检索结果-内蒙古大学图书馆

Structural dynamic effects of the freewheel-clutch in e-bike drive units using a hybrid measurement and simulation approach

引用

JOURNAL OF VIBRATION AND CONTROL 2025年

作者： Steinbach, Kevin Lechler, Dominik Kraemer, Peter Gross, Iris Reith, Dirk Robert Bosch GmbH eBike Syst Engn Platform Dr Unit D-72770 Reutlingen Germany Univ Siegen Dept Mech Engn Siegen Germany Univ Appl Sci Bonn Rhein Sieg Inst Technol Resource Efficiency & Energy Efficien St Augustin Germany Fraunhofer Inst Algorithms & Sci Comp SCAI St Augustin Germany

This study aims to investigate the bearing-free freewheel-clutch and its significant role in structural dynamic effects in e-bike drive units. It hypothesizes that the freewheel's flexibility and a lack of suitable bearings allow rigid body oscillations of the attached gear body which contribute to an overall increase of noise and vibration. As a first step, the method involves a measurement campaign conducted during operation, utilising a specialized test rig that includes torque and rotation sensors and distance-lasers. Combining these results with mathematical operations and direction-dependent forces, the load-dependent and three-dimensional stiffness of the freewheel-clutch is determined. As a second step, it uses dynamic-transient multi-body dynamic simulations to incorporate the gained stiffness as a general force element using spline interpolation and to analyse the system behaviour with subsequent application of frequency response functions and spectrograms. As a result, the determined stiffness reveals a non-linear behaviour, and a frequency calculation indicates that rigid body modes are present up to 5 kHz. Through consideration in the time domain, it can be verified that the system experiences self-excitation solely by varying load, which is independent of the rotational speed, and various resonances occur, especially through a discontinuity of the stiffness curve in the tilting direction. In summary, this study confirms the hypothesis and contributes to an in-depth comprehension that enables enhancing the design of future e-bike drive units.

关键词： Freewheel rigidity structural dynamics system identification dynamic-transient simulation experimental validation

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 (IEEM)

作者： Schmetz, A. Vahl, C. Zhen, Z. Reibert, D. Mayer, S. Zontar, D. Garcke, J. Brecher, C. Fraunhofer Inst Prod Technol IPT Aachen Germany Fraunhofer Ctr Machine Learning St Augustin Germany Fraunhofer Inst Algorithms & Sci Comp SCAI St Augustin Germany Rhein Westfal TH Aachen Lab Machine Tools & Prod Engn WZL Aachen Germany

ISBN: (纸本)9781665437714

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： Predictive maintenance condition monitoring interpretable ML explainable AI acoustic emission

来源：评论

学校读者我要写书评

暂无评论

AI reveals insights into link between CD33 and cognitive impairment in Alzheimer's Disease

引用

PLOS compUTATIONAL BIOLOGY 2023年第2期19卷 e1009894-e1009894页

作者： Raschka, Tamara Sood, Meemansa Schultz, Bruce Altay, Aybuge Ebeling, Christian Froehlich, Holger Fraunhofer Inst Algorithms & Sci Comp SCAI Dept Bioinformat St Augustin Germany Univ Bonn Bonn Aachen Int Ctr Informat Technol B IT Bonn Germany Fraunhofer Ctr Machine Learning St Augustin Germany Max Planck Inst Mol Genet Dept Computat Mol Biol Berlin Germany

Author summaryFor the last 20 years, the field of Alzheimer's Disease (AD) is marked by a series of continuous failures to deliver demonstrably effective medications to patients. One of the reasons for the continuous failure of trials in AD is the lack of understanding of how targeting a certain molecule would affect cognitive impairment in humans. One way to address this issue is the development of quantitative system level models connecting the molecular level with the phenotype. In this paper we propose a novel hybrid Artificial Intelligence (AI) approach, named Integrative Variational Autoencoder Modular Bayesian Networks (iVAMBN), combining clinical and patient level gene expression data while incorporating a disease focused knowledge graph. The model showed connections between various biological mechanisms playing a role in AD and allowed us to simulate a down-expression of the putative drug target CD33. Results showed a significantly increased cognition and predicted perturbation of several biological mechanisms. We experimentally validated these predictions using gene expression data from a knock-out THP-1 monocyte cell line, which confirmed our model predictions up to a very high extent. To our knowledge, we thus developed the first experimentally validated, quantitative, multi-scale model connecting molecular mechanisms with clinical outcomes in the AD field. Modeling biological mechanisms is a key for disease understanding and drug-target identification. However, formulating quantitative models in the field of Alzheimer's Disease is challenged by a lack of detailed knowledge of relevant biochemical processes. Additionally, fitting differential equation systems usually requires time resolved data and the possibility to perform intervention experiments, which is difficult in neurological disorders. This work addresses these challenges by employing the recently published Variational Autoencoder Modular Bayesian Networks (VAMBN) method, which we here trained

