检索结果-内蒙古大学图书馆

4th International Conference on Industrial Artificial Intelligence, IAI 2022

作者： Lu, Rongxiu Deng, Biao Ding, Kanghao Yang, Hui Zhu, Jianyong Liu, Hongliang School of Electrical and Automation Engineering East China Jiaotong University Key Laboratory of Advanced Control and Optimization of Jiangxi Province Jiangxi Nanchang330013 China

ISBN: (数字)9781665451208

ISBN: (纸本)9781665451208

To solve the difficulty of rapid and accurate detection of component content in the rare earth extraction process, a component content modeling method combining mechanism model and error compensation model based on just-in-time learning (JITL) was proposed. Considering the different dynamic characteristics of each section, the extraction section is simplified using the segmented-aggregation method, and the mechanism model of the rare earth extraction process based on material balance is established;in view of the error caused by the simplification of the model and the characteristics of some rare earth solutions with color features, the color features of rare earth solution samples are extracted by machine vision technology, and the error compensation model of the mechanism model is established by the just-in-time learning algorithm. Through the experimental verification of the field sample data of the praseodymium/neodymium (Pr/Nd) extraction process, the results show that the modeling method proposed in this paper is suitable for rapid and accurate detection of elemental component content in the rare earth extraction process with ionic color features. © 2022 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

A Fault Detection Method and System for Highway Tunnel dome light Based on Improved YOLO with Locatization Loss Function 4

A Fault Detection Method and System for Highway Tunnel dome ...

引用

4th International Conference on Industrial Artificial Intelligence, IAI 2022

作者： Dai, Lizhen Tang, Cailing Yang, Gang Yang, Hui Luo, Jiang Chen, Zhaozhang East China Jiaotong University Key Laboratory of Advanced Control and Optimization of Jiangxi Province School of Electrical and Automation Engineering Jiangxi Nanchang330013 China

ISBN: (数字)9781665451208

ISBN: (纸本)9781665451208

Sufficient light intensity in the tunnel plays an extremely important role in ensuring the safety of driving in the tunnel. Tunnel dome light is the basic facility to ensure tunnel lighting. The traditional fault detection method is manual inspection, and the discovery of the problem is not timely. In this paper, a tunnel dome light fault detection method and system based on video monitoring is proposed. Constructing a tunnel dome light detection data set. The original positioning loss function in YOLOv5 is changed from CIOD_Loss function to SCALoss function, which is composed of side overlap (SO), corner distance (CD) and aspect ratio (AR) loss. So that the network can generate more penalties for low overlap positioning frames, and the network model has better positioning performance and faster convergence speed, it is more suitable for the dense and small target such as tunnel headlight. After improving the model, the recognition accuracy is improved by 13.1 %, and the positioning loss is also reduced. So that it can quickly and accurately locate the target to be detected. Finally, the fault lamp detection model is constructed to locate the specific location of the fault lamp. The experiment shows that the model has good performance, and it can effectively detect the state of tunnel dome light in real time and detect abnormal working conditions. © 2022 IEEE.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Improvement and Application of Discrete State Transition Algorithm 4

Improvement and Application of Discrete State Transition Alg...

引用

4th International Conference on Industrial Artificial Intelligence, IAI 2022

作者： Lu, Rongxiu Liu, Hongliang Yang, Hui Dai, Wenhao School of Electrical and Automation Engineering East China Jiaotong University Key Laboratory of Advanced Control and Optimization of Jiangxi Province Jiangxi Nanchang330013 China

ISBN: (数字)9781665451208

ISBN: (纸本)9781665451208

Discrete state transition algorithm relies on the initial solution and can easily fall into the local optimum. This paper proposes an improved discrete state transition algorithm (CDSTA) for the above problem. Firstly, the genetic algorithm is used to initialize to obtain the initial solution with high quality and quickly approximate the optimal value. Secondly, the optimal recovery strategy reduces the number of iterations to accelerate the algorithm's convergence rate. Finally, the chaotic perturbation strategy is introduced. When the algorithm falls into the stagnation state, a chaotic sequence is generated by Tent mapping to get rid of the local extremum. Two single-peaked and three multi-peaked functions are used to experiment with the improved algorithm, and the performance is compared and analyzed with other algorithms. The results show that the improved algorithm's solution accuracy and convergence rate are better than other comparative algorithms. The application of the improved algorithm to the traveling salesman problem demon-strates that CDSTA has good practical engineering application potential. © 2022 IEEE.

