检索结果-内蒙古大学图书馆

Smart World Congress (SWC), IEEE

作者： Long Cheng Huiru Yan Hanlin Zhou Ying Wang Haichuan Tang Fang Fang State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Control and Computer Engineering North China Electric Power University Beijing China Chinese Academy of Sciences Institute of Computing Technology Beijing China AI Lab of CRRC Academy Beijing China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

Preventing network attacks and protecting user privacy are consistently hot research topics in the Internet of Things (IoT) and edge computing fields. Recent advancements in Federated Learning (FL) have shown promise in addressing these challenges. FL allows various clients to collaboratively build an intrusion detection system (IDS) without sharing their private data. However, most existing methods train a single intrusion detection model for all clients and assume that the training and test data distribution are identical, leading to unsatisfactory detection accuracy and generalization abilities in practice. To overcome these challenges, this paper introduces a prototype-guided personalized FL approach named PG-FedIDS. We propose two novel mechanisms within this method. Firstly, we utilize class prototypes as auxiliary information carriers to generate personalized models for each client, rather than generating a single global model as in previous works. Secondly, we propose a prototype-guided ensemble learning strategy, which can leverage the global knowledge in prototypes to enhance detection accuracy and generalization abilities for each client. We conduct extensive experiments on two benchmark datasets with different evaluation test settings. The results demonstrate that our PG-FedIDS achieves promising detection accuracy and consistently outperforms other FL baselines.

关键词： Training Privacy Accuracy Federated learning Image edge detection Prototypes Intrusion detection Data models Ensemble learning Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Combined with Heuristic Search for Solving Discrete Space Path Planning Problems

Reinforcement Learning Combined with Heuristic Search for So...

引用

第33届中国控制与决策会议

作者： Xiuling Zhang Xuenan Kang Kailun Wei Jinxiang Li Kai Ma Engineering Research Center of the Ministry of Education for Intelligent Control System and Intelligent Equipment Yanshan University Key Laboratory of Industrial Computer Control Engineering of Hebei Province Yanshan University

Reinforcement learning(RL) has been successfully applied to solve path planning problems,but learning is generally *** main reason is not making full use of information collected during interaction with the *** paper proposes a novel method to solve the discrete space path planning problem in an environment without prior knowledge with intensive obstacles based on RL and heuristic ***,we apply Dyna-Q algorithm of RL to explore the map and search for the target point and optimize its policy with upper confidence bound(UCB).Then,when the target point is found,we use heuristic search to plan the path from the starting point to the target point and narrow the path to a small ***,we combine Dyna-Q algorithm with the heuristic search recommended path for path *** evaluate our algorithm using maze navigation *** results verify that heuristic search accelerates Dyan-Q convergence.

关键词： Dyna-Q algorithm Heuristic search Path planning Discrete space

来源：评论

学校读者我要写书评

暂无评论

3D printing of self-powered triboelectric intelligent system with enhanced output performance for material identification via machine learning

引用

Chemical engineering Journal 2025年 515卷

作者： Huang, Bingyu Xu, Kailong Zhang, Xiaofei Zhang, Yongcheng Long, Yun-Ze Ge, Shuzhi Sam Wei, Xiangxia School of Automation Shandong Key Laboratory of Industrial Control Technology Qingdao University Qingdao266071 China College of Materials Science and Engineering Qingdao University Qingdao266071 China Collaborative Innovation Center for Nanomaterials & Devices College of Physics Qingdao University Qingdao266071 China College of Physics Qingdao University Qingdao266071 China Department of Electrical & Computer Engineering National University of Singapore 117576 Singapore

Triboelectric nanogenerators (TENGs) have attracted global attention for energy conversion from various types of mechanical energy into electricity. Traditional approaches for improving triboelectric conversion efficiency generally involved complicated preparation methods and strict structural design, which cannot fulfill the stringent requirements of material adaptability and application scenarios. In this work, a flexible TENG was developed based on zirconium-doped barium titanate (BaZrxTi1−xO3, BZT) particles in polydimethylsiloxane (PDMS) matrix. Subsequently, BZT/PDMS composites with patterned structures were fabricated by direct ink writing (DIW) based three-dimensional (3D) printing to significantly enhance the electrical performance. It was demonstrated that the TENG could deliver a maximum open-circuit voltage (VOC) of 350 V and a short-circuit current (ISC) of 4.9 µA with a maximum power density of 2.4 W m−2. Moreover, an effective utilization of the TENG was designed to detect the presence of humans, saving a huge amount of electrical energy. Finally, a TENG-based tactile sensor was integrated with machine learning to construct a material identification system, which was capable of recognizing different materials with a high accuracy of 98.54 %. The TENG-based tactile sensor with machine learning demonstrated a tremendous application in material perception, promoting the development of versatile sensors in the field of machine intelligence. © 2025 Elsevier B.V.

