检索结果-南通市图书馆

Event-triggered distributed cross-dimensional formation control for heterogeneous multi-agent systems

在线全文

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic engineering 2024年第8期25卷 1123-1133页

作者： Huimin WEI Chen PENG Min ZHAO school of mechatronic engineering and automation Shanghai UniversityShanghai 200444China school of Mathematics and Statistics Nantong UniversityNantong 226019China

This paper concerns the event-triggered distributed cross-dimensional formation control problem of heterogeneous multi-agent systems(HMASs)subject to limited network *** central aim is to design an effective distributed formation control scheme that will achieve the desired formation control objectives even in the presence of restricted ***,a multi-dimensional HMAS is first developed,where a group of agents are assigned to several subgroups based on their ***,to mitigate the excessive consumption of communication resources,a cross-dimensional event-triggered communication mechanism is designed to reduce the information interaction among agents with different *** the proposed event-based communication mechanism,the problem of HMAS cross-dimensional formation control is transformed into the asymptotic stability problem of a closed-loop error ***,several stability criteria for designing a cross-dimensional formation control protocol and communication schedule are presented in an environment where there is no information interaction among follower ***,a simulation case study is provided to validate the effectiveness of the proposed formation control protocol.

关键词： Heterogeneous multi-agent systems Formation control Cross-dimensional event-triggered mechanism

YOLO-DD:Improved YOLOv5 for Defect Detection

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第1期78卷 759-780页

作者： Jinhai Wang Wei Wang Zongyin Zhang Xuemin Lin Jingxian Zhao Mingyou Chen Lufeng Luo school of Electronic and Information engineering Foshan UniversityFoshan528000China school of mechatronic engineering and automation Foshan UniversityFoshan528000China

As computer technology continues to advance,factories have increasingly higher demands for detecting ***,detecting defects in a plant environment remains a challenging task due to the presence of complex backgrounds and defects of varying shapes and *** address this issue,this paper proposes YOLO-DD,a defect detectionmodel based on YOLOv5 that is effective and *** improve the feature extraction process and better capture global information,the vanilla YOLOv5 is augmented with a new module called Relative-Distance-Aware Transformer(RDAT).Additionally,an Information Gap Filling Strategy(IGFS)is proposed to improve the fusion of features at different *** classic lightweight attention mechanism Squeeze-and-Excitation(SE)module is also incorporated into the neck section to enhance feature expression and improve the model’s *** results on the NEU-DET dataset demonstrate that YOLO-DDachieves competitive results compared to state-of-the-art methods,with a 2.0% increase in accuracy compared to the original YOLOv5,achieving 82.41% accuracy and38.25FPS(framesper second).Themodel is also testedon a self-constructed fabric defect dataset,and the results show that YOLO-DD is more stable and has higher accuracy than the original YOLOv5,demonstrating its stability and generalization *** high efficiency of YOLO-DD enables it to meet the requirements of industrial high accuracy and real-time detection.

关键词： YOLO-DD defect detection feature fusion attention mechanism

An improved lightweight network based on deep learning for grape recognition in unstructured environments

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Information Processing in Agriculture 2024年第2期11卷 202-216页

作者： Bingpiao Liu Yunzhi Zhang Jinhai Wang Lufeng Luo Qinghua Lu Huiling Wei Wenbo Zhu school of mechatronic engineering and automation Foshan UniversityFoshan 528000China

In unstructured environments,dense grape fruit growth and the presence of occlusion cause difficult recognition problems,which will seriously affect the performance of grape picking *** address these problems,this study improves the YOLOx-Tiny model and proposes a new grape detection model,YOLOX-RA,which can quickly and accurately identify densely growing and occluded grape *** proposed YOLOX-RA model uses a 3×3 convolutional layer with a step size of 2 to replace the focal layer to reduce the computational *** CBS layer in the ResBlock_Body module of the second,third,and fourth layers of the backbone layer is removed,and the CSPLayer module is replaced by the ResBlock-M module to speed up the *** auxiliary network(AlNet)with the remaining network blocks was added after the ResBlock-M module to improve the detection *** depth-separable convolutions(DsC)are used in the neck module layer to replace the normal convolution to reduce the computational *** evaluated the detection performance of SSD,YOLOv4 SSD,YOLOv4-Tiny,YOLO-Grape,YOLOv5-X,YOLOX-Tiny,and YOLOX-RA on a grape test *** results show that the YOLOX-RA model has the best detection performance,achieving 88.75%mAP,a recognition speed of 84.88 FPS,and model size of 17.53 *** can accurately detect densely grown and shaded grape bunches,which can effectively improve the performance of the grape picking robot.

