检索结果-内蒙古大学图书馆

Improved dynamic regret of distributed online multiple Frank-Wolfe convex optimization

Science China(Information Sciences) 2024年第11期67卷 164-179页

作者： Wentao ZHANG Yang SHI Baoyong ZHANG Deming YUAN School of Automation Nanjing University of Science and Technology Department of Mechanical Engineering University of Victoria

In this paper, we explore a distributed online convex optimization problem over a time-varying multi-agent network. The network aims to minimize a global loss function through local computation and communication with neighboring agents. To effectively handle the optimization problem which involves highdimensional and structural constraint sets, we develop a distributed online multiple Frank-Wolfe algorithm that circumvents the expensive computational cost associated with projection operations. The dynamic regret bounds are established as O(T1-γ+ HT) with the linear oracle number O(T1+γ), which depends on the horizon（total iteration number） T, the function variation HT, and the tuning parameter 0 < γ < *** particular, when the prior knowledge of HTand T is available, the bound can be enhanced to O（1 +HT）. Moreover, we explore the significant advantages provided by the multiple iteration technique and reveal a trade-off between dynamic regret bound, computational cost, and communication cost. Finally,the performance of our algorithm is validated and compared through the distributed online ridge regression problems with two constraint sets.

关键词： distributed online convex optimization multiple iterations Frank-Wolfe algorithm dynamic regret gradient tracking method

来源：评论

学校读者我要写书评

暂无评论

Active sensing in froth flotation

引用

International Journal of Mining and Mineral engineering 2024年第2期15卷 111-130页

作者： Salo, Mikko Juntunen, Teijo Ritala, Risto Department of Automation Technology and Mechanical Engineering Tampere University Tampere Finland

The idea of active sensing is to embed sensor systems with intelligence to require less human interaction. Accurate but limited main measurement systems are complemented with broadband auxiliary measurements that gather data and alert the main measurement to focus on certain area. This is similar with the way that our eyesight works in context of gathering data from our surroundings. The purpose of this study is to introduce and test a control architecture that could improve the operation of froth flotation process. An active sensing architectures on linear quadratic Gaussian control is developed and tested in a simulation environment based on plant data for froth flotation with X-ray fluorescence and visible and near-infrared measurements. The architecture is tested in cases where external disturbances or auxiliary measurement model drifting go unnoticed by the main measurement. In both scenarios, the anomalies are successfully corrected by the active sensing architecture. © The Authors(s) 2024.

关键词： Infrared devices

来源：评论

学校读者我要写书评

暂无评论

Evaluating Effect of Magnetic Field on Nusselt Number and Friction Factor of Fe_(3)O_(4)-TiO_(2)/Water Nanofluids in Heat-Sink Using Artificial Intelligence Techniques

引用

Frontiers in Heat and Mass Transfer 2025年第1期23卷 131-162页

作者： L.S.Sundar Sérgio M.O.Tavares António M.B.Pereira Antonio C.M.Sousa Centre for Mechanical Technology and Automation Department of Mechanical EngineeringUniversity of AveiroAveiro3810-131Portugal

The experimental analysis takes too much time-consuming process and requires considerable effort,while,the Artificial Neural Network(ANN)algorithms are simple,affordable,and fast,and they allow us to make a relevant analysis in establishing an appropriate relationship between the input and output *** paper deals with the use of back-propagation ANN algorithms for the experimental data of heat transfer coefficient,Nusselt number,and friction factor of water-based Fe_(3)O_(4)-TiO_(2) magnetic hybrid nanofluids in a mini heat sink under magnetic *** data considered for the ANN network is at different Reynolds numbers(239 to 1874),different volume concentrations(0%to 2.0%),and different magnetic fields(250 to 1000 G),*** types of ANN back-propagation algorithms Levenberg-Marquardt(LM),Broyden-Fletcher-Goldfarb-Shanno Quasi Newton(BFGS),and Variable Learning Rate Gradient Descent(VLGD)were used to train the heat transfer coefficient,Nusselt number,and friction factor data,*** ANOVA t-test analysis was also performed to determine the relative accuracy of the three ANN *** Nusselt number of 2.0%*** Fe_(3)O_(4)-TiO_(2) hybrid nanofluid is enhanced by 38.16%without a magnetic field,and it is further enhanced by 88.93%with the magnetic field of 1000 Gauss at a Reynolds number of 1874,with respect to the base fluid.A total of 126 datasets of heat transfer coefficient,Nusselt number,and friction factor were used as input and output *** three ANN algorithms of LM,BFGS,and VLGD,have shown good acceptance with the experimental data with root-mean-square errors of 0.34883,0.25341,and 1.0202 with correlation coefficients(R2)of 0.99954,0.9967,and 0.94501,respectively,for the Nusselt number ***,the three ANN algorithms predict root-mean-square errors of 0.001488,0.005041,and 0.006924 with correlation coefficients(R2)of 0.99982,0.99976,and 0.99486,respectively,for the friction factor *** to BFGS and V

关键词： Artificial neural network nusselt number friction factor heat sink correlations

