检索结果-内蒙古大学图书馆

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

作者： Sun, Shu Qian, Jinchuan Zhang, Xinmin Song, Zhihuan College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China

ISBN: (纸本)9798350361674

With the development of big data, data-driven fault diagnosis models have experienced rapid growth. However, as the complexity of models increases, there is a corresponding rise in the demand for data. To obtain a substantial amount of data, traditional approaches involve centralizing datasets from multiple factories for training. However, due to heightened emphasis on data privacy from enterprises and regulatory bodies, this method becomes more challenging to implement and poses risks of data leakage. In response to this challenge, this paper designs a novel federated learning-based fault diagnosis modeling approach. Each local device trains its model on its local dataset and subsequently uploads updated model parameters to a central server for global model aggregation and updating. However, it is worth noting that in industrial processes, there may be concurrent class imbalance and data client imbalance, which brings challenges to fault diagnosis modeling based on federated learning. To address this challenge, we further propose a dynamic client aggregation fault diagnosis method based on category loss in federated learning. Experimental results indicate that the proposed approach not only protects data privacy in imbalanced class and client scenarios but also achieves outstanding fault recognition accuracy and robustness. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Path Planning Algorithm for Manipulator Based on Manipulability-Maximizing 13

Path Planning Algorithm for Manipulator Based on Manipulabil...

引用

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

作者： Zhang, Rui Liu, Shan College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China

ISBN: (纸本)9798350361674

An improved path planning algorithm based on RRT∗ is proposed for the manipulator to generate a collision-free path for end-effector in this paper, which maximizes the manipulator's manipulability throughout the entire path. The algorithm introduces manipulability information as prior information to guide the RRT node toward desired regions. By introducing hybrid cost into improved RRT* algorithm, the path length is minimized while the expected manipulability is maximized. Finally, the end-effector path is transformed into a configuration trajectory by solving a multi-objective optimization problem. The simulation results compared with RRT* demonstrates the effectiveness of the proposed algorithm. © 2024 IEEE.

关键词： End effectors

来源：评论

学校读者我要写书评

暂无评论

Few-shot object detection via class encoding and multi-target decoding

引用

IET Cyber-Systems and Robotics 2023年第2期5卷 1-14页

作者： Xueqiang Guo Hanqing Yang Mohan Wei Xiaotong Ye Yu Zhang State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhouChina Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province HangzhouChina

The task of few‐shot object detection is to classify and locate objects through a few annotated *** many studies have tried to solve this problem,the results are still not *** studies have found that the class margin significantly impacts the classification and representation of the targets to be *** methods use the loss function to balance the class margin,but the results show that the loss‐based methods only have a tiny improvement on the few‐shot object detection *** this study,the authors propose a class encoding method based on the transformer to balance the class margin,which can make the model pay more attention to the essential information of the features,thus increasing the recognition ability of the ***,the authors propose a multi‐target decoding method to aggregate RoI vectors generated from multi‐target images with multiple support vectors,which can significantly improve the detection ability of the detector for multi‐target *** on Pascal visual object classes(VOC)and Microsoft Common Objects in Context datasets show that our proposed Few‐Shot Object Detection via Class Encoding and Multi‐Target Decoding significantly improves upon baseline detectors(average accuracy improvement is up to 10.8%on VOC and 2.1%on COCO),achieving competitive *** general,we propose a new way to regulate the class margin between support set vectors and a way of feature aggregation for images containing multiple objects and achieve remarkable *** method is implemented on mmfewshot,and the code will be available later.

