检索结果-内蒙古大学图书馆

Machine learning-based performance predictions for steels considering manufacturing process parameters:a review

Journal of Iron and Steel Research International 2024年第7期31卷 1555-1581页

作者： Wei Fang Jia-xin Huang Tie-xu Peng Yang Long Fu-xing Yin Tianjin Key Laboratory of Materials Laminating Fabrication and Interface Control Technology School of Materials Science and EngineeringHebei University of TechnologyTianjin 300132China Institute of New Materials Guangdong Academy of ScienceGuangzhou 510651GuangdongChina

Steels are widely used as structural materials,making them essential for supporting our lives and ***,further improving the comprehensive properties of steel through traditional trial-and-error methods becomes challenging due to the continuous development and numerous processing parameters involved in steel *** address this challenge,the application of machine learning methods becomes crucial in establishing complex relationships between manufacturing processes and steel *** review begins with a general overview of machine learning methods and subsequently introduces various performance predictions in steel *** classification of performance pre-diction was used to assess the current application of machine learning model-assisted *** important issues,such as data source and characteristics,intermediate features,algorithm optimization,key feature analysis,and the role of environmental factors,were summarized and *** insights will be beneficial and enlightening to future research endeavors in this field.

关键词： Steel Manufacturing process Machine learning Performance prediction Algorithm

来源：评论

学校读者我要写书评

暂无评论

Pitting corrosion behavior of Cu-P-RE weathering steels

引用

Journal of Rare Earths 2023年第2期41卷 321-330页

作者： Lijie Yue Yeshu Meng Jinsheng Han Kun Xie Yipin Sun Yunliang Tan School of Material Science and Engineering Shandong University of Science and TechnologyQingdao 266590China School of Civil Engineering and Architecture Shandong University of Science and TechnologyQingdao 266590China State Key Laboratory of Mining Disaster Prevention and Control Shandong University of Science and TechnologyQingdao 266590China

The weathering steels are prone to pitting corrosion in an environment containing chloride *** pitting behavior of Cu-P-RE weathering steels and its effect on the corrosion resistance of steels were investigated by multifarious analytical techniques,such as field emission-scanning electron microscopy(FE-SEM),electron probe microanalysis(EPMA),scanning Kelvin probe force microscopy(SKPFM),electrochemical workstation and a series of immersion *** results show that the original stripshaped MnS inclusions and Al_(2)O_(3)inclusions with sharp angles are modified into the fine spherical rare earth(RE)inclusions with small average size,which are mainly RE oxysulfides after adding appropriate amount of mischmetal(48.9 wt%Ce-42 wt%La-5 wt%Nd-Fe)into the Cu-P weathering *** the environment containing Cl^(-),the pitting corrosion in RE weathering steel is induced by the preferential dissolution of RE inclusions in that the RE inclusions have a more negative potential than steel matrix at the initial corrosion *** the increase of corrosion time,the driving force of pitting expansion is weakened as a re sult of the continuous dissolution of RE inclusions,which makes the pitting tend to propagate horizontally around the RE *** the RE inclusions completely dissolve,the open corrosion pits with shallow depth are formed in *** dispersed pitting pits with small size and shallow depth induced by RE inclusions are conducive to the formation of uniform and dense corrosion products layer on the steel surface,which reveals that the addition of RE can improve the corrosion resistance of weathering steels.

关键词： Inclusion Pitting corrosion Weathering steel Rare earths Corrosion resistance

来源：评论

学校读者我要写书评

暂无评论

Effect of industrial alkene ozonolysis on atmospheric H_(2)SO_(4)formation

引用

Journal of Environmental sciences 2025年第4期150卷 466-476页

作者： Xing Wang Xiaowen Shi Youling Jiang Yan Ma Jun Zheng School of Environmental Science and Engineering Nanjing University of Information Science and TechnologyNanjing 210044China Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control Nanjing 210044China Jiangsu Provincial Academy of Environmental Sciences Nanjing 210036China

