检索结果-内蒙古大学图书馆

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 285-295页

作者： Liu, Chen Shi, Zhenyu He, Shibo Tang, Shunpu Yang, Qianqian The State Key Lab. of Industrial Control Technology Zhejiang University Hangzhou310027 China

Detecting defects on railway tracks is critical for the operation of high-speed trains. Despite a plethora of machine vision-based methods designed to tackle this problem, the majority adopt a supervised setting and demand considerable labeled training data, inclusive of defective samples, which is expensive and impractical. In this paper, we propose an Invertible Reconstruction neural Network (IRNet) for semi-supervised rail surface defect detection, where only normal images are accessible during training. Firstly, we devise an information-preserving feature encoder comprising several invertible blocks. This structure safeguards subtle visual patterns distinguishing normal and defective images from being obscured by background information, guaranteed by its mathematical reversibility property. Second, to overcome the overgeneralization issue of conventional autoencoders caused by imperfectly crafted decoders, we propose a novel decoder-free reconstruction workflow based on the invertible feature encoder. Specifically, we force one portion of extracted features to approach a predefined constant tensor during the training stage by minimizing their mean squared error. Next, we feed the remained features and the predefined constant tensor backward into the encoder to reconstruct the original images. During the testing phase, we formulate an anomaly score that consolidates the reconstruction error and mean squared error to spot defects. Extensive experiments are conducted on 4 real-world datasets. Our method consistently outperforms state-of-the-art techniques, demonstrating an average increase of 8.5% on the F1 score. © 2023 IEEE. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

A novel rotor dynamic balancing method based on blade tip clearance measurement without the once per revolution sensor

引用

Chinese Journal of Aeronautics 2025年第2期38卷 445-458页

作者： Weibo LI Weimin WANG Shuai ZHANG Jiale WANG Yulong LIN Tianqing LI Key Lab of Engine Health Monitoring-Control and Networking of Ministry of Education Beijing University of Chemical TechnologyBeijing 100029China State Key Laboratory of High-end Compressor and System Technology Beijing University of Chemical TechnologyBeijing 100029China

The existence of the aeroengine casing,limited monitoring points,and multi-fault characteristics make obtaining the rotor’s vibration transmission characteristics challenging,resulting in difficulties accurately identifying the rotor *** paper utilizes a high-frequency composite sensor to monitor the engine’s blade tip clearance(BTC)and extracts unbalanced information from BTC signals for rotor dynamic balancing,while avoiding the need for the once per revolution(OPR)***,the vibration characteristics of the rotor-blade system under multi-fault conditions are ***,based on BTC measurement,a none OPR method and an unbalance identification method are proposed,in which the radial vibration of the blade tip in the BTC signals at different speeds is extracted and operated in the time domain to obtain the rotor unbalanced vibration,the signal is reconstructed,and cross-correlation analysis is used to accurately identify the magnitude and phase of the unbalanced ***,a rotor test bench is utilized for experimental *** results reveal that the dynamic balancing method based on the BTC signal can more precisely identify the rotor unbalance than the traditional rotor dynamic balancing *** application of this technique will effectively improve engine health management and fault prediction.

关键词： Aeroengine Rotor unbalance Composite sensor None once per revolution Blade tip clearance Dynamic balancing

来源：评论

学校读者我要写书评

暂无评论

Dynamic coupling of ferrihydrite transformation and associated arsenic desorption/redistribution mediated by sulfate-reducing bacteria

引用

Journal of Environmental Sciences 2024年第1期135卷 39-50页

作者： Wenjing Zhou Huiyan Zhu Shiwen Hu Bowei Zhang Kun Gao Zhi Dang Chongxuan Liu State Environmental Protection Key Laboratory of Integrated Surface Water-Groundwater Pollution Control School of Environmental Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China The Key Lab of Pollution Control and Ecosystem Restoration in Industry Clusters Ministry of EducationSouth China University of TechnologyGuangzhou 510006China

