检索结果-内蒙古大学图书馆

Sustainable Power and Energy conference (iSPEC)

作者： Yanzhao Chang Chenhao Gai Changgang Li Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education Shandong University Jinan China

ISBN: (纸本)9781665414401

Emergency load shedding (ELS) optimization by the meta-heuristic algorithm is confronted with a heavy computing burden as time-domain simulation (TDS) is needed to evaluate individuals. In this paper, an ELS optimization algorithm based on differential evolution driven by deep transfer learning is proposed to decrease TDS times. First, an optimization model of ELS is established in a single scenario based on differential evolution. Then, a Deep Belief Network (DBN) model is deployed to evaluate load shedding schemes to speed up the optimization. Moreover, when scenarios are changed, transfer learning is utilized to update the DBN model, avoiding massive samples regeneration by TDS. Finally, the optimal load shedding scheme is rolling updated following scenarios change. A simplified provincial power grid verifies the effectiveness of the proposed algorithm.

关键词： Computational modeling conferences Transfer learning Load shedding Power grids Time-domain analysis optimization

来源：评论

学校读者我要写书评

暂无评论

Accurate modeling of Antenna Structures by Means of Domain Confinement and Gradient-Enhanced Kriging

Accurate Modeling of Antenna Structures by Means of Domain C...

引用

European conference on Antennas and Propagation, EuCAP

作者： Anna Pietrenko-Dabrowska Slawomir Koziel Muath Al-Hasan Faculty of Electronics Telecommunications and Informatics Gdansk University of Technology Gdansk Poland Engineering Optimization & Modeling Center Reykjavik University Reykjavik Iceland Al Ain University Abu Dhabi United Arab Emirates

ISBN: (纸本)9788831299022;9781728188454

High cost of electromagnetic (EM)-simulation-based antenna design fosters the incorporation of surrogate modeling techniques as the most promising tools for expediting the procedures such as parametric optimization or uncertainty quantification. Data-driven metamodels are by far the most popular ones due to their versatility and easy handling even by inexperienced users. Notwithstanding, construction of reliable surrogates for contemporary antenna structures is, in a large part, hindered by the curse of dimensionality and nonlinear relationships between the geometry parameters and antenna characteristics. A possible workaround are performance-driven modeling methods. The idea it to restrict the construction of the surrogate to small parts of the parameter space, containing designs that are of high quality with respect to the relevant figures of interest. This leads to a significant reduction of the required number of training samples, the improvement of the model predictive power, and a possibility of representing antenna outputs over broad ranges of operating conditions. The model domain is established using the sets of so-called reference designs that need to be pre-optimized beforehand. The CPU cost of this acquisition adds to the overall expenses of surrogate model setup and may undermine the computational benefits of the performance-driven modeling paradigm. This paper proposes an alternative approach, where gradient-enhanced kriging is employed to reduce the number of required reference points, thus leading to lowering the cost of the model setup without compromising its accuracy. A quasi-Yagi antenna example is provided for demonstration purposes.

关键词： Training Geometry Uncertainty Limiting Computational modeling Tools Predictive models

来源：评论

学校读者我要写书评

暂无评论

2nd International conference on Artificial Intelligence in HCI, AI-HCI 2021, Held as Part of the 23rd HCI International conference, HCII 2021

2nd International Conference on Artificial Intelligence in H...

引用

2nd International conference on Artificial Intelligence in HCI, AI-HCI 2021, Held as Part of the 23rd HCI International conference, HCII 2021