关键词： Gene expression Prostaglandin Alzheimer's disease Human learning Cognitive impairment Learning Clustering algorithms Statistical distributions

来源：评论

学校读者我要写书评

暂无评论

CLEP: a hybrid data- and knowledge-driven framework for generating patient representations

引用

BIOINFORMATICS 2021年第19期37卷 3311-3318页

作者： Bharadhwaj, Vinay Srinivas Ali, Mehdi Birkenbihl, Colin Mubeen, Sarah Lehmann, Jens Hofmann-Apitius, Martin Hoyt, Charles Tapley Domingo-Fernandez, Daniel Fraunhofer Inst Algorithms & Sci Comp Dept Bioinformat D-53757 St Augustin Germany Univ Bonn Bonn Aachen Int Ctr Informat Technol B IT D-53115 Bonn Germany Rheinische Friedrich Wilhelms Univ Bonn D-53113 Bonn Germany Fraunhofer Inst Intelligent Anal & Informat Syst Dresden Germany Fraunhofer Inst Intelligent Anal & Informat Syst St Augustin Germany Fraunhofer Ctr Machine Learning Bonn Germany

A Summary: As machine learning and artificial intelligence increasingly attain a larger number of applications in the biomedical domain, at their core, their utility depends on the data used to train them. Due to the complexity and high dimensionality of biomedical data, there is a need for approaches that combine prior knowledge around known biological interactions with patient data. Here, we present CLinical Embedding of Patients (CLEP), a novel approach that generates new patient representations by leveraging both prior knowledge and patient-level data. First, given a patient-level dataset and a knowledge graph containing relations across features that can be mapped to the dataset, CLEP incorporates patients into the knowledge graph as new nodes connected to their most characteristic features. Next, CLEP employs knowledge graph embedding models to generate new patient representations that can ultimately be used for a variety of downstream tasks, ranging from clustering to classification. We demonstrate how using new patient representations generated by CLEP significantly improves performance in classifying between patients and healthy controls for a variety of machine learning models, as compared to the use of the original transcriptomics data. Furthermore, we also show how incorporating patients into a knowledge graph can foster the interpretation and identification of biological features characteristic of a specific disease or patient subgroup. Finally, we released CLEP as an open source Python package together with examples and documentation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based detection of psychiatric attributes from German mental health records

引用

INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS 2022年第0期161卷 104724-104724页

作者： Madan, Sumit Zimmer, Fabian Julius Balabin, Helena Schaaf, Sebastian Frohlich, Holger Fluck, Juliane Neuner, Irene Mathiak, Klaus Hofmann-Apitius, Martin Sarkheil, Pegah Fraunhofer Inst Algorithms & Sci Comp SCAI Dept Bioinformat Schloss Birlinghoven D-53757 St Augustin Germany Univ Bonn Inst Comp Sci D-53113 Bonn Germany Rhein Westfal TH Aachen Dept Psychiat Psychotherapy & Psychosomat Fac Med Pauwelsstr 30 D-52074 Aachen Germany German Ctr Neurodegenerat Dis DZNE HPC & Sci Comp D-53127 Bonn Germany Univ Bonn Bonn Aachen Int Ctr Informat Technol B IT D-53113 Bonn Germany ZB Medinformat Ctr Life Sci Knowledge Management D-50931 Cologne Germany Univ Bonn Agr Fac D-53115 Bonn Germany Univ Munster Dept Psychiat & Psychotherapy D-48149 Munster Germany

