检索结果-南通市图书馆

Steel Surface Defect Detection Using Learnable Memory Vision Transformer

Computers, Materials & Continua 2025年第1期82卷 499-520页

作者： Syed Tasnimul Karim Ayon Farhan Md.Siraj Jia Uddin department of Computer Science and engineering BRAC UniversityDhaka1212Bangladesh department of ai and Big Data Endicott CollegeWoosong UniversityDaejeon34606Republic of Korea

This study investigates the application of Learnable Memory Vision Transformers(LMViT)for detecting metal surface flaws,comparing their performance with traditional CNNs,specifically ResNet18 and ResNet50,as well as other transformer-based models including Token to Token ViT,ViT withoutmemory,and Parallel *** awidely-used steel surface defect dataset,the research applies data augmentation and t-distributed stochastic neighbor embedding(t-SNE)to enhance feature extraction and *** techniques mitigated overfitting,stabilized training,and improved generalization *** LMViT model achieved a test accuracy of 97.22%,significantly outperforming ResNet18(88.89%)and ResNet50(88.90%),aswell as the Token to TokenViT(88.46%),ViT without memory(87.18),and Parallel ViT(91.03%).Furthermore,LMViT exhibited superior training and validation performance,attaining a validation accuracy of 98.2%compared to 91.0%for ResNet 18,96.0%for ResNet50,and 89.12%,87.51%,and 91.21%for Token to Token ViT,ViT without memory,and Parallel ViT,*** findings highlight the LMViT’s ability to capture long-range dependencies in images,an areawhere CNNs struggle due to their reliance on local receptive fields and hierarchical feature *** additional transformer-based models also demonstrate improved performance in capturing complex features over CNNs,with LMViT excelling particularly at detecting subtle and complex defects,which is critical for maintaining product quality and operational efficiency in industrial *** instance,the LMViT model successfully identified fine scratches and minor surface irregularities that CNNs often *** study not only demonstrates LMViT’s potential for real-world defect detection but also underscores the promise of other transformer-based architectures like Token to Token ViT,ViT without memory,and Parallel ViT in industrial scenarios where complex spatial relationships are *** research m

关键词： Learnable Memory Vision Transformer(LMViT) Convolutional Neural Networks(CNN) metal surface defect detection deep learning,computer vision image classification learnable memory gradient clipping label smoothing t-SNE visualization

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Comparative Evaluation and Performance Analysis of Heat Exchangers Featured with Peened Surface

引用

Journal of Thermal Science 2025年第1期34卷 50-61页

作者： DINESHBABU Chinnadurai SHIVA SANKARAN Nallasamy VENKATESH RAJA Krishnan VENKATESH Rathinavelu department of Mechanical engineering Kongunadu College of Engineering and Technology department of Mechanical engineering Selvam College of Technology department of Mechanical engineering Sona College of Technology department of Mechanical engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical Sciences (SIMATS)Saveetha University

Heat exchangers have the potential for various engineering applications,and their performance is enriched by surface *** proposed system enriches the heat exchanger's performance by adapting a peened stainless steel（SS） surface blasted with copper,grinding,sand,and *** influences peened SS surface modified with a copper blast,grinding,sandblast,and iron blast on the surface morphology of shell and tube heat exchanger surface（STHE） is analyzed via tungsten heated cathode electron gun featured scanning electron microscope and observed coarse grain *** SS surface featured STHE performance is experimentally evaluated by different flow rates（30,60,90,and 120 L/min） underwater fluid medium functioned by the temperature ranges of 25-75℃ and its results are compared with computational fluid dynamic（CFD）/heat transfer research（HTRI） analyzed *** 60 L/min flow rate was spotted as an optimum value for both shell and tube side *** STHE is operated with a 60 L/min flow rate under the different peened surfaces and evaluated its Stanton number,Nusselt number,logarithmic mean temperature difference（LMTD）,overall heat transfer coefficient,number of transfer units（NTU）,effectiveness,and exergy *** iron blasted SS peened surface was observed to have better SHTE performance like Stanton number（0.0012）,Nusselt number（2180）,reduced LMTD of 31℃,improved overall heat transfer co-efficient of 2400 W/（m2·K）,better NTU of 0.5532,good effectiveness value of 0.451 62,and hiked exergy efficiency of 10% respectively.

