检索结果-内蒙古大学图书馆

AIAA Aviation Forum

作者： Priem, Rainy Diouane, Youssef Bartoli, Nathalie Dubreuil, Sylvain Saves, Paul DGA Maitrise Informat Aeronaut Syst Tech Unit Bruz France Polytech Montreal Math & Ind Engn Dept Montreal PQ Canada Univ Toulouse DTIS ONERA Informat Proc & Syst Dept Toulouse France Univ Toulouse ISAE SUPAERO F-31055 Toulouse 4 France

ISBN: (数字)9781624107047

ISBN: (纸本)9781624107047

Bayesian optimization (BO) is one of the most powerful strategies to solve expensive blackbox optimization problems. However, BO methods are conventionally used for optimization problems of small dimension because of the curse of dimensionality. In this paper, to solve high dimensional optimization problems, we propose to incorporate linear embedding subspaces of small dimension to efficiently perform the optimization. An adaptive learning strategy for these linear embeddings is carried out in conjunction with the optimization. The resulting BO method, named EGORSE, combines in an adaptive way both random and supervised linear embeddings. EGORSE has been compared to state-of-the-art algorithms and tested on academic examples with a number of design variables ranging from 10 to 600. The obtained results show the high potential of EGORSE to solve high-dimensional black-box optimization problems, both in terms of CPU time and number of calls to the expensive black-box.

关键词： Black Box Cumulative Distribution Function Bayesian optimization Python Surrogate Model Robots optimization algorithm Information Processing Path Planning Artificial Intelligence

来源：评论

学校读者我要写书评

暂无评论

Motion Generation Around Obstacles: A Multidimensional Sampling-Based Planner

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2025年

作者： Xie, Zongwu Wang, Zhengpu Cao, Baoshi Liu, Yang Sun, Wandong Xie, Guanghu Ji, Yiming Ma, Boyu Harbin Inst Technol State Key Lab Robot & Syst Harbin 150080 Peoples R China

The quintic polynomial trajectory of the space manipulators holds significant value for the transmitting of ground-based data. In practice, it is frequently employed for large-scale transfer motions. However, this approach leads to an uncontrollable end-effector trajectory, which in turn restricts the applicability of various trajectory planning techniques reliant on end-effector trajectories. Sampling-based motion planner can be used to plan polynomial joint trajectories and optimize specific objectives, such as obstacle avoidance. Nevertheless, existing approaches either fix the sample dimensionality or neglect dimensional optimization. This article presents an enhancement based on genetic algorithms, introducing coding and crossover mechanisms for samples of varying dimensions. The trajectory planner performs search and optimization on a multidimensional sample set, thereby expanding the search domain and overcoming dimensional constraints. The mutual inspiration among samples of different dimensions enhances the search capabilities of the algorithm, yielding superior results. This work focuses on an actual engineering problem, and through simulation and validation experiments, it demonstrates that the proposed trajectory planner can generate a safe and coordinated quintic polynomial joint trajectory for the manipulator.

关键词： Trajectory Encoding optimization optimization models Polynomials Genetic algorithms Space stations Search problems End effectors Collision avoidance Modified genetic algorithm (GA) optimization algorithm sampling-based motion planner (SBMP) space manipulators

来源：评论

学校读者我要写书评

暂无评论

Motor Imagery Recognition Based on an Optimized Probabilistic Neural Network with the Particle Swarm optimization 35

Motor Imagery Recognition Based on an Optimized Probabilisti...