Background: Health care records provide large amounts of data with real-world and longitudinal aspects, which is advantageous for predictive analyses and improvements in personalized medicine. Text-based records are a main source of information in mental health. Therefore, application of text mining to the electronic health records - especially mental state examination - is a key approach for detection of psychiatric disease phenotypes that relate to treatment ***: We focused on the mental state examination (MSE) in the patients' discharge summaries as the key part of the psychiatric records. We prepared a sample of 150 text documents that we manually annotated for psychiatric attributes and symptoms. These documents were further divided into training and test sets. We designed and implemented a system to detect the psychiatric attributes automatically and linked the pathologically assessed attributes to AMDP terminology. This workflow uses a pre-trained neural network model, which is fine-tuned on the training set, and validated on the independent test set. Furthermore, a traditional NLP and rule-based component linked the recognized mentions to AMDP terminology. In a further step, we applied the system on a larger clinical dataset of 510 patients to extract their ***: The system identified the psychiatric attributes as well as their assessment (normal and pathological) and linked these entities to the AMDP terminology with an F-1-score of 86% and 91% on an independent test set, ***: The development of the current text mining system and the results highlight the feasibility of text mining methods applied to MSE in electronic mental health care reports. Our findings pave the way for the secondary use of routine data in the field of mental health, facilitating further clinical data analyses.

关键词： Electrical Health Records Mental State Examination Clinical Text Mining Deep Learning AMDP

来源：评论

学校读者我要写书评

暂无评论

MultiPaths: a Python framework for analyzing multi-layer biological networks using diffusion algorithms

引用

BIOINFORMATICS 2021年第1期37卷 137-139页

作者： Marin-Llao, Josep Mubeen, Sarah Perera-Lluna, Alexandre Hofmann-Apitius, Martin Picart-Armada, Sergio Domingo-Fernandez, Daniel Fraunhofer Inst Algorithms & Sci Comp SCAI Dept Bioinformat D-53757 St Augustin Germany Univ Politecn Cataluna Dept Engn Sistemes Automat & Informat Ind B2SLab CIBER BBN Barcelona 08028 Spain Fraunhofer Ctr Machine Learning Munich Germany

A Summary: High-throughput screening yields vast amounts of biological data which can be highly challenging to interpret. In response, knowledge-driven approaches emerged as possible solutions to analyze large datasets by leveraging prior knowledge of biomolecular interactions represented in the form of biological networks. Nonetheless, given their size and complexity, their manual investigation quickly becomes impractical. Thus, computational approaches, such as diffusion algorithms, are often employed to interpret and contextualize the results of high-throughput experiments. Here, we present MultiPaths, a framework consisting of two independent Python packages for network analysis. While the first package, DiffuPy, comprises numerous commonly used diffusion algorithms applicable to any generic network, the second, DiffuPath, enables the application of these algorithms on multi-layer biological networks. To facilitate its usability, the framework includes a command line interface, reproducible examples and documentation. To demonstrate the framework, we conducted several diffusion experiments on three independent multi-omics datasets over disparate networks generated from pathway databases, thus, highlighting the ability of multi-layer networks to integrate multiple modalities. Finally, the results of these experiments demonstrate how the generation of harmonized networks from disparate databases can improve predictive performance with respect to individual resources.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Methodology for Integrating Hierarchical VMAP-Data Structures into an Ontology Using Semantically Represented Analyses

引用

INFORMATION 2024年第1期15卷 21-21页

作者： Spelten, Philipp Meyer, Morten-Christian Wagner, Anna Wolf, Klaus Reith, Dirk Fraunhofer Inst Algorithms & Sci Comp SCAI D-53757 St Augustin Germany PROSTEP AG Dolivostr 11 D-64293 Darmstadt Germany Bonn Rhein Sieg Univ Appl Sci Inst Technol Resource & Energy Efficient Engn TREE Grantham Allee 20 D-53757 Bonn Germany

Integrating physical simulation data into data ecosystems challenges the compatibility and interoperability of data management tools. Semantic web technologies and relational databases mostly use other data types, such as measurement or manufacturing design data. Standardizing simulation data storage and harmonizing the data structures with other domains is still a challenge, as current standards such as the ISO standard STEP (ISO 10303 "Standard for the Exchange of Product model data") fail to bridge the gap between design and simulation data. This challenge requires new methods, such as ontologies, to rethink simulation results integration. This research describes a new software architecture and application methodology based on the industrial standard "Virtual Material Modelling in Manufacturing" (VMAP). The architecture integrates large quantities of structured simulation data and their analyses into a semantic data structure. It is capable of providing data permeability from the global digital twin level to the detailed numerical values of data entries and even new key indicators in a three-step approach: It represents a file as an instance in a knowledge graph, queries the file's metadata, and finds a semantically represented process that enables new metadata to be created and instantiated.