ISBN: (纸本)9783030777715

The proceedings contain 36 papers. The special focus in this conference is on Artificial Intelligence in HCI. The topics include: How Intuitive Is It? Comparing Metrics for Attitudes in Argumentation with a Human Baseline;What Does It Mean to Explain? A User-Centered Study on AI Explainability;Morality Beyond the Lines: Detecting Moral Sentiment Using AI-Generated Synthetic Context;designing a Gender-Inclusive Conversational Agent For Pair Programming: An Empirical Investigation;estimation of Learners’ Engagement Using Face and Body Features by Transfer Learning;toward Automated Mixed Reality Interface Design: An Evolutionary optimization Approach;building Conversational Agents for Military Training: Towards a Virtual Wingman;natural Interaction with Traffic Control Cameras Through Multimodal Interfaces;why Developing simulation Capabilities Promotes Sustainable Adaptation to Climate Change;towards an Ambient Smart City: Using Augmented Reality to Geospatially Filter the Right Airbnb via Artificial Intelligence;Disentangling Trust and Anthropomorphism Toward the Design of Human-Centered AI Systems;Assisting Text Localization and Transcreation Tasks Using AI-Based Masked Language modeling;KLSI Methods for Human Simultaneous Interpretation and Towards Building a Simultaneous Machine Translation System Reflecting the KLSI Methods;investigating Viewer’s Reliance on Captions Based on Gaze Information;pet Dogs’ and Their Owners’ Reactions Toward Four Differently Shaped Speaking Agents: A Report on Qualitative Results in a Pilot Test;a Questionnaire Data Clustering Method Based on Optimized K-Modes Algorithm;Automatic Generation of Machine Learning Synthetic Data Using ROS;visual Prediction Based on Photorealistic Style Transfer;Towards Design Principles for User-Centric Explainable AI in Fraud Detection;HCD3A: An HCD Model to Design Data-driven Apps;foreword.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Warm-Start Expedited optimization of Antenna Structures Using Kriging Surrogates and Iterative Correction Scheme 23

Warm-Start Expedited Optimization of Antenna Structures Usin...

引用

23rd International Microwave and Radar conference (MIKON)

作者： Koziel, Slawomir Pietrenko-Dabrowska, Anna Reykjavik Univ Engn Optimizat & Modeling Ctr Reykjavik Iceland Gdansk Univ Technol Fac Elect Telecommun & Inf Gdansk Poland

ISBN: (纸本)9788394942175

Electromagnetic (EM)-driven adjustment of geometry parameters, often referred to as design closure, is nowadays a mandatory stage of antenna design process. It is executed to improve the system performance as much as possible while taking into account parameter dependencies that cannot be handled by simpler methods (e.g., theoretical models), typically employed at the initial steps of the antenna development. Unfortunately, EM-based optimization is a time consuming task, especially when the quality of the initial design is poor. This paper proposes a novel framework for accelerated antenna optimization. Our methodology involves a database of previously obtained designs, kriging interpolation models, and an iterative correction scheme for design refinement. The incorporation of pre-existing data permits generation of a good initial design as well as rapid optimization entailing the cost of just a few EM antenna analyses. The technique is demonstrated using a dual-band uniplanar dipole antenna. The structure is optimized within wide ranges of operating frequencies (2 GHz to 3 GHz for the lower band and 4 GHz to 5.5 GHz for the upper band). Benchmarking indicates that the proposed approach exhibits improved computational efficiency and reliability as compared to gradient-based warm-start optimization techniques.

关键词： Antenna design design optimization kriging interpolation EM simulation iterative design correction

来源：评论

学校读者我要写书评

暂无评论

A Data-driven Fault Classification Method for Microgrids

A Data-driven Fault Classification Method for Microgrids

引用

International conference on High Voltage Engineering and Application, ICHVE

作者： Jingsong Wang Yongfu Li Xiaoxiao Luo Han Zhang Wenxia Sima Ming Yang State Key Laboratory of Power Transmission Equipment & System Security and New Technology Chongqing China State Grid Chongqing Electric Power Research Institute Chongqing China

ISBN: (数字)9781665407502

ISBN: (纸本)9781665407519

This paper proposes a method that combines wavelet decomposition and deep learning for fault classification in microgrids (MGs). Random Search optimization is used to find the best wavelet function for matching traces to extract deep features of data. And these extracted deep features are used as complementary inputs to a deep learning model. One-dimension convolutional neural network (1-D CNN) is used to complete the secondary conversion of data features and high-dimensional feature mapping. The data are transformed by dimensionality and bidirectional long and short-term memory network. The data information mining is completed by using the multi-branch structure of the network to filter and merge the multidimensional effective information learned from each network branch. We also compare and analyze five different classification techniques (i.e., k-nearest neighbor(KNN), decision tree(DT), support vector machine(SVM), random forest(RF), and XGBoost(XGB) $)$ and compare their performance statistically. After modeling the MGs system in the simulation software, the Consortium for Electrical Reliability Technology Solutions (CERTS) MG effectively illustrates the validity of our proposed method.

