检索结果-南通市图书馆

Multi-model ensemble learning for battery state-of-health estimation:Recent advances and perspectives

Journal of Energy Chemistry 2025年第1期100卷 739-759页

作者： Chuanping Lin Jun Xu Delong Jiang Jiayang Hou Ying Liang Zhongyue Zou Xuesong Mei State Key Laboratory for manufacturing Systems Engineering Xi'an Jiaotong University Shaanxi Key Laboratory of Intelligent Robots School of Mechanical Engineering Xi'an Jiaotong University Department of Electrical Engineering and automation Luoyang Institute of Science and Technology school of Mechanical Engineering Hangzhou Dianzi University

The burgeoning market for lithium-ion batteries has stimulated a growing need for more reliable battery performance monitoring. Accurate state-of-health(SOH) estimation is critical for ensuring battery operational performance. Despite numerous data-driven methods reported in existing research for battery SOH estimation, these methods often exhibit inconsistent performance across different application scenarios. To address this issue and overcome the performance limitations of individual data-driven models,integrating multiple models for SOH estimation has received considerable attention. Ensemble learning(EL) typically leverages the strengths of multiple base models to achieve more robust and accurate outputs. However, the lack of a clear review of current research hinders the further development of ensemble methods in SOH estimation. Therefore, this paper comprehensively reviews multi-model ensemble learning methods for battery SOH estimation. First, existing ensemble methods are systematically categorized into 6 classes based on their combination strategies. Different realizations and underlying connections are meticulously analyzed for each category of EL methods, highlighting distinctions, innovations, and typical applications. Subsequently, these ensemble methods are comprehensively compared in terms of base models, combination strategies, and publication trends. Evaluations across 6 dimensions underscore the outstanding performance of stacking-based ensemble methods. Following this, these ensemble methods are further inspected from the perspectives of weighted ensemble and diversity, aiming to inspire potential approaches for enhancing ensemble performance. Moreover, addressing challenges such as base model selection, measuring model robustness and uncertainty, and interpretability of ensemble models in practical applications is emphasized. Finally, future research prospects are outlined, specifically noting that deep learning ensemble is poised to advance ens

关键词： Lithium-ion battery State-of-health estimation Data-driven Machine learning Ensemble learning Ensemble diversity

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

Effect of lamellarization on the microstructure and mechanical properties of marine 10Ni5CrMoV steel

引用

International Journal of Minerals,Metallurgy and Materials 2025年第2期32卷 402-413页

作者： Tao Zou Yanwu Dong Zhouhua Jiang Shuyang Du Yushuo Li school of Metallurgy Northeastern UniversityShenyang 110819China Key Laboratory of Rolling and automation Northeastern UniversityShenyang 110819China Key Laboratory for Ecological Metallurgy of Multimetallic Ores(Ministry of Education) Northeastern UniversityShenyang 110819China

Multistage heat treatment involving quenching(Q),lamellarizing(L),and tempering(T)is applied to marine 10Ni5CrMoV *** microstructure and mechanical properties were studied by multiscale characterizations,and the kinetics of reverse austenite transformation,strain hardening behavior,and toughening mechanism were further *** lamellarized specimens possess low yield strength but high toughness,especially cryogenic *** leads to the development of film-like reversed austenite at the martensite block and lath boundaries,refining the martensite structure and lowering the equivalent grain *** analysis of austenite reversion based on the JMAK model shows that the isothermal transformation is dominated by the growth of reversed austenite,and the maximum transformation of reversed austenite is reached at the peak temperature(750℃).The strain hardening behavior based on the modified Crussard-Jaoul analysis indicates that the reversed austenite obtained from lamellarization reduces the proportion of martensite,significantly hindering crack propagation via martensitic transformation during the *** a consequence,the QLT specimens exhibit high machinability and low yield *** with the QT specimen,the ductile-brittle transition temperature of the QLT specimens decreases from-116 to-130℃due to the low equivalent grain size and reversed austenite,which increases the cleavage force required for crack propagation and absorbs the energy of external load,*** work provides an idea to improve the cryogenic toughness of marine 10Ni5CrMoV steel and lays a theoretical foundation for its industrial application and comprehensive performance improvement.