关键词： Liquid crystals

来源：评论

学校读者我要写书评

暂无评论

Condition Monitoring and Fault Diagnosis of Coal Mill Based on Mechanism Modeling Simulation and D-S Evidence Fusion

Condition Monitoring and Fault Diagnosis of Coal Mill Based ...

引用

第34届中国控制与决策会议

作者： Tian Qiu Yuchen Yang Yue Guo Xiaofeng Chen Key Laboratory of Industrial Process Measurement and Control New Technology and System North China Electric Power University School of Control and Computer Engineering North China Electric Power University North China Electric Power Research Institute Co. Ltd

The coal mill is the key equipment of powdering system in coal-fired power plants,whose working state has an important influence on the combustion stability of boiler as well as the operation ***,owing to the lack of real fault data,it is difficult and not available enough to support and achieve the research of data-driven fault diagnosis ***-type medium-speed coal mill was selected as the research object in this ***,the existing mechanism model had been further improved to make it more effective and reasonable,and we used it to respectively simulate the typical operating data of the normal condition and three fault *** paper transformed the problem of fault diagnosis into the measurement of similarity between the testing and the typical fault samples,taking the numerical distance and changing trends into account,and adopted the concept of similarity function and transformed the results into the expression and calculation of probability level,which was calculated as the diagnostic evidence of individual parameters under the same time scale.D-S evidence theory was employed to fuse the individual evidence between multiple parameters evidence,getting the fusion of multiparametric evidence as to the final diagnosis ***,the experiments verified the high accuracy of the proposed diagnostic method,and the similarity function has high rationality and feasibility.

关键词： Coal Mill System Process Fault Dynamic Mathematical Model Similarity Function D-S Evidence Fusion Theory Fault Diagnosis

来源：评论

学校读者我要写书评

暂无评论

A Novel YJQR-LSTM Model for Nonparametric Probabilistic Sustainable Agriculture Wind Power Forecasting Based on Intelligent IoT

引用

IEEE Internet of Things Journal 2024年

作者： Wang, Jie Jiang, Junhui Chen, Xinlong Cai, Defu Wu, Yue Lu, Renzhi School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Harbin Engineering University College of Computer Science and Technology Harbin150001 China State Grid Hubei Electric Power Research Institute Hubei Wuhan430079 China School of Technology State Key Laboratory of Efficient Production of Forest Resources Key Laboratory of National Forestry and Grassland Administration on Forestry Equipment and Automation Beijing Forestry University Beijing100083 China Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Industrial Internet of Things and Networked Control Ministry of Education Chongqing400065 China State Key Laboratory of Mechanical Transmission for Advanced Equipment Chongqing University Chongqing400044 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China

Energy costs associated with the consumption of non-renewable energy sources have become an important issue in improving the international competitiveness of agriculture. Wind power, as a renewable energy source, can replace non-renewable energy sources to reduce energy costs and improve the sustainability of agricultural. However, the inherent intermittency, randomness, and volatility within weather conditions and wind speed presents a substantial challenge in accurately predicting wind power generation. This work proposes a novel YJQR-LSTM algorithm that leverages Yeo-Johnson quantile regression (YJQR) with a long short-term memory (LSTM) network for nonparametric probabilistic forecasting of wind power generation via the Intelligent Internet of Things. First, an improved YJQR model based on the YJ transformation is designed to obtain a more precise characterization of wind uncertainty, providing a more flexible probability density function for wind power generation. Then, utilizing the unique structure of the LSTM network to learn the parameters of the YJQR model, temporal features can be extracted from time series data. To mitigate the impact of outliers in the raw data on accuracy and improve computational efficiency, a novel logarithmic likelihood function is developed as the loss function utilized in the training phase. The effectiveness of the proposed algorithm is validated using a real-world dataset from five wind farms from the Global Energy Forecasting Competition. Numerical results demonstrate that the algorithm provides more accurate wind power prediction results in complex wind power data environments, which is important for making full use of wind energy and thus reducing the consumption of non-renewable energy in agriculture. © 2024 IEEE.

