检索结果-内蒙古大学图书馆

Optimizing deep learning-driven computer vision for civil infrastructure defect Identification: Challenges and strategies

引用

engineering Applications of Artificial Intelligence 2025年 158卷

作者： Ronghua Fu Zhimeng Huang Maosen Cao Drahomír Novák Chunhui Xie Jinwen Huang College of Mechanics and Engineering Science Hohai University Nanjing China National Engineering Research Center of Visual Technology School of Computer Science Peking University Beijing China Institute of Structural Dynamics and Control Hohai University Nanjing China Jiangxi Province Key Laboratory of Environmental Geotechnical Engineering and Hazards Control Jiangxi University of Science and Technology Ganzhou China Institute of Structural Mechanics Faculty of Civil Engineering Brno University of Technology Brno Czech Republic

With advancements in Internet of Things (IoT) technologies and deep learning, Structural Health Monitoring (SHM) is progressing towards long-distance and intelligent applications. To promote the widespread adoption of deep learning in vision-based SHM, this survey compiles optimization strategies derived from deep learning models specifically designed for defect identification in civil infrastructure—an area that has not been comprehensively explored. First, a concise overview of fundamental deep learning models for vision-based defect identification is provided. Next, optimization methods are categorized into three main groups, each addressing a distinct challenge encountered in practical vision-based SHM: optimizing considering defect-specific characteristics, lightweight design for real-time identification, and enhance robustness under complex environmental conditions. These methods are further classified systematically based on their similar features. This survey offers researchers a deeper understanding of the challenges in vision-based defect identification and assists them in selecting appropriate optimization techniques to address these challenges. Ultimately, it aims to enhance the effective deployment of deep learning models in vision-based SHM by improving accuracy, enabling real-time operation, and facilitating automated defect identification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research and practice of overpressure protection system for EPR primary hydrostatic test

Research and practice of overpressure protection system for ...

引用

第三十九届中国控制会议

作者： Xiaoning Yuan Kejing Zhou Xiangqian Yan Jun Liang State Key Laboratory of Nuclear Power Safety Monitoring Technology and Equipment China Nuclear Power Engineering Co. Ltd Daya Bay Nuclear Power Operations And Management Co. Ltd State Key Lab of Industrial Control Technology College of Control Science and Engineering Zhejiang University

According to the requirements of design and construction rules for mechanical components of pressurized water reactor nuclear islands, the primary hydrostatic test must be carried out before and after the operation of nuclear power plant. The overpressure protection system is used to prevent the accidental overpressure of the primary circuit during the hydrostatic test, and to alleviate the serious consequences of overpressure on the involved test equipment. The system design and equipment selection for the primary circuit of the third generation nuclear power plants are much different from that of the second generation ones. In addition, the construction of the third generation nuclear power plants is too late to have the reference experience. Based on the control characteristics of the primary process system in European pressurized water reactor and the deficiency of the overpressure protection system in china pressurized water reactor, the research work is conducted from the hereafter aspects, the pressure control strategy of the primary hydrostatic test, scheme design of the overpressure protection system, commissioning and site application. And it is also applied in the primary hydrostatic test of a nuclear power plant. The practical results show that the implementation principle of the overpressure protection system is correct, the analysis of risks and various countermeasures is appropriate, and the implementation scheme is feasible. The research work and practice can provide some reference for the subsequent project construction.