来源：评论

学校读者我要写书评

暂无评论

TFN-FICFM:sEMG-Based Gesture Recognition Using Temporal Fusion Network and Fuzzy Integral-based Classifier Fusion

引用

Journal of Bionic engineering 2024年第4期21卷 1878-1891页

作者： Fo Hu Kailun He Mengyuan Qian Mohamed Amin Gouda College of Information Engineering Zhejiang University of TechnologyHangzhou310023China Department of Mechanical Engineering and Automation Northeastern UniversityShenyang110819China

Surface electromyography(sEMG)-based gesture recognition is a key technology in the field of human–computer ***,existing gesture recognition methods face challenges in effectively integrating discriminative temporal feature representations from sEMG *** this paper,we propose a deep learning framework named TFN-FICFM comprises a Temporal Fusion Network(TFN)and Fuzzy Integral-Based Classifier Fusion method(FICFM)to improve the accuracy and robustness of gesture ***,we design a TFN module,which utilizes an attention-based recurrent multi-scale convolutional module to acquire multi-level temporal feature representations and achieves deep fusion of temporal features through a feature pyramid ***,the deep-fused temporal features are utilized to generate multiple sets of gesture category prediction confidences through a feedback ***,we employ FICFM to perform fuzzy fusion on prediction confidences,resulting in the ultimate *** study conducts extensive comparisons and ablation studies using the publicly available datasets Ninapro DB2 and *** demonstrate that the TFN-FICFM model outperforms state-of-the-art methods in classification *** research can serve as a benchmark for sEMG-based gesture recognition and related deep learning modeling.

关键词： Gesture recognition sEMG Deep learning Temporal fusion Fuzzy fusion

来源：评论

学校读者我要写书评

暂无评论

Solid-state Al-air battery with an ethanol gel electrolyte

引用

Green Energy & Environment 2023年第4期8卷 1117-1127页

作者： Yifei Wang Wending Pan Kee Wah Leong Shijing Luo Xiaolong Zhao Dennis Y.C.Leung School of Mechanical Engineering and Automation Harbin Institute of TechnologyShenzhenChina Department of Mechanical Engineering The University of Hong KongHong KongChina

Hydrogel electrolyte is especially suitable for solid-state Al-air batteries targeted for various portable applications, which may, however, lead to continuous Al corrosion during battery standby. To tackle this issue, an ethanol gel electrolyte is developed for Al-air battery for the first time in this work, by using KOH as solute and polyethylene oxide as gelling agent. The ethanol gel is found to effectively inhibit Al corrosion compared with the water gel counterpart, leading to stable Al storage. When assembled into an Al-air battery, the ethanol gel electrolyte achieves a much improved discharge lifetime and specific capacity, which are 5.3 and 4.1 times of the water gel electrolyte at 0.1 mA cm^(-2), *** studying the gel properties, it is found that a lower ethanol purity can improve the battery power output, but at the price of decreased discharge efficiency. On the contrary, a higher polymer concentration will decrease the power output, but can bring extra benefit to the discharge efficiency. As for the gel thickness, a moderate value of 1 mm is preferred to balance the power output and energy efficiency. Finally, to cater the increasing market of flexible electronics, a flexible Al-air battery is developed by impregnating the ethanol gel into a paper substrate, which can function normally even under serious deformation or damage.

关键词： Al-air battery Gel electrolyte Ethanol gel Al corrosion Polyethylene oxide

来源：评论

学校读者我要写书评

暂无评论

Optimal output regulation for PMSM speed servo system using approximate dynamic programming

引用

Science China(Information Sciences) 2023年第7期66卷 75-76页

作者： Zhaowu PING Yingjie JIA Bangguo XIONG Hongwei ZHANG Jun-Guo LU School of Electrical Engineering and Automation Hefei University of Technology School of Mechanical Engineering and Automation Harbin Institute of Technology Department of Automation Shanghai Jiao Tong University

In recent decades, the output regulation problem has received considerable attention from researchers in the control community because it simultaneously addresses reference signal tracking, disturbance rejection, and robustness [1].Furthermore, when transient performance is considered by solving an optimization problem with a prescribed cost function, this output regulation problem is called an optimal output regulation(OOR) problem.

关键词：

来源：评论

学校读者我要写书评

暂无评论

mechanical and microstructure properties evaluation of Pterocarpus marsupium/ Cochlospermum gossypium polyester composite

引用

Interactions 2024年第1期245卷 1-11页

作者： Ramkumar, V. Selvakumar, P. Arunprasath, K. Manikandan, V. Department of Mechanical and Automation Engineering PSN College of Engineering and Technology Tirunelveli627152 India Department of Mechanical Engineering PSN College of Engineering and Technology Tirunelveli627152 India