关键词： YOLOX Grape recognition Depthwise separable convolution Res Block-M AINet

Review of Key Technologies for Developing Personalized Lower Limb Rehabilitative Exoskeleton Robots

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Shanghai Jiaotong university(Science) 2024年第1期29卷 16-28页

作者：陶璟周振欢 school of mechatronic engineering and automation Shanghai UniversityShanghai 200444China school of Mechanical engineering Shanghai Jiao Tong UniversityShanghai 200240China

Rehabilitative training and assistance to daily living activities play critical roles in improving the life quality of lower limb dyskinesia patients and older people with motor function *** limb reha-bilitative exoskeleton has a promising application prospect in support of the above *** this paper,critical technologies for developing lower limb rehabilitative exoskeleton for individualized user needs are identi-fied and reviewed,including exoskeleton hardware modularization,bionic compliant driving,individualized gait planning and individual-oriented motion intention *** by the idea of servitization,potentials in exoskeleton product-service system design and its enabling technologies are then *** is suggested that future research will focus on exoskeleton technology and exoskeleton-based service development oriented to an individual's physical features and personalized requirements to realize better human-exoskeleton coordination in terms of technology,as well as accessible and high-quality rehabilitation and living assistance in terms of utility.

关键词： powered exoskeleton lower limb dyskinesia rehabilitation personalization product-service system

Investigation of Adhesive Perception Based on Friction and Brain Activation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Bionic engineering 2024年第4期21卷 1862-1877页

作者： Xingxing Fang Wei Tang Shousheng Zhang Tengfei Zhuang school of mechatronic engineering China University of Mining and TechnologyXuzhou221116JiangsuChina

The enhancement of adhesive perception is crucial to maintaining a stable and comfortable grip of the skin-touch *** study the tactile perception of adhesive surfaces,subjective evaluation,skin friction and vibrations,and neurophysiological response of the brain activity were investigated *** materials,which are commonly used for bionic materials and skin-touch products,were chosen for the tactile *** results showed that with the increasing of surface adhesion,the dominant friction transferred from a combination of adhesive friction and deformation friction to adhesive *** friction coefficient and vibration amplitude had strong correlations with the perceived adhesion of *** parietal lobe and occipital lobe were involved in adhesive perceptions,and the area and intensity of brain activation increased with the increasing surface *** with larger adhesion tended to excite a high P300 amplitude and short latency,indicating that the judgment was faster and that more attentional resources were involved in adhesive ***,the electroencephalograph signals of the adhesive perception were simulated by the neural mass *** demonstrated that the excitability and intensity of brain activity,and the connectivity strength between two neural masses increased with the increasing surface *** study is meaningful to understand the role of surface adhesion in tactile friction and the cognitive mechanism in adhesive perception to improve the tactile experience of adhesive materials.

关键词： Surface adhesion Tactile perception Friction Brain activation Neural mass model

Numerical and experimental investigation on hydraulic-electric rock fragmentation of heterogeneous granite

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Mining Science and Technology 2024年第1期34卷 15-29页

作者： Xiaohua Zhu Ling He Weiji Liu Yunxu Luo Youjian Zhang Wuji Tang school of mechatronic engineering Southwest Petroleum UniversityChengdu 610500China school of Mechanical engineering Sichuan University of Science and EngineeringYibin 643002China

Hydraulic-electric rock fragmentation(HERF)plays a significant role in improving the efficiency of high voltage pulse rock ***,the underlying mechanism of HERF remains *** this study,considering the heterogeneity of the rock,microscopic thermodynamic properties,and shockwave time domain waveforms,based on the shockwave model,digital imaging technology and the discrete element method,the cyclic loading numerical simulations of HERF is achieved by coupling electrical,thermal,and solid mechanics under different formation temperatures,confining pressure,initial peak voltage,electrode bit diameter,and loading ***,the HERF discharge system is conducive to the laboratory experiments with various electrical parameters and the resulting broken pits are numerically reconstructed to obtain the geometric *** results show that,the completely broken area consists of powdery rock *** the pre-broken zone,the mineral cementation of the rock determines the transition of type CⅠcracks to type CⅡand type CⅢ***,the peak pressure of the shockwave increased with initial peak voltage but decreased with electrode bit diameter,while the wave front time ***,increasing well depth,formation temperature and confining pressure augment and inhibit HERF,but once confining pressure surpassed the threshold of 60 MPa for 152.40,215.90,and 228.60 mm electrode bits,and 40 MPa for 309.88 mm electrode bits,HERF is ***,for the same kind of rock,the volume and width of the broken pit increase with higher initial peak voltage and rock fissures will promote ***,the electrode drill bit with a 215.90 mm diameter is more suitable for drilling pink *** research contributes to a better microscopic understanding of HERF and provides valuable insights for electrode bit selection,as well as the optimization of circuit parameters for HERF technology.