关键词： Class Margin Few-Shot Object Detection Multi-Target Transformer

来源：评论

学校读者我要写书评

暂无评论

High-impedance Fault Section Location for Distribution Networks Based on t-distributed Stochastic Neighbor Embedding and Variable Mode Decomposition

引用

Journal of Modern Power Systems and Clean Energy 2024年第5期12卷 1495-1505页

作者： Zhihua Yin Yuping Zheng Zhinong Wei Guoqiang Sun Sheng Chen Haixiang Zang the College of Energy and Electrical Engineering Hohai UniversityNanjing 210098China State Key Laboratory of Smart Grid Protection and Control NARI Group CorporationNanjing 211106China

When high-impedance faults(HIFs)occur in resonant grounded distribution networks,the current that flows is extremely weak,and the noise interference caused by the distribution network operation and the sampling error of the measurement devices further masks the fault ***,locating a fault section with high sensitivity is *** existing technologies,this study presents a novel fault feature identification framework that addresses this *** framework includes three key steps:(1)utilizing the variable mode decomposition(VMD)method to denoise the fault transient zero-sequence current(TZSC);(2)employing a manifold learning algorithm based on t-distributed stochastic neighbor embedding(t-SNE)to further reduce the redundant information of the TZSC after denoising and to visualize fault information in high-dimensional 2D space;and(3)classifying the signal of each measurement point based on the fuzzy clustering method and combining the network topology structure to determine the fault section *** simulations and field testing confirm that the proposed method accurately detects the fault location,even under the influence of strong noise interference.

关键词： High-impedance fault noise interference fault section location t-distributed stochastic neighbor embedding(t-SNE) transient zero-sequence current

来源：评论

学校读者我要写书评

暂无评论

Steady-state and dynamic simulation of gas phase polyethylene process

引用

Chinese Journal of Chemical engineering 2024年第11期75卷 110-120页

作者： Xiaodong Hong Wanke Chen Zuwei Liao Xiaoqiang Fan Jingyuan Sun Yao Yang Chunhui Zhao Jingdai Wang Yongrong Yang State Key Laboratory of Chemical Engineering College of Chemical and Biological EngineeringZhejiang UniversityHangzhou 310027China Engineering Research Center of Functional Materials Intelligent Manufacturing of Zhejiang Province ZJU-Hangzhou Global Scientific and Technological Innovation CenterHangzhou 311215China Ningbo Research Institute Zhejiang UniversityNingbo 315100China State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhou 310027China

Gas-phase polyethylene(PE)processes are among the most important methods for PE production.A deeper understanding of the process characteristics and dynamic behavior,such as properties of PE and reactor stability,holds substantial interest for both academic researchers and *** this study,both steady-state and dynamic models for a gas-phase polyethylene process are established as a simulation platform,which can be used to study a variety of operation tasks for commercial solution polyethylene processes,such as new product development,process control and real-time *** copolymerization kinetic parameters are fitted by industrial ***,a multi-reactor series model is developed to characterize the temperature distribution within the fluidized bed *** accuracy in predicting melt index and density of the polymer,and the dynamic behavior of the developed models are verified by real plant ***,the dynamic simulation platform is applied to compare four practical control schemes for reactor temperature by a series of simulation experiments,since temperature control is important in industrial *** results reveal that all four schemes effectively track the setpoint ***,only the demineralized water temperature cascade control demonstrates excellent performance in handling disturbances from both the recycle gas subsystem and the heat exchange subsystem.

关键词： Gas-phase polyethylene process Steady state Dynamic modeling control

来源：评论

学校读者我要写书评

暂无评论

TCPP: A Benchmark Platform for Traffic Congestion Prediction with Multi-source Auxiliary Data

TCPP: A Benchmark Platform for Traffic Congestion Prediction...

