检索结果-内蒙古大学图书馆

Flame region segmentation of a coal-fired power plant boiler burner through YOLOv8-MAH model

Fuel 2025年 398卷

作者： Pu, Sixu Li, Jian Han, Zhezhe Zhu, Xiaoyu Xu, Chuanlong National Engineering Research Center of Power Generation Control and Safety School of Energy and Environment Southeast University Nanjing China School of Communication and Artificial Intelligence Nanjing Institute of Technology Nanjing China

Effective segmentation of flame regions in coal-fired power plant boiler burners is critical for enhancing combustion monitoring and operational safety. Traditional methods often suffers from the interference of complicated furnace environments, such as furnace background, adjacent burners and fly ash. This study introduces an advanced flame segmentation approach utilizing the YOLOv8 framework, improved by a multi-level augment head (MAH) and single-object tracking techniques to integrate shallow and deep feature information. Moreover, a convolutional block attention module (CBAM) is embedded in the backbone network to refine feature extraction, while the reparameterization and cross-stage feature reuse are applied in the neck network to bolster multi-scale feature fusion. Experimental results demonstrate that the improved model achieves a mean intersection over union (mIoU) of 82.6—an 8.8 increase over the original YOLOv8—while maintaining high computational efficiency with an inference time of 4.43 ms. Compared with other semantic segmentation models, the proposed model achieves superior accuracy and inference speed. Its performance is validated on a 660 MW opposed-fired boiler, where it can mitigate external disturbances and effectively segment the flame regions under varying load conditions. This method provides a reliable foundation for image-based flame detection systems, enabling real-time and precise monitoring of combustion conditions. © 2025 Elsevier Ltd

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Correction to: An advanced reinforcement learning control method for quadruped robots in typical urban terrains (International Journal of Machine Learning and Cybernetics, (2024), 10.1007/s13042-024-02478-9)

引用

International Journal of Machine Learning and Cybernetics 2025年 1-2页

作者： Yan, Chi Wang, Ning Gao, Hongbo Wang, Xinmiao Tang, Chao Zhou, Lin Li, Yuehua Wang, Yue School of Information Science and Technology University of Science and Technology of China No. 96 Jinzhai Road Anhui Hefei230026 China School of Information and Security Chongqing College of Mobile Communication No. 36 Dengying Avenue Qijiang District Sichuan Chongqing401520 China Institute of Advanced Technology University of Science and Technology of China No. 5089 Wangjiang West Road Anhui Hefei230088 China School of Electrical and Electronic Engineering Nanyang Technological University 50 Nanyang Avenue Nanyang639798 Singapore Zhejiang Lab Kechuang Avenue Zhongtai Sub-District Zhejiang Hangzhou311121 China College of Control Science and Engineering Zhejiang University Zhejiang Hangzhou310027 China

In this article, the affiliation details for Authors "Ning Wang2, Hongbo Gao1,3,4, Yuehua Li5, Yue Wang6" were interchanged and it is corrected now. Incorrect affiliation: 2Institute of Advanced technology, University of Science and technology of China, No. 5089 Wangjiang West Road, Hefei 230088, Anhui, China 3school of Electrical and Electronic engineering, Nanyang Technological University, 50 Nanyang Avenue, 639798 Nanyang, Singapore 4Zhejiang Lab, Kechuang Avenue, Zhongtai Sub-District, Hangzhou 311121, Zhejiang, China 5College of control Science and engineering, Zhejiang University, Hangzhou 310027, Zhejiang, China 6school of Information and Security, Chongqing College of Mobile communication, No. 36 Dengying Avenue, Qijiang District, Chongqing 401520, Sichuan, China Correct affiliation: 2school of Information and Security, Chongqing College of Mobile communication, No. 36 Dengying Avenue, Qijiang District, Chongqing 401520, Sichuan, China 3Institute of Advanced technology, University of Science and technology of China, No. 5089 Wangjiang West Road, Hefei 230088, Anhui, China 4school of Electrical and Electronic engineering, Nanyang Technological University, 50 Nanyang Avenue, 639798 Nanyang, Singapore 5Zhejiang Lab, Kechuang Avenue, Zhongtai Sub-District, Hangzhou 311121, Zhejiang, China 6College of control Science and engineering, Zhejiang University, Hangzhou 310027, Zhejiang, China The original article has been corrected. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Embodied Intelligence Empowering Customized Manufacturing: Architecture, Opportunities, and Challenges

