检索结果-内蒙古大学图书馆

Surrogate Modeling: Review and Opportunities for Expert Knowledge Integration

Procedia Computer Science 2025年 257卷 826-833页

作者： Dušan Šturek Sanja Lazarova-Molnar Institute of Applied Informatics and Formal Description Methods Karlsruhe Institute of Technology Kaiserstr. 89 76133 Karlsruhe Germany Mærsk Mc-Kinney Møller Institute University of Southern Denmark Campusvej 55 5230 Odense Denmark

Digital Twins (DTs), essential for digitalization and Industry 4.0, demand high-fidelity yet computationally efficient models for real-time replication of physical systems. However, simulating continuous dynamical systems, often stiff and highly granular, poses significant computational challenges. Driven by industry’s need for more efficient simulations, this study explores Surrogate Modeling (SMing) as a solution to reduce computational costs while preserving accuracy, enabling real-time performance, iterative design optimization and enhancing feasibility of DT simulations. We review existing traditional and machine learning SMing approaches, analyzing their limitations, accuracy and efficiency. We, furthermore, emphasize the critical role of domain expertise in SMing workflows and explore systematic strategies for incorporating expert knowledge to improve model reliability and applicability. Finally, we identify and discuss challenges and opportunities that emerge by the fusion of expert knowledge with machine learning techniques, highlighting their potential to advance next-generation SMing techniques.

关键词： Surrogate Modeling High-fidelity Simulation Knowledge Integration

来源：评论

学校读者我要写书评

暂无评论

Optimum settings for PID control of nonlinear systems

arXiv

引用

arXiv 2025年

作者： Vrabel, R. Slovak University of Technology in Bratislava Institute of Applied Informatics Automation and Mechatronics Bottova 25 Trnava917 01 Slovakia

This paper investigates the application of piecewise linear approximation for the control of nonlinear systems, particularly focusing on the effective linearization of systems modeled by the differential equation y(n) + f(y, y', . . . , y(n-1)) = u(t). We explore the use of PID controllers in conjunction with piecewise linearization, tackling the challenges of nonlinear dynamics by dividing the function f into smaller regions or simplices over a predefined compact set D ⊂ Rn. The parameter h determines the number of linear pieces and influences the approximation accuracy. By increasing h, the system's behavior increasingly mirrors that of the original nonlinear system, leading to enhanced performance of the control system. The paper further discusses the optimization of PID controller parameters through the Particle Swarm Optimization method, with a focus on minimizing the ITAE and ISO criteria. Numerical simulations demonstrate the efficacy of the approach, highlighting the trade-off between computational complexity and approximation accuracy in the context of control system *** Codes 93C10 © 2025, CC BY.

关键词： Three term control systems

来源：评论

学校读者我要写书评

暂无评论

A Conceptual Framework for Digital Twins of Multi-Agent Systems 16

A Conceptual Framework for Digital Twins of Multi-Agent Syst...

引用

16th International Conference on Ambient Systems, Networks and Technologies Networks, ANT 2025 / 8th International Conference on Emerging Data and Industry 4.0, EDI40 2025

作者： Lee, Hui Min Jamali, Ruhollah Lazarova-Molnar, Sanja Institute of Applied Informatics and Formal Description Methods Karlsruhe Institute of Technology Kaiserstr. 89 Karlsruhe76133 Germany The Maersk Mc Kinney Moller Institute University of Southern Denmark Campusvej 55 Odense5230 Denmark

Multi-agent Systems (MASs) are complex systems made up of agents that can be any entities with the ability to interact autonomously and make decentralized decision-making to solve complex problems. Data-driven Agent-based Modeling and Simulation (DDABMS) equips MASs with access to decisions based on near-real-time data, allowing for more informed decisions for systems' enhancements. Digital Twins (DTs) can further enhance MASs by serving as virtual replicas that enable what-if scenarios exploration and allow continuous validation and refinement of the underlying models with real-time data from MASs. However, we discovered a gap in systematically integrating DTs with DDABMS, as existing efforts focus on specific problems and domains rather than providing a generalized framework to develop DTs with DDABMS. This paper addresses this gap by proposing a generalized framework to develop DTs for MASs with DDABMS. To demonstrate the practicability of our proposed framework for modeling and simulation of complex systems, we present an illustrative case study based on an epidemiological Susceptible-Infected-Recovered model. © 2025 Elsevier B.V.. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Surrogate Modeling: Review and Opportunities for Expert Knowledge Integration 16

Surrogate Modeling: Review and Opportunities for Expert Know...