引用

2024 China Automation Congress, CAC 2024

作者： Zhou, Yusong Zhang, Xinmin Jiang, Xiaoyu Song, Zhihuan State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Zhejiang China Huzhou Institute of Industrial Control Technology Zhejiang Huzhou China

ISBN: (纸本)9798350368604

With rapid urbanization, traffic congestion has become a challenge to efficient urban transportation. To address this challenge, we develop a novel traffic congestion prediction platform (TCPP) which is a unified benchmark tool for traffic congestion prediction with multi-source auxiliary data. By combining data integration, model selection and evaluation modules, TCPP provides a standardized framework for researchers to compare and evaluate different models and datasets. Meanwhile, through a comprehensive and detailed configuration syntax, TCPP allows users to flexibly schedule tasks and execute multiple tasks continuously and uninterruptedly. In addition, two datasets collected from California highways are enriched with multi-source weather data and temporal features. We evaluate the performance of TCPP on these two datasets and demonstrate its effectiveness in predicting traffic congestion. The results demonstrate that TCPP can contribute to future research on traffic congestion prediction and the development of intelligent transportation systems and urban traffic management. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

A Novel Trajectory Planning Method Based on Trust Region Policy Optimization

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-15页

作者： Ye, Bao-Lin Zhang, Jiajie Li, Lingxi Wu, Weimin Jiaxing Key Laboratory of Smart Transportations the School of Information Science and Engineering Jiaxing University China Elmore Family School of Electrical and Computer Engineering Purdue University Indianapolis USA State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China

Trajectory planning method is a research hotspot in autonomous driving. Existing reinforcement learning-based trajectory planning methods suffer from unstable performance due to the strong randomness of network weight parameter updates during the training process. Therefore, this paper proposes a novel trajectory planning method based on deep reinforcement learning trust region policy optimization (TRPO). Firstly, in order to enhance the robustness of the trajectory planning method based on deep reinforcement learning TRPO, a TRPO-LSTM based decision model was proposed. More specifically, a long short term memory (LSTM) based state feature extraction network was designed and embeded into a TRPO-based decision model to enhance the ability of TRPO to extract information from the environmental state space. Secondly, in order to make the planned trajectory adaptive to the dynamic changes of traffic environment, we presented a novel TRPO-LSTM trajectory fitting algorithm. To the best of our knowledge, this is the first work aiming at applying the TRPO-LSTM based decision model in the trajectory fitting process to search the optimal longitudinal trajectory speed. Finally, the proposed trajectory planning method was implemented and simulated on the CARLA simulator. The experimental results show that, compared with existing trajectory planning methods based on deep reinforcement learning algorithms, our proposed method achieves a cumulative reward improvement of over 28.9% in the scenario of four lane highway, and has better robustness. Meanwhile, the proposed method can achieve a lower collision rate of 0.93% while improving the average speed and comfort of vehicle driving. IEEE

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Research on Optimization Method of Injection Molding Machine Temperature control System Based on IK-SS

Research on Optimization Method of Injection Molding Machine...

引用

2024 China Automation Congress, CAC 2024

作者： Zou, Haipeng Ye, Quanxiang Li, Xiaoyu Kong, Xiangsong Zhao, Dan Shao, Zhijiang School of Electrical Engineering and Automation Xiamen University of Technology Xiamen China State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China Zhangzhou Hongxingtai Electronics Co. Ltd China College of Control Science and Engineering State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou310027 China

ISBN: (纸本)9798350368604

Injection molding, as a plastic processing technology, is widely used in the mass production of plastic products with high precision and automation. However, the performance optimization process of this system currently faces some prominent issues, such as time consumption, reliance on experience, and difficulty in achieving optimality. Traditional optimization methods typically rely on manual experience and rules, which are inefficient and time-consuming. To enhance the performance of the control system, this paper focuses on utilizing an improved simplex search method based on the data-driven optimization concept to optimize the parameters of the temperature control system of the injection molding machine. The method introduced in this paper is termed the Knowledge-Informed Simplex Search Method Based on Adjacent Historical Centroid Points Information (IK-SS). The IK-SS algorithm is a variant of the simplex search method that utilizes information from the centroids of neighboring simplices to evaluate the current state of the optimization process and dynamically adjust the iteration step size. This approach aims to improve optimization efficiency while reducing computational complexity and time costs. Simulation and experimental validation demonstrate that the IK-SS algorithm significantly enhances the temperature control performance of the injection molding machine (IMM). This demonstrates the potential of the IK-SS algorithm as a tool for optimizing the temperature control system of injection molding machines. © 2024 IEEE.