关键词： Traveling salesman problem

来源：评论

学校读者我要写书评

暂无评论

Tuning oxygen molecule passivation and transfer on the catalyst surface for highly efficient hydrogen evolution from formaldehyde

引用

Journal of Colloid and Interface Science 2025年 697卷 137905页

作者： Cai, Liangjun Wang, Yang Ren, Sili Liu, Hongxia Zhang, Ding Yan, Xiaoxiao Jiangxi Province Key Laboratory of Environmental Pollution Prevention and Control in Mining and Metallurgy Jiangxi University of Science and Technology Ganzhou 341000 China School of Materials Science and Engineering National Institute for Advanced Materials Nankai University Tianjin 300350 China

In hydrogen evolution reactions (HER), hydrogen–oxygen recombination reaction typically reduces the hydrogen generation rate. However, in the HER from formaldehyde, un-dissociated oxygen molecules can promote hydrogen generation. In this paper, a series of PdZn/g-C₃N₄ alloy catalysts were synthesized, and by varying the catalyst composition successfully regulated the reactive sites and surface-interface behaviors, thus enhancing the HER rate. Under optimal conditions (1.5 M NaOH, 2.0 M HCHO, Pd₁Zn₁/g-C₃N₄), the Pd₁Zn₁ alloy catalyst exhibits the highest catalytic activity for hydrogen evolution reaction, with a hydrogen evolution rate of 422.86 μmol·h⁻¹. Mechanistic study of hydrogen production from formaldehyde revealed that O₂ molecules are converted into reactive oxygen species HOO⁻, which then react with formaldehyde to produce hydrogen. The adsorption energies of formaldehyde and oxygen molecules, as well as the O₂ dissociation energy barrier, vary significantly with the PdZn alloy compositions, affecting O₂ chemical behavior, impeding O₂ dissociation, and accelerating the transfer of active species. The results of theoretical calculations indicate that on the surface of the Pd₁Zn₁/g-C₃N₄ alloy catalyst, oxygen molecules possess an appropriate adsorption energy and a relatively high dissociation energy barrier. This is conducive to the formation of oxygen-containing active species. Meanwhile, the coordination between metal atoms promotes the efficient transfer of photogenerated electrons and prolongs the photoelectron lifetime. Thus, adjusting the PdZn alloy composition can effectively regulate and enhance the catalyst's hydrogen production activity. © 2025 Elsevier Inc.

关键词： Active site regulation Nanoalloy catalyst Oxygen-containing species Oxygen-induced hydrogen evolution Photocatalysis

来源：评论

学校读者我要写书评

暂无评论

A Neuron-Significance-Index-based Self-organization Pruning Algorithm for S-LINN

引用

IFAC-PapersOnLine 2017年第1期50卷 14976-14981页

作者： Yang, Gang Wang, Le Chen, Wen Dai, Lizhen Yang, Hui School of Electrical and Automation Engineering East China Jiaotong University Key Laboratory of Advanced Control and Optimization of Jiangxi Province Nanchang330013 China Division of Engineering Technology Wayne State University DetroitMI48202 United States

For constructing a span-lateral inhibition neural network (S-LINN) with optimal architecture and parameters for actual application, an improved self-organizing optimization approach is proposed in this paper to tune the architecture and parameters simultaneously. This self-organization pruning algorithm can prune insignificant hidden neurons automatically through building a modified significance index function to evaluate the significance of hidden neurons. A preprocessing training of the initial network with assumed redundant hidden neurons will be allowed in the tuning process. A subsequent learning after the self-organization pruning process is also implemented to optimize the parameters of pruned network. The proposed self-organizing approach has been tested on nonlinear dynamic system identification benchmark problem. Simulation results demonstrate that the proposed method has good exploration and exploitation capabilities in terms of searching the optimal structure and parameters for S-LINN. © 2017

关键词： Neural networks Dynamical systems Network architecture Neurons Nonlinear dynamical systems Structural optimization Exploration and exploitation Lateral inhibition Optimal architecture Pruning Redundant hidden neurons Self organizations Self organizing approaches Self organizing optimization

来源：评论

学校读者我要写书评

暂无评论

iCycleGAN: An Improved CycleGAN for Rain Streak Removal From Single Image 4

iCycleGAN: An Improved CycleGAN for Rain Streak Removal From...