引用

35th Chinese Control and Decision Conference (CCDC)

作者： Yang, Yufei Li, Mingai Beijing Univ Technol Fac Informat Technol Beijing Peoples R China

ISBN: (纸本)9798350334722

At present, how to efficiently and effectively identify motor imagery tasks is still a huge challenge for the development of the Brain Computer Interface (BCI) systems in the field of human rehabilitation. Therefore, this paper proposes an optimized recognition method based on temporal features and spatial features re-representation. The Local Mean Decomposition (LMD) algorithm is used to extract the Product Functions (PFs) of the Motor Imagery Electroencephalogram (MI-EEG) signals and the Common Spatial Pattern (CSP) algorithm is applied to reconstruct the spatial distribution of each PF, then the MI-EEG signals are re-represented as features with temporal and spatial characteristics. The Probabilistic Neural Network (PNN) is constructed, in which the smoothing factor is optimized by the Particle Swarm optimization (PSO). By introducing the PSO algorithm, the PNN can be adaptively determined according to the respective conditions of different subjects or datasets. The experimental results show, compared with the Support Vector Machine (SVM) based on feature re-representation and other state-of-the-art machine learning methods, the proposed method in this paper has both high recognition accuracy and adaptability. This optimized PNN with PSO method establishes a theoretical foundation and methodological guidance for the decoding of motor imagery recognition.

关键词： motor imagery recognition probabilistic neural network particle swarm optimization optimization algorithm feature re-representation

来源：评论

学校读者我要写书评

暂无评论

Analysis of Flow Around an Aerial Tactical Pod carried by the A29B Aircraft for Viscous Drag optimization

Analysis of Flow Around an Aerial Tactical Pod carried by th...

引用

AIAA Aviation Forum

作者： Anguisaca, Jose N. Castellanos, Santiago Sanchez, Xavier Ctr Res & Dev Ecuadorian Air Force Sangolqui 171103 Pichincha Ecuador Ctr Res & Dev Ecuadorian Air Force Mech Engn Dept Mfg Proc Lab Sangolqui 171103 Pichincha Ecuador Armed Forces Univ ESPE Mech Engn Dept Composite Mat Lab Sangolqui 171103 Pichincha Ecuador

ISBN: (数字)9781624107047

ISBN: (纸本)9781624107047

The goal of this study is to identify the best geometry for a tactical pod to reduce viscous drag. To accomplish this, the body's geometry has been mathematically described and controlled by a set of shape parameters. The baseline geometry can then be changed to produce different iterations of the pod. Then, a simple method is used to qualitatively predict the drag due to viscosity based on the momentum deficit of the boundary layer at the body's trailing edge. This technique has been improved by incorporating dynamic boundary layer transition calculation when evaluating different geometries. The viscous drag prediction method and a (1+1)-Evolution Strategy optimization algorithm are used to iteratively alter the geometry by perturbing the shape parameters until a shape with the least drag is achieved. At the final stage, the results from the optimization process are compared to the solution of the Transition-SST viscous model for both the baseline and optimized geometries, from which it is confirmed that the viscous drag calculation method based on the momentum deficit of the boundary layer can be effectively used to optimize an axisymmetric body and that including the dynamic calculation of the boundary layer transition is a valid improvement to the method that could lead to better results during the optimization process.

关键词： Freestream Velocity Aircrafts Laminar to Turbulent Transition Trailing Edges optimization algorithm Kinematic Viscosity Reynolds Averaged Navier Stokes Axisymmetric Flow Skin Friction Coefficient MATLAB

来源：评论

学校读者我要写书评

暂无评论

Optimizing domestic energy management with a wild Mice colony-inspired algorithm: Enhancing efficiency and coordination in smart grids through dynamic distributed energy storage

引用

HELIYON 2024年第16期10卷 e35462页

作者： Wang, Liang Li, Dajun Southeast Univ Sch Mech Engn Nanjing 211189 Jiangsu Peoples R China Chengdu Univ Technol Sch Mech & Elect Engn Chengdu 610000 Sichuan Peoples R China

