检索结果-内蒙古大学图书馆

Design and fabrication of metal spherical conformal thin film multisensor for high-temperature environment

Chinese Journal of Aeronautics 2024年第11期37卷 535-547页

作者： Lida XU Xiong ZHOU Yong HUANG Yusen WANG Chenhe SHAO Yuelong LI Lingyun WANG Qingtao YANG Daoheng SUN Qinnan CHEN Discipline of Intelligent Instrument and Equipment Pen-Tung Sah Institute of Micro-Nano Science and TechnologyXiamen UniversityXiamen 361102China Fujian Micro/nano Manufacturing Engineering Technology Research Center Xiamen UniversityXiamen 361102China China Aerodynamics Research and Development Center Mianyang 621000China

Conformal thin-film sensors enable precise monitoring of the operating conditions of components in extreme ***,the development of these sensors encounters major challenges,especially in uniformly applying multiple film layers on complex metallic surfaces and accurately capturing diverse operational *** work reports a multi-sensor design and multi-layer additive manufacturing process targeting spherical metallic *** proposed high-temperature dip-coating and self-leveling fabrication process achieves high-temperature thin-film coatings with excellent uniformity,high-temperature electrical insulation,and adhesion *** fabricated Ag/Pt thin film thermocouple arrays and a heat flux sensor exhibit a maximum temperature resistance of up to 960℃,with thermoelectric potential outputs and hightemperature resistance closely mirroring those of wire-based Ag/Pt *** environmental testing was conducted using high-power lasers and a flame *** results show that the array of thin-film conformal thermocouples more accurately reflected temperature changes at different points on a spherical *** heat flux sensors achieve responses within 95 ms and with-stand environments with heat fluxes over 1.2 MW/m^(2).The proposed multi-sensor design and fabrication method offers promising monitoring applications in harsh environments,including aerospace and nuclear power.

关键词： Conformal thin-film sensor Metallic spherical surfaces Multi-sensor perception Harsh environments Additive manufacturing

来源：评论

学校读者我要写书评

暂无评论

Partial Attention-Based Direction-Aware Vehicle Re-identification 18th

Partial Attention-Based Direction-Aware Vehicle Re-identific...

引用

18th International Conference on Computer Science and Education, ICCSE 2023

作者： Zhou, Yujie Yuan, Caihong Su, Chenshuang Zou, Mingdong Zhu, Xiaoke Liang, Wenjuan School of Computer and Information Engineering Henan University Henan Engineering Research Center of Intelligent Technology and Application Henan Province Spatial Information Processing Engineering Technology Research Center Kaifeng China

ISBN: (纸本)9789819707294

With the rapid development of urban transportation, vehicle re-identification has become a focal point in traffic management and vehicle tracking problems. In order to address the problem of small inter-class similarity among vehicles, previous studies utilize vehicle parsing models to extract local features. Therefore, we introduce the Squeeze-and-Excitation attention mechanism to extract important discriminative information from these local features. Furthermore, we propose a local co-occurrence attention mechanism to represent the proportion of common parts feature matching. To address the issue of large intra-class differences caused by vehicle direction change, we propose a lightweight and effective direction weighted fusion strategy. Experiments on two large datasets show that the proposed algorithm performs competitively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

Kinship verification based on multi-scale feature fusion

引用

Multimedia Tools and applications 2024年第40期83卷 88069-88090页

作者： Yan, Chunman Liu, Yanling Engineering Research Center of Gansu Province for Intelligent Information Technology and Application School of Physics and Electronic Northwest Normal University Lanzhou730070 China School of Physics and Electronic Northwest Normal University Lanzhou730070 China

