检索结果-内蒙古大学图书馆

Distributed adaptive control for high-order stochastic nonlinear systems with unknown control gains and uncertainties

引用

Journal of Control and Decision 2023年第4期10卷 484-493页

作者： Baoyu Wen Jiangshuai Huang Shaoxin Sun Xingyue Sheng Xiaowen Yue Chongqing Engineering Laboratory of Robotics for Traffic Engineering Chongqing Jiaotong UniversityChongqingPeople’s Republic of China School of Automation Chongqing UniversityChongqingPeople’s Republic of China Chongqing Zhixiang Paving Technology Engineering Co. Ltd.ChongqingPeople’s Republic of China

The leader-following tracking consensus problem of a class of high-order stochastic nonlinearmulti-agent systems with unknown control gains and unknown system parameters is solved inthis paper. For a class of high-orderstochastic nonlinear multi-agentsystemsin parametric strictfeedback, the distributed control scheme is designed by using backstepping technology. Theadaptive control method is used to deal with the unknown control gains and unknown systemparameters. Besides, to save communication resources, the event-trigged control is applied. Thecontrol algorithms ensure that allstatesin the closed-loop system and tracking errors are globallybounded stable in probability. Two simulation examples verify the effectiveness of the designedalgorithms.

关键词： Adaptive control nonlinear stochastic systems leader-following consensus control

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient buffer and service rate allocation in manufacturing systems using hybrid machine learning and evolutionary algorithms

引用

Advances in Manufacturing 2024年第2期12卷 227-251页

作者： Si-Xiao Gao Hui Liu Jun Ota Key Laboratory of Traffic Safety on Track of Ministry of Education Institute of Artificial Intelligence and Robotics(IAIR)School of Traffic and Transportation EngineeringCentral South UniversityChangsha410075People’s Republic of China Research into Artifacts Center for Engineering School of EngineeringThe University of TokyoTokyoJapan

Currently,simultaneous buffer and service rate allocation is a topic of interest in the optimization of manufacturing *** allocation problems have been solved previously to satisfy economic requirements;however,owing to the progress of green manufacturing,energy conservation and environmental protection have become increasingly ***,an energy-efficient approach is developed to maximize the throughput and minimize the energy consumption of manufacturing systems,subject to the total buffer capacity,total service rate,and predefined energy *** energy-efficient approach integrates the simulated annealing-non-dominated sorting genetic algorithm-II with the honey badger algorithm-histogram-based gradient boosting regression *** former algorithm searches for Pareto-optimal solutions of sufficient *** latter algorithm builds prediction models to rapidly calculate the throughput,energy consumption,and energy *** examples show that the proposed hybrid approach can achieve a better solution quality compared with previously reported ***,the prediction models can rapidly evaluate manufacturing systems with sufficient *** study benefits the multi-objective optimization of green manufacturing systems.

关键词： Energy-efficient allocation Multi-objective optimization Energy efficiency Energy consumption Machine learning

来源：评论

学校读者我要写书评

暂无评论

An improved multiscale fusion dense network with efficient multiscale attention mechanism for apple leaf disease identification

引用

Frontiers of Agricultural Science and engineering 2025年第2期12卷 173-189页

作者： Dandan DAI Hui LIU Institute of Artificial Intelligence & Robotics (IAIR) Key Laboratory of Traffic Safety on Track of Ministry of EducationSchool of Traffic and Transportation Engineering Central South University

With the development of smart agriculture, accurately identifying crop diseases through visual recognition techniques instead of by eye has been a significant challenge. This study focused on apple leaf disease, which is closely related to the final yield of apples. A multiscale fusion dense network combined with an efficient multiscale attention(EMA) mechanism called Incept＿EMA＿DenseNet was developed to better identify eight complex apple leaf disease images. Incept＿EMA＿DenseNet consists of three crucial parts: the inception module, which substituted the convolution layer with multiscale fusion methods in the shallow feature extraction layer; the EMA mechanism,which is used for obtaining appropriate weights of different dense blocks; and the improved DenseNet based on DenseNet＿121. Specifically, to find appropriate multiscale fusion methods, the residual module and inception module were compared to determine the performance of each technique, and Incept＿EMA＿DenseNet achieved an accuracy of 95.38%. Second, this work used three attention mechanisms, and the efficient multiscale attention mechanism obtained the best performance. Third, the convolution layers and bottlenecks were modified without performance degradation, reducing half of the computational load compared with the original ***＿EMA＿DenseNet, as proposed in this paper, has an accuracy of 96.76%,being 2.93%, 3.44%, and 4.16% better than Resnet50, DenseNet＿121 and GoogLeNet, respectively, proved to be reliable and beneficial, and can effectively and conveniently assist apple growers with leaf disease identification in the field.

