检索结果-内蒙古大学图书馆

Assistance Method for the Application-Driven Design of machine Learning Algorithms

IOP Conference Series: Materials Science and Engineering 2021年第1期1140卷

作者： Adalbert Fono Gregor Thiele Max Klein Jörg Krüger Fraunhofer Institute for Production Systems and Design Technology 10587 Berlin Germany Head of the Department for Industrial Automation at the Institute for Machine Tools and Factory Management Technical University of Berlin 10587 Berlin Germany

machine learning (ML) offers a lot of potential for applications in Industry 4.0. By applying ML many processes can be improved. Possible benefits in production are a higher accuracy, an early detection of failures, a better resource efficiency or improvements in quantity control. The use of ML in industrial production systems is currently not widespread. There are several reasons for this, among others the different expertise of data scientists and automation engineers. There are no specific tools to apply ML to industrial facilities neither guidelines for setting up, tuning and validating ML implementations. In this paper we present a taxonomy structure and according method which assist the design of ML architectures and the tuning of involved parameters. As this is a very huge and complex field, we concentrate on a ML algorithm for time series forecast, as this can be used in many industrial applications. There are multiple possibilities to approach this problem ranging from basic feed-forward neural networks to recurrent networks and (temporal) convolutional networks. These different approaches will be discussed and basic guidelines regarding the model selection will be presented. The introduced assistance method will be validated on a industrial dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automated CRISPR/Cas9-based genome editing of human pluripotent stem cells using the StemCellFactory

引用

Cytotherapy 2025年第5期27卷 S36-S37页

作者： Nießing, B. Breitkreuz, Y. Elanzew, A. de Toledo, M.A.S. Vajs, P. Nolden, M. Erkens, F. Wanek, P. Yeung, S. Au Haupt, S. Koenig, N. Peitz, M. Schmitt, R. Zenke, M. Brustle, O. Bioadaptive Production Fraunhofer Institute for Production Technology IPT Aachen Germany Cellomics Unit LIFE&BRAIN GmbH Bonn Germany Institute of Reconstructive Neurobiology University of Bonn Medical Faculty and University Hospital Bonn Bonn Germany Institute for Biomedical Engineering Cell Biology Faculty of Medicine RWTH Aachen University Aachen Germany Helmholtz Institute for Biomedical Engineering RWTH Aachen University Aachen Germany Department of Medicine IV Hematology Oncology and Stem Cell Transplantation RWTH Aachen University Hospital Aachen Germany Center for Integrated Oncology Aachen Bonn Cologne Düsseldorf (CIO ABCD) Aachen Germany Fraunhofer Institute for Production Technology IPT Aachen Germany Cell Programming Core Facility University of Bonn Medical Faculty Bonn Germany Laboratory for Machine Tools and Production RWTH Aachen University Aachen Germany

Background & AimCRISPR/Cas9 technology is a leading method for efficient gene editing, enabling the creation of isogenic pairs of mutant and control human induced pluripotent stem cells (hiPSCs). While hiPSCs provide valuable opportunities for disease modeling and personalized medicine, challenges remain in distinguishing specific mutation effects from genetic backgrounds. Manual genome editing processes often face scalability and standardization limitations. The StemCellFactory, a modular robotic system, has been developed to automate the reprogramming, expansion, and differentiation of hiPSCs, enhancing the application of CRISPR/Cas9 in research. MethodologyHiPSCs were cultured in StemMACS iPS-Brew XF medium, with daily medium changes and mycoplasma testing. For CRISPR/Cas9 editing, target gene-specific CRISPR-RNA and tracrRNA formed ribonucleoprotein complexes, utilizing an optimized nucleofection protocol. HiPSCs were dissociated, counted, and nucleofected through manual and automated processes. The automated StemCellFactory workflow included cell preparation, nucleofection, and cell seeding, managed by the COPE software for data visualization. Genotyping of polyclonal hiPSCs was performed via Sanger sequencing to assess editing efficiency, with automated isolation of monoclonal colonies conducted using an integrated CellCelector. ResultsThe StemCellFactory successfully integrated a 4D-Nucleofector with a 96-well shuttle device for automated CRISPR/Cas9 editing. Adjustments replaced manual consumables with scalable formats, enhancing efficiency. The CM150 electroporation program yielded high cell viability (83.5%) and indel rates (81.7%). Optimal culture conditions combined Laminin 521 with CloneR-supplemented iPS-Brew medium, supporting hiPSC survival and colony formation. The automated system allowed parallel processing of up to 24 conditions, demonstrating high editing efficiencies, with indel rates exceeding 80% across all tested cell lines, comparable to ma