关键词： Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

Self-Enhanced Oxidation of Fluoroquinolone Antibiotics by Cu2+/Peroxymonosulfate: Copper Coordination Mechanism with Antibiotics

SSRN

引用

SSRN 2023年

作者： Zhao, Qing Chen, Long Wang, Zhiqiang Zhou, Lei Gong, Xueqing Xiu, Guangli Shanghai Environmental Protection Key Laboratory for Environmental Standard and Risk Management of Chemical Pollutants School of Resources & Environmental Engineering East China University of Science and Technology Shanghai200237 China State Environmental Protection Key Lab of Environmental Risk Assessment and Control on Chemical Processes School of Resources & Environmental Engineering East China University of Science and Technology Shanghai200237 China State Key Laboratory of Green Chemical Engineering and Industrial Catalysis Centre for Computational Chemistry Research Institute of Industrial Catalysis School of Chemistry and Molecular Engineering East China University of Science and Technology Shanghai200237 China Shanghai Institute of Pollution Control and Ecological Security Shanghai200092 China

Trace amounts of copper have been reported to effectively promote peroxymonosulfate (PMS) induced degradation of several contaminants, while the underlying mechanism remains controversial in the transformation process of copper. Fluoroquinolone antibiotics (FQs) are a class of drugs applied to both humans and animals, widely used in animal husbandry, aquaculture and other farming industries since they have a wide antimicrobial spectrum and strong antimicrobial activity. However, FQs are not completely absorbed by receptors, and enter the environmental media through various pathways in the form of parent or metabolite. In this study, the existence of metallic copper promoted PMS induced FQs oxidation over a range of pH 5-9, and the promotion effect was highly related with copper-FQs complexation. Formation of highly reactive trivalent copper species (Cu3+) was proposed to be responsible for such promotion effect, which was further confirmed by quenching experiments, spectroscopic analyses and electron paramagnetic resonance (EPR) test. A stepwise copper reduction-oxidation mechanism was explored, herein Cu2+ was initially reduced to Cu+ with a relatively slow rate, which can be rapidly oxidize to Cu3+ by PMS. Results obtained in this study emphasize that the system undergoes the valence transition Cu2+/Cu+/Cu3+ rather than the free radical process. In particular, the promotion of copper in the system showed a significant positive correlation with the complexation ratio, further emphasizing the key role of the coordination of pollutants with Cu (II) in the oxidative transformation. © 2023, The Authors. All rights reserved.

关键词： Copper compounds

来源：评论

学校读者我要写书评

暂无评论

Predictor-Based Constrained Fixed-Time Sliding Mode control of Multi-Uav Formation Flight

SSRN

引用

SSRN 2024年

作者： Khodaverdian, Maria Hajshirmohamadi, Shahram Hakobyan, Aleksandr Ijaz, Salman Center for Scientific Innovation and Education Aerial Robotics Laboratory of National Polytechnic University of Armenia Yerevan Armenia Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan84156-83111 Iran Key Laboratory of More Electric Aircraft and Control System Lab University of Nottingham Ningbo China

In this work, a predictor-based fixed-time sliding mode control is designed to tackle the problem of achieving precise trajectory tracking control of multiple unmanned aerial vehicles formation flight. The proposed approach simultaneously addresses various practical requirements, such as optimality, constraints, fixed-time convergence, external interferences, and computational ***, a constrained performance index is constructed based on the prediction of the fixed-time sliding surface, the reaching law, and the control input. Secondly, optimal control input is calculated by solving the constrained quadratic optimization problem. An outstanding feature of this study is the theoretical guarantee of closed-loop system stability in the presence of external disturbances and ***, the comparative evaluation with sliding mode predictive control law and fixed-time sliding mode control methods demonstrates that the proposed approach achieves a straightforward control method with improved performance and acceptable accuracy. Finally, a test is conducted to demonstrate the algorithm's potential for hardware implementation by employing Hardware-in-the-Loop (HIL) test. © 2024, The Authors. All rights reserved.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Adaptive Muti-Scale Tf-Net for High-Resolution Time-Frequency Representations