关键词： 10Ni5CrMoV steel lamellarizing reversed austenite cryogenic toughness ductile-brittle transition temperature

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Endoscopy-assisted lightweight diagnosis system based on transformers for colon polyp detection

引用

Optoelectronics Letters 2025年第1期21卷 57-64页

作者： FAN Weiming YU Jiahui JU Zhaojie school of automation and Electrical Engineering Shenyang Ligong University Department of Biomedical Engineering Zhejiang University school of Computing University of Portsmouth

The integration of endoscopy has significantly propelled the diagnosis and treatment of gastrointestinal diseases, with colonoscopy establishing itself as the primary method for early diagnosis and preventive care in colorectal cancer(CRC). Although deep learning holds promise in mitigating missed polyp rates, modern endoscopy examinations pose additional challenges, such as image blurring and atomizing. This study explores lightweight yet powerful attention mechanisms, introducing the spatial-channel transformer(SCT), an innovative approach that leverages spatial channel relationships for attention weight calculation. The method utilizes rotation operations for inter-dimensional dependencies, followed by residual transformation, encoding inter-channel and spatial information with minimal computational overhead. Extensive experiments on the CVC-Clinic DB polyp detection dataset, addressing endoscopy pitfalls, underscore the superiority of our SCT over other state-of-the-art methods. The proposed model maintains high performance, even in challenging scenarios.

关键词： Endoscopy

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

SensFL:Privacy-Preserving Vertical Federated Learning with Sensitive Regularization

引用

Computer Modeling in Engineering & Sciences 2025年第1期142卷 385-404页

作者： Chongzhen Zhang Zhichen Liu Xiangrui Xu Fuqiang Hu Jiao Dai Baigen Cai Wei Wang school of automation and Intelligence Beijing Jiaotong UniversityBeijing100044China Shuohuang Railway Development Co. Ltd.National Energy GroupCangzhou062350China Beijing Key Laboratory of Security and Privacy in Intelligent Transportation School of Computer Science and TechnologyBeijing Jiaotong UniversityBeijing100044China

In the realm of Intelligent Railway Transportation Systems,effective multi-party collaboration is crucial due to concerns over privacy and data *** Federated Learning(VFL)has emerged as a promising approach to facilitate such collaboration,allowing diverse entities to collectively enhance machine learning models without the need to share sensitive training ***,existing works have highlighted VFL’s susceptibility to privacy inference attacks,where an honest but curious server could potentially reconstruct a client’s raw data from embeddings uploaded by the *** vulnerability poses a significant threat to VFL-based intelligent railway transportation *** this paper,we introduce SensFL,a novel privacy-enhancing method to against privacy inference attacks in ***,SensFL integrates regularization of the sensitivity of embeddings to the original data into the model training process,effectively limiting the information contained in shared *** reducing the sensitivity of embeddings to the original data,SensFL can effectively resist reverse privacy attacks and prevent the reconstruction of the original data from the *** experiments were conducted on four distinct datasets and three different models to demonstrate the efficacy of *** results show that SensFL can effectively mitigate privacy inference attacks while maintaining the accuracy of the primary learning *** results underscore SensFL’s potential to advance privacy protection technologies within VFL-based intelligent railway systems,addressing critical security concerns in collaborative learning environments.

关键词： Vertical federated learning privacy defenses

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

Robust interface and excellent as-built mechanical properties of Ti–6Al–4V fabricated through laser-aided additive manufacturing with powder and wire

引用

International Journal of Minerals,Metallurgy and Materials 2025年第1期32卷 154-168页

作者： Fei Weng Guijun Bi Youxiang Chew Shang Sui Chaolin Tan Zhenglin Du Jinlong Su Fern Lan Ng Key Laboratory for Liquid-Solid Structural Evolution and Processing of Materials Ministry of EducationShandong Engineering&Technology Research Center for Superhard MaterialSchool of Materials Science and EngineeringShandong UniversityJinan 250061China Institute of Intelligent manufacturing Guangdong Academy of SciencesGuangzhou 510095China Singapore Institute of manufacturing Technology 5 Cleantech Loop636732Singapore