This study has employed the master chemical mechanism(MCM)to investigate the influence of the ozone oxidation pathways in the atmospheric formation of H_(2)SO_(4)from shortchain olefins in industrialized ***-situ H_(2)SO_(4)formation data were obtained using a high-resolution chemical ionization time-of-flight mass spectrometer,and the simulated H_(2)SO_(4)concentrations calculated using updated parameters for the MCM model exhibited good agreementwith *** the simulation analysis of different reaction pathways involved in H_(2)SO_(4)formation,hydroxyl radicals were found to dominate H_(2)SO_(4)production during the daytime,while olefin ozone oxidation contributed up to 65%of total H_(2)SO_(4)production during the night-time.A sensitivity analysis of the H_(2)SO_(4)production parameters has revealed a high sensitivity to changes in sulfur dioxide,and a relatively high sensitivity to olefins with fast ozonolysis reaction rates and bimolecular reaction rates of resulting stabilized Criegee Intermediates.A high relative humidity promotes daytime H_(2)SO_(4)formation,but has an inhibiting effect during the night-time due to the different dominant reaction pathways.

关键词： Gaseous sulfuric acid Alkene ozonation reaction MCM model Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Frequency Attacks Based on Invertible Neural Networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第2期6卷 292-300页

作者： Shao, Ming-Wen Yang, Jian-Xin Meng, Ling-Zhuang Hu, Zhi-Yong China University of Petroleum School of Computer Science and Technology East China Qingdao266580 China China University of Petroleum College of Control Science and Engineering East China Qingdao266580 China

Adversarial attacks reveal the vulnerability of classifiers based on deep neural networks to well-designed perturbations. Most existing attack methods focus on adding perturbations directly to the pixel space. However, the perturbations generated by these methods may be easily perceived by humans. To alleviate the aforementioned problem, we propose a novel high-frequency attack based on invertible neural networks (HA-INN) that relies on INNs to adds perturbations to the high-frequency space of the image instead of the pixel space. In this way, we can fool the classifier while the perturbations are not easily detected by humans. Specifically, we introduce INNs to separate the high-frequency and low-frequency components of the image. And the low-frequency components are guaranteed to be reconstructed as the original image, while the high-frequency components are replaced with resampled high-frequency latent variables with additional adversarial information. Then, the low-frequency components and the high-frequency components with adversarial information are inversely fed into the INN to generate effective adversarial examples. Extensive experiments on two datasets (CIFAR-10 and CIFAR-100) show that our method can generate misleading and transferable cross-architectural adversarial examples with greatly reduced computational resource requirements. Under the white-box setting, the attack success rate of CIFAR10 and CIFAR100 is 99.8% and 99.74%, respectively. Further, under the black-box setting, the adversarial examples generated by our method are more effective than the other methods. © 2020 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Distributed state estimation for heterogeneous mobile sensor networks with stochastic observation loss

引用

Chinese Journal of Aeronautics 2022年第2期35卷 265-275页

作者： Yingrong YU Jianglong YU Yishi LIU Zhang REN Science and Technology on Aircraft Control Laboratory School of Automation Science and Electrical EngineeringBeihang.UniversityBeijing 100191China

The problem of distributed fusion and random observation loss for mobile sensor networks is investigated *** view of the fact that the measured values,sampling frequency and noise of various sensors are different,the observation model of a heterogeneous network is constructed.A binary random variable is introduced to describe the drop of observation component and the topology switching problem caused by complete observation loss is also considered.A cubature information filtering algorithm is adopted to design local filters for each observer to suppress the negative effects of measurement *** derive a consistent and accurate estimation result,a novel weighted average consensus-based filtering approach is put *** the sensor that suffers from observation loss,its local prediction information vector is fused with the information contribution vectors of the neighbors to obtain the local *** the consensus weight matrix is designed for consensus-based distributed collaborative information *** boundness of the estimation errors is proved by employing the stochastic stability *** the end,two numerical examples are offered to assert the validity of the presented method.

