检索结果-内蒙古大学图书馆

Proceedings of the Winter simulation conference

作者： Kimia Vahdat Sara Shashaani North Carolina State University

ISBN: (纸本)9781728194998

In machine learning, removing uninformative or redundant features from a dataset can significantly improve the construction, analysis, and interpretation of the prediction models, especially when the set of collected features is extensive. We approach this challenge with simulation optimization over a high dimensional binary space in place of the classic greedy search in forward or backward selection or regularization methods. We use genetic algorithms to generate scenarios, bootstrapping to estimate the contribution of the intrinsic and extrinsic noise and sampling strategies to expedite the procedure. By including the uncertainty from the input data in the measurement of the estimators' variability, the new framework obtains robustness and efficiency. Our results on a simulated dataset exhibit improvement over state-of-the-art accuracy, interpretability, and reliability. Our proposed framework provides insight for leveraging Monte Carlo methodology in probabilistic data-driven modeling and analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using Multi-objective Grammar-Based Genetic Programming to Integrate Multiple Social Theories in Agent-Based modeling 11th

Using Multi-objective Grammar-Based Genetic Programming to I...

引用

11th International conference on Evolutionary Multi-Criterion optimization, EMO 2021

作者： Vu, Tuong Manh Davies, Eli Buckley, Charlotte Brennan, Alan Purshouse, Robin C. University of Sheffield Sheffield United Kingdom

ISBN: (纸本)9783030720612

Different theoretical mechanisms have been proposed for explaining complex social phenomena. For example, explanations for observed trends in population alcohol use have been postulated based on norm theory, role theory, and others. Many mechanism-based models of phenomena attempt to translate a single theory into a simulation model. However, single theories often only represent a partial explanation for the phenomenon. The potential of integrating theories together, computationally, represents a promising way of improving the explanatory capability of generative social science. This paper presents a framework for such integrative model discovery, based on multi-objective grammar-based genetic programming (MOGGP). The framework is demonstrated using two separate theory-driven models of alcohol use dynamics based on norm theory and role theory. The proposed integration considers how the sequence of decisions to consume the next drink in a drinking occasion may be influenced by factors from the different theories. A new grammar is constructed based on this integration. Results of the MOGGP model discovery process find new hybrid models that outperform the existing single-theory models and the baseline hybrid model. Future work should consider and further refine the role of domain experts in defining the meaningfulness of models identified by MOGGP. © 2021, Springer Nature Switzerland AG.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Data-driven Car-Following Modal Based on LSTM Deep Learning Method

Data-Driven Car-Following Modal Based on LSTM Deep Learning ...

引用

International conference on Intelligent Transportation, Big Data & Smart City (ICITBS)

作者： Jie Zou Hongyi Huang Leshu Ma Jiandong Zhao School of Traffic and Transportation Beijing Jiaotong University Beijing China Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport School of Traffic and Transportation Beijing Jiaotong University Beijing China

In this paper, a data-driven car-following model based on the long short-term memory (LSTM) neural network in deep learning is proposed. Different from the traditional theoretical model, it can portray the complex decision-making and execution behaviors of drivers more accurately. The speed difference and the spacing between the leading vehicle and the following vehicle are set as the model input while the speed of the follower is set as the output. We determine the optimal values of parameters such as training times and the proportion of data used for testing and training and complete the modeling, testing, and optimization. Compared with other models, this model has two distinctive properties: First, it takes time-series data into consideration, which means the micro-behaviors of drivers such as the predictive ability and memory effects are integrated with the macroscopic traffic flow model. Second, we compared this model with models based on other neural networks such as SVR, FNN, and RNN. Respectively, the error value of this model is 83.8%, 69.5%, and 44.2% lower than those of the other three, which indicates that the car-following model based on LSTM has higher simulation accuracy than other kinds of the car following models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Numerical modeling of a flexural displacement-converter mechanism to excite a flat acoustic source driven by piezoelectric stack actuators

引用

JOURNAL OF SOUND AND VIBRATION 2020年 473卷

作者： Tajdari, F. Berkhoff, A. P. de Boer, A. Univ Twente Fac Engn Technol Drienerlolaan 5 NL-7500 AE Enschede Netherlands TNO Tech Sci Acoust & Sonar Oude Waalsdorperweg 63 NL-2597 AK The Hague Netherlands