关键词： penned surface performance analysis shell and tube heat exchanger stainless steel

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Three-Stage Transfer Learning with AlexNet50 for MRI Image Multi-Class Classification with Optimal Learning Rate

引用

Computer Modeling in engineering & Sciences 2025年第1期142卷 155-183页

作者： Suganya Athisayamani A.Robert Singh Gyanendra Prasad Joshi Woong Cho School of Computing Sastra Deemed to be UniversityThanjavur613401India department of Computational Intelligence SRM Institute of Science and TechnologyKattankulathur603203India department of ai and Software engineering Kangwon National UniversitySamcheok25913Republic of Korea department of Electronics Information and Communication EngineeringKangwon National UniversitySamcheok25913Republic of Korea

In radiology,magnetic resonance imaging(MRI)is an essential diagnostic tool that provides detailed images of a patient’s anatomical and physiological *** is particularly effective for detecting soft tissue ***,radiologists manually interpret these images,which can be labor-intensive and time-consuming due to the vast amount of *** address this challenge,machine learning,and deep learning approaches can be utilized to improve the accuracy and efficiency of anomaly detection in MRI *** manuscript presents the use of the Deep AlexNet50 model for MRI classification with discriminative learning *** are three stages for learning;in the first stage,the whole dataset is used to learn the *** the second stage,some layers of AlexNet50 are frozen with an augmented dataset,and in the third stage,AlexNet50 with an augmented dataset with the augmented *** method used three publicly available MRI classification datasets:Harvard whole brain atlas(HWBA-dataset),the School of Biomedical engineering of Southern Medical University(SMU-dataset),and The National Institute of Neuroscience and Hospitals brain MRI dataset(NINS-dataset)for *** hyperparameter optimizers like Adam,stochastic gradient descent(SGD),Root mean square propagation(RMS prop),Adamax,and AdamW have been used to compare the performance of the learning ***-dataset registers maximum classification *** evaluated the performance of the proposed classification model using several quantitative metrics,achieving an average accuracy of 98%.

关键词： MRI tumors classification AlexNet50 transfer learning hyperparameter tuning optimizer

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Maximizing biomass utilization: An integrated strategy for coproducing multiple chemicals

引用

Journal of Energy Chemistry 2025年第1期100卷 180-191页

作者： Byeongchan Ahn Sua Jo Jonggeol Na J.Jay Liu Young-Ju Kim Wangyun Won department of Chemical and Biological engineering Korea University department of Chemical engineering (Integrated process) Kyung Hee University department of Chemical engineering and Materials Science Ewha Womans University department of Chemical engineering Pukyong National University Resources engineering Plant Research department Korea Institute of Geoscience and Mineral Resources

Lignocellulosic biomass is one of the viable solutions to alleviate the global warming. However, the limited utilization of biomass majorly focused on cellulose and hemicellulose restricts the economic and environmental feasibilities. To cope with this issue, we proposed an integrated process of co-producing 1,6-hexanediol（1,6-HDO） with tetrahydrofuran and adipic acid from biomass, referred to as Strategy A. To compare the impacts of lignin upgrading and feedstock, Strategy B, which co-produces tetrahydrofuran alone, and Strategy C, which is the traditional route to produce 1,6-HDO from fossil fuels, were used. Heat networks are also designed to reduce operating costs and indirect carbon emissions due to energy consumption, saving 87% and 83% of the heat and cooling requirements, respectively, in Strategy A. The market competitiveness of Strategy A was evaluated by determining the minimum selling price through techno-economic analysis, and sustainability was thoroughly investigated by quantifying the environmental impacts through both midpoint and endpoint life-cycle assessments（LCAs）.Strategy A was found to be the most favorable both economically（USRDSCHARDOLLAR3,402/ton） and environmentally（-26.9 kg CO2eq.）. This indicates that lignin valorization is not only economically but also environmentally preferred. Finally, changes in economic and environmental feasibilities depending on economic, process, and environmental parameters were investigated using sensitivity and uncertainty analyses. The results of these analyses provide valuable insight into bio-based chemical production.

关键词： Carbon capture and utilization

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Nano-Enhanced Dairy Scum Biodiesel Blends:Unleashing the Power of Aluminium Oxide for Sustainable and Efficient Engine Performance

引用

Journal of Thermal Science 2025年第1期34卷 283-302页

作者： Veeranna MODI Prasad B.RAMPURE Sunil Kumar SHETTY Madeva NAGARAL Channa Keshava NaiK N Johar MGM Muhammad Irsyad ABDULLAH Abdullah I.AL-MANSOUR Shamshad ALAM KLE College of engineering and Technology ChikodiVisvesvaraya Technological University Nitte (Deemed to be University) NMAM Institute of Technology (NMAMIT)Department of Mechanical Engineering aircraft Research and Design Centre HAL department of Mechanical engineering BGS College of Engineering and TechnologyBengaluruAffiliated to Visvesvaraya Technological University Management and Science University department of Civil engineering College of EngineeringKing Saud University