关键词： Consistency theorem Heterogeneous sensor networks Information fusion State estimation Stochastic boundedness

来源：评论

学校读者我要写书评

暂无评论

Effect of blade tilt angle on fluid flow characteristics in spray-blowing agitation composite process:a simulation

引用

Journal of Iron and Steel Research International 2024年第9期31卷 2142-2155页

作者： Chao Lv Hai-wei Zhang Tao Yang Hong-liang Zhao Zhao-xiang Ji School of Control Engineering Northeastern University at QinhuangdaoQinhuangdao066000HebeiChina State Key Laboratory of Complex Nonferrous Metal Resources Clean Utilization Kunming University of Science and TechnologyKunming650093YunnanChina School of Metallurgy and Ecological Engineering University of Science and Technology BeijingBeijing100083China

Aiming at the paddle tilt angle of the spray-blowing agitation composite process,the four-blade stirring and blowing composite desulfurization agitator was chosen as the research object,and the computational fluid dynamics numerical simulation was used to investigate the changes in flow field velocity,turbulent kinetic energy magnitude,and distribution caused by the blade tilt ***,the impact of blade tilt angle on the flow fragmentation behavior of individual bubbles and the coalescence process of multiple bubbles at different positions was *** the same stirring and blowing process parameters,with the increase in the blade tilt angle of the agitator,the velocity of the flow field and the average turbulent kinetic energy inside the agitator decreased,and the bubble fragmentation speed decreased while the merging speed *** turbulent kinetic energy at the agitator bottom was greater when the blade tilt angle was 3.2°compared to when it was 13.2°,while the turbulent kinetic energy at the agitator upper part was relatively *** results for single bubbles represented the state and trajectory of the bubble fragmentation process,and the results for multiple bubbles illustrated the state and trajectory of the bubble aggregation process.

关键词： Blade tilt angle Numerical simulation Stirring Spray-blowing Bubble fragmentation Bubble aggregation

来源：评论

学校读者我要写书评

暂无评论

Liner Damage Analysis for Hydrogen Storage Vessels Subjected to Local Compressive Loads Using the Submodeling Method

引用

Chinese Journal of Mechanical engineering 2024年第6期37卷 382-395页

作者： Wen Liu Lele Zhang Geng Chen Yu Zhu Baofeng Ruan School of Mechanical Electronic and Control EngineeringBeijing Jiaotong UniversityBeijing 100044China National International Science and Technology Cooperation Base Beijing Jiaotong UniversityBeijing 100044China School of Mechanical and Electrical Engineering Lanzhou University of TechnologyLanzhou 730050China

When a hydrogen storage vessel is subjected to a local impact load, damage may occur in the liner and result in hydrogen leakage and other catastrophic consequences. When predicting liner damage of a hydrogen storage vessel using the finite element method(FEM), although large element size is required to achieve a desired computational efficiency, it oftentimes causes inaccuracy in the damage model. To remedy this problem, in this study a novel approach which calculates the material damage based on the GISSMO(Generalized Incremental Stress State dependent damage Model) damage model and employs a submodeling strategy is proposed. According to this approach,the global model is discretized to large elements to increase the efficiency, while the submodel is meshed to much smaller elements to accurately reflect the material damage. Employing the established approach and material parameters calibrated from a large set of notched aluminum alloy 5083 specimens, the liner damage of a type Ⅲ hydrogen storage vessel subjected to a local compressive load was simulated. This way, the study reveals how the characteristics of the stress and material damage interact with each other. In addition, the study also demonstrates that the proposed approach can be used as a viable means to evaluate the damage within hydrogen storage vessels.

关键词： Hydrogen storage vessel Compression Damage Submodel FEM

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Feature Fusion Model for Marine Raft Aquaculture Sematic Segmentation Based on SAR Images 14

Unsupervised Feature Fusion Model for Marine Raft Aquacultur...

