检索结果-内蒙古大学图书馆

4th International Conference on industrial Artificial Intelligence, IAI 2022

作者： Song, Pengyu Zhao, Chunhui Huang, Biao Ding, Jinliang College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China University of Alberta Department of Chemical and Materials Engineering EdmontonABT6G 2G6 Canada Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China

ISBN: (数字)9781665451208

ISBN: (纸本)9781665451208

Root cause diagnosis (RCD) is an important technique for maintaining the safe operation of industrial processes. Traditional RCD methods usually require stationarity assumptions. However, the process inevitably shows nonstationarity due to factors such as switching of operating conditions. Although there have been some previous studies trying to overcome the challenge of nonstationarity, these methods fail to guarantee the significance of the extracted causalities and lead to redundant relationships. To address the above issues, a sparse causal analysis model with time-varying parameters is extracted in this study. First, we propose an end-to-end information fusion and prediction task to characterize predictive relationships between variables and avoid repeated modeling. Second, we design time-varying parameters for the information fusion mechanism to cope with nonstationarity and automatically identify significant causality through sparse parameter updates. We design an update strategy that constrains the gradient information to guarantee sparsity. Finally, a causal metric is constructed for the time-varying predictive relationship to comprehensively obtain the overall causal relationship, which further guarantees causal significance. The validity of the proposed method is illustrated through a real industrial example collected from a thermal power plant. © 2022 IEEE.

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

Microstructure and properties evolution of plasma sprayed Al_(2)O_(3)-Y_(2)O_(3) composite coatings during high temperature and thermal shock treatment

引用

Journal of Rare Earths 2021年第6期39卷 718-727,I0004页

作者： Xingyu Wang Xiaolong Wang Xiaowen Sun Yong Yang Chen Zhang Yuduo Ma Yuhang Cui Yanchun Dong Dianran Yan You Wang Key Lab.for New Type of Functional Materials in Hebei Province State Key Laboratory of Reliability and Intelligence of Electrical EquipmentTianjin Key Laboratory of Materials Laminating Fabrication and Interface Control TechnologySchool of Materials Science and EngineeringHebei University of TechnologyTianjin 300132China Department of Materials Science Harbin Institute of TechnologyHarbin 150001China

Al_(2)O_(3)-Y_(2)O_(3) composite powder with TiO_(2) additive was plasma sprayed to prepare Al_(2)O_(3)-Y_(2)O_(3) composite *** micro structure and properties evolution of the Al_(2)O_(3)-Y_(2)O_(3) coatings during high temperature and thermal shock resistance were *** results show that the micro structure of the Al_(2)O_(3)-Y_(2)O_(3)-TiO_(2) coating is more uniform than that of the Al_(2)O_(3)-Y_(2)O_(3) ***,amorphous phase is formed in the two *** Al_(2)O_(3)-Y_(2)O_(3)(-TiO_(2)) coatings were heat treated for 2 h at temperatures of 800,1000 and 1200℃,*** is found that the microstructure and properties of the two coatings have no obvious change at 800℃.Some of the amorphous phase is crystallized at1000℃,and meanwhile Y_(2)O_(3) and Al_(2)O_(3) react to form YAG phase and YAM *** 1200℃,all of the amorphous phases are *** heat treatment,the micro hardness of the two coatings is *** thermal shock resistance of the Al_(2)O_(3)-Y_(2)O_(3) system coatings can be improved by using TC4 titanium alloy as substrate and with NiCrAlY bonding ***,the Al_(2)O_(3)-Y_(2)O_(3)-TiO_(2) coating exhibits better thermal shock resistance due to the addition of TiO_(2).