关键词： Standardization Personalized Medicine COPE

来源：评论

学校读者我要写书评

暂无评论

Influence of contaminants on part quality during Laser-Based Powder Bed Fusion of nickel base alloys

引用

Procedia CIRP 2020年 94卷 233-238页

作者： Mathias S. Palm Max Horn Andreas Bachmann Georg Schlick Michael F. Zaeh Gunther Reinhart Institute for Machine Tools and Industrial Management of Technical University of Munich Boltzmannstr. 15 85748 Garching b. München Germany ArianeGroup GmbH Robert-Koch-Straße 1 82024 Taufkirchen Germany Fraunhofer Research Institution for Casting Composite and Processing Technology IGCV Am Technologiezentrum 10 86159 Augsburg Germany

Laser-based Powder Bed Fusion (LPBF) has become a key Additive Manufacturing (AM) technology for the production of complex metallic components within a short lead-time. Contaminated powder feedstock is a major challenge in LPBF due to the uncertain influence of contaminations on part quality. This study investigates the effects of different contaminants inside the feedstock on material density and metallurgical structure in order to evaluate their implications for serial production. Pieces of rubber gloves, human, and recoater brush hair as well as five more substances were applied manually at a defined layer during the manufacturing process of Hastelloy® X (HX) specimens. The part densities were 99.9% for all contaminated specimens. Cross-sections did not show increased porosity. For some contaminants, inclusions of foreign material residue were observed. The results for HX were evaluated and implications for comparable materials were derived. Lastly, the criticality of the investigated contaminants on part quality was analyzed.

关键词： Additive Manufacturing powder quality foreign particles contamination HastelloyX

来源：评论

学校读者我要写书评

暂无评论

Product Flexible Car Body Fixtures with Position-dependent Load Balancing Based on Finite Element Method in Combination with Methods of Artificial Intelligence

引用

Procedia CIRP 2018年 67卷 452-457页

作者： Rayk Fritzsche Andreas Richter Matthias Putz Head of group assembly systems at Fraunhofer Institute for Machine Tools and Forming Technology IWU Reichenhainer Strae 88 Chemnitz 09126 Germany Scientific employee at Fraunhofer Institute for Machine Tools and Forming Technology IWU Reichenhainer Strae 88 Chemnitz 09126 Germany

In car-body production, the fixtures used for fixing the car-body panels during the joining processes predominantly consist of rigid constructions that are precise and specific for one car-model. In addition to the already presented automatic adaptation of such fixtures, and specific for the production of many different car-models using same fixture, different clamping robots have been developed. In order to meet the high quality requirements, the positional deviations of these clamping robots are adjusted due to different external loads. This control loop is carried out using a combination of finite element method, mathematical algorithms and modern methods of artificial intelligence.

关键词： Quality management Body in white Rramp up Artificial intelligence Neuronal network Database

来源：评论

学校读者我要写书评

暂无评论

Methodology and model for predicting energy consumption in manufacturing at multiple scales

引用

Procedia Manufacturing 2018年 21卷 694-701页

作者： Jan Reimann Ken Wenzel Marko Friedemann Matthias Putz Fraunhofer Institute for Machine Tools and Forming Technology IWU Reichenhainer Straße 88 09126 Chemnitz Germany