Recent advancements in kinship verification research suggest that extracting suitable face kinship features is the key to solving this problem. Due to the emergence of deep learning, most of the existing methods for kinship verification use a convolutional neural network-based approach to perform the extraction of the overall feature information in the image, thus ignoring the local detail information in the image, resulting in incomplete extracted feature information. To address this problem, this paper proposes a method for kinship verification using extracted multi-scale features and fusion. Firstly a lightweight backbone framework based on convolutional neural network is constructed by stacking the designed residual block network several times. Second, the two convolutional neural networks with shared weight arguments are used for extracting features at different scales and fusing them for feature fusion with a view to better providing global contextual information about the kinship face images. Finally, the channel and spatial attention mechanisms are embedded in the feature extraction network to improve the ability of the network to extract feature information. Experiments are conducted on two widely used face kinship datasets, KinFaceW-I and KinFaceW-II, and the proposed method achieves an average accuracy of 83.85% and 91.75% for kinship verification, which verifies that the measures taken in this paper have better validation properties in kinship. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Maritime image deraining algorithm based on improved MPRNet

Maritime image deraining algorithm based on improved MPRNet

引用

2024 International Conference on Advanced Image Processing technology, AIPT 2024

作者： Yuan, Zhixin Zhao, Lining Tian, Shukai Zhang, Dong National-Local Joint Engineering Research Center for Integrated Application Technology of Intelligent Shipping Dalian Maritime University Liaoning Dalian116026 China

ISBN: (纸本)9781510682542

When ships navigate, they often encounter rain, which can reduce the resolution of both onboard intelligent perception systems and shore-based monitoring systems. This reduction compromises ship target detection accuracy, posing a significant threat to maritime safety. To address this issue and ensure safe maritime navigation, this study introduces an enhanced maritime image deraining model based on MPRNet. By improving image quality during rainy conditions, the model supports subsequent ship target detection tasks, ensuring safe vessel navigation. In this study, MPRNet is used as the baseline model. A Pixel Convolution (PConv) structure is added after each stage's channel attention module, creating the Pixel and Channel Attention Block (PCAB) to effectively reduce residual raindrops in images under heavy rain. Additionally, a Total Variation Regularizer Term is included in the loss function to smooth derained images, addressing coarse details. Extensive comparative experiments show that the proposed model significantly outperforms existing models. Compared to the baseline, the proposed model increases PSNR by 2.24 and improves SSIM by 0.045. © 2024 SPIE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Multimodal Interaction Fusion Network for Cloth-Changing Person Re-Identification 22

Multimodal Interaction Fusion Network for Cloth-Changing Per...

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with applications, ISPA 2024

作者： Yuan, Caihong Xu, Yuanchen Guan, Zhijie Chen, Xiaopan Zhu, Xiaoke Liang, Wenjuan Henan University School of Computer and Information Engineering Kaifeng China Henan Engineering Research Center of Intelligent Technology and Application Henan Province Spatial Information Processing Engineering Technology Research Center Kaifeng China

ISBN: (纸本)9798331509712

Cloth-Changing Person Re-Identification (CC-ReID) refers to the technology that can identify the same individual in surveillance scenarios, even after changing their clothes. The core of CC-ReID is to exact cloth-irrelevant identity features. Existing methods usually extract them from body contours, skeletons, human faces, etc. However, information extracted from a single modality is often insufficient. Therefore, we propose a novel Multimodal Interaction Fusion (MIF) framework that could facilitate the deep integration of multimodal information, thereby enhancing the generalization ability of CC-ReID. Specifically, we design a triple-interaction collaborative module that strategically integrates features captured from body posture, original RGB images, and clothes-erased images, maximizing the advantages of each modality and overcoming their limitations. Additionally, we develop an Adapt-Blend Pool (ABP) module that effectively improves pooling methods to enhance the model's ability to process images with complex backgrounds and varied features. Following training, our framework effectively harnesses a variety of modal inputs to capture identity representations independent of clothing accurately. Extensive experimental results on PRCC, LTCC, and VC-Clothes datasets demonstrate the effectiveness of the proposed method. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Prediction of Processing Parameters Based on Multi-objective Bayesian Optimization Combined with Machine Learning Model for High Frequency Heat Treatment of Metals 2nd

Prediction of Processing Parameters Based on Multi-objective...

