检索结果-内蒙古大学图书馆

Integrating Cloud computing, Bayesian Optimization, and Neural-Additive Modeling for Enhanced CAM Systems in 5-Axis Milling

引用

Procedia CIRP 2024年 128卷 532-537页

作者： Viktor Rudel Georg Vinogradov Philipp Ganser Thomas Bergs Christopher Vahl Markus Frings Valentina König Maximilian Schambach Stefan Dietzel Michael Königs Fraunhofer Institute for Production Technology IPT Steinbachstraße 17 52074 Aachen Germany Laboratory for Machine Tools and Production Engineering (WZL) RWTH Aachen University Campus-Boulevard 30 52074 Aachen Germany Fraunhofer Institute for Algorithms and Scientific Computing SCAI Schloss Birlinghoven 1 53757 Sankt Augustin Germany ModuleWorks GmbH Henricistraße 50 52072 Aachen Germany Merantix Momentum Merantix AI Campus Max-Urich-Straße 3 13355 Berlin Germany EXAPT Systemtechnik GmbH Theaterstraße 12 52062 Aachen Germany

This publication introduces the development and application of an advanced CAD/CAM/CAE system that leverages the computational capabilities of an edge-cloud infrastructure. The developed system consists of containerized technology models for various complex process planning simulation tasks in 5-axis-milling, such as toolpath calculation, cutter-workpiece-engagement, uncut chip geometry or cutting force simulations. Moreover, a Bayesian optimization (BO) algorithm is coupled with the system enabling multi-objective optimizations of the considered machining operations by varying predefined CAM-parameters. The result of the optimization consists of a set of Pareto-efficient solutions. Each solution realizes a different tradeoff between the technological objectives of the process planner. Since mastering the complexity of the design space is a major challenge in today’s CAM programming workflow, a Neural-Additive Model (NAM) is coupled with the system improving guided search through the configuration/result space. This reduces the convergence time to an optimal CAM parameter set. The coupling of the cloud computing, multi-objective optimization and artificial intelligence method with a CAM-kernel is demonstrated based on the process design of 5-axis milling operations for a blade-integrated disk (blisk).

关键词： Computer-aided Manufacturing systems (CAM-Systems) Multi-objective optimization Design methodology tools technologies

来源：评论

学校读者我要写书评

暂无评论

On Dark Stars, Planck Cores and the Nature of Dark Matter 23

On Dark Stars, Planck Cores and the Nature of Dark Matter

引用

23rd Workshop What Comes Beyond the Standard Models

作者： Nikitin, I. Fraunhofer Institute for Algorithms and Scientific Computing Schloss Birlinghoven Sankt Augustin53757 Germany

Dark stars are compact massive objects, described by Einstein gravitational field equations with matter. The type we consider possesses no event horizon, instead, there is a deep gravitational well with a very strong redshift factor. Observationally, dark stars can be identified with black holes. Inside dark stars, Planck density of matter is reached, Planck cores are formed, where the equations are modified by quantum gravity. In the paper, several models of dark stars with Planck cores are considered, resulting in the following hypothesis on the composition of dark matter. The galaxies are flooded with low-energetic radiation from the dark stars. The particle type can be photons and gravitons from the Standard Model, can also be a new type of massless particles. The model estimations show that the extremely large redshift factor z ∼ 1049 and the emission wavelength λ0 ∼ 1014m can be reached. The particles are not registered directly in the existing dark matter experiments. They come in a density sufficient to explain the observable rotation curves. The emission has a geometric dependence of density on radius ρ ∼ r−2, producing flat rotation curves. The distribution of sources also describes the deviations from the flat shape. The model provides a good fit of experimental rotation curves. Outbreaks caused by a fall of an external object on a dark star lead to emission wavelength shifted towards smaller values. The model estimations give the outbreak wavelength λ ∼ 1m compatible with fast radio bursts. The paper raises several principal questions. White holes with Planck core appear to be stable. Galactic rotation curves in the considered setup do not depend on the matter type. Inside the galaxy, dark matter can be of hot radial type. At cosmological distances, it can behave like the cold uniform type. © 2020 DMFA zaloznistvo. All rights reserved.

关键词： Stars

来源：评论

学校读者我要写书评

暂无评论

ProtSTonKGs: A Sophisticated Transformer Trained on Protein Sequences, Text, and Knowledge Graphs 13

ProtSTonKGs: A Sophisticated Transformer Trained on Protein ...

