检索结果-内蒙古大学图书馆

50th International Congress and Exposition of Noise Control Engineering, INTER-NOISE 2021

作者： Trautmann, Florian Knöfel, Björn Drossel, Welf-Guntram Troge, Jan Freund, Markus Penter, Lars Anders, Damian Fraunhofer Institute for Machine Tools and Forming Technology IWU Nöthnitzer Strasse 44 Dresden01087 Germany University of Technology Dresden Dresden01062 Germany

ISBN: (纸本)9781732598652

Intuition enables experienced machine operators to detect production errors and to identify their specific sources. A prominent example in machining are chatter marks caused by machining vibrations. The operators assessment, if the process runs stable or not, is not exclusively based on technical parameters such as rotation frequency, tool diameter, or the number of teeth. Because the human ear is a powerful feature extraction and classification device, this study investigates to what degree the hearing sensation influences the operators decision making. A steel machining process with a design of experiments (DOE)-based variation of process parameters was conducted on a milling machine. Microphone and acceleration sensors recorded machining vibrations and machine operators documented their hearing sensation via survey sheet. In order to obtain the optimal data set for calculating various psychoacoustic characteristics, a principle component analysis was conducted. The subsequent correlation analysis of all sensor data and the operator information suggest that psychoacoustic characteristics such as tonality and loudness are very good indicators of the process quality perceived by the operator. The results support the application of psychoacoustic technology for machine and process monitoring. © INTER-NOISE 2021 .All right reserved.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

Target Costing as an Approach to reduce Costs in closed-loop Agriculture Systems - Application for the Cultivation of Algae in Photobioreactors

引用

Procedia CIRP 2023年 116卷 372-377页

作者： Maximilian Stange Marc Tieding Gordon Brinitzer Steffen Ihlenfeldt Fraunhofer Institute for Machine Tools and Forming Technology IWU Reichenhainer Strasse 88 09126 Chemnitz Germany Fraunhofer Institute for Interfacial Engineering and Biotechnology IGB Nobelstrasse 12 70569 Stuttgart Germany Institute of Mechatronic Engineering Technische Universität Dresden 01069 Dresden Germany

The rapidly growing world population, the consequences of climate change and conventional agriculture as well as the limited resources of our planet threaten the food supply of humanity, especially with vital proteins. Therefore, innovation of agricultural systems is crucial for global food security and sustainable development. One proposed system is the cultivation of algae in artificially illuminated photobioreactors, which is a promising technology to limit land and water use. To achieve a competitive position between other agricultural systems and to reduce costs in a systematic and proactive approach, we suggest using Target Costing (TC) at an early stage of development. The paper aims to provide an overview of the state of the art in TC of agricultural systems. The authors identify a suitable approach for the economic evaluation of algae cultivation in bioreactors and adapt it specifically for the extraction of proteins. Based on this, different scenarios are discussed how a cost reduction of the existing systems can be achieved. The focus is on the reduction of energy costs, a suitable site selection and the use of side streams and products.

关键词： Sustainable agriculture Energy costs Target costing Algae

来源：评论

学校读者我要写书评

暂无评论

Study on the explainability of deep learning models for time series analysis in sheet metal forming

引用

Procedia CIRP 2024年 126卷 727-732页

作者： Marco Becker Philipp Niemietz Thomas Bergs Laboratory for Machine Tools and Production Engineering (WZL) RWTH Aachen University 52074 Aachen Germany Fraunhofer Institute for Production Technology 52074 Aachen Germany

In recent research, force signals have been utilized to estimate the wear of tool components in sheet metal processing using, e.g., artificial neural networks (ANNs). ANNs learn predictive models from raw time series signals without requiring prior knowledge and manual feature engineering. However, ANNs are black-box models. Existing research on explainable AI provides methods to increase the transparency of ANNs, but mainly focusses on computer vision problems. This publication proposes an approach to learn explainable ANNs for time series data. The presented approach is applied to a tool wear prediction task using force signals from a fine blanking machine.

关键词： explainable AI fine blanking wear monitoring time series

来源：评论

学校读者我要写书评

暂无评论

Concept of a plug-and-play, machine Learning Digital Twin of the production resource for Detailed Capacity Planning and Scheduling 6

Concept of a plug-and-play, Machine Learning Digital Twin of...

引用

6th International Conference on Industry 4.0 and Smart Manufacturing, ISM 2024

作者： Luber, Mario Wagner, Sarah Wegmann, Marc Schilp, Johannes Fraunhofer Institute for Casting Composite and Processing Technology IGCV Am Technologiezentrum 10 Augsburg86159 Germany Technical University of Munich Institute for Machine Tools and Industrial Management Boltzmannstraße 15 Garching85748 Germany University of Augsburg Institute of Computer Science Am Technologiezentrum 8 Augsburg86159 Germany

Due to the progress of Digital Production and the Industrial Internet of Things, continuous shop floor data is available with high coverage, accuracy, and in high detail for Production Planning and Control software. Detailed Capacity Planning and Scheduling (DCPS) can benefit by applying the Digital Twin concept and machine Learning for an accurate and automated virtual representation of the production resource. However, the effort and difficulty required for data connection, data preparation, and modelling are high. Connection standards enable interoperability and plug-and-play software, and constitute an opportunity to reduce the effort and difficulty. This article compiles requirements regarding the virtual representation of the production resource for DCPS. It then proposes the concept of a plug-and-play, machine Learning Digital Twin to meet these requirements. The elements of the according Digital Twin software are described, and the need for future research is identified. © 2024 The Authors.