引用

4th International Conference on Industrial Artificial Intelligence, IAI 2022

作者： Weng, Yuyu Yang, Gang Tang, Cailing Yang, Hui Lu, Rongxiu Xu, Fangping Luo, Jiang School of Electrical and Automation Engineering East China Jiaotong University Key Laboratory of Advanced Control and Optimization of Jiangxi Province Jiangxi Nanchang330013 China Jiangxi Fangxing Technology Co. Ltd. Jiangxi Nanchang330025 China

ISBN: (数字)9781665451208

ISBN: (纸本)9781665451208

On the one hand, although the supervised learning methods have been used for image rain removal task, such methods have obvious limitations because maybe there is no or only few paired images with-without rain. On the other hand, problems such as color distortion and the inpainting of background information is not clear enough also limit the processing effect of unsupervised methods for image rain removal. An improved CycleGAN (iCycleGAN) was proposed to remove rain streak from a single image. First of all, CycleGAN's transfer learning ability and cyclic structure can solve the problem of the lack of paired data sets. Secondly, a densely connected convolutional network (DenseNet) was added to the generator backbone network to improve the protection of high-frequency information such as background textures, and a CBAM attention mechanism was added to the generator to focus on the repaired area near the rain streak and obtain a clearer repaired image. Finally, feature perceptual loss was introduced to strengthen the constraint of image feature restoration and obtain more realistic results. In order to verify the effectiveness of the proposed method, training was conducted on Rain100L and Rian800 data sets. The comparison of experimental results shows that the model is superior to the existing unsupervised methods in the overall repair effect, and also has comparable inpainting effect compared with mainstream supervised methods. © 2022 IEEE.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

optimization Setting of Reagent Dosage in Rare Earth Extraction Process Based on JITL 4

Optimization Setting of Reagent Dosage in Rare Earth Extract...

引用

4th International Conference on Industrial Artificial Intelligence, IAI 2022

作者： Dai, Wenhao Yang, Hui Lu, Rongxiu Zhu, Jianyong Chen, Pengzhan School of Electrical and Automation Engineering East China Jiaotong University Key Laboratory of Advanced Control and Optimization of Jiangxi Province Jiangxi Nanchang China School of Intelligent Manufacture Taizhou University Zhejiang Taizhou China

ISBN: (数字)9781665451208

ISBN: (纸本)9781665451208

The mechanism of the rare earth extraction process is complex, and the extraction efficiency is greatly affected by the environment. The optimal dose setting value determined by the mechanism model is not the optimal setting value for the actual extraction process. In order to make the rare earth extraction process always run in the most economical state, this paper proposes an optimal setting approach for the dosage of the rare earth extraction process based on just-in-time learning (JITL). Firstly, according to the mechanism model of the rare earth extraction process, an optimization model of the rare earth extraction process with the goal of maximizing economic benefits is established, and the theoretical optimal dose value is obtained;Then, a local model of reagent dosage increment and economic benefit increment is established utilizing the JITL, and the dosage increment that maximizes the economic benefit increment is then obtained;Finally, the increment is applied to the rare earth production process, and the approach is iterated continuously to maximize the economic benefit. The simulation result of the CePr/Nd extraction process demonstrates the effectiveness of the proposed method. © 2022 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Radar-stealth and thermal-insulating MOF-derived cellulose-carbon aerogels for broadband electromagnetic wave absorption

引用

Chinese Chemical Letters 2025年第7期36卷

作者： Luo, Jingyuan Wu, Liping Yan, Jinxi Lv, Xintong Luo, Yuqi Jiang, Wei Xiong, Zhiqiang Ni, Anqi Liu, Chongbo Che, Renchao Key Laboratory of Jiangxi Province for Persistent Pollutants Control and Resources Recycle School of Environmental and Chemical Engineering Nanchang Hangkong University Nanchang 330063 China Laboratory of Advanced Materials Shanghai Key Lab of Molecular Catalysis and Innovative Materials Academy for Engineering & Technology Fudan University Shanghai 200438 China