关键词： Hydrostatic test overpressure protection system European pressurized water reactor primary circuit nuclear power plant

来源：评论

学校读者我要写书评

暂无评论

Insight into the critical factors determining the particle number concentrations during summer at a megacity in China

引用

Journal of Environmental sciences 2019年第1期31卷 169-180页

作者： Baoshuang Liu Xiaohui Bi Jiaying Zhang Jie Yuan Zhimei Xiao Qili Dai Yinchang Feng Yufen Zhang State Environmental Protection Key Laboratory of Urban Ambient Air Particulate Matter Pollution Prevention and Control & Center for Urban Transport Emission Research College of Environmental Science and EngineeringNankai University Tianjin Environmental Monitoring Center

To identify the critical factors impacting the number concentration of particles with the aerodynamic diameters less than 2.5 μm(PNC_(2.5)), the continuous measurement of PNC_(2.5),chemical components in PM_(2.5), gaseous pollutants and meteorological conditions were conducted at an urban site in Tianjin in June 2015. Results indicated that the average PNC_(2.5) was 2839 ± 2430 d N/dlog Dp 1/cm^3 during the campaign. Compared to other meteorological parameters, the relative humidity(RH) had the strongest relationship with PNC_(2.5), with a Pearson's correlation coefficient of 0.53, and RH larger than 30% influenced strongly PNC_(2.5).The important influence of secondary reactions on PNC_(2.5) was inferred due to higher correlation coefficients between PNC_(2.5) and SO_4^(2-), NO_3^-, NH_4^+(r = 0.78–0.89; p < 0.01) and between PNC_(2.5) and ratios that represent the conversion of nitrogen and sulfur oxides to particulate matter(r = 0.42–0.49; p < 0.01). Under specific RH conditions, there were even stronger correlations between PNC_(2.5) and NO_3^-, SO_4^(2-), NH_4^+, while those between PNC_(2.5) and EC, OC were relatively weak, especially when RH exceeded 50%. Principal component analysis(PCA) and Pearson's correlation analysis indicated that secondary sources, vehicle emission and coal combustion might be major contributors to PNC_(2.5). Backward trajectory and potential source contribution function(PSCF) analysis suggested that the transport of air masses originated from these regions around Tianjin(Liaoning, Hebei, Shandong and Jiangsu) influenced critically PNC_(2.5). The north of Jiangsu, the west of Shandong, and the east of Hebei were distinguished as major potential source-areas of PNC_(2.5) by PSCF model.

关键词： Particle number concentration Correlation analysis Emission sources PSCF

来源：评论

学校读者我要写书评

暂无评论

Multi-hop reasoning over sparse knowledge graphs with deep reinforcement learning

引用

Expert Systems with Applications 2025年 290卷

作者： Liu, Yiyang Fu, Lejun Fu, Yukai Wu, Tianxing Bai, Hongfei State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China College of Information Engineering Shenyang University of Chemical Technology Shenyang110142 China School of Computer Science and Engineering Southeast University Nanjing211189 China

In recent years, knowledge reasoning has demonstrated substantial progress in inferring missing information, effectively alleviating the limitations caused by the incompleteness of knowledge graphs (KGs). Dealing with entities that have sufficient paths between them, multi-hop reasoning methods have achieved notable success and demonstrated interpretability, but they still exhibit deficiencies when dealing with sparse KGs. To overcome the insufficiency of edges in sparse KGs and the absence of effective guidance in multi-hop reasoning methods, a hybrid multi-hop collaborative Multi-Agent Sparse Knowledge Graph Reasoning model (MASKGR) is proposed. Attention-based dynamic completion (ADC) and variable rule guidance(VRG) are used to enhance the reasoning capability of deep reinforcement learning (RL) in sparse KGs. ADC focuses on high-value relations based on attention weights and combines embedding-based methods to predict the tail entities of these relations, expanding the original action space and improving the exploration capability of agents. Moreover, VRG greatly improves the ability of MASKGR to use rule-guided agent learning by utilizing the variable rule ratio and the variable loss reshaping. ADC can be applied to both single-agent and multi-agent in other models, while VRG is specifically designed for multi-agent. Comprehensive experiments have been conducted on four datasets: FB15K-237-10 %, FB15K-237-50 %, NELL23K, and WD-singer. Specifically, MASKGR achieves relative improvements of 1.3 % in Mean Reciprocal Rank (MRR) and 1.1 % in the proportion of correct tail entity rankings in the top 3 (Hit@3) on the FB15K-237-10 %, 2.4 % in MRR and 1.3 % in Hit@3 on the NELL23K, and 2.7 % in MRR and 3.6 % in Hit@3 on the WD-singer. The results indicate that MASKGR outperforms state-of-the-art multi-hop reasoning models based on reinforcement learning. © 2025