Energy management (EM) is a critical strategy that spans the production and consumption of electricity, enhancing the stability of the electricity network. Smart grid technology significantly improves the electrical system's energy efficiency (EE), facilitating a transformation from a conventional power grid (PG) to a smart PG. This paper presents a key strategy for modeling the EE of the smart grid tailored to domestic demand, establishing smart coordination between domestic demand, energy production, and storage to reduce energy waste and costs. Our model integrates various energy sources, including renewable energy (RE), photovoltaic (PV) systems, wind power, and an energy storage system (ESS), interconnected with the PG. The model's structure ensures the coordinated flow of electricity in a residential house through an optimal control method (OCM). To develop a robust closed-loop control model, we employ Demand Response (DR) schemes within the Real-Time Electricity Pricing (RTEP) framework. We construct a dynamic model of the ESS to compute the System Performance Index (SPI), corresponding to energy costs. To enhance our model, we introduce a Dynamic Distributed Energy Storage Strategy (DDESS). Additionally, we introduce a novel optimization algorithm inspired by the behavioral patterns of wild mice, called the Wild Mice Colony (WMC). By analyzing the targeted and advantageous behaviors of wild mice in colonies, we propose that these behaviors can serve as a model for addressing complex, uncertain problems. This strategy is highly advantageous, capable of reducing total energy consumption (EC) from the main grid by over 100 % of the load demand, optimizing the energy system, and ensuring synchronization. The performance of DDESS optimizes energy flow (EF) during the repayment plan, leading to minimized EC costs from the PG.

关键词： Renewable energy Dynamic distributioned energy storage Energy efficiency optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Source term inversion of nuclear accidents based on ISAO-SAELM model

引用

NUCLEAR ENGINEERING AND TECHNOLOGY 2024年第9期56卷 3914-3924页

作者： Xiao, Dong Zhang, Zixuan Li, Jianxin Fu, Yanhua Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Peoples R China Northeastern Univ JangHo Architecture Coll Shenyang 110169 Peoples R China Northeastern Univ POB 135 Shenyang 110819 Liaoning Peoples R China

The release source term of radioactivity becomes a critical foundation for emergency response and accident consequence assessment after a nuclear accident Rapidly and accurately inverting the source term remains an urgent scientific challenge. Today source term inversion based on meteorological data and gamma dose rate measurements is a common method. But gamma dose rate actually includes all nuclides information, and the composition of radioactive nuclides is generally uncertain. This paper introduces a novel nuclear accident source term inversion model, which is Improve Snow Ablation Optimizer-Sensitivity Analysis Pruning Extreme Learning Machine (ISAO-SAELM) model. The model inverts the release rates of 11 radioactive nuclides (I-131, Xe-133, Cs- 137, Kr-88, Sr-91, Te-132, Mo-99, Ba-140, La-140, Ce-144, Sb-129). It does not require the use of the physical field of the reactor to obtain prior information and establish a dispersion model. And the robustness is validated through noise analysis test. The mean absolute errors of the release rates of 11 nuclides are 15.52 %, 15.28 %, 15.70 %, 14.99 %, 14.85 %, 15.61 %, 15.96 %, 15.42 %, 15.84 %, 15.13 %, 17.72 %, which show the significant superiority of ISAO-SAELM. ISAO-SAELM model not only achieves notable advancements in accuracy but also receives validation in terms of practicality and feasibility.

关键词： Nuclear accident Source term inversion Extreme learning machine optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

optimization algorithms for ultrasonic array imaging in homogeneous anisotropic steel components with unknown properties

引用

NDT & E INTERNATIONAL 2020年 116卷 102327-102327页

作者： Menard, Corentin Robert, Sebastien Miorelli, Roberto Lesselier, Dominique CEA LIST Dept Imaging & Simulat Nondestruct Testing Bat 565Pc 120 F-91191 Gif Sur Yvette France Univ Paris Saclay Lab Signaux & Syst Cent Supelec CNRS F-91190 Gif Sur Yvette France

In this paper, we investigate the ability of an adaptive ultrasonic method to image point-like reflectors inside anisotropic and homogeneous nuclear steels with unknown properties, such as V-shape welds or cladded components. The optimization scheme combines the Total Focusing Method (TFM) imaging algorithm with a customized gradient ascent method to improve both the quality and the reliability of ultrasound images. A statistical analysis of its robustness is performed with simulated echoes and using a surrogate model to speed up the computation times of the TFM images. Then, the optimization procedure is evaluated with several experimental cases and provides highly enhanced images with a 5 MHz array. The positioning of the artificial defects of 2.0 mm diameter is estimated with less than 1 mm error with respect to their actual position, and the signal-to-noise ratio is increased by up to 10 dB. The elastic properties are also estimated with less than 10% error when compared to their actual values.

