检索结果-内蒙古大学图书馆

Blisk Specific Query Language (BLISQL) – An approach for domain specific data querying in Blisk Manufacturing

Procedia CIRP 2023年 118卷 366-371页

作者： Sven Schiller Markus Landwehr Georg Vinogradov 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

Product lifecycle management (PLM) is constantly improved by a steadily growing amount of data collected along the product and process development chain. This data supports designing optimized geometries and manufacturing processes. For the optimization of the manufacturing process, data from process design and manufacturing are extracted and processed. The use of a query language is helpful to make the extraction more efficient. Query languages, referring to the specific domain of a component, simplify the formulation of the queries. We present an approach for domain specific data querying in blisk manufacturing based on the Resource Description Framework (RDF) using SPARQL.

关键词： Computer Aided Manufacturing (CAM) Internet of Things (Iot) Onotology Semantic Web Technologies Product Lifecycle Management (PLM)

来源：评论

学校读者我要写书评

暂无评论

Concept for life cycle oriented ecological assessment in tooling

引用

Procedia CIRP 2023年 120卷 362-367页

作者： Christian Lürken Gonsalves Grünert Lars Stauder Sebastian Barth Thomas Bergs Laboratory for 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

The increasing demands of customers to use climate neutral products are leading to severe challenges for manufacturing companies in various industry sectors. The most significant issues lie in measuring and evaluating the resulting environmental impacts across the various lifecycle phases of a product. Especially for the tooling industry, it can be a decisive competitive factor, not only to measure and evaluate the environmental impact of the tool manufacturing processes, but also of the use phase of the manufactured tools. Therefore, this paper presents a concept for ecological assessment for tooling companies, taking the manufacturing phase and the use phase into account. It describes how tool manufacturers can evaluate their own processes based on material and energy inputs and outputs in order to link the environmental impacts to the manufactured product. In tool manufacturing, the digital twin is used as an essential medium for collecting ecological information and converting it into impact variables. The recorded production data from the manufacturing and use phase will be aggregated into different target dimensions: By using the target dimensions “Tool”, ”Tool component” and “Process” the evaluation concept can not only be used for a holistic report on environmental impacts of the manufactured products, but also be used to improve technology use and application from an ecological perspective. By adding the target dimension “Product” the use phase of the tool will be considered, in order to be able to visualize effects in which an ecologically intensive production can lead to reduction in environmental impact over the use phase. Furthermore, the target dimension “Company” is aggregating the derived data, which is necessary for the evaluation of the other target dimensions, to reporting types, such as the Greenhouse Gas Protocol or the Corporate Sustainability Reporting Directive.

关键词： Ecological assessment Tooling Tool making Evaluation System Digital Twin

来源：评论

学校读者我要写书评

暂无评论

On the importance of domain expertise in feature engineering for predictive product quality in production

引用

Procedia CIRP 2023年 118卷 1096-1101页

作者： Hendrik Mende Maik Frye Paul-Alexander Vogel Saksham Kiroriwal Robert H. Schmitt Thomas Bergs Fraunhofer Institute for Production Technology IPT Steinbachstr. 17 Aachen 52074 Germany Laboratory for Machine Tools and Production Engineering WZL of RWTH Aachen University Campus-Boulevard 30 Aachen 52074 Germany

machine Learning (ML) offers significant potential for quality management in production with predictive analytics. Key aspects to building ML models are the selection and engineering of features from data. They allow the usage of relevant data for training ML models. Using the right features consequently improves the quality of the ML models. However, feature engineering requires knowledge of the data, data preprocessing techniques, algorithms, the domain, and use case. Hence, automatic feature engineering tools have become popular. In this paper, we investigate how domain experts and automatic tools compare for engineering features based on a time series dataset from production.