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Functional characterization of ampd1 and its SNPs in the muscle IMP synthesis of hybrid bream (Megalobrama amblycephala ♀ × Culter alburnus ♂)

引用

Aquaculture 2025年 609卷

作者： Xu, Zhehua Xiao, Qinqin Zhang, Mingyu He, Yimiao Zheng, Qianting Zhao, Junchi Zuo, Anli Tang, Jianzhou Zhou, Yonghua Cao, Shenping Qu, Fufa Liu, Zhen Hunan Provincial Key Laboratory of Nutrition and Quality Control of Aquatic Animals Department of Biological and Chemical Engineering Changsha University Changsha 410022 China State Key Laboratory of Developmental Biology of Freshwater Fish College of Life Science College of Life Sciences Hunan Normal University Changsha 410081 China

Adenosine monophosphate deaminase 1 (AMPD1) plays a key role in the formation of inosine monophosphate (IMP), which is an important umami substance in fish muscle. The BBTB is a new type of hybrid bream derived from two rounds of backcrossing within an established hybrid lineage resulting from the crossing of blunt snout bream (Megalobrama amblycephala, BSB, ♀) × topmouth culter (Culter alburnus, TC, ♂). In this study, the role of ampd1 in IMP synthesis was first investigated in muscle cells of the BBTB. The content of IMP and the expression of genes involved in the IMP salvage and metabolism pathway (aprt, hprt, impdh, and gmps) were inhibited after the knockdown of ampd1. The cDNA sequence of ampd1 was subsequently cloned from BBTB, and it contained a full open reading frame (ORF) of 2160 bp encoding 719 amino acids. The analysis of sequence identity and the phylogenetic tree revealed that BBTB is closely related to BSB. Tissue expression analysis revealed that the mRNA expression of ampd1 was highest in the muscle of BSB and BBTB. Sanger sequencing was employed for the identification of single nucleotide polymorphisms (SNPs) of ampd1 from BBTB and BSB, revealing four SNPs located in the 8th exon (g.9801 T > G), 16th exon (16,920 T > C), and 3’UTR (g.16947 T > C, g.16984 G > T). These SNPs are significantly associated with IMP content, with individuals of the homozygous genotype showing higher IMP content than those of the heterozygous genotype. Moreover, the proportion of homozygous genotypes in BBTB was significantly greater than that in BSB. Finally, three SNP loci (g.16920 T > C, g.16947 T > C and g.16984 G > T) exhibited strong pairwise linkage disequilibrium. These findings suggest a strong correlation between ampd1 polymorphisms and IMP content in BBTB and BSB, and the ampd1 gene could be used as a candidate marker for the genetic selection of BBTB with high IMP content. © 2024

关键词： ampd1 BBTB BSB Inosine monophosphate acid SNPs

来源：评论

学校读者我要写书评

暂无评论

Transmission Line Fault Detection and Classification Based on Sa-Mobilenetv3

SSRN

引用

SSRN 2022年

作者： Xi, Yanhui Zhang, Weijie Zhou, Feng Tang, Xin Li, Zewen Zeng, Xiangjun Zhang, Pinghua Hunan Province Higher Education Key Laboratory of Power System Safety Operation and Control Changsha University of Science and Technology Hunan Province Changsha410114 China School of Electronic Information and Electrical Engineering Changsha University Hunan Province Changsha410022 China Hunan College of Information Hunan Province Changsha410200 China