引用

13th International Conference on Semantic Web Applications and Tools for Health Care and Life Sciences, SWAT4HCLS 2022

作者： Balabin, Helena Hoyt, Charles Tapley Gyori, Benjamin M. Bachman, John Kodamullil, Alpha Tom Hofmann-Apitius, Martin Domingo-Fernández, Daniel Department of Bioinformatics Fraunhofer Institute for Algorithms and Scientific Computing Sankt Augustin53757 Germany Bonn-Rhein-Sieg University of Applied Sciences Sankt Augustin53757 Germany Laboratory of Systems Pharmacology Harvard Medical School BostonMA02115 United States Fraunhofer Center for Machine Learning Germany Enveda Biosciences BoulderCO80301 United States

While most approaches individually exploit unstructured data from the biomedical literature or structured data from biomedical knowl- edge graphs, their union can better exploit the advantages of such ap- proaches, ultimately improving representations of biology. Using mul- timodal transformers for such purposes can improve performance on context dependent classification tasks, as demonstrated by our previ- ous model, the Sophisticated Transformer Trained on Biomedical Text and Knowledge Graphs (STonKGs). In this work, we introduce Prot- STonKGs, a transformer aimed at learning all-encompassing representa- tions of protein-protein interactions. ProtSTonKGs presents an extension to our previous work by adding textual protein descriptions and amino acid sequences (i.e., structural information) to the text- and knowledge graph-based input sequence used in STonKGs. We benchmark Prot- STonKGs against STonKGs, resulting in improved F1 scores by up to 0.066 (i.e., from 0.204 to 0.270) in several tasks such as predicting protein interactions in several contexts. Our work demonstrates how multimodal transformers can be used to integrate heterogeneous sources of infor- mation, paving the foundation for future approaches that use multiple modalities for biomedical applications. Copyright © 2022 for this paper by its authors.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Knowledge Detection and Discovery using Semantic Graph Embeddings on Large Knowledge Graphs generated on Text Mining Results 15

Knowledge Detection and Discovery using Semantic Graph Embed...

引用

15th Federated Conference on Computer Science and Information Systems, FedCSIS 2020

作者： Dorpinghaus, Jens Jacobs, Marc Bonn Germany Fraunhofer Institute for Algorithms and Scientific Computing Schloss Birlinghoven Sankt Augustin Germany

ISBN: (纸本)9788395541674

Knowledge graphs play a central role in big data integration, especially for connecting data from different domains. Bringing unstructured texts, e.g. from scientific literature, into a structured, comparable format is one of the key assets. Here, we use knowledge graphs in the biomedical domain working together with text mining based document data for knowledge extraction and retrieval from text and natural language structures. For example cause and effect models, can potentially facilitate clinical decision making or help to drive research towards precision medicine. However, the power of knowledge graphs critically depends on context information. Here we provide a novel semantic approach towards a context enriched biomedical knowledge graph utilizing data integration with linked data applied to language technologies and text mining. This graph concept can be used for graph embedding applied in different approaches, e.g with focus on topic detection, document clustering and knowledge discovery. We discuss algorithmic approaches to tackle these challenges and show results for several applications like search query finding and knowledge discovery. The presented remarkable approaches lead to valuable results on large knowledge graphs. © 2020 Polish Information Processing Society - as it is since 2011.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Optimization of Retrieval algorithms on Large Scale Knowledge Graphs 15

Optimization of Retrieval Algorithms on Large Scale Knowledg...

引用

15th Federated Conference on Computer Science and Information Systems, FedCSIS 2020

作者： Dorpinghaus, Jens Stefan, Andreas Bonn Germany Fraunhofer Institute for Algorithms and Scientific Computing Schloss Birlinghoven Sankt Augustin Germany

ISBN: (纸本)9788395541674

Knowledge graphs have been shown to play an important role in recent knowledge mining and discovery, for example in the field of life sciences or bioinformatics. Although a lot of research has been done on the field of query optimization, query transformation and of course in storing and retrieving large scale knowledge graphs the field of algorithmic optimization is still a major challenge and a vital factor in using graph databases. Few researchers have addressed the problem of optimizing algorithms on large scale labeled property graphs. Here, we present two optimization approaches and compare them with a naive approach of directly querying the graph database. The aim of our work is to determine limiting factors of graph databases like Neo4j and we describe a novel solution to tackle these challenges. For this, we suggest a classification schema to differ between the complexity of a problem on a graph database. We evaluate our optimization approaches on a test system containing a knowledge graph derived biomedical publication data enriched with text mining data. This dense graph has more than 71M nodes and 850M relationships. The results are very encouraging and- depending on the problem-we were able to show a speedup of a factor between 44 and 3839. © 2020 Polish Information Processing Society - as it is since 2011.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Feature-based prediction of properties of cross-linked epoxy polymers by molecular dynamics and machine learning techniques

arXiv

引用

arXiv 2023年

作者： Sindu, B.S. Hamaekers, Jan Special and Multifunctional Structures Laboratory CSIR-Structural Engineering Research Centre Taramani Tamil Nadu Chennai600113 India Fraunhofer Institute for Algorithms and Scientific Computing Schloss Birlinghoven Sankt AugustinD-53757 Germany

Epoxy polymers are used in wide range of applications. The properties and performance of epoxy polymers depend upon various factors like the type of constituents and their proportions used and other process parameters. The conventional way of developing epoxy polymers is usually labor-intensive and may not be fully efficient, which has resulted in epoxy polymers having a limited performance range due to the use of predetermined blend combinations, compositions and development parameters. Hence, in order to experiment with more design parameters, robust and easy computational techniques need to be established. To this end, we developed and analyzed in this study a new machine learning (ML) based approach to predict the mechanical properties of epoxy polymers based on their basic structural features. The results from molecular dynamics (MD) simulations have been used to derive the ML model. The salient feature of our work is that for the development of epoxy polymers based on EPON-862, several new hardeners were explored in addition to the conventionally used ones. The influence of additional parameters like the proportion of curing agent used and the extent of curing on the mechanical properties of epoxy polymers were also investigated. This method can be further extended by providing the epoxy polymer with the desired properties through knowledge of the structural characteristics of its constituents. The findings of our study can thus lead toward development of efficient design methodologies for epoxy polymeric systems. © 2023, CC BY-NC-ND.

