Information requirements analysis for process-oriented decision support via predictive quality models in production

引用

Procedia CIRP 2024年 130卷 1428-1434页

作者： Daniel Buschmann Tobias Schulze Sebastian Beckschulte Robert H. Schmitt Laboratory for Machine Tools and Production Engineering WZL of RWTH Aachen University Campus-Boulevard 30 52074 Aachen Germany Fraunhofer Institute for Production Technology IPT Steinbachstraße 17 52074 Aachen Germany

In production environments, failure management and process optimization are essential elements for preventing interruptions and fulfilling customer expectations in terms of product quality. In this context, not only the establishment of standardized failure management and process optimization processes are of central importance, but also the use of modern analysis methods for the efficient identification and correction of product and process failures. Advances in the field of machine learning enable the prediction of quality characteristics during production, supporting in the identification of potential defects. However, merely predicting defects proves insufficient for supporting the decision-making process toward specific measures for process optimization. This paper examines the information demand for decision support through predictive quality models in production by means of a targeted information requirements analysis. For this purpose, established methods for failure analysis and process optimization, such as fault tree analysis, 8D-reports, and design of experiments, were evaluated. Thereupon, ten hypotheses with two additional research questions regarding the information demand were derived. Based on the derived hypotheses and questions, a cross-industry semi-structured expert survey (n=33) was conducted, followed by an evaluation of the results with regards to the information requirements for process-oriented decision support. The survey results (Cronbach’s alpha=0.77) confirm that predicting possible deviations and defects alone is insufficient for supporting decision-making process. The results indicate that additional information is required to support decision-making through predictive quality models with the objective of optimising the production process. The identification of important characteristics and interactions as well as the associated effect size is of paramount importance. Regarding the requirements for the provision of information via pre

关键词： Information Requirements Analysis Data Analytics Predictive Quality Process Optimization

来源：评论

学校读者我要写书评

暂无评论

Methodical assessment of the value of sensory captured data regarding the suitability for influencing manufacturing process goals

引用

Procedia Computer Science 2024年 232卷 406-415页

作者： Johannes Mayer Tobias Kaufmann Philipp Niemietz Thomas Bergs Laboratory for Machine Tools and Production Engineering (WZL) of the RWTH Aachen University Campus-Boulevard 30 52074 Aachen Germany Fraunhofer Institute for Production Technology IPT Steinbachstraße 17 52074 Aachen Germany

Pricing and assessing sensory captured data is an essential part of the data economy. In current approaches data are assessed based on individual data quality dimensions describing structured properties of data for downstream analyses. From the domain-specific perspective, an assessment regarding the suitability of data for manufacturing process goals is missing. For this reason, this paper presents a methodology for assessing datasets from the manufacturing perspective using an adapted balanced scorecard. This enables the mapping of manufacturing goals in a single score. The assessment is based on a process model that defines the measurable signals of specific manufacturing processes and represents their interactions. To evaluate the importance of process signals, the number of interactions with quality characteristics is examined. Alternatively, the change in affecting quality characteristics with variation of process signals is determined with a sensitivity analysis. On the application of the methodology, a fictitious dataset of a grinding process is analysed.

关键词： Data Assessment Data Monetization Pricing Model Manufacturing Process Data

来源：评论

学校读者我要写书评

暂无评论

Development of a Friction Model for Cutting Simulations of Lead-Free CuZn-Alloys

引用

Procedia CIRP 2024年 126卷 463-468页

作者： Kilian Brans Nicklas Gerhard Markus Meurer Thomas Bergs Laboratory for Machine Tools and Production Engineering (WZL) of RWTH Aachen University Campus-Boulevard 30 52074 Aachen Germany Fraunhofer Institute for Production Technology IPT Steinbachstr. 17 52074 Aachen Germany

The element lead is used as an alloying element in CuZn-alloys with mass contents of up to m PB = 4 % to improve machinability properties. Due to its toxicity, a variety of legislative initiatives aim to reduce the lead content in CuZn-alloys, which leads to critical machinability problems and a reduction in productivity of machining processes. In order to improve the machinability of lead-free CuZn alloys, it is imperative to analyze the influencing variables and mechanisms of chip formation in detail. In addition to the experimental analysis of the machining process, numerical modeling approaches can be used for this purpose. So far, no valid chip formation model for the description of the chip formation of lead-free CuZn-alloys has been established. Within the scope of this work, the foundation for the chip formation model is to be laid by developing a friction model for the meshing conditions in the machining process between lead-free brass and carbide. In addition to the material model, this model is the subsequent input variable for the chip formation model and thus enables the numerical simulation of machining processes with lead-free CuZn-alloys.

关键词： Lead-free CuZn-Alloys Brass Machining FEM Simulation Fricition

来源：评论

学校读者我要写书评

暂无评论

Numerical modeling for shearing of unidirectional carbon fiber reinforced plastic laminates by means of near-net-shape blanking

引用

Procedia Structural Integrity 2024年 61卷 206-213页

作者： T. Stoel L. Uhlmann F. Schweinshaupt M. Müller T. Herrig T. Bergs Laboratory for Machine Tools and Production Engineering (WZL) of RWTH Aachen University Campus Boulevard 30 52074 Aachen Germany Fraunhofer Institute for Production Technology IPT Steinbachstraße 17 52074 Aachen Germany

Structural components made of carbon fiber reinforced plastics (CFRP) exhibit a high degree of lightweight suitability. In order to fulfill geometric and functional requirements, a finishing process step of outer and inner contours is necessary. Near-net-shape blanking processes show potential for economical finishing of CFRP structural components. For the knowledge-based design of a near-net-shape blanking process comparable to fine blanking an understanding of the separation mechanisms during shearing of CFRP laminates is required. Therefore, this paper deals with the development of a finite element (FE) process model for near-net-shape blanking of unidirectional (UD) CFRP laminates with different fiber volume fraction and fiber orientation. Material modeling of the UD CFRP laminates was carried out by means of experimental characterization based on tensile, compression and shear tests. The formulation of the material model was implemented using a VUMAT user subroutine. The application of the blank holder and counter force was realized using a kinematic model based on a VUAMP user subroutine. A validation based on experimental near-net-shape blanking tests will be conducted in the next step.

关键词： Near-net-shape blanking Carbon fiber reinforced plastic Shearing process model

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Enhanced Transferability and Learning Capacity in Tool Wear Estimation

引用

Procedia CIRP 2024年 126卷 360-365页

作者： Zongshuo Li Markus Meurer Thomas Bergs Laboratory for Machine Tools and Production Engineering (WZL) of RWTH Aachen University Campus-Boulevard 30 52074 Aachen Germany Fraunhofer Institute for Production Technology IPT Steinbachstr. 17 52074 Aachen Germany

As an integral part of contemporary manufacturing, monitoring systems obtain valuable information during machining to oversee the condition of both the process and the machine. Recently, diverse algorithms have been employed to detect tool wear using single or multiple sources of measurements. In this study, a deep learning approach is proposed for estimating tool wear, considering cutting parameters. The model's accuracy and transferability in tool wear estimation were assessed with milling experiments conducted under varying cutting parameters. The results indicate that the proposed method outperforms conventional methods in terms of both transferability and rapid learning capabilities.

关键词： Tool wear Deep learning Transferability Milling

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：