关键词： Incept_EMA_DenseNet multi-scale fusion module efficient multiscale attention mechanism apple leaf disease identification

来源：评论

学校读者我要写书评

暂无评论

Design and Performance Analysis of HMDV Dynamic Inertial Suspension Based on Active Disturbance Rejection Control

引用

Computer Modeling in engineering & Sciences 2024年第8期140卷 1485-1506页

作者： Xiaofeng Yang Wei Wang Yujie Shen Changning Liu Tianyi Zhang School of Automotive and Traffic Engineering Jiangsu UniversityZhenjiang212013China Automotive Engineering Research Institute Jiangsu UniversityZhenjiang212013China Chongqing Key Laboratory of Urban Rail Transit System Integration and Control Chongqing400074China State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle Hunan universityChangsha410082China

This paper addresses the impact of vertical vibration negative effects,unbalanced radial forces generated by the static eccentricity of the hub motor,and road excitation on the suspension performance of Hub Motor Driven Vehicle(HMDV).A dynamic inertial suspension based on Active Disturbance Rejection Control(ADRC)is proposed,combining the vertical dynamic characteristics of dynamic inertial suspension with the features of ADRC,which distinguishes between internal and external disturbances and arranges the transition ***,a simulation model of the static eccentricity of the hub motor is established to simulate the unbalanced radial electromagnetic force generated under static eccentricity.A quarter-vehicle model of an HMDV with a controllable dynamic inertial suspension is then ***,the passive suspension model is studied under different grades of road excitation,and the impact mechanism of suspension performance at speeds of 0–20 m/s is ***,the three main components within the ADRC controller are designed for the second-order controlled system,and optimization algorithms are used to optimize its internal ***,the performance of the traditional passive suspension,the PID-based controllable dynamic inertial suspension,and the ADRC-based controllable dynamic inertial suspension are analyzed under different road *** results show that,under sinusoidal road input,the ADRC-based controllable dynamic inertial suspension exhibits a 52.3%reduction in the low-frequency resonance peak in the vehicle body acceleration gain diagram compared to the traditional passive suspension,with significant performance optimization in the high-frequency *** random road input,the ADRC-based controllable dynamic inertial suspension achieves a 29.53%reduction in the root mean square value of vehicle body acceleration and a 14.87%reduction in dynamic tire *** indicates that the designed controllable dynamic inertia

关键词： HMDV static eccentricity ADRC dynamic inertial suspension road excitation

来源：评论

学校读者我要写书评

暂无评论

A clustering analysis of car-hailing travel behavior based on latent class model: A study from a prefecture-level city in china

Advances in Transportation Studies

引用

Advances in Transportation Studies 2024年 64卷 55-72页

作者： Yang, Y.Z. Gao, Y.Y. Niu, H.L. School of Traffic & Transportation Chongqing Jiaotong University Chongqing400074 China Chongqing Key Laboratory of Intelligent Integrated and Multidimensional Transportation System Chongqing Jiaotong University Chongqing400074 China Yunhan Engineering Technology Co. Ltd. Guizhou Province Guiyang550029 China

This article used a latent category regression model to explore how different factors affect the travel behavior of car-hailing users. Online and offline surveys were distributed across various districts of Pingdingshan, Henan Province, resulting in 527 valid responses. Data analysis was done using Statalö and RStudio software for descriptive statistics and regression analysis. Two user groups were identified: Opportunistic passengers and loyal passengers. Waiting time and travel environment emerged as key factors in this classification. Longer waiting times led to lower overall user satisfaction. Comparative analysis showed that the travel environment had a significant impact on opportunistic passengers, surpassing its effect on loyal passengers with a 95% confidence level. In newly developed urban areas, opportunistic passengers were 42% more likely to recommend car-hailing services. Additionally, higher passenger satisfaction was linked to increased car-hailing usage, rising from less than weekly to at least six times weekly. These findings offer valuable insights for improving urban transportation infrastructure. © 2024, Aracne Editrice. All rights reserved.