This paper studies an acoustic source with a relatively small thickness and a high bending stiffness. The acoustic source operates in the low frequency, quasi-static regime. The focus of the current study is on the actuation part in order to design an appropriate excitation mechanism. A flexural mechanism is modeled in combination with a piezoelectric actuator to convert an in-plane displacement of the actuator to the out-of-plane direction. First, an optimization simulation is used to determine the size of the required piezoelectric actuator. An equivalent electrical circuit of the lumped acoustic source is used for the optimization. A coupled 3D numerical finite element (FE) analysis is carried out using COMSOL Multiphysics software package. The fully-coupled analysis combines the suggested flexural mechanism, the piezoelectric stack actuator, and the thin acoustic source. Finally, the sound pressure field that is generated by the thin acoustic source is investigated and compared using both the finite element analysis and the lumped model. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Thin acoustic source Low frequency Piezoelectric stack actuators Flexural mechanism Finite element

来源：评论

学校读者我要写书评

暂无评论

A Novel Repulsion Hydraulic Operating Mechanism for Fast High Voltage Circuit Breaker

A Novel Repulsion Hydraulic Operating Mechanism for Fast Hig...

引用

Power and Electrical Technology conference (APET), Asia

作者： Feiyue Yan Baoying He Xiaohui Duan Dawei He Yu Liu Jiayuan Xu Technology Center Pinggao Group Co. LTD Pingdingshan China

As the scale and complexity of the grid continues to escalate, the short-circuit current level of the power system keep increasing. Fast circuit breaker can effectively reduce the impact of short-circuit current and become one of the research hotspots of high-voltage circuit breaker (HVCB). The novel repulsive hydraulic operating mechanism proposed in this paper takes the comprehensive advantages of the fast response characteristic of repulsion mechanism and the characteristic of large output in the large stroke range of the hydraulic mechanism, which can help to achieve rapid opening of HVCB. The working principle and technical route of the proposed repulsive hydraulic operating mechanism are expounded. And the research on repulsion device and hydraulic system is conducted respectively from functional requirement, system modeling and parameter optimization. On the basis of which, the prototype of 252kV circuit breaker driven by the novel repulsion hydraulic mechanism is built to verify the correctness of the design and optimization method for the novel operating mechanism, and the feasibility of the novel repulsion hydraulic mechanism used to drive HVCB to achieve rapid opening. The tests show that the 252kV fast circuit breaker can complete arc extinguishing within 25ms, which is about forty percent less than conventional circuit breakers.

关键词： Performance evaluation Analytical models Circuit breakers Short-circuit currents simulation Prototypes Hydraulic systems

来源：评论

学校读者我要写书评

暂无评论

Metamodels and Iterative Design Correction for Rapid optimization of Compact Microwave Components

Metamodels and Iterative Design Correction for Rapid Optimiz...

引用

IEEE-MTT-S International conference on Numerical Electromagnetic and Multiphysics modeling and optimization (NEMO)

作者： Pietrenko-Dabrowska, Anna Koziel, Slawomir Cheng, Qingsha S. Zhang, Zhen Gdansk Univ Technol Fac Elect Telecom Inf Gdansk Poland Reykjavik Univ Engn Optimizat & Modeling Ctr Reykjavik Iceland Southern Univ Sci & Tech Dept Elect & Elect Engn Shenzhen Peoples R China Harbin Inst Technol Harbin Heilongjiang Peoples R China

ISBN: (纸本)9781728169668

Electromagnetic (EM)-driven design has become a commonplace of contemporary microwave engineering, primary reasons being reliability and versatility of EM analysis. For certain classes of structures such as miniaturized components, it is a practical necessity as simpler representations (e.g., equivalent networks) are either inadequate or simply not available. On the other hand, simulation-based procedures such as parameter tuning or statistical analysis entail considerable computational expenses. This paper proposes a technique for accelerated design optimization of compact microwave structures. Our methodology involves kriging metamodels constructed using already available designs as well as an iterative correction procedure, feeding the accumulated discrepancies between the target and the actual design objective values back to the metamodel to yield improved predictions. The presented approach is comprehensively validated using a three-section impedance matching transformer and compared to a gradient-based correction scheme. As demonstrated, the designs optimized for wide ranges of the operating bandwidths are obtained at the cost of just a few EM analyzes of the transformer circuit.

关键词： microwave design design optimization EM-driven design miniaturized circuits metamodeling

来源：评论

学校读者我要写书评

暂无评论

The Influence of simulation Tool Usage on Architecture Student Design: Shifting from a Technical Perspective to a Design-Focused Perspective 7th

The Influence of Simulation Tool Usage on Architecture Stude...

引用

7th International conference on Learning and Collaboration Technologies (LCT)

作者： Maia, Camilla Park, Jaewan Lee, Sungeun Choi, Bokgiu Choi, Suji Lee, Sangwon Yonsei Univ Dept Human Environm & Design Seoul 03722 South Korea Yonsei Univ Dept Cognit Sci Seoul 03722 South Korea

ISBN: (纸本)9783030505127;9783030505134

In this paper, we describe the influence that simulation tools can potentially have on architecture students' design process. In order to understand the simulation usage in the educational context, we first reviewed the previous uses of technological tools in architectural design. In the experiment, students of South Korea performed design tasks guided by either a simulation tool or a studio instructor. The given task also differed by its nature, optimization- vs. concept-driven. As a result, we found that the simulation provided a creative-prone environment to the students and increased their attention to detail.