Certain fields of manufacturing, like casting, forming or cutting, may cause high energy load. Especially under the consideration of renewable energy sources it is beneficial to negotiate production schedules and consumption forecasts with the energy supplier. This would enable an optimized management of energy sources and infrastructure components on the supplier side, helping to reduce costs. Optimal and balanced expenses for production would be the consequence. The problem of power consumption prediction in manufacturing was subject of many studies in the past. Most of them either consider the physical modeling of processes at a very detailed level, or they introduce tailored prediction models for specific production processes. Thus, it is hard to apply their results to other uses cases in different scenarios. As a consequence, a generic methodology and model regarding power consumption prediction in manufacturing is required in order to cover the variety of processes, machines and materials. Furthermore, an approach must support flexible levels of granularity for predicting the energy consumption of manufacturing processes. On the one hand, a whole factory may be the object of investigation while, on the other hand, predictions for finer-grained levels, such as certain parts of a machine, are required to allow for specific optimizations. Our contribution is twofold. First, we propose a generic model for the specification of the power-consuming machine. A tree-based compositional approach supports arbitrary levels, depending on the structure of the machine, or external factors, such as company policies. This approach is highly extensible since the models are stored in ontologies. Second, we propose a methodology for static and dynamic modeling of power consumption for every structural level. Based on that model the prediction can be realized. In addition, we provide an example implementation and prediction for a continuous casting machine process.

关键词： Energy efficiency Predictive Model Ontology

来源：评论

学校读者我要写书评

暂无评论

Decision Support for Planning Techniques in Energy Efficiency Projects

引用

Procedia CIRP 2018年 69卷 306-311页

作者： Marian Süße Johannes Stoldt Andreas Schlegel Matthias Putz Fraunhofer Institute for Machine Tools and Forming Technology IWU Reichenhainer Straße 88 09126 Chemnitz Germany

Factory operators can select from a multitude of measures to improve their energy efficiency. Despite the variety of planning techniques intended to help investigating the energy flows, little assistance is available for determining the most efficient approach to pursue in a specific project. This paper presents decision support procedures for making appropriate selections during planning, focusing on the selections of an energy model and a matching energy data acquisition method. They build on problem-independent decision models and systematize available alternatives. The models are solved independently by applying the Analytic Hierarchy Process that allows the integration and quantification of different criteria.

关键词： Energy efficiency Sustainable development Decision-making Analytic Hierarchy Process

来源：评论

学校读者我要写书评

暂无评论

Investigating the potential of electrical discharge machining for antibacterial coating of titanium implants 18

Investigating the potential of electrical discharge machinin...

引用

18th International Conference of the European Society for Precision Engineering and Nanotechnology, EUSPEN 2018

作者： Bui, Viet D. Mwangi, James W. Berger, Thomas Schubert, Andreas Technische Universität Chemnitz Prof. Micromanufacturing Technology Reichenhainer Strasse 70 Chemnitz09126 Germany Fraunhofer Institute for Machine Tools and Forming Technology Reichenhainer Strasse 88 Chemnitz09126 Germany

ISBN: (纸本)9780995775121

Titanium and titanium alloys are some of the best materials for medical implants owing to their excellent properties including biocompatibility, corrosion resistance and high fatigue strength among others. However, many implants have to be removed after implantation because of bacterial infection. Coating titanium implants with copper or silver has demonstrated antibacterial abilities and has therefore been widely applied to solve this problem. Ion implantation, physical vapour deposition, magnetron sputtering and many other different methods are used to coat these materials. However, until now, there is no method that allows for concurrent machining and coating of the antibacterial layer. Electrical Discharge Machining (EDM) has demonstrated its potential on surface modification owing to the fact that the material from tool electrode and/or powder mixed in dielectric fluid is implanted on the workpiece thereby changing its characteristics. In this study, the suitability of EDM for coating copper and silver on titanium alloy is investigated. Titanium alloy samples are machined using a high precision EDM machine and later analysed for surface quality and chemical composition. © 2018 CURRAN-CONFERENCE. All rights reserved.