引用

IEEE Access 2025年 13卷 92740-92755页

作者： Jinbiao Tan Jianhua Shi Ligang Wu Baotong Chen Hao Tang Chunhua Zhang Wujie Zhang Shiyong Wang Jiafu Wan School of Mechanical and Automotive Engineering South China University of Technology Guangzhou China School of Mechanical and Electrical Engineering Shanxi Datong University Datong China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan China Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan University of Science and Technology Wuhan China School of Information and Communication Engineering Hainan University Haikou China

With the continued advancement of Artificial Intelligence (AI) technology in Customized Manufacturing (CM), the current intelligence model, which separates ‘perception’ from ‘execution,’ lacks adaptability and generalizability. Embodied Intelligence (EI), an emerging technology emphasizing real-time environmental interaction and feedback, is expected to enable integrated intelligent manufacturing systems characterized by ‘perception-cognition-execution-feedback,’ enhancing the performance and intelligence of multifactor systems like the Internet of Manufacturing Things (IoMT), equipment management, and resource scheduling. However, current AI systems in CM remain isolated and lack methods for environmental interaction with multi-source perception and feedback, hindering the development of autonomous, evolving intelligent systems. To address the environmental interaction bottlenecks among diverse production elements in CM, this paper proposes a Circular Embodied Intelligence Manufacturing (CEIM) architecture aimed at enabling the fusion of heterogeneous production-element information. The objective is to enhance environmental perception and establish autonomous system evolution mechanisms, thereby optimizing production decision-making. By integrating sensor data and AI model outputs, and leveraging the advanced reasoning capabilities of large language models (LLMs), CEIM facilitates the semantic fusion of multiple production elements—including IoMT, intelligent devices, and manufacturing resources—to enable the deployment of EI applications in CM. The implementation of CEIM is illustrated and validated through a case study on a customized gift box packaging platform. Finally, this paper discusses the opportunities and challenges of applying EI in manufacturing and aims to provide insights into the future development of EI-oriented manufacturing systems.

关键词： Manufacturing Production Artificial intelligence Computer architecture Decision making Data models Collaboration Robot sensing systems Optimization Job shop scheduling

来源：评论

学校读者我要写书评

暂无评论

Design of Orthogonal Polyphase Codes for MIMO Radar Using an Enhanced Salp Swarm Algorithm 1

Design of Orthogonal Polyphase Codes for MIMO Radar Using an...

引用

1st International Conference on Intelligent Manufacturing and Cloud Computing, ICIMCC 2024

作者： Pang, Yu Zhao, Runhui Wen, Hong Wang, Yongfeng Feng, Xuewei Tang, Tao Zhao, Ziang Ma, Wendi School of Aeronautics and Astronautics University of Elec.Science and Tech. of China Chengdu611731 China Aircraft Swarm Intelligent Sensing and Cooperative Control Key Lab. of Sichuan Province UESTC 611731 China Intelligent IoT Communication Technology Engineering Research Center of Sichuan Province UESTC 611731 China

ISBN: (纸本)9781643685779

This paper presents the design of highly orthogonal waveforms focusing on minimizing autocorrelation sidelobes and cross-correlation peaks. An enhanced Salp Swarm Algorithm is proposed to improve global search capabilities through refined population initialization and leader position updates. The feasibility and benefits of this approach are demonstrated through practical implementation. © 2025 The Authors.

关键词： MIMO radar

来源：评论

学校读者我要写书评

暂无评论

Adaptive Differentially Private Robust Federated Learning Against Backdoor Attacks 1

Adaptive Differentially Private Robust Federated Learning Ag...

引用

1st International Conference on Intelligent Manufacturing and Cloud Computing, ICIMCC 2024

作者： Yao, Ruixiang Wen, Hong Hou, Wenjing Ma, Wendi Sun, Fan Zhao, Ziang School of Aeronautics and Astronautics University of Elec.Science and Tech. of China Chengdu611731 China Aircraft Swarm Intelligent Sensing and Cooperative Control Key Lab. of Sichuan Province UESTC 611731 China Intelligent IoT Communication Technology Engineering Research Center of Sichuan Province UESTC 611731 China