关键词： ontology simulation process data management CAE metadata structures semantic technologies

来源：评论

学校读者我要写书评

暂无评论

Challenges and opportunities in quantum optimization

NATURE REVIEWS PHYSICS

引用

NATURE REVIEWS PHYSICS 2024年第12期6卷 718-735页

作者： Abbas, Amira Ambainis, Andris Augustino, Brandon Baertschi, Andreas Buhrman, Harry Coffrin, Carleton Cortiana, Giorgio Dunjko, Vedran Egger, Daniel J. Elmegreen, Bruce G. Franco, Nicola Fratini, Filippo Fuller, Bryce Gacon, Julien Gonciulea, Constantin Gribling, Sander Gupta, Swati Hadfield, Stuart Heese, Raoul Kircher, Gerhard Kleinert, Thomas Koch, Thorsten Korpas, Georgios Lenk, Steve Marecek, Jakub Markov, Vanio Mazzola, Guglielmo Mensa, Stefano Mohseni, Naeimeh Nannicini, Giacomo O'Meara, Corey Tapia, Elena Pena Pokutta, Sebastian Proissl, Manuel Rebentrost, Patrick Sahin, Emre Symons, Benjamin C. B. Tornow, Sabine Valls, Victor Woerner, Stefan Wolf-Bauwens, Mira L. Yard, Jon Yarkoni, Sheir Zechiel, Dirk Zhuk, Sergiy Zoufal, Christa Univ Amsterdam Inst Phys Amsterdam Netherlands QuSoft Amsterdam Netherlands Univ Latvia Fac Comp Riga Latvia MIT Sloan Sch Management 77 Massachusetts Ave Cambridge MA 02139 USA Los Alamos Natl Lab CCS Informat Sci 3 Los Alamos NM USA Univ Amsterdam CWI Amsterdam Netherlands Los Alamos Natl Lab Adv Network Sci Initiat Los Alamos NM USA E ON Digital Technol GmbH Hannover Germany Leiden Univ Appl Quantum Algorithms Initiat Leiden Netherlands IBM Res Europe Zurich IBM Quantum Ruschlikon Switzerland IBM TJ Watson Res Ctr IBM Res Yorktown Hts NY USA Fraunhofer Inst Cognit Syst IKS Quantum Enhanced AI Dept Munich Germany Erste Grp Bank AG Erste Digital GmbH Vienna Austria IBM TJ Watson Res Ctr IBM Quantum Yorktown Hts NY USA Ecole Polytech Fed Lausanne Inst Phys Lausanne Switzerland Wells Fargo Adv Technol New York NY USA Tilburg Univ Dept Econometr & Operat Res Tilburg Netherlands NASA Ames Res Ctr Quantum Artificial Intelligence Lab QuAIL Moffett Field CA 94035 USA Univ Space Res Assoc RIACS Mountain View CA USA Fraunhofer ITWM Optimizat Dept Kaiserslautern Germany Quantagonia GmbH Bad Homburg Germany Zuse Inst Berlin Appl Algorithm Intelligence Methods Berlin Germany Tech Univ Berlin Software & Algorithms Discrete Optimizat Berlin Germany HSBC Quantum Technol Grp Emerging Technol Innovat & Ventures Singapore Singapore Czech Tech Univ Dept Comp Sci Prague Czech Republic Athena Res Ctr Archimedes Res Unit AI Data Sci & Algorithms Maroussi Greece Fraunhofer Inst Optron Syst Technol & Image Explo Appl Syst Technol Div AST Cognit Energy Syst Dept Ilmenau Germany German Aerosp Ctr DLR Inst Quantum Technol Ulm Germany Univ Zurich Inst Computat Sci Zurich Switzerland STFC Sci Tech Daresbury Hartree Ctr Daresbury England Univ Southern Calif Dept Ind & Syst Engn Los Angeles CA 90007 USA Zuse Inst Berlin Berlin Germany Tech Univ Berlin Inst Math Berlin Germany Natl Univ Singapore Ctr Quantum Technol Singapore Singapore Univ B