Sulfate-reducing bacteria play an important role in the geochemistry of iron(oxyhydr)oxide and arsenic(As)in natural environments;however,the associated reaction processes are yet to be fully *** this study,batch experiments coupled with geochemical,spectroscopic,microscopic,and thermodynamic analyses were conducted to investigate the dynamic coupling of ferrihydrite transformation and the associated As desorption/redistribution mediated by Desulfovibrio vulgaris(***).The results indicated that *** could induce ferrihydrite transformation via S^(2-)-driven and direct reduction *** the absence of SO_(4)^(2-),*** directly reduced ferrihydrite,and As desorption and re-sorption occurred simultaneously during the partial transformation of ferrihydrite to *** increase in SO_(4)^(2-)loading promoted the S^(2-)-driven reduction of ferrihydrite and accelerated the subsequent mineralogical *** the low and medium SO_(4)^(2-)treatments,ferrihydrite was completely transformed to a mixture of magnetite and mackinawite,which increased the fraction of As in the residual phase and stabilized *** the high SO_(4)^(2-)treatment,although the replacement of ferrihydrite by only mackinawite also increased the fraction of As in the residual phase,22.1%of the total As was released into the solution due to the poor adsorption affinity of As to mackinawite and the conversion of As^(5+)to As^(3+).The mechanisms of ferrihydrite reduction,mineralogy transformation,and As mobilization and redistribution mediated by sulfate-reducing bacteria are closely related to the surrounding SO_(4)^(2-)*** results advance our understanding of the biogeochemical behavior of Fe,S,and As,and are helpful for the risk assessment and remediation of As contamination.

关键词： Sulfate-reducing bacteria Arsenic Ferrihydrite Transformation Redistribution

来源：评论

学校读者我要写书评

暂无评论

Data-driven consensus control of fully distributed event-triggered multi-agent systems

引用

Science China(Information Sciences) 2023年第5期66卷 147-161页

作者： Yifei LI Xin WANG Jian SUN Gang WANG Jie CHEN School of Automation Beijing Institute of Technology The State Key Lab of Autonomous Intelligent Unmanned Systems Beijing Institute of Technology Beijing Institute of Technology Chongqing Innovation Center Department of Control Science and Engineering Tongji University

This study investigates the consensus control issue in discrete-time linear multi-agent systems(MASs) using data-driven control under undirected communication networks. To alleviate the communication burden, an adaptive event-triggered control strategy involving only local information is proposed and a model-based stability condition is derived that guarantees the asymptotic consensus of MASs. Furthermore,a data-based consensus condition for unknown MASs is established by combining a data-based system representation with the model-based stability condition, using only pre-collected noisy input-state data instead of the accurate system information a priori. Specifically, both model-based and data-driven event-triggered controllers can be utilized without requiring any global information. The validity and correctness of the controllers and associated theoretical results are demonstrated via numerical simulations.

关键词： distributed control event-triggered control data-driven control discrete-time MASs

来源：评论

学校读者我要写书评

暂无评论

Interval Weight state Update Approach with Deep Reinforcement Learning for Dynamic Load Change Tasks in Air Separation Processes 13

Interval Weight State Update Approach with Deep Reinforcemen...

引用

13th IEEE Data Driven control and Learning Systems Conference, DDCLS 2024

作者： Qiu, Ruiyu Yang, Guanghui Xu, Zuhua Shao, Zhijiang College of Control Science and Engineering Zhejiang University State Key Lab of Industrial Control Technology Hangzhou310027 China HuZhou Research Institute of Industrial Control Technology China

ISBN: (纸本)9798350361674

The air separation unit (ASU) is important for producing high-purity oxygen, nitrogen, and argon, and dynamic load change operation helps meet the needs of downstream industries. The ASU has an extremely long delay, and the requirements for this operation are strict, and model predictive control (MPC) is usually used for this task. However, the burden of online MPC computation is a key issue in improving production and economic efficiency. In this paper, a framework based on Reinforcement Learning (RL) is proposed to solve the long-delayed task in ASU. The state and reward function are specially designed for this task. First, training increases the sampling time of the original model to create a low resolution environment, which makes training more efficient. As a sacrifice, the control precision is reduced in the original high resolution environment. Then, an algorithm called Interval Weighted state Update (IWSU) is proposed to restore the agent and keeps the action accuracy in the original environment. The dynamic load change task works as the case in this paper. The performance of RL is compared with that of MPC, and results show that RL is almost exactly the same as MPC in key flow indicators, and can well meet the remaining content and purity range requirements. IWSU shows good performance compared with directly applying the agent to the original high resolution environment. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

MND-GAN: A Research on Image Deblurring Algorithm Based on Generative Adversarial Network 42

MND-GAN: A Research on Image Deblurring Algorithm Based on G...