引用

2nd International Conference on Security and Information Technologies with AI, Internet Computing and Big-data applications, SITAIBA 2023

作者： Lin, Chih-Hsueh Tseng, Yu-Hsiang Hu, Kuo-Hsin Ho, Chia-Wei Department of Electronic Engineering National Kaohsiung University of Science and Technology Kaohsiung City Taiwan Knowledge Application Development Group Metal Industry Research and Development Center Taguig Philippines

ISBN: (纸本)9789819777853

In the process of metal processing, heat treatment is a common metal processing method, which is usually used to change the mechanical properties of metal alloys to control such as hardness, strength, toughness, ductility, and elasticity. The high-frequency heat treatment is to rapidly heat the surface of the steel with high frequency, stop the heating when it reaches the quenching temperature, and use an appropriate coolant to implement quenching. In the process of processing, it is often necessary to set processing parameters for the processed products, so as to ensure that each processed product meets the requirements. This manual setting method is not only inefficient but also needs to rely on the experience of field personnel to set parameters. Even so, the problem of artificially setting wrong parameters still occurs. Therefore, this paper applies machine learning technology to analyze the correlation between processing parameters and establishes a predictive evaluation model in combination with hyperparameter optimization, and then predicts the best processing parameters. In order to achieve the concept of intelligent production line, and can reduce the problems caused by human setting errors, thereby improving efficiency. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Quenching

来源：评论

学校读者我要写书评

暂无评论

research on the performance of harmony search with local search algorithms for solving flexible job-shop scheduling problem

引用

Journal of intelligent and Fuzzy Systems 2025年第3期48卷 291-304页

作者： Li, Jia Xue, Shuaihao Li, Minghui Shi, Xiaoqiu School of Manufacturing Science and Engineering Southwest University of Science and Technology Mianyang China State Key Laboratory of Intelligent Manufacturing Equipment and Technology School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan China Low Speed Aerodynamics Institute China Aerodynamics Research and Development Center Sichuan Mianyang China Key Laboratory of Icing and Anti/De-icing China Aerodynamics Research and Development Center Sichuan Mianyang China Mianyang Science and Technology City Intelligent Manufacturing Industry Technology Innovation Institute Sichuan Mianyang China

Combining the harmony search algorithm (HS) with the local search algorithm (LS) can prevent the HS from falling into a local optimum. However, how LS affects the performance of HS has not yet been studied systematically. Therefore, in this paper, it is first proposed to combine four frequently used LS with HS to obtain several search algorithms (HSLSs). Then, by taking the flexible job-shop scheduling problem (FJSP) as an example and considering decoding times, study how the parameters of HSLSs affect their performance, where the performance is evaluated by the difference rate based on the decoding times. The simulation results mainly show that (I) as the harmony memory size (HMS) gradually increases, the performance of HSLSs first increases rapidly and then tends to remain unchanged, and HMS is not the larger the better;(II) as harmony memory considering rate increases, the performance continues to improve, while the performance of pitch adjusting rate on HSLSs goes to the opposite;Finally, more benchmark instances are also used to verify the effectiveness of the proposed algorithms. The results of this paper have a certain guiding significance on how to choose LS and other parameters to improve HS for solving FJSP. © 2025 – IOS Press. All rights reserved.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Humic acid-mediated transport of a typical soil passivation remediation product(chloropyromorphite)in saturated porous media

引用

Journal of Environmental Sciences 2024年第7期141卷 51-62页

作者： Xinying Li Mengjia Zhang Siyuan Li Wei Wei School of Environment Jiangsu Engineering Lab of Water and Soil Eco-remediationJiangsu Province Engineering Research Center of Environmental Risk Prevention and Emergency Response TechnologyNanjing Normal UniversityNanjing 210023China Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing 210023China