关键词： Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

On dark stars, planck cores and the nature of dark matter

arXiv

引用

arXiv 2021年

作者： Nikitin, Igor Fraunhofer Institute for Algorithms and Scientific Computing Schloss Birlinghoven Sankt Augustin53757 Germany

关键词： Galaxies

来源：评论

学校读者我要写书评

暂无评论

Galactic model with a phase transition from dark matter to dark energy

arXiv

引用

arXiv 2021年

作者： Nikitin, Igor Fraunhofer Institute for Algorithms and Scientific Computing Schloss Birlinghoven Sankt Augustin53757 Germany

This work continues the construction of a recently proposed model of dark matter stars. In this model, dark matter quanta are sterile massless particles that are emitted from the central regions of the galaxy in the radial direction. As a result, at large distances r from the center of the galaxy, the mass density of dark matter has the form ρ ∼ r−2, in contrast to the homogeneous model ρ = Const. In the cosmological context, the homogeneous model with massless particles corresponds to the radiation epoch of the expansion of the universe, while the proposed inhomogeneous model turns out to be equivalent to ΛCDM. In this paper, scenarios will be considered in which the radial emission of dark matter is brought into hydrostatic equilibrium with a uniform background. It is shown that solutions exist if the uniform background has an equation of state typical for dark energy. Thus, this model describes a phase transition from dark matter inside the galaxy to dark energy outside of it. The specific mechanism for such a transition could be Bose-Einstein condensation. In addition, the question of what happens if dark matter particles are not sterile, for example, are photons of the Standard Model, is considered. © 2021, CC BY.

关键词： Galaxies

来源：评论

学校读者我要写书评

暂无评论

Wormholes and Teleporters

arXiv

引用

arXiv 2021年

作者： Nikitin, Igor Fraunhofer Institute for Algorithms and Scientific Computing Schloss Birlinghoven Sankt Augustin53757 Germany

In general relativity, there is a class of solutions that currently do not have observed analogues, but on which the theory is shaped, giving an understanding what is fundamentally possible within its framework. Such solutions include wormholes, tunnels that connect distant regions in spacetime. Although not a single wormhole has yet been discovered, there is a large number of works devoted to their study, thanks to which wormholes as a class of solutions become firmly established in modern science. In this paper, we consider two topologically nontrivial types of solutions related to wormholes. First: Wormholes that can open and close. In this relation, we will discuss topological censorship theorems, which under certain conditions prohibit changing topology. We will also discuss known ways to circumvent these theorems. Using analytical and numerical methods, as well as visualization, we will construct an example of an opening and closing wormhole with the dimensions of the central black hole in the Milky Way galaxy. Our construction continues the work by Kardashev, Novikov and Shatskiy, in which a static wormhole with the same parameters was considered. The second type is a modification of Visser's dihedral wormhole solution for a dynamic case, which can be considered as a model of a teleportation event. © 2021, CC BY.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Decision Support by Interpretable Machine Learning in Acoustic Emission Based Cutting Tool Wear Prediction

Decision Support by Interpretable Machine Learning in Acoust...

引用

IEEE International Conference on Industrial Engineering and Engineering Management

作者： A. Schmetz C. Vahl Z. Zhen D. Reibert S. Mayer D. Zontar J. Garcke C. Brecher Fraunhofer-Institute for Production Technology IPT Aachen Germany Fraunhofer-Center for Machine Learning and Fraunhofer-Institute for Algorithms and Scientific Computing SCAI Sankt Augustin Germany Laboratory for Machine Tools and Production Engineering (WZL) RWTH Aachen University Germany

ISBN: (纸本)9781665437721

Predictive maintenance is a prominent and active field for applications of machine learning in industry in recent years. The health and wear of equipment directly influences the productivity and quality of the production process. Especially in ultra-precision manufacturing, tool wear has a major impact on the achievable quality while the wear itself cannot be measured directly in-process. In this paper we present a machine learning-based classification of the tool wear in-process using acoustic emission sensors. To increase the interpretability of the process – to open the black box model – we apply a feature importance analysis and use the obtained feature importances to provide augmented data representations to the users. These representations increase the transparency of the model's decision process and assist the users in validating the model's decisions and gain new insight into the phenomenon of tool wear itself.

关键词： Productivity Industries Engineering management Machine learning Acoustic emission Industrial engineering Sensors

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：