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

An improved deep learning model for soybean future price prediction with hybrid data preprocessing strategy

引用

Frontiers of Agricultural Science and engineering 2025年第2期12卷 208-230页

作者： Dingya CHEN Hui LIU Yanfei LI Zhu DUAN Institute of Artificial Intelligence & Robotics (IAIR) Key Laboratory of Traffic Safety on Track of Ministry of EducationSchool of Traffic and Transportation Engineering Central South University School of Mechatronic Engineering Hunan Agricultural University

The futures trading market is an important part of the financial markets and soybeans are one of the most strategically important crops in the world. How to predict soybean future price is a challenging topic being studied by many researchers. This paper proposes a novel hybrid soybean future price prediction model which includes two stages of data preprocessing and deep learning prediction. In the data preprocessing stage, futures price series are decomposed into subsequences using the ICEEMDAN(improved complete ensemble empirical mode decomposition with adaptive noise) method. The Lempel-Ziv complexity determination method was then used to identify and reconstruct high-frequency subsequences. Finally, the high frequency component is decomposed secondarily using variational mode decomposition optimized by beluga whale optimization algorithm. In the deep learning prediction stage, a deep extreme learning machine optimized by the sparrow search algorithm was used to obtain the prediction results of all subseries and reconstructs them to obtain the final soybean future price prediction *** on the experimental results of soybean future price markets in China,Italy, and the United States, it was found that the hybrid method proposed provides superior performance in terms of prediction accuracy and robustness.

关键词： Deep extreme learning machine hybrid data preprocessing optimization algorithm soybean future price prediction

来源：评论

学校读者我要写书评

暂无评论

A hybrid ensemble deep reinforcement learning model for locomotive axle temperature using the deterministic and probabilistic strategy

引用

Transportation Safety and Environment 2023年第3期5卷 20-29页

作者： Guangxi Yan Hui Liu Chengqing Yu Chengming Yu Ye Li Zhu Duan Institute of Artificial Intelligence&Robotics(IAIR) Key Laboratory of Traffic Safety on Track of Ministry of EducationSchool of Traffic and Transportation EngineeringCentral South UniversityChangsha 410075HunanChina

This paper proposes a hybrid deep reinforcement learning framework for locomotive axle temperature by combining the wavelet packet decomposition(WPD),long short-term memory(LSTM),gated recurrent unit(GRU)reinforcement learning and generalized autoregressive conditional heteroskedasticity(GARCH)*** WPD is utilized to decompose the raw nonlinear series into *** the deep learning predictors LSTM and GRU are established to predict the future axle temperatures in each *** Q-learning could generate optimal ensembleweights to integrate the predictors to finish the deterministic forecasting and GARCH is used to conduct the deterministic forecasting based on the deterministic forecasting *** parts of the hybrid ensemble structure contributed to optimal modelling accuracy and provided effective support in the real-time monitoring and fault diagnosis of transportation.

关键词： locomotive axle temperature reinforcement learning wavelet packet decomposition(WPD) deterministic forecasting probabilistic forecasting

来源：评论

学校读者我要写书评

暂无评论

Construction of laser-induced graphene/silver nanowire composite structures for low-strain,high-sensitivity flexible wearable strain sensors

引用

Science China(Technological Sciences) 2024年第11期67卷 3524-3534页

作者： YANG PingAn ZHAO JingYuan LI Rui ZHOU ZhiHao GUI YinGang SUN RuiXue WU DeCheng WANG XiaoJie School of Automation Chongqing University of Posts and TelecommunicationsChongqing 400065China College of Engineering and Technology Southwest UniversityChongqing 400715China Bio-inspired Robotics and Intelligent Material Laboratory Institute of Advanced Manufacturing TechnologyHefei Institutes of Physical ScienceChinese Academy of SciencesChangzhou 213164China