关键词： Deep learning Wavelet transforms Support vector machine classification Microgrids Feature extraction Software Software reliability

来源：评论

学校读者我要写书评

暂无评论

Data-driven Reconstruction of Firing Rate Dynamics in Brain Networks

Data-Driven Reconstruction of Firing Rate Dynamics in Brain ...

引用

IEEE conference on Decision and Control

作者： Xuan Wang Jorge Cortés George Mason University Fairfax University of California San Diego

ISBN: (纸本)9781665436601

This paper studies the reconstruction from data of firing rate dynamics in linear-threshold network models of brain activity. Instead of identifying the system paramaters directly, which would lead to a large number of variables and a highly non-convex objective function, the novelty of our approach stems from reformulating the identification problem as a scalar variable optimization of a discontinuous, nonconvex objective function. We formally show that the reformulated optimization problem has a unique solution and establish that it leads to the identification of all the desired system parameters. These results form the basis for the introduction of an algorithm to find the optimizer that identifies the different regions in the domain of definition of the objective function. The results not only validate the system identifiability but also provide the foundation for further research on data-driven control of firing rate dynamics. We demonstrate the algorithm effectiveness in simulation.

关键词： Firing Heuristic algorithms conferences Linear programming Brain modeling Data models Object recognition

来源：评论

学校读者我要写书评

暂无评论

Auto-generation of hybrid automata for real-time operation optimization of building energy systems 33

Auto-generation of hybrid automata for real-time operation o...

引用

33rd International conference on Efficiency, Cost, optimization, simulation and Environmental Impact of Energy Systems, ECOS 2020

作者： Storek, Thomas Oberkirsch, Laurin Kriwet, Jonathan Baranski, Marc Schreiber, Thomas Muller, Dirk RWTH Aachen University E.ON Energy Research Center Institute for Energy Efficient Buildings and Indoor Climate Aachen Germany

The optimization of operation holds great potential for energy savings in building energy systems (BES). One of the most promising techniques is model predictive control (MPC). In the implementation of MPC for BES, system modeling is the most challenging step. The models do not only need to cover time-varying nonlinear system dynamics, set-point variation and disturbances sufficiently but exhibit very low computation times. Although modeling libraries for BES are available, most of the models lack either accuracy or suffer from high computing times. A solution to this is the transformation of the available complex models into lightweight fast computing data-driven black-box models. However, most of the known modeling approaches lead to models that are neither easy to interpret nor capable of predicting the system behavior of hybrid systems or in states that have not been trained before. To overcome these drawbacks, we introduce a novel modeling approach for MPC known as hybrid automata. Assuming that components of BES exhibit hybrid system behavior we automatically analyze and split our training data into small traces that we approximate with linear time invariant (LTI) models. Extracting transition conditions from the physical models, we concatenate the single LTI models. Finally, the whole set of transitions and LTI models are reformulated to build a global hybrid automaton. Comparing the hybrid automaton model to the original models, we achieve computation time reductions of up to a factor of 125 with only negligible losses in accuracy. Deploying the models in an MPC of a BES equipped with a boiler, heat pump and photovoltaic system, we demonstrate the feasibility of our models for this kind of application. The MPC reduces the energy costs by 14.6% compared to a conventional hysteresis control. © ECOS *** right reserved.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Digital servo control of hydraulic actuator: stepper motion problem

Digital servo control of hydraulic actuator: stepper motion ...