引用

42nd Chinese control Conference, CCC 2023

作者： Peng, Jiaheng Guan, Tong Liu, Feihu Liang, Jun Zhejiang University State Key Lab of Industrial Control Technology Hangzhou China

ISBN: (纸本)9789887581543

Aiming at the image blurring problem that often occurs in machine vision applications in intelligent transportation and unmanned driving scenarios, an image blurring algorithm MobileNetDeblur-GAN (MND-GAN) based on generative adversarial network is proposed in this paper. The algorithm has the following characteristics: the least square generative adversarial model (LS-GAN) is used for network training to solve the gradient disappearance problem in the traditional GAN network training process;the generator structure is designed based on MobileNet and two scales of input images are used to improve the authenticity of image restoration at different scales;the weights of nonlinear layers at different scales are shared, which greatly reduces the overall reasoning time of the deblurring algorithm;a global discriminator and a local discriminator are combined to construct a dual discriminator structure to improve the adaptability of the model to different scenarios;the loss function uses the combination of perception loss and structure loss to make the deblurring effect more consistent with the visual characteristics of clear images. The performance of MND-GAN algorithm is compared on multiple datasets, and good deblurring effect is obtained. At the same time, the reasoning speed of the network exceeds that of other comparison algorithms, and it can meet the real-time requirements of intelligent transportation and unmanned driving scenarios. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

External blast flow field evolution and response mechanism of single-layer reticulated dome structure

引用

Defence technology（防务技术） 2023年第6期24卷 241-253页

作者： Shao-bo Qi Guang-yan Huang Xu-dong Zhi Feng Fan State Key Laboratory of Explosion Science and Technology Beijing Institute of TechnologyBeijing100081PR China Key Lab of Structure Dynamic Behaviour and Control of the Ministry of Education Harbin Institute of TechnologyHarbin150090China Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters of Ministry of Industry and Information Technology Harbin Institute of TechnologyHarbin150090China Beijing Institute of Technology Chongqing Innovation Center Chongqing401120China

Single-layer reticulated dome structure are commonly high-profile building in the public and can be attractive targets for terrorist bombings,so the public can benefit from enhanced safety with a stronger understanding of the behavior of single-layer reticulated dome structure under *** paper investigates the fluid-structure interaction process and the dynamic response performance of the singlelayer reticulated dome under external blast *** experimental and numerical results shown that structural deformation is remarkably delayed compared with the velocity of blast wave,which advises the dynamic response of large-span reticulated dome structure has a negligible effect on the blast wave propagation under *** failure modes are identified by comparing the plastic development of each ring and the residual spatial geometric of the structure,i.e.,minor vibration,local depression,severe damage,and overall *** plastic deformation energy and the displacement potential energy of the structure are the main consumers of the blast *** addition,the stress performance of the vertex member and the deep plastic ratio of the whole structure can serve as qualitative indicators to distinguish different failure modes.

关键词： External blast loading Reticulated dome structure Fluid-structure interaction Dynamic response mode Response mechanism

来源：评论

学校读者我要写书评

暂无评论

Sensitivity analysis and probability modelling of the structural response of a single-layer reticulated dome subjected to an external blast loading

引用

Defence technology（防务技术） 2023年第5期23卷 152-163页

The structural response of a single-layer reticulated dome to external explosions is shaped by many variables,and the associated uncertainties imply non-deterministic *** deterministic methods for predicting the consequences of specific explosions do not account for these ***,the impact of the uncertainties associated with these input variables on the structures’response needs to be studied and *** this study,a parametric uncertainty analysis was conducted ***,local and global sensitivity analyses were carried out to identify the drivers of the structural dynamic response.A probabilistic structural response model was established based on sensitive variables and a reasonable sample ***,some deterministic empirical methods for explosion-resistance design,including the plane blast load model of CONWEP,the curved blast load model under the 50%assurance level,and the 20%mass-increased method,were used for evaluating their *** results of the analyses revealed that the structural response of a single-layer reticulated dome to an external blast loading is lognormally ***,the MB0.5 method based on the curved reflector load model yielded results with a relatively stable assurance rate and reliability,but CONWEP did not;thus,the 1.2MB0.5 method can be used for making high-confidence simple *** addition,the results indicated that the structural response is very sensitive to the explosion *** on these results,it is suggested that for explosion proofing,setting up a defensive barrier is more effective than structural strengthening.

