检索结果-内蒙古大学图书馆

26th International Conference on Industrial Technology, ICIT 2025

作者： Yi, Kang Liu, Xin Hu, Wenkai Li, Yupeng School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9798331521950

Accurately and promptly detecting the pipeline anomaly is crucial to the safe operation of pipeline systems, while a difficulty lies in that many existing methods require massive data for training models. However, pipelines are running under normal state for the most of the time, and labeled pipeline anomaly data is usually scarce. Among the commonly used sensors, vibration sensors are widely utilized in pipeline detection because of their advantages such as easy installation and high sensitivity. However, the vibration signal shows non-stationary characteristics when anomalies occur, and are contaminated by noises, making it difficult to represent the actual state with features extracted from either the time or frequency domain. Accordingly, this paper proposes a pipeline anomaly detection method based on the KPCA (kernel principal component analysis) and cosine distance prototypical network. First, features are extracted from original signals;then, the feature dimension is reduced by KPCA;last, the cosine distance is introduced to the prototypical network for anomaly detection. The effectiveness of the proposed method is demonstrated by case studies involving experimental data. © 2025 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Bandwidth enhancement and the flattening of a chaotic laser with a microring resonator

引用

Optics Express 2025年第9期33卷 19535-19545页

作者： Guo, Zhi-Yong Li, Jian-Cheng Qiao, Li-Jun Wei, Xiao-Jing Zhang, Ming-Jiang College of Physics and Optoelectronic Engineering Taiyuan University of Technology Taiyuan030024 China Key Laboratory of Advanced Transducers and Intelligent Control System Ministry of Education Taiyuan University of Technology Taiyuan030024 China Shanxi Key Laboratory of Precision Measurement Physics Taiyuan University of Technology Taiyuan030024 China

We propose and experimentally demonstrate what we believe to be a novel scheme for bandwidth enhancement and flattening of a chaotic laser with a microring resonator. By leveraging the multi-beam interference effect within the MRR, the multiple chaotic laser exhibited improved bandwidth and power spectrum flatness. With a feedback strength of 6 and a laser bias current of 11.8 mA, the chaotic laser with a power spectrum that extends to 22.65 GHz within -3 dB is experimentally achieved. Additionally, we investigated the impact of the different feedback strengths and bias currents on the bandwidth and flatness of the chaotic laser. Finally, we investigated the correlation between the two channels, which can produce single-channel chaotic lasers with correlations below 0.25 over a wide range. This method offers promising chaotic light sources for applications in chaotic distributed fiber optic sensing, secure communication, and chaotic LIDARs. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Group Formation control of Cyber-Physical Systems via Distributed Cloud Computing

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 341-350页

作者： Ren, Hongru Long, Yinren Li, Hongyi Huang, Tingwen Guangdong University of Technology School of Automation Guangdong-Hong Kong Joint Laboratory for Intelligent Decision and Cooperative Control Guangdong Provincial Key Laboratory for Intelligent Decision and Cooperative Control Guangzhou510006 China Southwest University College of Electronic and Information Engineering Chongqing400715 China Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen518055 China

This paper investigates the group formation control problem for cyber-physical systems (CPSs) with random communication constraints. The distributed cloud computing system is constructed to divide agents into groups and establish communication between agents. A data-driven predictive control strategy is proposed by combining networked predictive control and model-free adaptive control method. The desired group formation control performance can be achieved and the three-channel random communication constraints of CPSs are actively compensated. Thisstrategy does not require the system model and relies solely on the system's I/O data for adaptive learning. Further analyses concludes the conditions for simultaneous reach stability and group formation of the closed-loop CPSs using the data-driven predictive control strategy. The effectiveness of the proposed strategy is validated by simulation results. © 2023 IEEE.

关键词： Distributed cloud

来源：评论

学校读者我要写书评

暂无评论

Multi-Level Features Fusion for Zero-Shot Object Pose Estimation 26

Multi-Level Features Fusion for Zero-Shot Object Pose Estima...