关键词： Hydraulic-electric rock fragmentation Shockwave Thermodynamics Microcracks Weak Linear Parallel Bond Model

Leakage and diffusion characteristics of underground hydrogen pipeline

在线全文

学校读者我要写书评

暂无评论

Petroleum 2024年第2期10卷 319-325页

作者： Wenkang Zhang Guanghui Zhao school of mechatronic engineering Southwest Petroleum University

Soil corrosion and hydrogen embrittlement are the main factors of hydrogen pipeline failure. The gas escapes, diffuses and accumulates in the soil and enters the atmosphere when leak occurs. The mechanism of gas diffusion in buried pipelines is very complicated. Mastering the evolution law of hydrogen leakage diffusion is conducive to quickly locating the leakage point and reducing the loss. The leakage model of the underground hydrogen pipeline is established in this paper. The effect of leakage hole, soil type, pipeline pressure, pipeline diameter on hydrogen leakage diffusion were investigated. The results show that when the hydrogen pipeline leaks, the hydrogen concentration increases with the increase of leakage time, showing a symmetrical distribution trend. With the pipeline pressure increase, hydrogen leakage speed is accelerated, and longitudinal diffusion gradually becomes the dominant direction. As the leakage diameter increases, hydrogen leakage per unit of time increases sharply. Hydrogen diffuses more easily in sandy soil, and its diffusion speed, concentration, and range are higher than that in clay soil. The research content provides a reference and basis for the detection and evaluation of buried hydrogen pipeline leakage.

关键词： Buried pipeline Hydrogen leakage Diffusion characteristics Numerical simulation

Deterministic and Robust Volt-var Control Methods of Power System Based on Convex Deep Learning

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Modern Power Systems and Clean Energy 2024年第3期12卷 719-729页

作者： Qing Ma Changhong Deng the school of Electrical engineering and automation Wuhan UniversityWuhanChina

Volt-var control(VVC)is essentially a non-convex optimization problem due to the non-convexity of power flow(PF)constraints,resulting in the difficulty in obtaining the optimum without convexity *** existing second-order cone method for the convexity conversion often leads to a sharp increase in PF constraints and optimization variables,which in turn increases the optimization difficulty or even leads to optimization *** paper first proposes a deterministic VVC method based on convex deep learning power flow(DLPF).This method uses the input convex neural network(ICNN)to establish a single convex mapping between state parameters and node voltage to complete the convexity conversion while the optimization variables only correspond to reactive power equipment,which can ensure the global optimum with extremely fast computation *** cope with the impact brought by the uncertainty of distributed energy and omit the additional worst scenario search of traditional robust VVC,this paper proposes robust VVC method based on convex deep learning interval power flow(DLIPF),which continues to adopt ICNN to establish another convex mapping between state parameters and node voltage *** DLIPF with DLPF,this method decreases the modeling and optimization difficulty of robust VVC *** results on 30-bus,118-bus,and 200-bus systems prove the correctness and rapidity of the proposed methods.

关键词： Volt-var control convexity conversion convex deep learning power flow

Multi-USV Formation Collision Avoidance via Deep Reinforcement Learning and COLREGs

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第11期 2349-2351页

作者： Cheng-Cheng Wang Yu-Long Wang Li Jia the Shanghai Key Laboratory of Power Station automation Technology and also with the School of Mechatronic Engineering and Automation Shanghai University IEEE

Dear Editor,This letter focuses on the collision avoidance for a multi-unmanned surface vehicle(multi-USV) system. A novel multi-USV collision avoidance(MUCA) algorithm is proposed. Firstly, in order to get a more reasonable collision avoidance policy, reward functions are constructed according to international regulations for preventing collisions at sea(COLREGS) and USV dynamics.

关键词：