This study investigates the effect of aluminium oxide nanoparticlesaddition to biodiesel blends made from dairy milk scum on performance and combustion characteristics of the diesel *** dispersion of Al2O3nanoparticles in B20 blends at different concentrations was done with the help of *** number of blends were prepared for the *** Machine learning algorithms(Random Forest（RF）and CatBoost) was used for the *** results show that in comparison to biodiesel blends without nanoparticles,the kinematic viscosity and density is higher for fuel blends with *** these Fuel blends have higher calorific *** blends exhibited reduced Brake Specific Fuel Consumption（BSFC） of2.85% than the blends without nano particles(Dairy Scum Methyl Ester Biodiesel 20%+Neat Diesel 80%（in volume）,DSMEB20),57.14% less CO,40.8% less hydrocarbon,and increased NOxemissions compared to conventional diesel,contributing to the development of environmentally friendly and renewable biofuel blends with *** B20NP30 is the optimal blend for performance and emission *** study concludes with findings on enhanced Brake Thermal Efficiency（BTE） of 26.29% in 3×10-5（in volume） Al2O3nanoparticle-blended DSME B20 and other DSME B20 fuel blends,emphasizing the importance of optimal nanoparticle *** correlation matrix shows how engine load,efficiency measures（BTE,BSFC）,and emissions（CO,CO2,NOx,Smoke） are connected in complex *** results help us understand the complicated dynamics of engine performance and emission characteristics ***'s diagram for BTE and BSFC shows that CatBoost-based BTE models perform superior to RF-based models during the training as well as testing *** results were obtained for CO and CO2emission results.

关键词： Al2O3 concentration CI engine Dairy Scum Methyl Ester Biodiesel

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Nanosecond pulse and dual-wavelength Q-switched 1.5 μm fiber laser using MAX phase Cr2TiAlC2 saturable absorber

引用

Optoelectronics Letters 2025年第1期21卷 7-12页

作者： Ahmed Shakir AL-HITI Hiba HASSAN department of Electrical engineering Faculty of Engineering University of Anbar department of Laser and Optoelectronics engineering University of Technology-Iraq

We demonstrated a new type of MAX phase material, chromium titanium aluminum carbide（Cr2TiAlC2） polymer film, to generate a passively Q-switched erbium-doped fiber laser（EDFL）. The film thickness was measured to be around 45 μm, which was fabricated using the embedding method with polyvinyl alcohol（PVA） polymer as hoster. The saturable absorber（SA） film demonstrates a dual-wavelength passively Q-switched EDFL which operates at 1 531 nm and 1 560.19 nm, respectively. The Q-switching pulse duration could be varied from 2.46 μs to 770 ns, while the repetition rate varied from 92.76 kHz to 106.6 kHz with an increasing input pumping range from 154 mW to 300 mW. The maximum output power and pulse energy of 15.05 mW and 141.18 nJ were obtained at the maximum input power of 300 mW, respectively.

关键词： Saturable absorbers

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Dynamic Multi-Graph Spatio-Temporal Graph Traffic Flow Prediction in Bangkok:An Application of a Continuous Convolutional Neural Network

引用

Computer Modeling in engineering & Sciences 2025年第1期142卷 579-607页

作者： Pongsakon Promsawat Weerapan Sae-dan Marisa Kaewsuwan Weerawat Sudsutad Aphirak Aphithana department of Civil engineering Faculty of EngineeringRamkhamkaeng UniversityBangkok10240Thailand department of Computer engineering Faculty of EngineeringRamkhamkaeng UniversityBangkok10240Thailand department of Statistics Faculty of ScienceRamkhamkaeng UniversityBangkok10240Thailand

The ability to accurately predict urban traffic flows is crucial for optimising city ***,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to understand complex mobility *** learning techniques,such as graph neural networks(GNNs),are popular for their ability to capture spatio-temporal ***,these models often become overly complex due to the large number of hyper-parameters *** this study,we introduce Dynamic Multi-Graph Spatial-Temporal Graph Neural Ordinary Differential Equation Networks(DMST-GNODE),a framework based on ordinary differential equations(ODEs)that autonomously discovers effective spatial-temporal graph neural network(STGNN)architectures for traffic prediction *** comparative analysis of DMST-GNODE and baseline models indicates that DMST-GNODE model demonstrates superior performance across multiple datasets,consistently achieving the lowest Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)values,alongside the highest *** the BKK(Bangkok)dataset,it outperformed other models with an RMSE of 3.3165 and an accuracy of 0.9367 for a 20-min interval,maintaining this trend across 40 and 60 ***,on the PeMS08 dataset,DMST-GNODE achieved the best performance with an RMSE of 19.4863 and an accuracy of 0.9377 at 20 min,demonstrating its effectiveness over longer *** Los_Loop dataset results further emphasise this model’s advantage,with an RMSE of 3.3422 and an accuracy of 0.7643 at 20 min,consistently maintaining superiority across all time *** numerical highlights indicate that DMST-GNODE not only outperforms baseline models but also achieves higher accuracy and lower errors across different time intervals and datasets.