Accurate fault detection and classification help to analyze fault causes and quickly restore faulty phases. This paper presents a robust fault classification method based on SA-MobileNetV3 for transmission systems. Considering that the SE (Squeeze-and-Excitation) attention module cannot aggregate the spatial dimension information on the channel, SA (shuffle attention) module is introduced into MobileNetV3, which can effectively fuse the importance of pixels in different channels and in different locations at the same channel. Also, transforming the signals into two dimensional images based on CWT (continuous wavelet transform) makes the proposed method be similar to image recognition, which can mine high level fault features and classify the faults visually. To verify the effectiveness of the method, a 735kV transmission line model is built for data generation through Simulink. Various kinds of fault conditions and factors are considered to verify the adaptability and generalizability. Simulation results show that the method can quickly and accurately identify 11 types of faults, and the accuracy rate is as high as 99.90%. A comparison between the proposed method and other existing techniques shows the superiority of the proposed SA- MobileNetV3, and better anti-noise performance makes it more suitable for real fault signals taken on-site. © 2022, The Authors. All rights reserved.

关键词： Simulink

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Switching Optimal control Strategy for Aircraft Engine Acceleration Dynamics

引用

The International Journal of Intelligent control and Systems 2024年第4期29卷 154-163页

作者： Zelin Li Yan Shi Shuoshuo Liu Tao Sun Xudong Zhao Lijuan Liu Key Laboratory of Intelligent Control and Optimization for Industrial Equipment(Dalian University of Technology) Ministry of EducationDalian 116024China School of Control Science and Engineering Dalian University of TechnologyDalian 116024China Department of Automation Tsinghua UniversityBeijing 100084China School of Software Dalian Jiaotong UniversityDalian 116028China

The transient-state acceleration control of aircraft engines has consistently been a focal point in the field of aircraft engine control *** address the controller design problem of transient-state acceleration in aircraft engines based on switched linear systems,a data-driven optimization control algorithm is ***,the optimization control problem for the transient-state acceleration process of aircraft engines is mathematically ***,the Bellman optimal criterion in optimal control is utilized to derive the invariance of a value function at switching instants,providing an initial value for the optimization of the next *** optimization problem is then transformed into solving a Lyapunov equation using the principles of dynamic programming,and an iterative adaptive dynamic programming(ADP)algorithm is introduced to obtain optimal feedback control gains,which makes the solution of Lyapunov equation approach the optimal solution ***,simulation validation is conducted on a switched linear system for the transient-state acceleration of a specific aircraft *** effectiveness and superiority of the proposed algorithm are verified by comparing to traditional proportion integral differential(PID)control algorithms and active disturbance rejection control(ADRC).

关键词： Aircraft engine transient-state switched linear system data-driven approach adaptive dynamic programming optimal control

来源：评论

学校读者我要写书评

暂无评论

A novel fault diagnosis framework for harmonic reducer using transmission error signal

引用

Measurement 2025年 256卷

作者： Runjun Liu Guoyan Li Jingbin Zhang Yongming Zhang Jue Zhang Yiduo Mei Key Laboratory of Advanced Transducers and Intelligent Control System Ministry of Education College of Mechanical Engineering Taiyuan University of Technology Taiyuan 030024 China State Key Laboratory of Intelligent Mining Equipment Technology Shanxi TZ Intelligent Mining Equipment Technology Co.Ltd Taiyuan 030024 China Inspur Yunzhou Industrial Internet Co. Ltd Jinan City Shandong 250101 China

