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 lab.led 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

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

A Distributed Algorithm for Large-Scale Multi-Agent MINLPs 63

A Distributed Algorithm for Large-Scale Multi-Agent MINLPs

引用

63rd IEEE Conference on Decision and control, CDC 2024

作者： Dong, Sheng Xia, Weiguo Dalian University of Technology Key Lab. of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education School of Control Science and Engineering China

ISBN: (纸本)9798350316339

In this paper, we focus on the optimization of large-scale multi-agent systems, where agents collab.ratively optimize the sum of local objective functions through their own continuous and/or discrete decision variables, subject to global coupling constraints and local constraints. The resulting Mixed-Integer Nonlinear Programmings (MINLPs) are NP-hard, non-convex, and large-scale. Therefore, this paper aims to design distributed algorithms to find feasible suboptimal solutions with a guaranteed bound. To this end, considering dual decomposition as an effective method to decompose large-scale constraint-coupled optimization problems, we first show, based on the convexification effects of large-scale MINLPs, that the primal solutions from the dual are near-optimal under certain conditions. This expands recent results in Mixed-Integer Linear Programmings (MILPs) to the nonlinear case but requires additional efforts on the proof. Utilizing this result to tighten the coupling constraints, we develop a fully distributed algorithm for the tightened problem, based on dual decomposition and consensus protocols. The algorithm is guaranteed to provide feasible solutions for the original MINLP. Moreover, asymptotic suboptimality bounds are established for the obtained solution. Finally, the efficacy of the method is verified through numerical simulations. © 2024 IEEE.

关键词： Mixed-integer linear programming

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

A Novel Point Cloud Deep Learning Method for Predicting Variable Airfoil Flow Fields 43

A Novel Point Cloud Deep Learning Method for Predicting Vari...

引用

43rd Chinese control Conference, CCC 2024

作者： Zhang, Xinyao Cao, Junzhe Dalian University of Technology Control Science and Engineering Dalian116024 China Dalian University of Technology Key Lab. of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian116024 China

ISBN: (纸本)9789887581581

Airfoil flow field is of great significance to the design optimization of aircraft shape. Convolutional Neural Networks (CNNs) have been applied in flow field prediction studies, which greatly reduce the cost of computation time in traditional Computational Fluid Dynamics (CFD) methods. However, such CNN-based approaches normally bring extra errors due to the procedure of interpolating irregular grid data into Cartesian grids, which may lead to underperforming prediction accuracy. In this paper, an improved PointNet++ point cloud deep learning method was proposed for the airfoil flow field prediction. The unstructured grid vertices in the CFD domain were treated as point cloud as well as the input of neural network, and only the original information of the data was adopted to avoid interpolation. Neighborhood relationship features were defined and spliced with neighborhood point features, and the features were integrated by simultaneously solving for the maximum, minimum, sum, and average values to extract the local or global features of the system to enhance the performance of deep network for extracting the information. Finally, the proposed network was trained and tested by using 549 sets of flow field data formed by 61 airfoils under 9 angle-of-attack conditions, and further predicted for an additional 32 datasets with different airfoils and conditions. The simulation results show that the method proposed in this study gets lower prediction errors in terms of pressure, Mach number, x-direction velocity, and y-direction velocity than the two other current point cloud deep networks, PointNet and PointNet++. At the same time, the computation speed of this method is about 14 times faster than the traditional CFD method. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Computational fluid dynamics

来源：评论

学校读者我要写书评

暂无评论

Distributed Data Recovery Against False Data Injection Attacks in DC Microgrids

Distributed Data Recovery Against False Data Injection Attac...

引用

2022 IEEE International Conference on Communications, control, and Computing Technologies for Smart Grids, SmartGridComm 2022

作者： Jin, Zexuan Liu, Mengxiang Deng, Ruilong Cheng, Peng College of Control Science and Engineering Zhejiang University State Key Lab. of Industrial Control Technology Hangzhou China

ISBN: (数字)9781665432542

ISBN: (纸本)9781665432542

With the development of information and communications technology (ICT) in DC microgrids (DCmGs), the threat of false data injection attacks (FDIAs) is becoming more and more serious. However, the existing literature mainly focuses on the detection and identification of FDIAs in DCmGs, while the data recovery after the perception of FDIAs has never been thor-oughly investigated yet. In this paper, we propose a distributed data recovery scheme to eliminate the adverse impact caused by FDIAs in DCmGs. Firstly, by observing the point of common coupling (PCC) voltage under FDIAs, the injected constant bias can be roughly estimated. In order to obtain the precise constant bias, the mean filter (MF) is adopted to handle the measurement noises and small oscillations. Then, the estimated precise constant bias is compensated for the communicated signal to eliminate the attack impact. Furthermore, our proposed data recovery scheme, which only needs local information, is fully distributed. Finally, the accuracy and effectiveness of the distributed data recovery scheme are evaluated through systematical hardware-in-the-loop (HIL) experiments. © 2022 IEEE.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Scheduling Optimization of Coal Washing Process Based on Two-Stage Fuzzy Heuristic Algorithm 13

Scheduling Optimization of Coal Washing Process Based on Two...