关键词： Dome structure Blast load uncertainty Sensitivity analysis Probabilistic investigation Reliability evaluation

来源：评论

学校读者我要写书评

暂无评论

Prediction of Coefficient of Restitution for Impact Elastoplastic Spheres Considering Finite Plate Thickness

引用

Chinese Journal of Mechanical Engineering 2024年第4期37卷 183-193页

作者： Yunfeng Fan Hao Wang Tao Zhou Limin Zou Zhinong Jiang Minghui Hu State Key Laboratory of High-end Compressor and System Technology Beijing University of Chemical TechnologyBeijing 100029China China Ship Research and Development Academy Beijing 100101China Key Lab of Engine Health Monitoring-Control and Networking of Ministry of Education Beijing University of Chemical TechnologyBeijing 100029China Beijing Key Laboratory of High-End Mechanical Equipment Health Monitoring and Self-Recovery Beijing University of Chemical TechnologyBeijing 100029China

Collisions between objects are a relatively common phenomenon in *** of collision processes can greatly contribute to solving problems such as impact-rub faults and particle *** coefficient of restitution is a critical parameter in the analysis of collision *** experiments have shown that the coefficient of restitution is closely related to the plate thickness,and the smaller the plate thickness,the more inaccurate the coefficient of restitution predicted by the existing model,which seriously affects the process of collision *** remedy this shortcoming,this paper proposes a plate thickness influence factor with the ratio of sphere diameter to plate thickness as the *** plate thickness influence factor can optimize the coefficient of restitution model to effectively predict the coefficient of restitution of impacting elastoplastic spheres with finite plate ***,the validity of the new model is verified using a large amount of experimental data.

关键词： Collision Coefficient of restitution Energy loss Sphere

来源：评论

学校读者我要写书评

暂无评论

A Novel Foreign Object Detection Method in Transmission Lines Based on Improved YOLOv8n

引用

Computers, Materials & Continua 2024年第4期79卷 1263-1279页

作者： Yakui Liu Xing Jiang Ruikang Xu Yihao Cui Chenhui Yu Jingqi Yang Jishuai Zhou School of Mechanical and Automotive Engineering Qingdao University of TechnologyQingdao266520China State Key Laboratory of Electrical Insulation and Power Equipment Xi’an Jiaotong UniversityXi’an710049China Key Lab of Industrial Fluid Energy Conservation and Pollution Control Qingdao University of TechnologyMinistry of EducationQingdao266520China

The rapid pace of urban development has resulted in the widespread presence of construction equipment andincreasingly complex conditions in transmission corridors. These conditions pose a serious threat to the safeoperation of the power *** vision technology, particularly object recognition technology, has beenwidelyemployed to identify foreign objects in transmission line images. Despite its wide application, the technique faceslimitations due to the complex environmental background and other auxiliary factors. To address these challenges,this study introduces an improved YOLOv8n. The traditional stepwise convolution and pooling layers are replacedwith a spatial-depth convolution (SPD-Conv) module, aiming to improve the algorithm’s efficacy in recognizinglow-resolution and small-size objects. The algorithm’s feature extraction network is improved by using a LargeSelective Kernel (LSK) attention mechanism, which enhances the ability to extract relevant features. Additionally,the SIoU Loss function is used instead of the Complete Intersection over Union (CIoU) Loss to facilitate fasterconvergence of the algorithm. Through experimental verification, the improved YOLOv8n model achieves adetection accuracy of 88.8% on the test set. The recognition accuracy of cranes is improved by 2.9%, which isa significant enhancement compared to the unimproved algorithm. This improvement effectively enhances theaccuracy of recognizing foreign objects on transmission lines and proves the effectiveness of the new algorithm.

关键词： YOLOv8n data enhancement attention mechanism SPD-Conv Smoothed Intersection over Union(SIoU)Loss

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：