Transmission error (TE) has emerged as a reliable indicator for fault diagnosis. However, in harmonic reducers, the non-stationary nature of measured TE signals results in the coupling of fault information with various interference components, including manufacturing and assembly errors, thereby complicating fault feature identification. To address this issue, this paper first establishes a TE model that accounts for multiple error sources. Simulations of TE under fault conditions reveal that high-frequency components exhibit periodic peaks with distinct fault characteristics, rendering them effective as fault-sensitive features. Building upon the prior analysis, a comprehensive TE-based fault diagnosis framework for harmonic reducers is proposed, termed VMD-DRGAF-Swin Transformer. Initially, the VMD-DRGAF method is proposed for TE signal decomposition and fault feature fusion. This method extracts multi-modal fault-sensitive components and converts them into RGB images. Subsequently, the fused multi-modal images are input into a Swin Transformer-based diagnostic model for fault identification. Finally, an experimental TE signal dataset is collected to validate the diagnostic performance of the proposed method. The results demonstrate that the proposed method achieves higher diagnostic accuracy under various operating conditions, exhibiting strong generalization capabilities. Furthermore, ablation experiments confirm that the VMD-DRGAF method significantly enhances the fault recognition ability and robustness of the diagnostic model, outperforming traditional methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fixed-Time Cooperative control of Vehicles with Connectivity Preservation

引用

IEEE Transactions on Vehicular technology 2025年

作者： Guo, Ge Zhang, Qian Zhou, Zeng-Di Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China Northeastern University at Qinhuangdao School of Control Engineering Qinhuangdao066004 China Northeastern University College of Information Science and Engineering Shenyang110819 China

This article studies the lateral and longitudinal cooperative control problem of a collection of vehicles with limited communication capacity. A distributed two-layered control framework is established. Therein, the upper layer provides a pseudo velocity deviation command to achieve spacing error optimal consensus, incorporating a log-barrier penalty function to maintain communication connectivity. The lower layer contains a command-filtered tracking controller for the vehicle to follow the provided command in a predefined time. Together, they ensure the fixed-time stability of the vehicle group. Simulations are performed to validate the availability and feasibility of the methodology. © 1967-2012 IEEE.

关键词： Autonomous vehicles connectivity preservation cooperative control distributed control fixed-time

来源：评论

学校读者我要写书评

暂无评论

Milestones in Autonomous Driving and Intelligent Vehicles Part I: control, Computing System Design, Communication, HD Map, Testing, and Human Behaviors

arXiv

引用

arXiv 2023年

作者： Chen, Long Li, Yuchen Huang, Chao Xing, Yang Tian, Daxin Li, Li Hu, Zhongxu Teng, Siyu Lv, Chen Wang, Jinjun Cao, Dongpu Zheng, Nanning Wang, Fei-Yue The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Waytous Ltd. China BNU-HKBU United International College Zhuhai519087 China Hong Kong Baptist University Kowloon999077 Hong Kong The Department of Industrial and System Engineering Hong Kong Polytechnical University Hong Kong The School of Aerospace Transport and Manufacturing Cranfield University United Kingdom The School of Transportation Science and Engineering Beihang University China The Department of Automation Tsinghua University China The Department of Mechanical and Aerospace Engineering Nanyang Technological University Singapore The College of Artificial Intelligence Xi'an Jiaotong University China The School of Mechanical Engineering Tsinghua University China

Interest in autonomous driving (AD) and intelligent vehicles (IVs) is growing at a rapid pace due to the convenience, safety, and economic benefits. Although a number of surveys have reviewed research achievements in this field, they are still limited in specific tasks and lack systematic summaries and research directions in the future. Our work is divided into 3 independent articles and the first part is a Survey of Surveys (SoS) for total technologies of AD and IVs that involves the history, summarizes the milestones, and provides the perspectives, ethics, and future research directions. This is the second part (Part I for this technical survey) to review the development of control, computing system design, communication, High Definition map (HD map), testing, and human behaviors in IVs. In addition, the third part (Part II for this technical survey) is to review the perception and planning sections. The objective of this paper is to involve all the sections of AD, summarize the latest technical milestones, and guide abecedarians to quickly understand the development of AD and IVs. Combining the SoS and Part II, we anticipate that this work will bring novel and diverse insights to researchers and abecedarians, and serve as a bridge between past and future. Copyright © 2023, The Authors. All rights reserved.

关键词： Autonomous vehicles

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：