引用

26th International Conference on Industrial Technology, ICIT 2025

作者： Huang, Nanxin Xu, Chi School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China

ISBN: (纸本)9798331521950

Driven by advancements in industrial production and artificial intelligence, the need for pose estimation of new ob-jects in areas like robotic manipulation and virtual reality is increasing. We introduce a zero-shot object pose estimation approach that identifies the poses of objects excluded from the training dataset, removing the requirement for re-modeling. The method is built around a multi-level features fusion framework de-signed to enhance generalization. First, a trainable feature extraction module filters and selects multi-level features extracted by the backbone network. Unlike traditional convolutional ker-nels, we incorporate a dynamic convolution kernel to enhance the feature extraction capability. Second, in the feature fusion module, we adopt a dynamic weight generation strategy to perform weighted fusion of multi-level features. This method enhances template matching by effectively describing similarities between unseen objects (those absent from the training set) and templates, leveraging robust and adaptive feature representations to narrow the gap with seen objects. Experimental results demonstrate that our approach achieves state-of-the-art performance on two popu-lar benchmark datasets, LineMod and LineMod-Occlusion, proves that our method has better generalization than previous models. © 2025 IEEE.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

Investigation on machining mechanism and surface integrity of Sip/Al composites with ultrasonic vibration-assisted epoxy coating cutting

引用

Journal of Manufacturing Processes 2025年 146卷 427-444页

作者： Chen, Dachuan Zheng, Zhengding Ding, Jixiang Zhang, Jianguo Chen, Xiao Xiao, Junfeng Xu, Jianfeng State Key Laboratory of Intelligent Manufacturing Equipment and Technology School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Wuhan430081 China Key Laboratory of Modern Manufacturing Quality Engineering in Hubei Province Hubei University of Technology Wuhan430068 China

Due to the significant mechanical differences between the plastic Al matrix and the brittle Si particles, the ultra-precision machining of Sip/Al composites is considered a major challenge. To overcome this challenge, this paper proposes a new cutting strategy, namely ultrasonic vibration-assisted epoxy coating cutting (UV-ECC). By analyzing the groove morphology, cutting force, chip morphology, residual stress, and surface roughness, the effect of UV-ECC on the machining mechanism and surface integrity of Sip/Al composites is investigated. Research results indicate that epoxy coating can provide compressive stress to the surface of Sip/Al composites, thereby suppressing the formation and propagation of cracks as well as the pull-out or rotation of particles. After the introduction of ultrasonic vibration, the vibrating tool can compensate for the shortcomings of the epoxy coating in terms of chip removal. Furthermore, the intermittent separation reduces the damage to both the Sip/Al composites and the epoxy coating. Finally, the space gap created by the elliptical trajectory allows the crack suppression effect of the epoxy coating to be seen as a significant improvement. Overall, compared to traditional cutting and epoxy coating cutting, UV-ECC offers significant advantages in enhancing surface integrity, reducing specific cutting force, and achieving a uniform residual stress distribution. Among them, the surface roughness decreased by 75.4 % and 59.0 %, respectively, and the specific cutting force decreased by 75.01 % and 64.89 %, respectively. The current research provides a promising cutting strategy for achieving efficient and low-damage machining of Sip/Al composites. © 2025 The Society of Manufacturing Engineers

关键词： Ultrasonic cutting

来源：评论

学校读者我要写书评

暂无评论

Designing high-Q Fano resonance structures for enhancing fluorescence in all-dielectric metasurfaces

引用

Optics Letters 2025年第9期50卷 2930-2933页

作者： He, Shuai Wang, Zhiyuan Han, Bin Li, Shan Yao, Zhenyu Guo, Yulong Chen, Zhihui Wang, Yang Key Lab of Advanced Transducers and Intelligent Control System Ministry of Education College of Physics and Optoelectronics Taiyuan University of Technology Taiyuan030024 China Key Laboratory of Chemical Biology and Molecular Engineering of Ministry of Education Institute of Biotechnology Shanxi University Taiyuan030006 China