关键词： machine Learning Domain Expertise Feature Selection Feature Engineering Product Quality Production

来源：评论

学校读者我要写书评

暂无评论

Active Learning with Pre-trained Language Models for Named Entity Recognition in Requirements Engineering

引用

Procedia CIRP 2024年 128卷 339-344页

作者： M. Riesener M. Kuhn S. Schümmelfeder D. Xiao J. Norheim E. Rebentisch G. Schuh Laboratory of Machine Tools and Production Engineering (WZL) RWTH Aachen University Campus-Boulevard 30 52074 Aachen Germany Massachusetts Instiute of Technology 77 Massachusetts Avenue Cambridge MA USA Fraunhofer Institute for Production Technology IPT Steinbachstraße 17 52074 Aachen Germany

The ever-increasing number of textual requirements and the handling of these consumes significant time in product design. Therefore, automating requirements analysis with natural language processing is critical to increase efficiency. Pre-trained language models have proven useful for requirements analysis. However, to deploy pre-trained language models, a fully labeled dataset must first be created to finetune language models towards the requirements domain. The creation of a fully labeled dataset, especially for named entity recognition (NER) applications, poses a major challenge as it entails high manual labeling effort by requirements engineers. Furthermore, in an ever-changing requirements environment, the manual labeling process must be repeated to avoid model drift, adding additional workload. Recent advances of pre-trained language models combined with active learning can significantly reduce the manual labeling effort. Thus, we present a novel approach for leveraging active learning with pre-trained language models for NER. We demonstrate the efficacy of this combination in an experiment, where we are able to reduce the manual requirements labeling effort by 74% while even improving model performance. We argue that by reducing the manual effort, active learning can shorten the ramp-up time of language model deployment for requirements engineering and enable industrial adoption.

关键词： Named Entity Recognition Language Model Active Learning Query Strategy Requirements Engineering

来源：评论

学校读者我要写书评

暂无评论

Automated Robot Skill Parameterization Based On Task Specifications

Automated Robot Skill Parameterization Based On Task Specifi...

引用

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： Sebastian Kurscheid Ruediger Daub Technical University of Munich (TUM) TUM School of Engineering and Design Institute for Machine Tools and Industrial Management (iwb) Garching near Munich Germany Fraunhofer Institute for Casting Composite and Processing Technology IGCV Augsburg Germany

ISBN: (数字)9798350361230

ISBN: (纸本)9798350361247

High-mix, low-volume manufacturing still relies on manual labor despite the potential for automation. This is due to the high cost of robot programming, which is required on a frequent basis. Skill-based frameworks for robot programming have reduced the expertise level and effort required for automation to meet the demands of high-mix, low-volume manufacturing. In these frameworks, the capabilities of robots are encapsulated in skills. By parameterizing these robot skills, they are adapted to new variants or products. This paper presents a concept for automating the parameterization process based on task specifications to reduce worker efforts by combining natural language processing and knowledge models.

关键词： Adaptation models Costs Service robots Manuals Natural language processing Manufacturing Manufacturing automation Robot programming

来源：评论

学校读者我要写书评

暂无评论

Approaches for automated and computer-aided work plan generation for adaptive manufacturing process chains in one-off manufacturing - a literature review

引用

Procedia CIRP 2023年 120卷 1410-1415页

作者： Tammo Dannen Maximilian Gey Sebastian Weber Lars Stauder Sebastian Barth Thomas Bergs Laboratory for 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

Current trends such as mass individualization, matrix production, cloud manufacturing and production as a service can be addressed by implementing adaptive manufacturing process chains. Adaptive manufacturing process chains contain alternative manufacturing options at several levels (e.g. feature-based geometry sequence, manufacturing methods, production machines, clamping systems, fixture positions, tools or processing strategies) to be able to continuously adapt to the real time conditions of a manufacturing environment in the best possible way under given target variables. Currently, the design of process chains is often manual and based on implicit empirical knowledge, which on the one-side leads to non-optimal process chains and on the other side does not include alternative manufacturing possibilities. The required effort for implementing adaptive process chains is thus opposed to high costs and complexity in work planning. In this paper, a literature review is conducted to identify and evaluate approaches in the scientific literature for the generation of work plans of adaptive process chains in one-off manufacturing. The literature review is divided into three phases and is broken down into six steps. The preparation phase defines the scope of the research. In the implementation phase, approaches are first identified utilizing a keyword analysis based on the theoretical and practical principles of work planning and selected in a 2-step selection process. The evaluation of the relevant approaches by using defined evaluation criteria enables the identification of research deficits for the derivation of further research questions. The literature review in this paper concludes that no approach addresses all the different aspects of work planning comprehensively. In particular, the interactions of individual decisions between the planning dimensions are insufficiently considered.