关键词： Graph neural networks convolutional neural network deep learning dynamic multi-graph spatio-temporal

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Few-shot learning for screening 2D Ga2CoS4-x supported single-atom catalysts for hydrogen production

引用

Journal of Energy Chemistry 2025年第1期100卷 665-673页

作者： Nabil Khossossi Poulumi Dey department of Mechanical engineering (ME) Delft University of Technology

Hydrogen generation and related energy applications heavily rely on the hydrogen evolution reaction（HER）,which faces challenges of slow kinetics and high *** electrocatalysts,particularly single-atom catalysts （SACs） on two-dimensional （2D） materials,are *** study presents a few-shot machine learning （ML） assisted high-throughput screening of 2D septuple-atomic-layer Ga2CoS4-xsupported SACs to predict HER catalytic ***,density functional theory （DFT）calculations showed that 2D Ga2CoS4is inactive for ***,defective Ga2CoS4-x（x=0–0.25）monolayers exhibit excellent HER activity due to surface sulfur vacancies （SVs）,with predicted overpotentials （0–60 mV） comparable to or lower than commercial Pt/C,which typically exhibits an overpotential of around 50 m V in the acidic electrolyte,when the concentration of surface SV is lower than 8.3%.SVs generate spin-polarized states near the Fermi level,making them effective HER *** demonstrate ML-accelerated HER overpotential predictions for all transition metal SACs on 2D *** DFT data from 18 SACs,an ML model with high prediction accuracy and reduced computation time was *** intrinsic descriptor linking SAC atomic properties to HER overpotential was *** study thus provides a framework for screening SACs on 2D materials,enhancing catalyst design.

关键词： Hydrogen production Electrocatalyst 2D material Density functional theory Machine learning Surface sulfur vacancy

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

“One stone, two birds”: Salt template enabling porosity engineering and single metal atom coordinating toward high-performance zinc-ion capacitors

引用

Journal of Energy Chemistry 2025年第1期100卷 637-645页

作者： Chunliu Zhu Huanyu Liang Ping Li Chenglong Qiu Jingyi Wu Jingwei Chen Weiqian Tian Yue Zhu Zhi Li Huanlei Wang School of Materials Science and engineering Ocean University of China department of Chemical and Materials engineering University of Alberta

Zinc-ion hybrid capacitors （ZIHCs） have received increasing attention as energy storage devices owing to their low cost,high safety,and environmental ***,their progress has been hampered by low energy and power density,as well as unsatisfactory long-cycle stability,mainly due to the lack of suitable electrode *** this context,we have developed manganese single atoms implanted in nitrogen-doped porous carbon nanosheets （MnSAs/NCNs） using a metal salt template method as cathodes for *** metal salt serves a dual purpose in the synthesis process:It facilitates the uniform dispersion of Mn atoms within the carbon matrix and acts as an activating agent to create the porous *** applied in ZIHCs,the MnSAs/NCNs electrode demonstrates exceptional performance,including a high capacity of 203 m Ah g-1,an energy density of 138 Wh kg-1at 68 W kg-1,and excellent cycle stability with 91%retention over 10,000 *** calculations indicate that the introduced Mn atoms modulate the local charge distribution of carbon materials,thereby improving the electrochemical *** work demonstrates the significant potential of carbon materials with metal atoms in zinc-ion hybrid capacitors,not only in enhancing electrochemical performance but also in providing new insights and methods for developing high-performance energy storage devices.

关键词： Zinc ion hybrid capacitors Cathodes Carbon materials Heteroatoms Single atoms

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

CO2-mediated bicarbonate conversion to concentrated formate in a CEM-based electrolyzer

引用

Journal of Energy Chemistry 2025年第1期100卷 605-611页

作者： Haocheng Xiong Donghuan Wu Haonan Li Andrew Li Qikun Hu Siyao Song Bingjun Xu Qi Lu State Key Laboratory of Chemical engineering Department of Chemical Engineering Tsinghua University College of Chemistry and Molecular engineering Peking University Ordos Laboratory

Renewable energy-driven bicarbonate conversion to valuable chemicals presents an attractive strategy for mitigating CO2emissions,as bicarbonate can be efficiently generated from the capture of atmospheric CO2using alkaline solutions with reactive *** this work,we present a CO2-mediated bicarbonate conversion to pure formate using a cation exchange membrane-based electrolyzer with a 25 cm2electrode *** electrolysis achieved selectivities exceeding 75%for formate at a total current of 2.5 A,achieving formate concentrations up to 1.2 M and yields as high as 95%over extended *** techno-economic assessment confirmed the economic viability of the process,highlighting the potential for bicarbonate electrolysis as a sustainable method for producing valuable chemicals.

关键词： Electrocatalysis Techno-economic assessments Electrochemistry Flow electrolyzer

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：