引用

16th International Conference on Ambient Systems, Networks and Technologies Networks, ANT 2025 / 8th International Conference on Emerging Data and Industry 4.0, EDI40 2025

作者： Šturek, Dušan Lazarova-Molnar, Sanja Institute of Applied Informatics and Formal Description Methods Karlsruhe Institute of Technology Kaiserstr. 89 Karlsruhe76133 Germany Mærsk Mc-Kinney Møller Institute University of Southern Denmark Campusvej 55 Odense5230 Denmark

Digital Twins (DTs), essential for digitalization and Industry 4.0, demand high-fidelity yet computationally efficient models for real-time replication of physical systems. However, simulating continuous dynamical systems, often stiff and highly granular, poses significant computational challenges. Driven by industry's need for more efficient simulations, this study explores Surrogate Modeling (SMing) as a solution to reduce computational costs while preserving accuracy, enabling real-time performance, iterative design optimization and enhancing feasibility of DT simulations. We review existing traditional and machine learning SMing approaches, analyzing their limitations, accuracy and efficiency. We, furthermore, emphasize the critical role of domain expertise in SMing workflows and explore systematic strategies for incorporating expert knowledge to improve model reliability and applicability. Finally, we identify and discuss challenges and opportunities that emerge by the fusion of expert knowledge with machine learning techniques, highlighting their potential to advance next-generation SMing techniques. © 2025 Elsevier B.V.. All rights reserved.

关键词： High-fidelity Simulation Knowledge Integration Surrogate Modeling

来源：评论

学校读者我要写书评

暂无评论

Validation Towards Realistic Synthetic Datasets in Production Planning 24

Validation Towards Realistic Synthetic Datasets in Productio...

引用

Proceedings of the Winter Simulation Conference

作者： Jan Michael Spoor Marvin Matthes Martin Krockert Jens Weber Institute for Information Management in Engineering Karlsruhe Institute of Technology GERMANY Dept. of Informatics & Mathematics University of Applied Sciences Dresden GERMANY Faculty of Technology Baden-Wuerttemberg Cooperative State University Lörrach GERMANY

ISBN: (纸本)9798331534202

For large-scale simulations, a sufficient data amount is required. Despite an increasing data availability, it is still challenging to gather large-scale datasets, which are comprehensive, correct, accessible, and realistic, to validate new algorithms and models. An alternative is the use of synthetic data. Thus, we propose a novel methodology to generate realistic datasets. Based upon the statistical properties of real-world data, synthetic datasets are generated by ML models and filtered for anomalous values. The generated datasets are then compared to find the most suitable one. For this validation procedure, a modified Hopfield neural network model is extended to enable an analysis of sequences and to derive a comparison metric. The method demonstrates its applicability by providing an in-depth comparison of all tested data generators using a real-world dataset of a mid-size manufacturing company, whereby transformer-based generators proved most suitable. More diverse use cases should be evaluated in future research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analyzing Spatio-Temporal Dynamics of Dissolved Oxygen for the River Thames using Superstatistical Methods and Machine Learning

arXiv

引用

arXiv 2025年

作者： He, Hankun Boehringer, Takuya Schäfer, Benjamin Heppell, Kate Beck, Christian Centre for Complex Systems Queen Mary University of London United Kingdom University College London United Kingdom Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Germany Chilterns National Landscape United Kingdom School of Geography Queen Mary University of London United Kingdom

By employing superstatistical methods and machine learning, we analyze time series data of water quality indicators for the River Thames (UK). The indicators analyzed include dissolved oxygen, temperature, electrical conductivity, pH, ammonium, turbidity, and rainfall, with a specific focus on the dynamics of dissolved oxygen. After detrending, the probability density functions of dissolved oxygen fluctuations exhibit heavy tails that are effectively modeled using q-Gaussian distributions. Our findings indicate that the multiplicative Empirical Mode Decomposition method stands out as the most effective detrending technique, yielding the highest log-likelihood in nearly all fittings. We also observe that the optimally fitted width parameter of the q-Gaussian shows a negative correlation with the distance to the sea, highlighting the influence of geographical factors on water quality dynamics. In the context of same-time prediction of dissolved oxygen, regression analysis incorporating various water quality indicators and temporal features identify the Light Gradient Boosting Machine as the best model. SHapley Additive exPlanations reveal that temperature, pH, and time of year play crucial roles in the predictions. Furthermore, we use the Transformer, a state-of-the-art machine learning model, to forecast dissolved oxygen concentrations. For long-term forecasting, the Informer model consistently delivers superior performance, achieving the lowest Mean Absolute Error and Symmetric Mean Absolute Percentage Error with the 192 historical time steps that we used. This performance is attributed to the Informer’s ProbSparse self-attention mechanism, which allows it to capture long-range dependencies in time-series data more effectively than other machine learning models. It effectively recognizes the half-life cycle of dissolved oxygen, with particular attention to critical periods such as morning to early afternoon, late evening to early morning, and key intervals between t