关键词： Ultrasonic array Total Focusing Method Adaptive imaging Anisotropic materials optimization algorithm Surrogate-model

来源：评论

学校读者我要写书评

暂无评论

Attitude Quaternion Estimation from Two Vector Observations

引用

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS 2025年第3期48卷 700-706页

作者： Choukroun, Daniel Peng, Caitong Ben Gurion Univ Negev Pearlstone Ctr Aeronaut Engn Studies Mech Engn Dept POB 653 IL-84105 Beer Sheva Israel Ben Gurion Univ Negev Mech Engn Dept POB 653 IL-84105 Beer Sheva Israel

来源：评论

学校读者我要写书评

暂无评论

Application and effect evaluation of BIM technology in seismic design of high-rise buildings

引用

INFRASTRUCTURE ASSET MANAGEMENT 2025年

作者： Hu, Yunpeng Henan Univ Urban Construct Sch Management Pingdingshan Peoples R China

This paper discusses the application of Building Information Modelling (BIM) technology in the seismic design of high-rise buildings, focusing on digital modelling based on BIM, seismic performance optimisation algorithm, structural analysis and seismic load simulation, and data-driven performance evaluation methods. Through the construction and optimisation of the BIM model, not only is the design accuracy improved, but the intelligent and dynamic optimisation of the design process is also realized, especially in the application of seismic performance prediction and structural optimisation. The material utilisation rate of 23.5% shows a high resource utilisation efficiency, while 87% of the building structures meet the design seismic standards. When considering different optimisation schemes, a 54.8% improvement in seismic performance was recorded. However, a 12.9% increase in cost affected the final decision. The optimized scheme exhibited a 68.4% improvement in seismic stability, while a 91% shortened construction period, indicating that the optimized design improved performance and significantly improved in time. A good balance is achieved between the 34.7% increase in seismic effect and the 77.2% cost saving, indicating the critical role of BIM technology in optimisation design.

关键词： BIM technologies high-rise buildings optimization algorithm seismic design

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network- ANN- E (Tanh): A New Deep Learning Model for Predicting Rainfall

引用

WATER RESOURCES MANAGEMENT 2023年第4期37卷 1785-1810页

作者： Nia, Mahdie Afshari Panahi, Fatemeh Ehteram, Mohammad Univ Kashan Fac Nat Resources & Earth Sci Kashan Iran Semnan Univ Dept Water Engn Semnan Iran

The prediction of rainfall is essential for monitoring droughts and floods. The purpose of this paper is to develop a deep learning model for predicting monthly rainfall. The new model is used to predict rainfall in the Kashan plain of Iran. This study combines a deep learning model with an artificial neural network (ANN) model to predict rainfall. In this study, a convolutional neural network (CONV) is used as a deep learning model. The paper also introduces a new activation function called E-Tanh to develop ANN models. The new model has two main advantages. The model automatically determines key features. In addition, the new activation function can enhance the precision of ANN models. Lagged rainfall values are inserted into the models to predict rainfall. This study uses a bat optimization algorithm to choose inputs. At the training level, the mean absolute percentage errors (MAPES) of CONV-ANN-ANN-E-Tanh, CONV, and ANN-E-Tanh were 0.5%, 1%, and 2%, respectively. At the testing level, the MAPEs of CONV-ANN -E-Tanh, CONV, and ANN-E-Tanh were 1%, 3%, and 4%, respectively. The E-Tanh performed better than other activation functions based on error function values. Also, the CONV-ANN-E-Tanh can reduce CPU time. Our results show that the new hybrid model is a reliable tool for simulating complex phenomena.

关键词： Hydrological predictions Hybrid model Water resource management optimization algorithm New activation function

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：