关键词： Control Digital Twin interoperability machine Learning Production Planning

来源：评论

学校读者我要写书评

暂无评论

Investigation of bio-based cooling lubricants for the machining of aircraft stainless steels

引用

Procedia CIRP 2022年 110卷 47-52页

作者： Erik Selbmann Marcus Preiẞ Anas Ben Achour Uwe Teicher Albrecht Hänel Steffen Ihlenfeldt Fraunhofer Institute for Machine Tools and Forming Technology IWU 01187 Dresden Germany Technische Universität Dresden Institute of Mechatronic Engineering 01062 Dresden Germany

Water-miscible cooling lubricants are used in approx. 90% of metalworking processes mainly for lubrication and cooling of the contact zone between tool and workpiece. The base oils of the widely used water-miscible emulsions are often of mineral origin and represent a significant share of the CO2-fingerprint in production systems in terms of their extraction, processing and the possibility of recycling. Cooling lubricants are furthermore negatively discussed regarding to their health compatibility. Those disadvantages of conventional cooling lubricants drive the research for replacing mineral base oils with vegetable base oils, which contribute to a safer work environment and greener production. In this work, both conventional cooling lubricants and several water-miscible emulsions with various edible and non-edible vegetable-based oils were prepared and characterized regarding their suitability as cooling lubricants for the milling of aircraft stainless steels. Comprehensive experimental investigations were carried out to determine the process forces and the resulting tool wear as technical performance indicators for the test evaluation.

关键词： Bio-based lubricants stainless steel milling process forces tool wear

来源：评论

学校读者我要写书评

暂无评论

Characterization of vibration in continuous generating grinding and resulting influence on tooth flank topography and gear excitation 14

Characterization of vibration in continuous generating grind...

引用

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

作者： Böttger, Jonas Kimme, Simon Drossel, Welf-Guntram Institute for Machine Tools and Production Processes IWP Chemnitz University of Technology Reichenhainer Str. 70 Chemnitz09126 Germany Fraunhofer Institute for Machine Tools and Forming Technology IWU Reichenhainer Str. 88 Chemnitz09126 Germany

Besides harmonic meshing frequencies, excitation behavior of gears is highly affected by micro geometry of tooth surface caused by waviness on gear flank topography. Errors in finishing processes like continuous generating gear grinding are examined to demonstrate their impact on gear flank topography under consideration of characteristic waviness with a simulation model. Results of an experimental investigation on manufactured topography and measured transmission error show well correlation with the model. The pursued analysis of characteristic cutting volume in frequency domain of systematically considered process errors is a reasonable step towards the prediction of process conditions in the manufacturing process. © 2021 The Authors. Published by Elsevier B.V.

关键词： Grinding (machining)

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 16

On the importance of domain expertise in feature engineering...

引用

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

作者： Mende, Hendrik Frye, Maik Vogel, Paul-Alexander Kiroriwal, Saksham Schmitt, Robert H. Bergs, Thomas 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

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. © 2023 Elsevier B.V.. All rights reserved.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Hybrid ML for Parameter Prediction in Production 16

Hybrid ML for Parameter Prediction in Production

引用

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

作者： Dorißen, Jonas Heymann, Henrik 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

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. © 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

A survey on information requirements analysis for failure management and analysis in production 56

A survey on information requirements analysis for failure ma...

引用

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

作者： Beckschulte, Sebastian Buschmann, Daniel Günther, Robin Schulze, Tobias Schmitt, Robert H. Laboratory for Machine Tools and Production Engineering WZL of RWTH Aachen University Campus-Boulevard 30 Aachen52074 Germany Fraunhofer Institute for Production Technology IPT Steinbachstraße 17 Aachen52074 Germany

Failure management is essential in production environments to prevent disruptions and satisfy customers' expectations of product quality. Of central importance is not only the establishment of standardized failure management processes but also the use of modern analysis methods for the efficient correction of product and process failures. Due to the high complexity of production environments and failure management at the same time, the human factor still plays a central role in detecting, analyzing, and sustainable correcting product and process failures. However, according to a previous empirical study, around 50 % of all information collected in manufacturing companies remains unused. The study also confirms that around 70 % of the companies consulted are not aware of the information required for targeted analyses. To address the information demands of individual parties during the failure management process more effectively, this survey analyzed actual information requirements and determined which analysis methods are used in the production contexts. We conducted a target-group-specific survey on information requirements analysis in failure management, involving employees in managerial and quality management positions at four automotive OEMs. The survey results indicate the information required to initiate and successfully complete failure management processes in production environments. It became clear that the target group for failure analyses are primarily employees in managerial and quality management positions, rather than on the shop floor. The theoretical approach, which is still a state-of-the-art approach in the automotive industry, envisages a divergent procedure. At the same time, it is shown that despite the enormous developments in the field of data analytics in recent years, the initial analysis approach is still based on descriptive approaches, especially in failure management. © 2023 The Authors. Published by Elsevier B.V. This is an open access a

关键词： Failure Analysis Failure Management Information Requirements Analysis Original Equipment Manufacturer (OEM) Production

来源：评论

学校读者我要写书评

暂无评论

machine Learning Pipeline for Predictive Maintenance in Polymer 3D Printing 19

Machine Learning Pipeline for Predictive Maintenance in Poly...

引用

19th CIRP Conference on Modeling of Machining Operations, CMMO 2023

作者： Heymann, Henrik 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

Predictive maintenance is an enabler of achieving a sustainable production in 3D printing processes. The goal of this paper is to answer the question how to realize predictive maintenance for Fused Deposition Modeling (FDM) of Polyether Ether Ketone (PEEK). In a real-life use case, aging effects of the 3D printer's nozzle have a direct negative impact on product quality but are not detectable from the outside. For this purpose, a machine learning pipeline is built including the integration and preparation of sensor data as well as the training of a regression model to predict the nozzle's remaining useful lifetime. © 2023 Elsevier B.V.. All rights reserved.

关键词： Pipelines

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：