关键词： Agent-based modeling simulation Architecture education

来源：评论

学校读者我要写书评

暂无评论

A Data-driven MPC Algorithm for Bridge Cranes

A Data-driven MPC Algorithm for Bridge Cranes

引用

International conference on Advanced Mechatronic Systems (ICAMechS)

作者： Bao, HanQiu An, Jing Zhou, MengChu Kang, Qi Tongji Univ Dept Control Sci & Engn Shanghai Peoples R China Tongji Univ Shanghai Inst Intelligent Sci & Technol Shanghai Peoples R China Shanghai Inst Technol Sch Elect & Elect Engn Shanghai Peoples R China New Jersey Inst Technol Dept Elect & Comp Engn Newark NJ 07102 USA

ISBN: (纸本)9781728165301

A crane system often works in a complex environment. Traditional system identification methods are difficult to accurately model crane system identification's real dynamic performance, whether online or offline. Therefore, a Data-driven model predictive control (D-MPC) algorithm is proposed in this paper. Based on Bayesian optimization, the crane's local linear dynamic model is learned to improve the rapidly anti-swing and precise positioning. By collecting data through closed-loop experiments and using Bayes to construct the Gaussian model for guiding learning, the controller parameters and prediction model with the best closed-loop performance can be found. simulation results show that we explicitly find the dynamics model that produces the best control performance for the actual system, and the method can quickly suppress the swing and realize the accurate trolley positioning. The results verify the proposed control algorithm's effectiveness, feasibility and superior performance of the proposed method by comparing it with double-closed-loop proportional-integral-derivative (PID).

关键词： Bayesian optimization data-driven model predictive control

来源：评论

学校读者我要写书评

暂无评论

Model-driven GAN-Based Channel modeling for IRS-Aided Wireless Communication

Model-Driven GAN-Based Channel Modeling for IRS-Aided Wirele...

引用

2021 IEEE Global Communications conference (GLOBECOM)

作者： Yi Wei Ming-Min Zhao Min-Jian Zhao College of Information Science and Electronic Engineering Zhejiang University Hangzhou China

ISBN: (纸本)9781728181059

Intelligent reflecting surface (IRS) is a promising new technology that is able to create a favorable wireless signal propagation environment by collaboratively reconfiguring the passive reflecting elements, yet with low hardware and energy cost. In IRS-aided wireless communication systems, channel modeling is a fundamental task for communication algorithm design and performance optimization, which however is also very challenging since in-depth domain knowledge and technical expertise in radio signal propagations are required, especially for modeling the high-dimensional cascaded base station (BS)-IRS and IRS-user channels (also referred to as the reflected channels). In this paper, we propose a model-driven generative adversarial network (GAN)-based channel modeling framework to autonomously learn the reflected channel distribution, without complex theoretical analysis or data processing. The designed GAN (also named as IRS-GAN) is trained to reach the Nash equilibrium of a minimax game between a generative model and a discriminative model, where the special structure of the reflected channels is incorporated to improve the modeling accuracy. simulation results are presented to validate the effectiveness of the proposed IRS-GAN framework for IRS-related channel modeling.

关键词： Wireless communication Analytical models simulation MISO communication Generative adversarial networks Data processing Nash equilibrium

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Trajectory optimization for Flapping Flight with Data-driven Models

Two-Stage Trajectory Optimization for Flapping Flight with D...

引用

IEEE International conference on Robotics and Automation (ICRA)

作者： Jonathan Hoff Joohyung Kim University of Illinois Urbana-Champaign Urbana IL USA

Underactuated robots often require involved routines for trajectory planning due to their complex dynamics. Flapping-wing aerial vehicles have unsteady aerodynamics and periodic gaits that complicate the planning procedure. In this paper, we improve upon existing methods for flight planning by introducing a two-stage optimization routine to plan flapping flight trajectories. The first stage solves a trajectory optimization problem with a data-driven fixed-wing approximation model trained with experimental flight data. The solution to this is used as the initial guess for a second stage optimization using a flapping-wing model trained with the same flight data. We demonstrate the effectiveness of this approach with a bat robot in both simulation and experimental flight results. The speed of convergence, the dependency on the initial guess, and the quality of the solution are improved, and the robot is able to track the optimized trajectory of a dive maneuver.

关键词： Trajectory planning Computational modeling conferences Aerodynamics Data models Planning Vehicle dynamics

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：