引用

International conference on Electrotechnical Complexes and Systems (ICOECS)

作者： Ruslan Sharipov Arsen Mesrpyan Faculty of aircraft engines energy&transport Ufa State Aviation Technical University Ufa Russia

ISBN: (纸本)9781665407281

In this paper, we propose to solve the digital control problem in hydraulic actuator using a stepper motor to obtain accurate control with fast response. The system include microprocessor, stepper motor driven jet valves and hydraulic cylinder. modeling the system that describes the actuator operation and the digital strategies is crucial to developing a hydraulic smart actuator. The proposed the design and modeling methodology motivated by the solution of the parameter optimization problem of hydraulic actuator, is of general interest for electrical systems with discrete stepping characteristic can be established. (Abstract)

关键词： Digital control Quantization (signal) simulation Microprocessors Hydraulic actuators Process control Hydraulic systems

来源：评论

学校读者我要写书评

暂无评论

Reduced-Cost Constrained modeling of Microwave and Antenna Components: Recent Advances 20th

Reduced-Cost Constrained Modeling of Microwave and Antenna C...

引用

20th Annual International conference on Computational Science (ICCS)

作者： Pietrenko-Dabrowska, Anna Koziel, Slawomir Leifsson, Leifur Gdansk Univ Technol Fac Elect Telecommun & Informat Narutowicza 11-12 PL-80233 Gdansk Poland Reykjavik Univ Sch Sci & Engn Engn Optimizat & Modeling Ctr Menntavegur 1 IS-101 Reykjavik Iceland Iowa State Univ Dept Aerosp Engn Ames IA 50011 USA

ISBN: (纸本)9783030867973;9783030504250

Electromagnetic (EM) simulation models are ubiquitous in the design of microwave and antenna components. EM analysis is reliable but CPU intensive. In particular, multiple simulations entailed by parametric optimization or uncertainty quantification may considerably slow down the design processes. In order to address this problem, it is possible to employ fast metamodels. Here, the popular solution approaches are approximation surrogates, which are versatile and easily accessible. Notwithstanding, the major issue for conventional modeling methods is the curse of dimensionality. In the case of high-frequency components, an added difficulty are highly nonlinear outputs that need to be handled. A recently reported constrained modeling attempts to broaden the applicability of approximation surrogates by confining the surrogate model setup to a small subset of the parameter space. The said region contains the parameter vectors corresponding to high-quality designs w.r.t. the considered figures of interest, which allows for a dramatic reduction of the number of training samples needed to render reliable surrogates without formally restricting the parameter ranges. This paper reviews the recent techniques employing these concepts and provides real-world illustration examples of antenna and microwave structures.

关键词： Microwave engineering Antenna engineering Electromagnetic simulation Surrogate modeling Performance-driven modeling Kriging interpolation

来源：评论

学校读者我要写书评

暂无评论

Discrete simulation-based optimization methods for industrial engineering problems: A systematic literature review

引用

COMPUTERS & INDUSTRIAL ENGINEERING 2019年 128卷 526-540页

作者： de Sousa Junior, Wilson Trigueiro Barra Montevechi, Jose Arnaldo Miranda, Rafael de Carvalho Campos, Afonso Teberga Fed Univ Itajuba UNIFEI Ind Engn & Management Inst Itajuba MG Brazil Fed Univ Sao Joao del Rei UFSJ Acad Unit Ind Engn Sao Joao Del Rei MG Brazil

In recent years, some attention has been driven to modeling, simulation, and optimization techniques capable of representing and improving discrete event systems. These techniques can support decision making helping to determine the best scenario on a combinatorial search space with stochastic variables. This paper presents findings from a systematic literature review of discrete simulation-based optimization applied to industrial engineering problems. It indicates the most frequent contexts, problems, methods, tools, and intended results of discrete-simulation based studies published in the last 25 years (1991-2016) in scientific journals and conference proceedings. The four research questions presented a scenario to help practitioners and researchers to develop simulation optimization projects for industrial engineering problems. A conclusion presented the gap and prospects found during the writing of the research.

关键词： Discrete event simulation Industrial engineering optimization

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：