SSRN

引用

SSRN 2023年

作者： Chen, Tao Chen, Qiming Zheng, Qian Li, Zhishan Zhang, Ziyi Xie, Lei Su, Hongye State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou310027 China DAMO Academy Alibaba Group Hangzhou China College of Computer Science and Control Engineering Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China University of Michigan 500 S. State Street Ann ArborMI48109 United States

In this paper, a novel adaptive multi-scale time-frequency network (AMTFN) is proposed to provide high-resolution time-frequency representations for nonstationary signals. AMTFN is an end-to-end deep network, which firstly adaptively learns the comprehensive basis functions to produce time-frequency (TF) feature maps through multi-scale 1D convolutional kernels. Then, the channel attention mechanism is embedded into AMTFN to rescale the TF feature maps selectively. Thus, the subsequent residual encoder-decoder block’s energy concentration performance is greatly improved with these rescaled TF feature maps. Besides, this paper designs a new training strategy to elegantly enable the model to pay more attention to the intersections of instantaneous frequencies trajectories. In the end, a series of simulations as well as real-world cases is studied to demonstrated the effectiveness and advantages of the proposed method. © 2023, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Submodularity-based False Data Injection Attack Scheme in Multi-agent Dynamical Systems

arXiv

引用

arXiv 2022年

作者： Luo, Xiaoyu Zhao, Chengcheng Fang, Chongrong He, Jianping The Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China The State Key Laboratory of Industrial Control Technology Institute of Cyberspace Research Zhejiang University China The Department of Electrical and Computer Engineering University of Victoria BC Canada

Consensus in multi-agent dynamical systems is prone to be sabotaged by the adversary, which has attracted much attention due to its key role in broad applications. In this paper, we study a new false data injection (FDI) attack design problem, where the adversary with limited capability aims to select a subset of agents and manipulate their local multi-dimensional states to maximize the consensus convergence error. We first formulate the FDI attack design problem as a combinatorial optimization problem and prove it is NP-hard. Then, based on the submodularity optimization theory, we show the convergence error is a submodular function of the set of the compromised agents, which satisfies the property of diminishing marginal returns. In other words, the benefit of adding an extra agent to the compromised set decreases as that set becomes larger. With this property, we exploit the greedy scheme to find the optimal compromised agent set that can produce the maximum convergence error when adding one extra agent to that set each time. Thus, the FDI attack set selection algorithms are developed to obtain the near-optimal subset of the compromised agents. Furthermore, we derive the analytical suboptimality bounds and the worst-case running time under the proposed algorithms. Extensive simulation results are conducted to show the effectiveness of the proposed algorithm. Copyright © 2022, The Authors. All rights reserved.

关键词： Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

ICA and PIND based Remainder Particle Detection Technique for Space-borne Equipment

ICA and PIND based Remainder Particle Detection Technique fo...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Zhishuai Jiang Zengshuai Qiu Yuanda Tian Junyu Shi Chengzhong Yu Hongzhi Gao Yuliang Zhao School of Control Engineering Northeastern University at Qinhuangdao Qinhuangdao China Key Lab of Industrial Computer Control Engineering of Hebei Province School of Electrical Engineering Yanshan University Qinhuangdao China DFH Satellite Co. Ltd. Beijing China

ISBN: (纸本)9781665405362

Space-borne equipment is a major component of the satellite system, which plays a very important role in the process of satellite launch and reception. Therefore, the satellite system has high requirements for the reliability and safety of space-borne equipment. The remainder particle are metal and non-metal particles inside the space-borne equipment that affect the normal operation of the space-borne equipment. When the space-borne equipment is in a weightless state, the remainder particle will produce irregular movement accordingly cause huge safety hazards to the space-borne equipment. Particle impact noise detection (PIND) by way of vibrating the space-borne equipment cause remainder particle in the space-borne equipment to collide with the inner wall of the space-borne equipment. Then, the acoustic emission sensor is used to receive the sound generated by the vibration of the remainder particles. We can analyze the received sound signal to determine whether the space-borne equipment contains remainder particle. However, how to avoid the interference of environmental noise has always been a thorny issue in the process of using PIND to detect remainder particle. In the process of detecting noise, there may be environmental noise that will inevitably affect the detection of remainder particle. In order to filter out the environmental noise, we recorded mixed audio of the remainder particle. Then the ICA algorithm is used to separate the remainder particle signal. Through many experiments, we learn that the recognition rate of this judgment method reaches 100%.

关键词： Vibrations Satellites Working environment noise Metals Transforms Interference Robot sensing systems

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：