It is very strong and solid to work with Pterocarpus marsupium and Cochlospermumgossypium, two tropical hardwoods. In this study, these two types of wood were used as support materials to make a polyester composite. It was looked at how the composite’s mechanical and microstructure features worked. The results showed that the composite was very stiff and had a high modulus of flexibility. Both the bending strength and the modulus of burst were very high. The tiny parts of the mixture showed that the wood fibers were spread out in the polyester framework. The strands were shaped so that they stacked well, which gave the composite its high mechanical *** study’s results showed that the polyester blend made from Pterocarpus marsupium and Cochlospermum gossypium is a good material for underlying uses. Composites have good mechanical qualities, which means they can be used in places where strength and solidity are needed. This study also talked about mechanical qualities like tensile, flexural, impact, and low-velocity impact, as well as the microstructure analysis of fractures. The better outcome was seen for the Pterocarpus marsupium and Cochlospermum gossypium that were both equally supplied, with 50 weight% of Polyester composite. The composite is also likely to be a candidate for use in other situations where strength, firmness, and light weight are needed. The material could be used to make sharp edges for wind turbines, medical inserts, and furniture, among other things. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ultrasonic non-destructive evaluation of composites: A review

引用

Materials Today: Proceedings 2023年 78卷 627-632页

作者： Jodhani, Jitesh Handa, Abhay Gautam, Anandita Ashwni Rana, Ramakant Asst. Prof. Department of Mechanical and Automation Engineering Maharaja Agrasen Institute of Technology India Department of Mechanical and Automation Engineering Maharaja Agrasen Institute of Technology India

Ultrasonics is an NDT (Non-Destructive Testing) technique used to detect faults in structural components by applying a set of techniques and classifying them accordingly. This paper aims to bring together the most relevant published work on different types of techniques for Non-Destructive Evaluation (NDE) of various defects using Ultrasonic. The Ultrasonic testing techniques are relatively simple, highly sensitive and less time-consuming hence have been approved for use on various domains like composite testing, aerospace, automotive and transport. The fundamentals, their applications and constraints of various techniques are covered, along with motions to assess the performance of the techniques. Ultrasonic testing became popular, and with the progress made, new methods were discovered and corrected which resulted in defect detection and improving various material properties. © 2022

关键词： Nondestructive examination

来源：评论

学校读者我要写书评

暂无评论

Paper-based aqueous Al ion battery with water-in-salt electrolyte

引用

Green Energy & Environment 2023年第5期8卷 1380-1388页

作者： Yifei Wang Wending Pan Kee Wah Leong Yingguang Zhang Xiaolong Zhao Shijing Luo Dennis Y.C.Leung School of Mechanical Engineering and Automation Harbin Institute of TechnologyShenzhen518055China Department of Mechanical Engineering The University of Hong KongHong KongChina

Low-cost,flexible and safe battery technology is the key to the widespread usage of wearable electronics,among which the aqueous Al ion battery with water-in-salt electrolyte is a promising *** this work,a flexible aqueous Al ion battery is developed using cellulose paper as *** water-in-salt electrolyte is stored inside the paper,while the electrodes are either printed or attached on the paper surface,leading to a lightweight and thin-film battery ***,this battery can tolerate a charge and discharge rate as high as 4 A g^(-1) without losing its storage *** charge voltage is around 2.2 V,while the discharge plateau of 1.6–1.8 V is among the highest in reported aqueous Al ion batteries,together with a high discharge specific capacity of~140 mAh g^(-1).However,due to the water electrolysis side reaction,the faradaic efficiency can only reach 85%with a cycle life of 250 due to the dry out of *** from using flexible materials and aqueous electrolyte,this paper-based Al ion battery can tolerate various deformations such as bending,rolling and even puncturing without losing its *** two single cells are connected in series,the battery pack can provide a charge voltage of 4.3 V and a discharge plateau as high as 3–3.6 V,which are very close to commercial Li ion *** a cheap,flexible and safe battery technology may be widely applied in low-cost and large-quantity applications,such as RFID tags,smart packages and wearable biosensors in the future.

关键词： Al ion battery Aqueous electrolyte Water-in-salt Paper battery Flexible battery

来源：评论

学校读者我要写书评

暂无评论

Adaptive Unsupervised Learning-Based 3D Spatiotemporal Filter for Event-Driven Cameras

引用

Research 2024年第4期2024卷 579-595页

作者： Meriem Ben Miled Wenwen Liu Yuanchang Liu Department of Mechanical Engineering University College LondonLondonUK School of Automation Nanjing University of InformationScience and TechnologyNanjingChina

In the evolving landscape of robotics and visual navigation,event cameras have gained important traction,notably for their exceptional dynamic range,efficient power consumption,and low *** these advantages,conventional processing methods oversimplify the data into 2 dimensions,neglecting critical temporal *** overcome this limitation,we propose a novel method that treats events as 3D time-discrete *** inspiration from the intricate biological filtering systems inherent to the human visual apparatus,we have developed a 3D spatiotemporal filter based on unsupervised machine learning *** filter effectively reduces noise levels and performs data size reduction,with its parameters being dynamically adjusted based on population *** ensures adaptability and precision under various conditions,like changes in motion velocity and ambient *** our novel validation approach,we first identify the noise type and determine its power spectral density in the event *** then apply a one-dimensional discrete fast Fourier transform to assess the filtered event data within the frequency domain,ensuring that the targeted noise frequencies are adequately *** research also delved into the impact of indoor lighting on event stream ***,our method led to a 37%decrease in the data point cloud,improving data quality in diverse outdoor settings.

关键词： lighting overcome gained

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：