Sandwich-structured flexible sensors based on graphene have high sensitivity and *** graphene is combined with a flexible substrate in a sandwich structure,the weak bonding between them compromises the sensor's stability and sensitivity at low *** presents challenges in monitoring subtle physiological activities,such as hand bending and pulse *** this purpose,laser-induced graphene(LIG)is proposed to be used to prepare flexible sensors in order to improve the sensitivity and stability of the sensors at low ***(PDMS)with low modulus and polyimide(PI)with rich carbon content are selected as precursor materials for LIG,and graphene is formed through laser ***,silver nanowires(Ag NWs)solution is added to LIG to give the sensor low strain and high sensitivity *** the PI/PDMS ratio is 1:3,the Ag NWs/LIG flexible strain sensor exhibits excellent sensitivity(GF=778.468)over a small strain range(8.76%-11.25%).Meanwhile,the sensor still shows excellent stability after 2000 cycle *** Ag NWs/LIG flexible strain sensor shows good performance when placed on the back of the hand,around the eyes,*** is demonstrated that Ag NWs/LIG flexible strain sensors have good application potential in human physiological activity monitoring,health management and medical fields,and provide a low-strain,high-sensitivity sensor design strategy for flexible wearable devices.

关键词： flexible strain sensors high sensitivity strain range Ag NWs laser-induced graphene

来源：评论

学校读者我要写书评

暂无评论

Railway switch fault diagnosis based on Multi-heads Channel Self Attention,Residual Connection and Deep CNN

引用

Transportation Safety and Environment 2023年第1期5卷 58-65页

作者： Xirui Chen Hui Liu Zhu Duan Institute of Artificial Intelligence&Robotics(IAIR) Key Laboratory of Traffic Safety on Track of Ministry of EducationSchool of Traffic and Transportation EngineeringCentral South UniversityChangsha 410075HunanChina.

A novel switch diagnosis method based on self-attention and residual deep convolutional neural networks(CNNs)is *** of the imbalanced dataset,the K-means synthetic minority oversampling technique(SMOTE)is applied to balancing the dataset at ***,the deep CNN is utilized to extract local features from long power curves,and the residual connection is performed to handle the performance *** the end,the multi-heads channel self attention focuses on those important local *** ablation and comparison experiments are applied to verifying the effectiveness of the proposed *** the residual connection and multi-heads channel self attention,the proposed method has achieved an impressive accuracy of 99.83%.The t-SNE based visualizations for features of the middle layers enhance the trustworthiness.

关键词： fault diagnosis railway switch residual connection channel self-attention deep convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Visualization Analysis of Automated Motorway Driving Studies Based on Mapping Knowledge Domain 24

Visualization Analysis of Automated Motorway Driving Studies...

引用

24th COTA International Conference of Transportation Professionals: Resilient, Intelligent, Connected, and Lowcarbon Multimodal Transportation, CICTP 2024

作者： Hu, Shixinyue Yang, Xiaoguang Dept. of Transportation Engineering Chongqing Jiaotong Univ. Chongqing China Key Laboratory of Road and Traffic Engineering Ministry of Education Tongji Univ. Shanghai China

ISBN: (数字)9780784485484

ISBN: (纸本)9780784485484

To understand the status of automated motorway driving (AMD) studies and explore research hotspots and fronts, 1,281 related articles are retrieved as data samples. Based on mapping knowledge domain (MKD) and bibliometric approaches, these articles are analyzed from multiple perspectives, including spatiotemporal distribution, document co-citation, and keywords co-occurrence. The results show that knowledge bases of AMD studies over the last decade or so have focused on four major areas of "mixed traffic flow," "trajectory prediction," "computer vision," "simulation," and "connected and automated vehicle." The four dominant clusters of "driver behavior," "autonomous vehicles," "connected vehicle," and "task analysis" represent current research hotspots and fronts. Among these, exploring the impact of vehicle-infrastructure cooperation on the overall transportation environment is crucial and prospective for the introduction of intelligent vehicles. Safety technology challenges faced by AMD, such as autonomous driving, accident prevention, and control, also require great attention. © ASCE.

关键词： Autonomous vehicles

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：