ISBN: (纸本)9781643685779

In federated learning systems, malicious attackers can manipulate training datasets by injecting backdoor triggers to achieve data poisoning. Addressing this vulnerability, this paper proposes a new defense method, the adaptive differential privacy stochastic gradient descent (ADP-SGD) algorithm, which increases the Euclidean distance between malicious and benign updates to enhance aggregation efficiency. Experiments were conducted on typical datasets, and the results show that combining ADP-SGD with the m-Krum aggregation algorithm can effectively defend against backdoor attacks in complex attack environments. While ensuring the accuracy of the main task, it significantly reduces the success rate of backdoor attacks, especially under the condition of unknown proportions of malicious participants, proving to be effective and robust. © 2025 The Authors.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic Charging and Path Planning for UAV-Powered Rechargeable WSNs Using Multi-Agent Deep Reinforcement Learning

引用

IEEE Transactions on Automation Science and engineering 2025年 22卷 15610-15626页

作者： Betalo, Mesfin Leranso Leng, Supeng Seid, Abegaz Mohammed Abishu, Hayla Nahom Erbad, Aiman Bai, Xiaoshan Shenzhen University College of Mechatronics and Control Engineering Shenzhen518060 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Hamad Bin Khalifa University Division of Information and Computing Technology College of Science and Engineering Doha Qatar Shenzhen University College of Mechatronics and Control Engineering National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China

Unmanned Aerial Vehicle (UAV)-powered 5G/6G networks integrated with rechargeable wireless sensor networks (RWSNs) offer promising solutions for extending system lifetime, collecting data, and providing computing services and power to sensor nodes (SNs). UAVs offer significant advantages, including exceptional mobility, cost-effective deployment, and the ability to be easily reprogrammed for a wide range of missions. However, the limited onboard power capacity of UAVs, coupled with the lack of dynamic and intelligent charging station (CS) management and inefficient path planning, can lead to SN failure in dynamic mobile environments. To address these challenges, we propose an energy-efficient laser-charged UAV (LCU)-enabled RWSN environment, wherein UAVs, powered by laser beams from ground-based stations, provide services, collect data, and transfer energy to SNs. We formulate a joint optimization problem involving power allocation, dynamic charging strategy (DCS), and path planning to minimize task completion time and sensor node death time. Given the NP-hard nature of the problem, we employ a stochastic game model based on a Markov decision process (MDP) for its solution. To solve this problem, we propose a deep reinforcement learning (DRL) based algorithm that enables real-time charging scheduling decisions while optimizing network performance. We introduce a multi-agent double deep Q-network (MA-DDQN) model to determine the optimal trajectories for all UAVs in large and complex environments. Simulation results demonstrate that the MA-DDQN approach outperforms state-of-the-art techniques, showing significant improvements in terms of average delay, energy consumption, and task completion time. © 2004-2012 IEEE.

关键词： Stochastic models

来源：评论

学校读者我要写书评

暂无评论

Graph Convolutional Networks with Visual Masking and Social Interaction Models for Pedestrian Trajectory Prediction

Graph Convolutional Networks with Visual Masking and Social ...

引用

Consumer Electronics and Computer engineering (ICCECE), 2021 IEEE International Conference on

作者： Guopei Zeng Luping Wang School of Electronics and Communication Engineering Sun Yat-sen University Shenzhen China Zhejiang Aerospace Runbo Measurement and Control Technology Co. Ltd Zhejiang China

ISBN: (数字)9798331533113

ISBN: (纸本)9798331533120

Pedestrian trajectory prediction is critical for autonomous driving, crowd analysis, and urban surveillance. To address insufficient interaction modeling in existing methods, we propose two enhancements. First, a field-of-view(FoV)-aware masking mechanism filters irrelevant interactions by dynamically adjusting to pedestrian distances and motion directions. Second, we introduce a more detailed modeling of the influence among pedestrians, replacing the traditional modeling based on reciprocal of distance. This model, integrated with FoV masks to construct sparse adjacency matrices for graph convolution. A temporal convolutional network then predicts trajectories as bivariate Gaussian distributions. Evaluations on ETH and UCY benchmarks demonstrate the effectiveness of our method.