关键词： adaptive manufacturing process chain computer-aided work plan CAP one-off manufacturing Industrie 4.0

来源：评论

学校读者我要写书评

暂无评论

Approach for the numerical simulation of the machining behavior of WC-Co cemented carbide during grinding

引用

Procedia CIRP 2023年 118卷 596-601页

作者： Alexander Dehmer Sebastian Prinz Peter Breuer Sebastian Barth 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 Steinbachstraße 17 52074 Aachen Germany

Tungsten carbide cobalt (WC-Co) cemented carbides are two-phase, brittle-hard materials whose properties can be adapted to the application via the chemical composition. Due to the high requirements on form and dimensional tolerances of cemented carbide products, the material is mostly machined by grinding. In order to analyze the machining behavior when grinding cemented carbide, a costly and time-consuming analogy test is carried out, the so-called single-grain scratching. To substitute the time-consuming experiments, this paper focuses on the development of an approach for the numerical simulation of single-grain scratching of cemented carbide.

关键词： WC-Co cemented carbide grinding tool grinding numerical simulation single grain scratching

来源：评论

学校读者我要写书评

暂无评论

Simulation of material removal behavior during grinding of fiber reinforced non-oxide ceramics (SiC/SiC)

引用

Procedia CIRP 2023年 118卷 614-619页

作者： Sebastian Prinz Alexander Dehmer Christopher Schrenker Sebastian Barth Thomas Bergs Laboratory for Machine Tools and Production Engineering (WZL) of RWTH Aachen University Campus-Bouldevard 30 52074 Aachen Germany Fraunhofer Institute for Production Technology IPT Steinbachstraße 17 52074 Aachen Germany

Fiber-reinforced non-oxide ceramics have experienced increased interest due to their use as high-performance materials in aerospace. Since aerospace components are classified as safety-critical components, damage-free grinding of fiber-reinforced non-oxide ceramics components is inevitable. Due to two-phase material behavior, damage-free grinding of fiber-reinforced non-oxide ceramics is hard to achieve. To analyze the material removal behavior during grinding, the time and cost consuming analogy process single grain cutting is performed. To save time and cost, it is desirable to simulate the analogy process numerically. In this paper, the Smooth Particle Hydrodynamic (SPH) method is used to simulate single-grain cutting of fiber-reinforced non-oxid ceramics.

关键词： Fiber-reinforced ceramics silicon carbide grinding, Smooth Particle Hydrodynamic (SPH)

来源：评论

学校读者我要写书评

暂无评论

Hybrid ML for Parameter Prediction in Production

引用

Procedia CIRP 2023年 118卷 822-827页

作者： Jonas Dorißen Henrik Heymann Robert H. Schmitt Fraunhofer Institute for Production Technology IPT Steinbachstr. 17 Aachen 52074 Germany Laboratory for Machine Tools and Production Engineering WZL of RWTH Aachen University Campus-Boulevard 30 Aachen 52074 Germany

In the past, research in the production domain was driven by mathematical and physical description of production technologies. Over the last years, data-driven approaches like machine learning (ML) and artificial intelligence (AI) gave the research a new direction. Often, already existing knowledge is neglected when using data-driven approaches resulting in models that do not represent the best possible results. By combining these two approaches all available knowledge is used generating the best possible model. This combination is called hybrid modeling. In this paper, hybrid ML as part of hybrid modeling is introduced and the benefits and challenges using hybrid ML for the prediction of process parameters in the production domain are demonstrated.

关键词： Hybrid ML Hybrid Modeling machine Learning Artificial Intelligence

来源：评论

学校读者我要写书评

暂无评论

Experimental investigation of the friction behavior under cutting conditions

引用

Procedia CIRP 2023年 118卷 437-442页

作者： Nicklas Gerhard Kilian Brans Markus Meurer Daniel Schraknepper 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 turning of nickel-based alloy and tempered steel in industrial applications is carried out under supply of cutting fluids to ensure workpiece functionality and improve the machining results. Accurate mapping of the friction behavior is a fundamental part of FE chip formation simulations. Thus, a friction model is required under consideration of lubrication and cooling effects of the cutting fluids. The coefficient of friction and the contact temperature are measured. The relative speed and normal force are varied over a range, which is prevailing in turning for the specific material. The friction tests showed that the cutting fluid led to higher friction coefficients under the conditions investigated.

关键词： Friction Machining Lubrication

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：