Considering the challenges posed by severe electromagnetic wave pollution and escalating international tensions, there is a critical need to develop advanced electromagnetic wave absorbing (EMWA) materials that integrate radar stealth and thermal insulation capabilities. In this study, we have synthesized three-dimensional (3D) porous composites comprising V₂O₃ nanoparticles embedded in Juncus effusus cellulose-derived carbon aerogels (VCA) using a self-templating method followed by high-temperature pyrolysis. The V₂O₃ nanoparticles possess a 3D V-V framework and a relatively narrow bandgap, facilitating the Mott transition for enhanced conductivity. Furthermore, their uniform dispersion on hollow carbon tubes of Juncus effusus promotes efficient electron transfer and creates numerous heterogeneous interfaces. Consequently, VCA-2 demonstrates outstanding EMWA performance, achieving a minimum reflection loss of −63.92 dB at a matching thickness of 2.0 mm and a maximum effective absorption bandwidth of 8.24 GHz at a thickness of 2.44 mm, covering nearly half of the tested frequency range. Additionally, the radar cross-section reduction reaches a peak value of 29.40 dB m², underscoring the excellent radar stealth capabilities of the material. In summary, VCA exhibits exceptional EMWA, radar stealth, and thermal insulation properties, highlighting its potential for multifunctional applications in EMWA material development. © 2025

关键词： Broadband electromagnetic wave absorption Cellulose-derived carbon aerogels Radar stealth Thermal insulation Vanadium-metal organic framework

来源：评论

学校读者我要写书评

暂无评论

Static-feedback guaranteed cost control for linear systems with outage and loss of effectiveness actuator faults

引用

Journal of control and Decision 2022年第4期9卷 407-419页

作者： Chun-Hua Xie Zhe Li Yanli Zhou School of Electrical and Automation Engineering East China Jiaotong UniversityNanchangPeople’s Republic of China Key Laboratory of Advanced Control&Optimization of Jiangxi Province NanchangPeople’s Republic of China cCollege of Electrical and Information Engineering Hunan UniversityChangshaPeople’s Republic of China

This paper investigates the static-feedback guaranteed cost control problem for linear systems with actuator faults including outage and loss of *** the actuator redundancy condition,theoretical analysis shows that a static-feedback guaranteed cost controller can always be well designed to ensure that the resulting closed-loop system is stable with desirable quadratic *** particular,the feedback gain can be determined through the solution of a modified algebraic Riccati ***,extension to the system with uncertainties is further *** with the dynamic feedback controller,the static-feedback controller consists only of logical gates/modules and it does not require any memory element,and hence it is simplest in a design *** from the existing results,the severe and timevarying actuator outage faults can be handled very well by the proposed control ***,simulation on a linearised reduced-order aircraft system is provided for verifying the theoretical results.

关键词： Static-feedback guaranteed cost control linear systems actuator outage faults algebraic Riccati equation

来源：评论

学校读者我要写书评

暂无评论

Study on Food Information Online Monitoring System Utilized Wireless Sensor Network

引用

Advance Journal of Food Science and Technology 2016年第2期11卷 137-142页

作者： Li Bo Yang Hui Ting-Ting Li Huang Dechang School of Information Engineering East China Jiaotong University Key Laboratory Advanced Control and Optimization of Jiangxi Province Nanchang 330013 China

The farmland information monitoring generally has the characteristics of complex environment, more monitoring point and wide coverage. Wireless sensor networks technical is the main means to realize variables information collection of agricultural environment network. In order to solve the problem of reliable real-time transmission, a farmland information online monitoring based on wireless sensor network has been designed, which the ZigBee wireless communication technology was used. Monitoring data of different farmland regions are transmitted through the GPRS network to the monitoring center securely and reliably. The use of data monitoring center is aimed at collecting data for processing. The results show that the online monitoring system of field information can automatically complete the data acquisition and transmission throw GPRS network, the data can be sent to the data server with high stability, high reliability, punctuality, meeting the basic requirements of on-line monitoring of farmland information.

关键词： GPRS network structure wireless sensor network ZigBee technology

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：