The feasibility of manufacturing Ti-6Al-4V samples through a combination of laser-aided additive manufacturing with powder(LAAM_(p))and wire(LAAM_(w))was explored.A process study was first conducted to successfully circumvent defects in Ti-6Al-4V deposits for LAAM_(p) and LAAM_(w),*** the optimized process parameters,robust interfaces were achieved between powder/wire deposits and the forged substrate,as well as between powder and wire *** characterization results revealed the epitaxial prior β grains in the deposited Ti-6Al-4V,wherein the powder deposit was dominated by a finerα′microstructure and the wire deposit was characterized by lamellar α *** mechanisms of microstructure formation and correlation with mechanical behavior were analyzed and *** mechanical properties of the interfacial samples can meet the requirements of the relevant Aerospace Material Specifications(AMS 6932)even without post heat *** fracture occurred within the interfacial area,further suggesting the robust *** findings of this study highlighted the feasibility of combining LAAM_(p) and LAAM_(w) in the direct manufacturing of Ti-6Al-4V parts in accordance with the required dimensional resolution and deposition rate,together with sound strength and ductility balance in the as-built condition.

关键词： laser-aided additive manufacturing powder deposition wire deposition interfacial characteristic mechanical behavior

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Dry face milling of titanium alloys

引用

Journal of University of Science and Technology Beijing 2004年第6期11卷 545-548页

作者： Ahmed Hassan manufacturing and automation Department

In machining titanium alloys, cutting tools generally wear out very rapidlybecause of the high cutting temperature resulted from the low thermal conductivity and density ofthe work material. In order to increase the tool life, it is necessary to suppress the cutting heatas much as possible by applying an abundant amount of coolant, but this will entail serioustechno-environmental and biological problems. To study the performance and avoid these limitations,a PVD-coated insert was used to the dry face mill of (alpha + beta) titanium alloys. As a result itwas found that the inserts exhibit an excellent cutting performance at low cutting speeds and feedrates, and there is no significant difference in the dominant insert failure mode between the wetand dry cutting in discontinuous cutting.

关键词： carbide tool face milling titanium alloy

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Surface micro-arrays enhancing electromagnetic interference shielding of polydimethylsiloxane/multiwalled carbon nanotubes nanocomposites

引用

Nano Research 2025年第1期18卷 508-519页

作者： Ke Jiang Zhi Chen Ji Yu Chen Zheng Shan Huang Ming Wang Chongqing Key Laboratory of Soft-Matter Material manufacturing School of Chemistry and Chemical EngineeringSouthwest UniversityChongqing 400715China school of Mechanics Civil Engineering and ArchitecturesNorthwestern Polytechnical UniversityXi’an 710072China Jieyang Branch of Chemistry and Chemical Engineering Guangdong Laboratory(Rongjiang Laboratory) Jieyang 515200China

Herein,the electromagnetic shielding performance of surface concave-convex(SC)and zig-zag micro-arrays was studied by using a simulation prediction and a three-dimensional(3D)printing custom ***,surface stripe concaveconvex(SSC)and surface cylindrical concave-convex(SCC)micro-arrays with or without zig-zag micro-arrays are designed,and their shielding performance is simulated in multi-bands(C-,X-band).The multiwalled carbon nanotubes/polydimethylsiloxane composites(MWCNT/PDMS)with different SC structures and different electrical conductivity are molded in acrylonitrile-butadiene-styrene copolymer(ABS)molds which are printed by a 3D *** results show that the electromagnetic interference shielding effectiveness(EMI SE)of the samples can be enhanced by constructing the SC micro-arrays with zig-zag micro-arrays,and improving with the increase of conductivity and *** addition,the shielding mechanism of the SC-MWCNT/PDMS composites is investigated and discussed by an electromagnetic simulation.