关键词： Al_(2)O_(3)-Y_(2)O_(3)coating TiO_(2) Plasma spraying Thermal shock resistance Microstructure evolution

来源：评论

学校读者我要写书评

暂无评论

Multi-source Domain Generalization for CSI-based Human Activity Recognition

引用

IEEE Transactions on Mobile Computing 2025年

作者： Fan, Tianqi Qiu, Sen Gong, Wei Fang, Yuguang Beijing Institute of Technology School of Medical Technology Beijing100000 China Dalian University of Technology Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education School of Control Science and Engineering Dalian116024 China University of Science and Technology of China Hefei230026 China City University of Hong Kong Department of Computer Science Hong Kong

Domain generalization remains a key challenge in human activity recognition based on channel state information (CSI). Different domains correspond to distinct data distributions, deviating from the typical assumption of independent and identically distributed (i.i.d.) data, which leads to significant performance degradation when models are applied to unseen domains. To address this issue, we propose a novel domain generalization model that integrates meta-learning initialization and an adaptive channel grouping attention mechanism. First, a meta-learning strategy is employed to acquire well-initialized parameters from multiple source domain tasks, enabling the model to implicitly enhance its cross-domain generalization ability. Second, an adaptive grouping attention mechanism is designed in the feature extraction stage to effectively capture the sensitivity differences of different subcarriers to human activities. Meanwhile, a random masking training mechanism is introduced to simulate real-world domain variations and improve model robustness. In addition, a domain adversarial training framework based on the gradient reversal layer (GRL) is adopted to mitigate domain-specific feature dependency, further enhancing the model's generalization capability. We evaluate our proposed method on both a self-collected dataset, which includes human activity data from nine volunteers across six different environments, and a public CSI dataset. The experimental results demonstrate that our method significantly outperforms existing approaches in domain generalization performance, verifying its effectiveness and practical applicability. © 2002-2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Ultrafast multi-target control of tightly focused light fields

引用

Opto-Electronic Advances 2022年第3期5卷 76-87页

作者： Yanxiang Zhang Xiaofei Liu Han Lin Dan Wang Ensi Cao Shaoding Liu Zhongquan Nie Baohua Jia Key Lab of Advanced Transducers and Intelligent Control System Ministry of Education and Shanxi ProvinceCollege of Physics and OptoelectronicsTaiyuan University of TechnologyTaiyuan 030024China Department of Physics Harbin Institute of TechnologyHarbin 150001China Centre of Translational Atomaterials(CTAM) Faculty of ScienceEngineering and TechnologySwinburne University of TechnologyHawthornVIC 3122Australia

The control of ultrafast optical field is of great interest in developing ultrafast optics as well as the investigation on vari-ous light-matter interactions with ultrashort ***,conventional spatial encoding approaches have only lim-ited steerable targets usually neglecting the temporal effect,thus hindering their broad *** we present a new concept for realizing ultrafast modulation of multi-target focal fields based on the facile combination of time-depend-ent vectorial diffraction theory with fast Fourier *** is achieved by focusing femtosecond pulsed light carrying vectorial-vortex by a single objective lens under tight focusing *** is uncovered that the ultrafast temporal de-gree of freedom within a configurable temporal duration(~400 fs)plays a pivotal role in determining the rich and exotic features of the focused optical field at one time,namely,bright-dark alternation,periodic rotation,and longitudinal/trans-verse polarization *** underlying control mechanisms have been *** being of academic in-terest in diverse ultrafast spectral regimes,these peculiar behaviors of the space-time evolutionary beams may underpin prolific ultrafast-related applications such as multifunctional integrated optical chip,high-efficiency laser trapping,micro-structure rotation,super-resolution optical microscopy,precise optical measurement,and liveness tracking.

关键词： ultrafast optical field vectorial diffraction theory fast Fourier transform vectorial vortex beam space-time shaping

来源：评论

学校读者我要写书评

暂无评论

Deep Learning based Defect Detection Algorithm for Solar Panels 5

Deep Learning based Defect Detection Algorithm for Solar Pan...