关键词： Titanium alloys

来源：评论

学校读者我要写书评

暂无评论

Procedure and Validation of the Implementation of Automated Sensor Integration Kinematics in an LPBF System

引用

Procedia CIRP 2020年 93卷 1304-1309页

作者： Maximilian Binder Christian Dirnhofer Philipp Kindermann Max Horn Matthias Schmitt Christine Anstaett Georg Schlick Christian Seidel Gunther Reinhart Fraunhofer IGCV (Research Institution for Casting Composite and Processing Technology) Beim Glaspalast 5 86153 Augsburg Germany Department of Applied Sciences and Mechatronics University of Applied Sciences Munich Lothstr. 34 80335 Munich Germany Technical University of Munich Institute for Machine Tools and Industrial Management Boltzmannstr. 1585748 Garching Germany

The in-situ integration of sensors into additive manufactured (AM) components is becoming increasingly important and moving into the focus of current research. However, manual sensor integration during the metal- and laser-based powder bed fusion (LPBF) process is usually associated with long process downtimes, the loss of the shielding gas atmosphere and a change in component temperature. The resulting effects are e.g. changed mechanical properties. Therefore, one way to avoid these effects is presented by automated sensor integration. A procedure for the design of kinematics to meet the requirements is presented and experimentally validated. As a result, a functional automation unit in an LPBF plant is presented.

关键词： automated sensor integration metal additive manufacturing smart parts laser based powder bed fusion laser beam melting multi-material

来源：评论

学校读者我要写书评

暂无评论

Smart components by additive technologies

引用

IOP Conference Series: Materials Science and Engineering 2019年第1期480卷

作者： I Dani Fraunhofer Institute for Machine Tools and Forming Technology Germany

Smart components are key technologies for industry 4.0 as well as the Internet of Things. The application areas include e.g. systems for sustainable production, automotive, smart agriculture, and smart home. In order to integrate intelligence within a component, a sensor or actuator system typically needs to be embedded within the component itself during fabrication. Additive manufacturing has been extended to more and more industries and is now being used not only in toolmaking, but also in the series production of components. Geometric functionalization for conformal cooling is already state of the art in tool making. Despite the great potential of function-integrated parts, publications on sensor integration into parts fabricated by additive manufacturing are still rarely found. First approaches address multimaterial printing by using insulating and conductive materials as well as the integration of smart elements during the printing process. Laser beam melting (LBM) is an additive manufacturing technology for geometrically complex parts based on the layer wise and selective melting of metal powders. As proof-of-concept of the developed integration concept, based on LBM, the functionalization of tools and medical implants will be presented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Influence of pass reduction in cold rolling on damage evolution in deep drawing of rotationally symmetric cups

引用

IOP Conference Series: Materials Science and Engineering 2021年第1期1157卷

作者： M Nick C Liebsch M Müller IF Weiser G Hirt T Bergs Laboratory for Machine Tools and Production Engineering (WZL) of RWTH Aachen University Campus-Boulevard 30 52074 Aachen Germany Institute of Metal Forming (IBF) of RWTH Aachen University Intzestr. 10 52072 Aachen Germany Fraunhofer Institute for Production Technology IPT Steinbachstr. 17 52074 Aachen Germany

Improvement of component performance by controlling the damage state after metal forming enables a reduction in sheet thickness and, consequently, in component weight and material cost. To establish methods for controlling damage in finished parts, the entire process chain from steelmaking and casting through hot and cold rolling to deep drawing must be considered. Previous research has shown that in hot rolling of an S355 steel, the influence of pass reduction on damage in the hot strip disappears when the accumulated pass reduction becomes large. However, the influence of cold rolling parameters on damage and specifically on its evolution in subsequent forming processes has not yet been systematically investigated. In the present work, specimens of the the mentioned S355 steel are cold rolled with two different pass reductions and heat treated to obtain a DP800 dual phase steel. These specimens are deep drawn into rotationally symmetric cups with variation of the drawing die radius. Sheet specimens and deep drawn cups are investigated using scanning electron microscopy to determine the respective void area fractions. While no influence of height reduction on the void area fraction after cold rolling is found, the void area fraction after deep drawing differs with variation of the pass reduction. This effect is connected to the formation of a larger number of small voids in the material rolled with a larger pass reduction.

关键词：

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：