关键词： Aquatic ecosystems

来源：评论

学校读者我要写书评

暂无评论

Extrusion printing of radio frequency coplanar waveguides with commercial dispensing equipment

引用

Flexible and Printed Electronics 2025年第2期10卷

作者： Md Ashif, Nowab Reza Gengenbach, Ulrich Maier, Pascal Kotz, Alexander Koos, Christian Sieber, Ingo Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Karlsruhe Germany Institute of Photonics and Quantum Electronics Karlsruhe Institute of Technology Karlsruhe Germany Institute of Microstructure Technology Karlsruhe Institute of Technology Karlsruhe Germany

Coplanar waveguides (CPWs) are fundamental components of radio frequency and microwave circuits used for a variety of applications in telecommunications, radar systems and wireless communications. There is a need for low-cost and easily accessible manufacturing techniques that enable the fabrication of CPWs using commercial materials and equipment, thus reducing production costs and facilitating easy access to these versatile transmission lines. In this paper, we present CPWs on alumina substrates fabricated with an extrusion printing process based on low-cost commercial dispensing equipment and a commercial silver ink. For a 4 mm long CPW, we observe an insertion loss below 1 dB and a return loss better than 10 dB for the frequency range from 40 MHz to 33.8 GHz. © 2025 The Author(s). Published by IOP Publishing Ltd.

关键词： Extrusion

来源：评论

学校读者我要写书评

暂无评论

Mixed-Integer vs. Real-Valued Formulations of Battery Scheduling Problems

引用

IFAC-PapersOnLine 2018年第28期51卷 350-355页

作者： Murray, Alexander Faulwasser, Timm Hagenmeyer, Veit Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Karlsruhe Germany

Coordinating the charging and discharging of a population of batteries with respect to load and generation forecasts decreases operating costs. However, in the case of asymmetric charging and discharging efficiencies the mathematical formulation of this problem is not straightforward. This paper compares the scheduling problem for a population of batteries in two formulations: mixed-integer (MINLP) and non-convex real-valued (NLP). In the case of the latter, the resulting separable NLP is solved using the Augmented Lagrangian based Alternating Direction Inexact Newton (ALADIN). In the case of the latter, the resulting MINLP is solved in hierarchical distributed fashion, we propose a mixed-integer extension of ALADIN. Real load and generation data is used to create an example of 54 batteries demonstrating improved performance for the MINLP formulation. © 2018

关键词： Charging (batteries) Constrained optimization Natural language processing systems Operating costs Scheduling Secondary batteries Standby power systems ALADIN Alternating directions Augmented Lagrangians Distributed optimization Generation forecast Mathematical formulation MINLP Scheduling problem

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Distributed Mixed-Integer Optimization for Reactive Power Dispatch

引用

IFAC-PapersOnLine 2018年第28期51卷 368-373页

作者： Murray, Alexander Engelmann, Alexander Hagenmeyer, Veit Faulwasser, Timm Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Karlsruhe Germany

One key aspect of power system operation is the minimization of line losses while maintaining voltages within certain limits. Doing so can be achieved through the use of voltage regulators, tap changing transformers, and shunt capacitors. However, both tap changing transformers and/or shunt capacitors are operated in a discrete manner, i.e. the inputs can only take finitely many discrete values. Thus, the problem of minimizing line losses while maintaining voltage stability can be cast as a mixed-integer optimization problem. For large grids or cases where independent entities have concurrent control of the system, distributed optimization provides a solution. The present paper discusses a hierarchically distributed approach; i.e. the problem is partitioned into local subproblems and solved using a mixed-integer extension of the Augmented Lagrangian based Alternating Direction Inexact Newton (ALADIN) algorithm. We present results for the IEEE 14- and 30-bus systems and compare them with previous approaches, such as particle swarm optimization and genetic algorithms. © 2018

关键词： Electric load dispatching Concurrency control Constrained optimization Electric load flow Genetic algorithms Integer programming Particle swarm optimization (PSO) Reactive power Voltage regulators Alternating directions Distributed approaches Distributed optimization Mixed integer optimization Mixed integer problems Optimal power flows Power system operations Reactive power dispatch

来源：评论

学校读者我要写书评

暂无评论

It's a Match - Enhancing the Fit between Users and Phishing Training through Personalisation 25

It's a Match - Enhancing the Fit between Users and Phishing ...

引用

Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

作者： Lorin Schöni Neele Roch Hannah Sievers Martin Strohmeier Peter Mayer Verena Zimmermann Security Privacy & Society ETH Zurich Zurich Switzerland armasuisse Thun Switzerland Department of Mathematics and Computer Science University of Southern Denmark Odense Denmark and Institute of Applied Informatics and Formal Description Methods Karlsruhe Institute of Technology Karlsruhe Germany Department of Humanities Social and Political Sciences ETH Zürich Zürich Switzerland

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：