Quantum computers have demonstrable ability to solve problems at a scale beyond brute-force classical simulation. Interest in quantum algorithms has developed in many areas, particularly in relation to mathematical optimization - a broad field with links to computer science and physics. In this Review, we aim to give an overview of quantum optimization. Provably exact, provably approximate and heuristic settings are first explained using computational complexity theory, and we highlight where quantum advantage is possible in each context. Then, we outline the core building blocks for quantum optimization algorithms, define prominent problem classes and identify key open questions that should be addressed to advance the field. We underscore the importance of benchmarking by proposing clear metrics alongside suitable optimization problems, for appropriate comparisons with classical optimization techniques, and discuss next steps to accelerate progress towards quantum advantage in optimization.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

PS4DR: a multimodal workflow for identification and prioritization of drugs based on pathway signatures

引用

BMC BIOINFORMATICS 2020年第1期21卷 231-231页

作者： Emon, Mohammad Asif Domingo-Fernandez, Daniel Hoyt, Charles Tapley Hofmann-Apitius, Martin Fraunhofer Inst Algorithms & Sci Comp Fraunhofer Dept Bioinformat D-53757 St Augustin Germany Rhein Friedrich Wilhelms Univ Bonn Bonn Aachen Int Ctr IT D-53117 Bonn Germany

Background During the last decade, there has been a surge towards computational drug repositioning owing to constantly increasing -omics data in the biomedical research field. While numerous existing methods focus on the integration of heterogeneous data to propose candidate drugs, it is still challenging to substantiate their results with mechanistic insights of these candidate drugs. Therefore, there is a need for more innovative and efficient methods which can enable better integration of data and knowledge for drug repositioning. Results Here, we present a customizable workflow (PS4DR) which not only integrates high-throughput data such as genome-wide association study (GWAS) data and gene expression signatures from disease and drug perturbations but also takes pathway knowledge into consideration to predict drug candidates for repositioning. We have collected and integrated publicly available GWAS data and gene expression signatures for several diseases and hundreds of FDA-approved drugs or those under clinical trial in this study. Additionally, different pathway databases were used for mechanistic knowledge integration in the workflow. Using this systematic consolidation of data and knowledge, the workflow computes pathway signatures that assist in the prediction of new indications for approved and investigational drugs. Conclusion We showcase PS4DR with applications demonstrating how this tool can be used for repositioning and identifying new drugs as well as proposing drugs that can simulate disease dysregulations. We were able to validate our workflow by demonstrating its capability to predict FDA-approved drugs for their known indications for several diseases. Further, PS4DR returned many potential drug candidates for repositioning that were backed up by epidemiological evidence extracted from scientific literature. Source code is freely available at https://github. com/ps4dr/ps4dr..

关键词： Drug repositioning Drug discovery Multi-omics Pathways Software Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Reprint of: Application cases of biological transformation in manufacturing technology

引用

CIRP JOURNAL OF MANUFACTURING sciENCE AND TECHNOLOGY 2021年 34卷 95-104页

作者： Bergs, T. Schwaneberg, U. Barth, S. Hermann, L. Grunwald, T. Mayer, S. Biermann, F. Soezer, N. Rhein Westfal TH Aachen Lab Machine Tools & Prod Engn WZL Campus Blvd 30 D-52074 Aachen Germany Fraunhofer Inst Prod Technol IPT Steinbachstr 17 D-52074 Aachen Germany Rhein Westfal TH Aachen Inst Biotechnol ABBt Worringerweg 3 D-52074 Aachen Germany Fraunhofer Inst Algorithms & Sci Comp SCAI Schloss Birlinghoven 1 D-53757 St Augustin Germany

Digitalization and Industry 4.0 are promising developments for solving current technical challenges. However, to fully exploit the potential of digitalization and Industry 4.0, not only manufacturing and information systems must interact, but biological systems too. The interaction of biological, manufacturing and information systems is an emerging research field defined as Biological Transformation in manufacturing or biologicalisation in manufacturing. This publication introduces three different projects that represent the application of Biological Transformation in manufacturing to inspire and initiate further research in this area. The interactions of the three system types are described in detail, and their potential for the manufacturing sector is discussed in reference to the framework Biological Transformation in manufacturing. (C) 2020 The Author(s).

关键词： Biologicalisation in manufacturing Manufacturing technology Bioinspired manufacturing Manufacturing systems Biological transformation in manufacturing

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：