Highly sensitive fluorescence detection technology is crucial for biological sensing, imaging, and photonic technologies. The fluorescence enhancement effect with the same enhancement factor at multi-wavelengths is important for highly sensitive detection. However, achieving multiwavelength fluorescence enhancement remains challenging. Here, we introduce an all-dielectric metasurface composed of symmetry-broken silicon nanocylinders integrated with graphene, which is designed to significantly enhance and dynamically modulate the fluorescence emission of a single quantum dot. By fine-tuning structural parameters and adjusting the graphene Fermi level, we achieve a tunable high-Q Fano resonance, leading to a nearly 4000-fold fluorescence enhancement. Structural parameter adjustments enable consistent fluorescence enhancement across different wavelengths. Furthermore, at specific wavelengths, fluorescence enhancement can be similarly adjusted. The proposed structure can greatly expand the design strategy of heterogeneous all-dielectric metasurfaces with the same enhancement factor at multi-wavelengths. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Efficient Facial Expression Recognition Network Based on Spot-Adaptive Knowledge Distillation 26

Efficient Facial Expression Recognition Network Based on Spo...

引用

26th International Conference on Industrial Technology, ICIT 2025

作者： Wen, Xin Liu, Zhen-Tao Chen, Dan School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education China

ISBN: (纸本)9798331521950

Facial expression recognition plays a key role in promoting the development of comprehensive intelligence and building friendly human-computer interaction. Due to the interference of feature noise in expression data, the lightweight facial expression recognition model with fewer parameters is difficult to learn more expression features through simple training, which limits the improvement of its recognition performance. An efficient facial expression recognition network based on Spot-adaptive Knowledge Distillation is proposed in this paper. Inspired by VoVNetV2, the network designed in this paper is lightweightly improved using Depthwise Separable Convolution and the parameter-free SimAM attention mechanism, reducing the number of parameters to 0.21 M. To further improve the recognition accuracy of the model, Spot-adaptive Knowledge Distillation is employed to improve the characterization ability of the model. The recognition accuracies of the student network designed in this paper on the KDEF and RAF-DB datasets are 93.05% and 81.17% respectively after spot-adaptive distillation. © 2025 IEEE.

关键词： Facial Expression Recognition Knowledge Distillation Lightweight Neural Network

来源：评论

学校读者我要写书评

暂无评论

Combine deep learning and Bayesian analysis to separate overlapping gravitational wave signals

引用

Science China(Physics,Mechanics & Astronomy) 2025年第5期68卷 205-219页

作者： Cunliang Ma Weiguang Zhou Zhoujian Cao Mingzhen Jia Jiangxi Provincial Key Laboratory of Multidimensional Intelligent Perception and Control Jiangxi University of Science and TechnologyGanzhou 341000China Institute of Applied Mathematics Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Fundamental Physics and Mathematical Sciences Hangzhou Institute for Advanced StudyUCASHangzhou 310024China

Future gravitational wave(GW)observatories,such as the Einstein Telescope,are anticipated to encounter overlapping GW signals,presenting considerable obstacles to GW data processing techniques,including signal identification and parameter *** this letter,we propose a scheme of combining deep learning and Bayesian analysis to disentangle overlapping GW *** deep learning part takes a data-driven approach that employs an encoder-separation-decoder framework which is powerful enough to extract the shape of the signal even when the GW signals completely *** Bayesian analysis part takes the matched filtering technique to extract the amplitude of the GW *** scheme can facilitate the utilization of existing GW detection and parameter estimation methods for future instances of overlapping *** methodology effectively reduces biases in parameter estimation when handling multiple intertwined ***,this marks the first known instance where deep learning has been successfully utilized to disentangle overlapping GW signals.