引用

5th World Robot Conference Symposium on Advanced Robotics and Automation, WRC SARA 2023

作者： Li, Jiaqi Li, Hongxu Wu, Yifan Zhou, Hailiang Manfredi, Luigi Li, Peng Zhang, Hong Hebei Province Yanshan University Department of Key Lab of Industrial Computer Control Engineering Qinhuangdao066004 China University of Alberta Department of Computing Science EdmontonABT6G 2R3 Canada Hebei Baoding Jiasheng Photovoltaic Technology Co. Ltd. China United Kingdom Southern University of Science and Technology Department of Electronic and Electrical Engineering Shenzhen China

ISBN: (纸本)9798350307320

Defect detection of solar panels plays an essential role in guaranteeing product quality within automated production lines. However, traditional manual inspection of solar panel defects suffers from low efficiency. This paper proposes an enhanced YOLOv5 algorithm (EL-YOLOv5) fused with the CBAM hybrid attention module to ensure product quality. The algorithm focuses on detecting five common types of defects that frequently appear on photovoltaic production lines, namely hidden cracks, scratches, broken grids, black spots, and short circuits. This study utilizes publicly available solar panel datasets, as well as datasets collected from actual photovoltaic production lines. These datasets are annotated accordingly and used to train the proposed algorithm. The experimental results demonstrate that the proposed algorithm achieves good performance on both the public and actual solar panel defect datasets. Particularly in actual datasets, where defect features are often less apparent and defects are smaller in size, the proposed algorithm can still detect even minor black spots. © 2023 IEEE.

关键词： Solar panels

来源：评论

学校读者我要写书评

暂无评论

High-Porosity, Layered Iridium Oxide as an Efficient, Durable Anode Catalyst for Water Splitting

引用

CCS Chemistry 2025年第1期7卷 216-228页

作者： Zhoubing Xie Xiao Liang Zhenye Kang Yongcun Zou Xiyang Wang Yimin A.Wu Graham King Qi Liu Yalan Huang Xiao Zhao Hui Chen Xiaoxin Zou State Key Laboratory of Inorganic Synthesis and Preparative Chemistry College of ChemistryJilin UniversityChangchun 130012 State Key Laboratory of Marine Resource Utilization in South China Sea Hainan Provincial Key Lab of Fine ChemistrySchool of Chemical Engineering and TechnologyHainan UniversityHaikou 570228 Department of Mechanical and Mechatronics Engineering Waterloo Institute for NanotechnologyUniversity of WaterlooWaterlooOntario N2L 3G1 Canadian Light Source Saskatoon SK S7N 2V3 Department of Physics City University of Hong KongHong Kong 999077 School of Materials Science and Engineering Key Laboratory of Automobile Materials of MOEState Key Laboratory of Automotive Simulation and ControlElectron Microscopy CenterJilin UniversityChangchun 130012

Lowering iridium(Ir)loading without sacrificing activity and durability is critical to the future development of proton exchange membrane water electrolyzer(PEMWE).Here,we present the synthesis of iridate-derived,layered iridium oxide microparticles(dubbed p-L-IrO_(2))with a high open porosity of approximately 74%and their structural advantages for the fabrication of efficient,durable,low-Ir-loading anode catalytic layer in *** p-L-IrO_(2) material is synthesized by an easily scalable route involving acid treatment of alkali metal salt-templated iridates that form in mixed alkali metal nitrateshydroxides at low *** combination of high-porosity morphology and layered structure in the material preferentially exposes a high density of hydroxylated edge sites,which are catalytically active and stable to achieve the oxygen evolution reaction via a structurally hydroxyl group-participated adsorbate evolution *** material is further demonstrated to enable the fabrication of low-Ir-loading anode catalytic layers in PEMWE,which can afford excellent catalytic performance(2.7 A cm^(−2)@1.9 V@80℃;membrane:Nafion^(TM)N115)due to the simultaneous reduction of activation and mass transport losses and retention of catalytic activity for 2300 h at 1.0 A cm^(−2) current density.