关键词： Analytical models Visualization Pedestrians Filters Surveillance Predictive models Benchmark testing Vectors Trajectory Sparse matrices

来源：评论

学校读者我要写书评

暂无评论

VSQ: Enabling efficient and verifiable similarity queries in blockchain databases

引用

Expert Systems with Applications 2025年 285卷

作者： Yin, Bo Liu, Yihu Xu, Binyao School of Computer and Communication Engineering Changsha University of Science and Technology Changsha410114 China School of Control and Computer Engineering North China Electric Power University Beijing102206 China

Blockchain serves as the basis for secure and distributed applications like decentralized finance (DeFi). Light nodes can help reduce the storage and computation burden of full nodes in the blockchain by storing only block headers instead of full blocks. The resource constraint user runs a light node and sends the query request to the full node to find the answer. However, this approach raises security concerns, as query results from the full node may be altered or incomplete. In this paper, we explore verifiable similarity queries, commonly used in text mining, within the context of blockchain networks. The main challenge lies in designing an authenticated data structure (ADS) that enables efficient query processing and verification of query result soundness and completeness. Previous research on blockchain verifiable queries has focused on range queries, keyword queries, and existence queries, which are not applicable to verifiable similarity queries. Our proposed solutions include a baseline approach that uses the Merkle hash tree as the foundational ADS and adds leaf node pointers for query realization. Additionally, we introduce an enhanced solution Baseline+, which improves query efficiency and reduces storage overhead by leveraging minhash. Finally, we present a verifiable similarity query scheme (VSQ) based on the Merkle bucket tree, integrating minhash and locality-sensitive hashing to enhance query and verification efficiency. We conducted extensive experimental evaluation. The experimental results show that the query time and the verification object size of VSQ are reduced by two orders of magnitude compared to the Baseline approach. © 2025

关键词： Query languages

来源：评论

学校读者我要写书评

暂无评论

Cognitive Jammer Time Resource Scheduling With Imperfect Information Via Fuzzy Q-Learning

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年

作者： Gan, Linchuan Xiong, Kui Liao, Maosen Yu, Xianxiang Cui, Guolong University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Laboratory of Electromagnetic Space Cognition and Intelligent Control Technology Beijing100089 China UESTC Shenzhen Institute for Advanced Study Shenzhen518038 China

Effective strategy generation of the jammer with inaccurate or undetermined information for combating the radar system is a challenging problem and the relevant research is scarce in existing work. This paper aims at exploring this promising topic and proposing a transmitting time slots scheduling strategy generation method for the cognitive jammer with imperfect time-matching information based on fuzzy reinforcement learning. First, the interaction between the jammer and environment is modeled as a Markov decision process (MDP) with uncertain state and continuous action, in which the goal of the jammer in interaction is to maximize accumulated discount pulse transmitting time slot jamming probability. Then, the uncertain pulse repeat intervals (PRIs) of the radar signal is inferred using the fuzzy inference system (FIS), where the inferred reward is evaluated by the correntropy of the inferred radar PRI and the previously measured one, thus presenting the fuzzy Q-learning based time scheduling (TSFQL) algorithm. Finally, numerical simulations in typical scenarios are performed to illustrate the effectiveness and superiority of the TSFQL algorithm over conventional methods. © 1965-2011 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Enhanced Generalized Spatial Modulation for STAR-RIS-Aided Vehicular communication System

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Shang, Pingping Han, Xue Hou, Jia Li, Jun Wang, Shucheng Hubei University of Technology School of Electrical and Electronic Engineering Wuhan430068 China Hubei University of Technology Hubei Key Lab. for High-Efficiency Utiliz. of Solar Ener. and Oper. Control of Energy Storage System Wuhan430068 China Soochow University School of Electronic and Information Engineering Suzhou215000 China Guangzhou University School of Electronics and Communication Engineering Guangzhou510006 China Wuhan Maritime Communication Research Institute Wuhan430205 China

In this paper, a novel scheme is proposed by introducing the concept of generalized spatial modulation (GSM) and space-time block code (STBC) into simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) for vehicular communication system. To improve spectral efficiency and diversity gain of vehicular system, STAR-RIS array elements are categorized into reflective and transmissive blocks, establishing a mapping relationship with the index bits by using GSM. Subsequently, the modulated symbols are reflected or transmitted based on the predetermined allocation patterns of the blocks. Specifically, to enhance the reliability of signal reception, one of the most renowned STBC schemes, the Alamouti code, is employed at the STAR-RIS surface by receiving and detecting signals across two consecutive time slots. Furthermore, the new design of leveraging STAR-RIS as an access point (AP) is proposed, which plays the role of source in the communication scenario. The mathematical formulas and theoretical average bit error rate (BER) of the scheme are derived based on preceding analysis. According to simulation results, the suggested scheme can outperform conventional schemes in terms of BER performance. In addition, the proposed redesigned scheme further improves the BER performance with better channel conditions, exhibiting excellent performance advantages. © 1975-2011 IEEE.

关键词： Space-time block coding (STBC)

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：