引用

14th International Conference on Information science and Technology, ICIST 2024

作者： Li, Mengmeng Wang, Xinzhe Fan, Jianchao School of Information Science and Engineering Dalian Polytechnic University Dalian China School of Control Science and Engineering Dalian University of Technology Dalian China

ISBN: (纸本)9798350353334

Marine aquaculture semantic segmentation provides a scientific basis for marine regulation and plays an important role in marine ecological protection and management. Currently, most high-performance marine aquaculture segmentation networks are trained by supervised learning. This approach requires collecting a large number of accurate manually labelled samples for training, but the labelled samples are difficult to obtain. To solve this problem, this paper proposes an unsupervised feature fusion model (UFFM) for marine raft aquaculture semantic segmentation. Firstly, a pseudo-label generator is designed to label the training samples, and a coarse mask is generated using saliency feature clustering. The training samples with pseudo-labels are inputted into a multilevel feature fusion module to extract further and continuously improve the graphical shapes and categories of the objects under the guidance of cross-entropy loss. The pseudo-labels are optimised under continuous iteration to improve the model segmentation performance. Comparison experiments on the GF-3 dataset demonstrate the effectiveness of UFFM. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Explainable Neural Network for Sensitivity Analysis of Lithium-ion Battery Smart Production

引用

IEEE/CAA Journal of Automatica Sinica 2024年第9期11卷 1944-1953页

作者： Kailong Liu Qiao Peng Yuhang Liu Naxin Cui Chenghui Zhang School of Control Science and Engineering Shandong UniversityJinan 250061China Information Technology Analytics&Operations groupQueen’s University BelfastBelfast BT71NNUK

Battery production is crucial for determining the quality of electrode,which in turn affects the manufactured battery *** battery production is complicated with strongly coupled intermediate and control parameters,an efficient solution that can perform a reliable sensitivity analysis of the production terms of interest and forecast key battery properties in the early production phase is urgently *** paper performs detailed sensitivity analysis of key production terms on determining the properties of manufactured battery electrode via advanced data-driven *** be specific,an explainable neural network named generalized additive model with structured interaction(GAM-SI)is designed to predict two key battery properties,including electrode mass loading and porosity,while the effects of four early production terms on manufactured batteries are explained and *** experimental results reveal that the proposed method is able to accurately predict battery electrode properties in the mixing and coating *** addition,the importance ratio ranking,global interpretation and local interpretation of both the main effects and pairwise interactions can be effectively visualized by the designed neural *** to the merits of interpretability,the proposed GAM-SI can help engineers gain important insights for understanding complicated production behavior,further benefitting smart battery production.

关键词： Battery management battery manufacturing data science explainable artificial intelligence sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Noise-robust few-shot classification via variational adversarial data augmentation

引用

Computational Visual Media 2025年第1期11卷 227-239页

作者： Renjie Xu Baodi Liu Kai Zhang Honglong Chen Dapeng Tao Weifeng Liu College of Oceanography and Space Informatics China University of Petroleum(East China)Qingdao 266580China College of Control Science and Engineering China University of Petroleum(East China)Qingdao 266580China School of Petroleum Engineering China University of Petroleum(East China)Qingdao 266580China School of Information Science and Engineering Yunnan UniversityYunnan 650504China

Few-shot classification models trained with clean samples poorly classify samples from the real world with various scales of *** enhance the model for recognizing noisy samples,researchers usually utilize data augmentation or use noisy samples generated by adversarial training for model ***,existing methods still have problems:(i)The effects of data augmentation on the robustness of the model are limited.(ii)The noise generated by adversarial training usually causes overfitting and reduces the generalization ability of the model,which is very significant for few-shot classification.(iii)Most existing methods cannot adaptively generate appropriate *** the above three points,this paper proposes a noise-robust few-shot classification algorithm,VADA—Variational Adversarial Data *** existing methods,VADA utilizes a variational noise generator to generate an adaptive noise distribution according to different samples based on adversarial learning,and optimizes the generator by minimizing the expectation of the empirical *** VADA during training can make few-shot classification more robust against noisy data,while retaining generalization *** this paper,we utilize FEAT and ProtoNet as baseline models,and accuracy is verified on several common few-shot classification datasets,including MiniImageNet,TieredImageNet,and *** training with VADA,the classification accuracy of the models increases for samples with various scales of noise.

关键词： few-shot learning adversarial learning robustness variational method

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：