关键词： electrocatalysis water splitting iridium porous materials PEM electrolyzer

来源：评论

学校读者我要写书评

暂无评论

Predicting the Risk of Arterial Stiffness in Coal Miners Based on Different Machine Learning Models

引用

Biomedical and Environmental sciences 2024年第1期37卷 108-111页

作者： CHEN Qian Wei HUANG Xue Zan DING Yu ZHU Feng Ren WANG Jia ZOU Yuan Jie DU Yuan Zhen ZHANG Ya Jun HUI Zi Wen ZHU Feng Lin MU Min The Project was supported by Open Research Grant of Joint National-Local Engineering Research Centre for Safe and Precise Coal Mining Anhui University of Science and TechnologyHefei 232001AnhuiChina School of Public Health Anhui University of Science and TechnologyHefei 232001AnhuiChina Key Laboratory of Industrial Dust Prevention and Control Occupational Safety and HealthMinistry of EducationAnhui University of Science and TechnologyHefei 232001AnhuiChina Anhui Institute of Occupational Safety and Health Anhui University of Science and TechnologyHefei 232001AnhuiChina Joint Research Center of Occupational Medicine and Health Institute of Grand HealthHefei Comprehensive National Science CenterAnhui University of Science and TechnologyHefei 232001AnhuiChina Department of Occupational&Environmental Health School of Public HealthTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430030HubeiChina Key Laboratory of Environment and Health Ministry of Education&Ministry of Environmental Protectionand State Key Laboratory of Environmental Health(Incubating)School of Public HealthTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430030HubeiChina

Coal is one of the world’s main energy resources,accounting for approximately 68%of China’s current total power ***,several studies have demonstrated that dust,exhaust fumes,and other harmful factors in coal mines increase the risk of cardiovascular disease(CVD)among miners^([1]).Arterial stiffness(AS)is an independent risk factor of CVD,and epidemiological studies have shown that AS plays a vital role in assessing the risk of CVD^([2]).

关键词： Arterial cardiovascular assessing

来源：评论

学校读者我要写书评

暂无评论

Evaluation of laboratory and environmental exposure systems for protein modification upon gas pollutants and environmental factors

引用

Journal of Environmental sciences 2024年第9期143卷 213-223页

作者： Zhiwei Pan ShiyiWu Qiaoze Zhu Fobang Liu Yongjian Liang Chenglei Pei Haoyu Jiang Yingyi Zhang Senchao Lai The Key Lab of Pollution Control and Ecosystem Restoration in Industry Clusters Ministry of EducationSchool of Environment and EnergySouth China University of TechnologyGuangzhou 510006China Department of Environmental Science and Engineering Xi’an Jiaotong UniversityXi’an 710049China Guangzhou Sub-branch of Guangdong Ecological and Environmental Monitoring Center Guangzhou 510006China State Key Laboratory of Organic Geochemistry Guangdong Key Laboratory of Environmental Protection and Resources Utilizationand Joint Laboratory of the Guangdong-Hong Kong-Macao Greater Bay Area for the EnvironmentGuangzhou Institute of GeochemistryChinese Academy of SciencesGuangzhou 510640China School of Marine Sciences Sun Yat-sen UniversityZhuhai 519082China