关键词： Molding

来源：评论

学校读者我要写书评

暂无评论

Self-Contrastive Learning Fault Diagnosis Network for Signal Imaging: A Case Study

Self-Contrastive Learning Fault Diagnosis Network for Signal...

引用

2024 China Automation Congress, CAC 2024

作者： He, Wenbin Mao, Jianxu Wang, Yaonan Li, Zhe Yan, Feng Liu, Kexin College of Electrical & Information Engineering National Engineering Research Center of Robot Visual Perception & Control Technology Hunan University Hunan China College of Control Science & Engineering State Key Laboratory of Industrial Control Technology Zhejiang University Zhejiang China

ISBN: (纸本)9798350368604

The deep convolution method based on MSDP signal imaging has been proven to be an effective means of monitoring the robot grinding process. This method has very high requirements on the quality of imaging and requires a lot of computing resources. This paper proposes an image self-contrastive learning network that can effectively extract fault information from low-pixel fuzzy images and achieve efficient and accurate condition monitoring. The network first calculates the correlation distance matrix between two identical modified symmetrized dot pattern (MSDP) images and uses the generated similarity labels to calculate the contrast loss to extract the embedded features of the image. Finally, the classification network is trained using the cross entropy loss to achieve the classification of fault images. The method was verified on a robotic grinding platform to significantly reduce the calculation time while maintaining the recognition accuracy, which provides reliable technical support for the real-time monitoring of the robotic grinding process. © 2024 IEEE.

关键词： Contrastive Learning fault diagnosis robotic grinding signal imaging

来源：评论

学校读者我要写书评

暂无评论

Modulating the Coordination Environment of Cu Sites for Highly Selective CO2 Electroreduction to Ethylene

Chem and Bio Engineering

引用

Chem and Bio engineering 2024年第10期1卷 836-845页

作者： Luo, Wenfu Li, Shijie Shen, Yao Zhang, Shihan Li, Wei Li, Sujing Key Laboratory of Biomass Chemical Engineering of the Ministry of Education Institute of Industrial Ecology and Environment College of Chemical and Biological Engineering Zhejiang University Hangzhou310027 China Key Laboratory of Microbial Technology for Industrial Pollution Control of Zhejiang Province College of Environment Zhejiang University of Technology Hangzhou310014 China

Carbon dioxide (CO2) can be reduced to a variety of value-added products by the electrochemical reduction of CO2 (ERC). Modulating the coordination environment of the Cu sites can effectively optimize the selectivity and activity of the reduction process. In this work, we report a facile strategy to regulate the coordination environment of Cu sites for improving the Faradaic efficiency (FE) of ethylene. Room-temperature Ar plasma with different powers and treating times was employed to partially remove the 2,5-dihydroxyterephthalic moieties from the structure of Cu-MOF-74, thus resulting in more unsaturated coordinated Cu sites and lower oxidation state. The structure distortion and electron configuration change of Cu-MOF-74-P was observed from electron paramagnetic resonance (EPR). Meanwhile, the proportion of Cu+ in Cu-MOF-74-P has increased significantly. By combination of XAFS and in situ DRIFTS, it was shown that the coordination number of Cu-MOF-74-P has decreased from 2.7 to 1.6, thus facilitating the formation of more *CO intermediates on the surface during the reduction process. This modification strategy successfully increased the Faradaic efficiency of C2H4 in the product up to 48%, which was 3.2 times of its original performance. This work provides some guidance for the design of catalysts with tailored selectivity during CO2 electroreduction. © 2024 The Authors. Co-published by Zhejiang University and American Chemical Society.

关键词： Electron spin resonance spectroscopy

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：