关键词： surface micro-arrays electrical properties electromagnetic interference(EMI)shielding three-dimensional(3D)printing

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

Erosion–corrosion behavior of austenitic cast iron in an acidic slurry medium

引用

International Journal of Minerals,Metallurgy and Materials 2015年第6期22卷 598-603页

作者： Ke Yang Lan Sun Yu-zhen Liu Hong-yuan Fan school of Mechanical Engineering and automation Xihua University school of manufacturing Science and Engineering Sichuan University

A series of austenitic cast iron samples with different compositions were cast and a part of nickel in the samples was replaced by manganese for economic reason. Erosion–corrosion tests were conducted under 2wt% sulfuric acid and 15wt% quartz sand. The results show that the matrix of cast irons remains austenite after a portion of nickel is replaced with manganese.（Fe,Cr）3C is a common phase in the cast irons, and nickel is the main alloying element in high-nickel cast iron; whereas,（Fe,Mn）3C is observed with the increased manganese content in low-nickel cast iron. Under erosion–corrosion tests, the weight-loss rates of the cast irons increase with increasing time. Wear plays a more important role than corrosion in determining the weight loss. It is indicated that the processes of weight loss for the cast irons with high and low nickel contents are different. The erosion resistance of the cast iron containing 7.29wt% nickel and 6.94wt% manganese is equivalent to that of the cast iron containing 13.29wt% nickel.

关键词： cast irons erosion corrosion weight loss acidic environment

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

A Novel Self-Supervised Learning Network for Binocular Disparity Estimation

引用

Computer Modeling in Engineering & Sciences 2025年第1期142卷 209-229页

作者： Jiawei Tian Yu Zhou Xiaobing Chen Salman A.AlQahtani Hongrong Chen Bo Yang Siyu Lu Wenfeng Zheng Department of Computer Science and Engineering Major in Bio Artificial IntelligenceHanyang UniversityAnsan-si15577Republic of Korea school of Electrical and Computer Engineering Louisiana State UniversityBaton RougeLA 70803USA Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11574Saudi Arabia school of automation University of Electronic Science and Technology of ChinaChengdu610054China

Two-dimensional endoscopic images are susceptible to interferences such as specular reflections and monotonous texture illumination,hindering accurate three-dimensional lesion reconstruction by surgical *** study proposes a novel end-to-end disparity estimation model to address these *** approach combines a Pseudo-Siamese neural network architecture with pyramid dilated convolutions,integrating multi-scale image information to enhance robustness against lighting *** study introduces a Pseudo-Siamese structure-based disparity regression model that simplifies left-right image comparison,improving accuracy and *** model was evaluated using a dataset of stereo endoscopic videos captured by the Da Vinci surgical robot,comprising simulated silicone heart sequences and real heart video *** results demonstrate significant improvement in the network’s resistance to lighting interference without substantially increasing ***,the model exhibited faster convergence during training,contributing to overall performance *** study advances endoscopic image processing accuracy and has potential implications for surgical robot applications in complex environments.

关键词： Parallax estimation parallax regression model self-supervised learning Pseudo-Siamese neural network pyramid dilated convolution binocular disparity estimation

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

Advances in Graphene‑Based Electrode for Triboelectric Nanogenerator

引用

Nano-Micro Letters 2025年第1期17卷 378-403页

作者： Bin Xie Yuanhui Guo Yun Chen Hao Zhang Jiawei Xiao Maoxiang Hou Huilong Liu Li Ma Xin Chen Chingping Wong State Key Laboratory of Precision Electronic manufacturing Technology and Equipment Guangdong University of TechnologyGuangzhou 510006People’s Republic of China school of Electromechanical Engineering Guangdong University of TechnologyGuangzhou 510006People’s Republic of China school of Materials Science and Engineering Georgia Institute of TechnologyAtlantaGA 30332USA

With the continuous development of wearable electronics,wireless sensor networks and other micro-electronic devices,there is an increasingly urgent need for miniature,flexible and efficient nanopower generation *** nanogenerator(TENG)technology can convert small mechanical energy into electricity,which is expected to address this *** the core component of TENG,the choice of electrode materials significantly affects its *** metal electrode materials often suffer from problems such as durability,which limits the further application of ***,as a novel electrode material,shows excellent prospects for application in TENG owing to its unique structure and excellent electrical *** review systematically summarizes the recent research progress and application prospects of TENGs based on graphene *** precision processing methods of graphene electrodes are introduced,and the applications of graphene electrode-based TENGs in various scenarios as well as the enhancement of graphene electrodes for TENG performance are *** addition,the future development of graphene electrode-based TENGs is also prospectively discussed,aiming to promote the continuous advancement of graphene electrode-based TENGs.

关键词： Triboelectric nanogenerator Precision processing Graphene electrode Self-powered sensor

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

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：