Chemical modifications of proteins induced by ambient ozone(O_(3))and nitrogen oxides(NOx)are of public health concerns due to their potential to trigger respiratory *** laboratory and environmental exposure systems have been widely used to investigate their relevant mechanism in the *** bovine serum albumin(BSA)as a model protein,we evaluated the two systems and aimed to reduce the uncertainties of both the reactants and products in the corresponding kinetic *** the laboratory simulation system,the generated gaseous pollutants showed negligible *** layers of BSA were coated on the flow tube with protein extraction recovery of 87.4%.For environmental exposure experiment,quartz fiber filter was selected as the upper filter with low gaseous O_(3)(8.0%)and NO_(2)(1.7%)losses,and cellulose acetate filter was appropriate for the lower filter with protein extraction efficiency of 95.2%.The protein degradation process was observed without the exposure to atmospheric oxidants and contributed to the loss of protein monomer mass fractions,while environmental factors(e.g.,molecular oxygen and ultraviolet)may cause greater protein monomer *** on the evaluation,the study exemplarily applied the two systems to protein modification and both showed that O_(3) promotes the protein oligomerization and nitration,while increased temperature can accelerate the oligomerization and increased relative humidity can inhibit the nitration in the environmental exposure *** developed laboratory and environmental systems are suitable for studying protein modifications formed under different atmospheric conditions.A combination of the two will further reveal the actual mechanism of protein modifications.

关键词： Protein modification laboratory simulation Environmental exposure Oligomerization Nitration

来源：评论

学校读者我要写书评

暂无评论

Reliable 2−∞ state estimation for delayed neural networks under weighted try-one-discard protocol

引用

Neurocomputing 2025年 635卷

作者： Luo, Yuqiang Guo, Siyu Zhao, Di Lin, Hong Informatization Office University of Shanghai for Science and Technology Shanghai200093 China Shanghai Key Lab of Modern Optical System Department of Control Science and Engineering University of Shanghai for Science and Technology Shanghai200093 China Department of Control Science and Engineering University of Shanghai for Science and Technology Shanghai200093 China Business School University of Shanghai for Science and Technology Shanghai200093 China Institute of Intelligence Science and Engineering Shenzhen Polytechnic University Shenzhen518055 China

In this paper, the problem of reliable 2-∞ state estimation is addressed for discrete-time artificial neural networks with switched time-delays under weighted try-once-discard (WTOD) protocol. To mitigate data congestion and transmission burdens, the WTOD protocol is implemented in the transmission channels to optimize data communication, where the transmission priority is dynamically determined based on mission importance. A Bernoulli-distributed stochastic variable with known statistical properties is introduced to model the switching behavior between the presence and absence of time-delays and a failure matrix is constructed to characterize potential failures affecting the received measurement data. The primary objective of this paper is to develop a state estimator that effectively performs the desired estimation task by thoroughly accounting for the combined effects of switched time-delays and the WTOD protocol. Specifically, by utilizing Lyapunov theory and matrix inequality techniques, the estimator parameters are meticulously derived to ensure exponentially mean-square stability and 2-∞ performance. Finally, the efficacy and validity of the proposed algorithm are demonstrated through an illustrative example. © 2025 Elsevier B.V.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Indirect effects among biodiversity loss of mutualistic ecosystems

引用

National science Open 2022年第2期1卷 8-18页

作者： Guangwei Wang Xueming Liu Guanrong Chen Hai-Tao Zhang School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent ControlHuazhong University of Science and TechnologyWuhan 430074China State Key Lab of Digital Manufacturing Equipment and Technology Huazhong University of Science and TechnologyWuhan 430074China Department of Electrical Engineering City University of Hong KongHong KongChina

Drastic reduction in biodiversity has been a severe threat to ecosystems,which is exacerbated when losing few species leads to disastrous and even irreparable ***,revealing the mechanism underlying biodiversity loss is of uttermost *** this study,we show that abundant indirect interactions among mutualistic ecosystems are critical in determining species’*** topological and ecological characteristics,we propose an indicator derived from a dynamic model to identify keystone species and quantify their influence,which outperforms widely-used indicators like degree in realistic and simulated ***,we demonstrate that networks with high modularity,heterogeneity,biodiversity,and less intimate interactions tend to have larger indirect effects,which are more amenable in predicting decline of biodiversity with the proposed *** findings shed some light onto the influence of apposite biodiversities,paving the way from complex network theory to ecosystem protection and restoration.

关键词： biodiversity indirect effect complex network mutualism

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：