关键词： gravitational wave separation machine learning Einstein Telescope parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Techno-economic analysis of fuel cell trucks with different powertrain hybridization and hydrogen resources by 2040: case study of China

引用

International Journal of Hydrogen Energy 2025年 132卷 174-182页

作者： Nan, Long Xu, Feiyang Sui, Pang-Chieh Feng, Yanbiao Hao, Han Li, Shunxi Huang, Feng Hubei Key Laboratory of Advanced Technology for Automotive Components Hubei Collaborative Innovation Center for Automotive Components Technology and Hubei Research Center for New Energy & Intelligent Connected Vehicle School of Automotive Engineering Wuhan University of Technology Hubei 430070 China Institute for Integrated Energy Systems University of Victoria VictoriaBCV8W 2Y2 Canada School of Mechanical Engineering University of Science & Technology Beijing Beijing100083 China State Key Laboratory of Automotive Safety and Energy Tsinghua University Beijing100084 China

This study conducts a techno-economic analysis of fuel cell electric trucks with different hybridization factors (i.e., the power distribution ratio between batteries and fuel cells) by evaluating their life-cycle carbon dioxide (CO2) emissions and total cost of ownership (TCO) from 2020 to 2040. It integrates the energy consumption of trucks with varying hybridization factors under different driving cycles with China's hydrogen production, transportation models, and electric grid structure. Through this analysis, the TCO and emissions of individual trucks are examined across different scenarios. The study reveals that highly hybridized trucks offer advantages in both emissions reduction and cost savings across all hydrogen production and transport pathways. A 67% hybridization factor results in a 5%-9% reduction in emissions and a 34%-46% decrease in TCO compared to the lowest hybridization factor. The energy-saving and emission-reducing effects of highly hybridized fuel cell electric vehicles (FCEVs) also depend on the driving cycle, with optimal performance observed in the Urban Dynamometer Driving Schedule for Heavy-Duty Vehicles (UDDSHDV) cycle, while minimal advantages appear in the China Heavy-Duty Commercial Vehicle Test Cycle for Heavy Trucks (CHTC-HT) cycle. Furthermore, life-cycle emissions of trucks decrease gradually over time for all hydrogen production pathways, with the electrolysis of grid electricity showing the fastest decline. By 2040, trucks powered by hydrogen from grid electricity will have slightly lower emissions than those using coal, while green hydrogen remains the cleanest option. In conclusion, adopting fuel cell trucks with high hybridization factors, powered by green hydrogen, presents significant economic and environmental benefits for the future of transportation. © 2025 Hydrogen Energy Publications LLC

关键词： Commercial vehicles

来源：评论

学校读者我要写书评

暂无评论

NO_(2) gas sensor with high selectivity and fast response based on Pt-loaded nanoporous GaN

引用

International Journal of Minerals,Metallurgy and Materials 2025年第4期32卷 964-972页

作者： Dan Han Xiaoru Liu Donghui Li Jiexu Shi Yu Wang Yuxuan Wang Hongtao Wang Shengbo Sang Shanxi Key Laboratory of Micro/Nano Sensors&Artificial Intelligence Perception College of Integrated CircuitsTaiyuan University of TechnologyTaiyuan030024China Key Lab of Advanced Transducers and Intelligent Control System of the Ministry of Education Taiyuan University of TechnologyTaiyuan 030024China Shanxi Research Institute of 6D Artificial Intelligence Biomedical Science Taiyuan 030032China

In this work,we realized a room-temperature nitrogen dioxide(NO_(2))gas sensor based on a platinum(Pt)-loaded nanoporous gallium nitride(NP-GaN)sensing material using the thermal reduction method and coreduction with the catalysis of *** gas sensor gained excellent sensitivity to NO_(2) at a concentration range of 200 ppm to 100 ppb,benefiting from the loading of Pt nanoparticles,and exhibited a short response time(22 s)and recovery time(170 s)to 100 ppm of NO_(2) at room temperature with excellent selectivity to NO_(2) compared with other *** phenomenon was attributed to the spillover effect and the synergic electronic interaction with semiconductor materials of Pt,which not only provided more electrons for the adsorption of NO_(2) molecules but also occupied effective sites,causing poor sites for other *** low detection limit of Pt/NP-GaN was 100 ppb,and the gas sensor still had a fast response 70 d after ***,the gas-sensing mechanism of the gas sensor was further elaborated to determine the reason leading to its improved *** significant spillover impact and oxygen dissociation of Pt provided advantages to its synergic electronic interaction with semiconductor materials,leading to the improvement of the gas properties of gas sensors.

关键词： nanoporous gallium nitride platinum nitrogen dioxide gas sensor

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：