引用

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

作者： Zhou, Hui Wang, Zhiyuan Han, Zhongyang Wang, Linqing Zhao, Jun Wang, Wei Dalian University of Technology Key Lab. of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian116024 China School of Control Science and Engineering Dalian University of Technology Dalian116024 China

ISBN: (纸本)9798350361674

Coal washing and sorting plays a vital role for coal production. Reasonable scheduling of washing and sorting equipment, crushers and various coal silos in the coal washing and sorting process can effectively increase the total value of product coal and reduce the total energy consumption of equipment. In this paper, a multi-constrained nonlinear mixed integer programming model considering the start and stop of each equipment in the washing process is established to realize the specific regulation of the washing process. In order to overcome the problem such as local convergence when solving high-dimensional space problems, a two-stage fuzzy heuristic algorithm is proposed in this paper. In the first stage, a variety of population genetic algorithms based on fuzzy adaptive strategy control are designed for global search to establish an elite population bank to preserve high-quality individuals produced by various groups. In the second stage, an improved simulated annealing algorithm is used to perform a local search with a backtracking process on specific neighbors of individuals in the elite population bank, which can improve the stability of the algorithm and reduce the situation of falling into local convergence. Then the real data of a Chinese coal mining company was used for experiments, where the proposed algorithm is compared with other commonly used methods. The experimental results demonstrate that the proposed algorithm can increase the total coal value of the washed product by at least 1.7% compared to other algorithms, and the average total number of starts and stops of the equipment is reduced by about 7.3%, which are effectively beneficial for the related enterprise. © 2024 IEEE.

关键词： Coal mines

来源：评论

学校读者我要写书评

暂无评论

UniFace++: Revisiting a Unified Framework for Face Reenactment and Swapping via 3D Priors

引用

International Journal of Computer Vision 2025年第7期133卷 4538-4554页

作者： Xu, Chao Qian, Yijie Zhu, Shaoting Sun, Baigui Zhao, Jian Liu, Yong Li, Xuelong State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China Walf 1069B Lab Sany Group Guangzhou China China Telecom Beijing China Northwestern Polytechnical University Xi’an China

Face reenactment and swapping share a similar pattern of identity and attribute manipulation. Our previous work UniFace has preliminarily explored establishing a unification between the two at the feature level, but it heavily relies on the accuracy of feature disentanglement, and GANs are also unstable during training. In this work, we delve into the intrinsic connections between the two from a more general training paradigm perspective, introducing a novel diffusion-based unified method UniFace++. Specifically, this work combines the advantages of each, i.e., stability of reconstruction training from reenactment, simplicity and effectiveness of the target-oriented processing from swapping, and redefining both as target-oriented reconstruction tasks. In this way, face reenactment avoids complex source feature deformation and face swapping mitigates the unstable seesaw-style optimization. The core of our approach is the rendered face obtained from reassembled 3D facial priors serving as the target pivot, which contains precise geometry and coarse identity textures. We further incorporate it with the proposed Texture-Geometry-aware Diffusion Model (TGDM) to perform texture transfer under the reconstruction supervision for high-fidelity face synthesis. Extensive quantitative and qualitative experiments demonstrate the superiority of our method for both tasks. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： 3D reconstruction

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

Preclinical Assessment of Upper Limb Tremor in Parkinson's Disease with Deep Learning and Wearable technology

Preclinical Assessment of Upper Limb Tremor in Parkinson's D...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Lin, Fang Wang, Zhelong Qiu, Sen Zhao, Hongyu School of Control Science and Engineering Dalian University of Technology Key Lab. of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Liaoning Dalian China

ISBN: (纸本)9798350337020

Tremors are typically experienced by patients at the beginning of Parkinson's disease (PD). Clinicians evaluate clinical symptoms based on scale and experience, but mild tremors do not have significant characteristics and are difficult to observe with the naked eye. Implementing an intelligent and objective method to identify PD patients with early tremor symptoms and healthy controls (HC) is necessary. This study used wearable sensors to collect 9-axis inertial signals and 2-channel sEMG signals at the wrists of 13 HC and 24 PD patients from Dalian Municipal Central Hospital. Based on a Long Short-Term Memory Network (LSTM), an attention mechanism, and a Fully Convolutional Network (FCN), we develop a model to classify and recognize data from PD patients. Compared the proposed method with several classification methods, the results showed that the proposed method achieved higher classification accuracy (91.78%), precision (100%), recall (87.50%), and F1-score (93.33%) of PD class than Support Vector Machine, FCN, and LSTM. The computing time of the proposed method is approximately 1 second. The proposed method identifies early PD patients by pre-clinical assessment of mild upper limb tremors, which is valuable for early treatment and rehabilitation. © 2023 IEEE.

关键词：

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：