Conversion of labile Pb species into chloropyromorphite(CPY)using phosphorus-bearing amendments was considered to be an ideal strategy in soil passivation ***,the fate and transport of CPY in the soil are poorly *** study aims to fill the knowledge gap by evaluating the fate and transport of CPY under environmentally relevant conditions of humic acid(HA),pH,electrolyte concentration,and species through the saturated sandy *** showed that bare CPY colloids are basically immobile in sandy porous media while the co-existence of HA made the transport of CPY improved by30%-93.5%.Facilitated transport of CPY was attributed to the increased stability of CPY and the repulsive interaction between CPY particles and sands due to HA *** mobility of CPY was also increased with increasing pH from 5.0 to *** the pH was 9 with a10 mmol/L NaCl background solution,the stronger energy barrier between CPY and sand led to enhanced transport *** divalent Ca^(2+)had a more dramatic effect than monovalent Na^(+)on the aggregation and sedimentation of CPY colloids due to its effectivescreening of the surface charge of CPY and bridging interaction with CPY ***-LandauVerwey-Overbeek theory and attachment efficiency calculation indicated that high energy barriers were responsible for the high mobility of CPY colloids,while the retention of CPY in sands was mainly caused by secondary energy minimum and physically *** findings of this work can help to evaluate the fate of soil passivation remediation products in natural water and soil.

关键词： Chloropyromorphite DLVO theory Stability Saturated porous medium Transport

来源：评论

学校读者我要写书评

暂无评论

Clustering Optimization of intelligent Algorithms in Financial Management Software (FMS)

Clustering Optimization of Intelligent Algorithms in Financi...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Chen, Wenjun Western Guangdong Digital Intelligent Accounting Development Research Center Zhanjiang University of Science and Technology Guangdong Zhanjiang524088 China

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509828

intelligent algorithms, especially clustering algorithms, have been widely used in the field of software analysis. Therefore, this study proposes the new financial management software (FMS) analysis model. First, this study reviews existing clustering algorithms and analyzes limitations of basic algorithms when processing large-scale financial data. The challenges of noise analysis are also reviewed. To this end, this study proposes a new clustering algorithm based on Gaussian mixture model. The core of this algorithm is to optimize parameter estimation by combining expectation maximization algorithm. At the same time, in order to improve clustering stability, a multi-feature model is introduced. This model can optimize the data selection and distance calculation paradigm in the clustering process. As for the usage of the clustering analysis, the main scenario is the software security. Focusing on the security, the enhanced model is proposed. This study also designs a security algorithm based on data stream analysis, which aims to ensure the privacy protection of the financial data during the clustering process. The experimental results show that the proposed model can effectively improve the data processing efficiency and security in financial management software. At the same time, the clustering test shows that the proposed model can stably analyze the software. © 2025 IEEE.

关键词： Expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

A multi-step regularity assessment and joint prediction system for ordering time series based on entropy and deep learning

引用

Autonomous intelligent Systems 2024年第1期4卷 109-125页

作者： Yichen Zhou Wenhe Han Heng Zhou Science and Technology Development Co. Ltd.of Shanghai Research Institute of Building SciencesShanghai 201506China Shanghai Engineering Research Center for Safety Intelligent Control of Building Machinery Shanghai 200032China

Customer maintenance is of vital importance to the enterprise *** assessment and efficientprediction for customer ordering behavior can offer better decision-making and reduce business costs *** to existing studies about customer behavior regularity segment and demand prediction most focus one-commerce and other fields with large amount of data,making them not suitable for small enterprises and datafeatures like sparsity and outliers are not mined when doing regularity ***,more and morecomplex network structures for demand prediction are proposed,which builds on the assumption that all thesamples have predictive value,ignoring the fine-grained analysis of different time series regularity with high *** with the above issues,a multi-step regularity assessment and joint prediction system for ordering time series *** extracting features,comprehensive assessment of customer regularity based on entropy weightmethod with the result of predictability quantification using K-Means clustering algorithm,real entropy,LZWalgorithm and anomaly detection adopting Isolation Forest algorithm not only gives an objective result to‘how highthe regularity of customers is’,filling the gap in the field of regularity quantification,but also provides a theoreticalbasis for demand prediction models *** models:Random Forest regression,XGBoost,CNN andLSTM network are experimented with sMAPE and MSLE for performance evaluation to verify the effectiveness of theproposed regularity quantitation ***,a merged CNN-BiLSTM neural network model is established forpredicting those customers with low regularity and difficult to predict by traditional machine leaning algorithms,which performs better on the data set compared to *** Forest is still used for prediction of customerswith high regularity due to its high training ***,the results of prediction,regularity quantificatio

关键词： Regularity quantification Customer assessment Time series prediction Machine learning Deep learning

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：