检索结果-南通市图书馆

Fault diagnosis of a marine power-generation diesel engine based on the Gramian angular field and a convolutional neural network

引用

Journal of Zhejiang University-Science A(Applied Physics & Engineering) 2024年第6期25卷 470-482页

作者： Congyue LI Yihuai HU jiawei jiang Dexin CUI Merchant Marine College Shanghai Maritime UniversityShanghai 201306China School of Mechanical and Energy Engineering Shanghai Technical Institute of Electronics&InformationShanghai 2014llChina

Marine power-generation diesel engines operate in harsh environments.Their vibration signals are highly complex and the feature information exhibits a non-linear distribution.It is difficult to extract effective feature information from the network model,resulting in low fault-diagnosis accuracy.To address this problem,we propose a fault-diagnosis method that combines the Gramian angular field(GAF)with a convolutional neural network(CNN).Firstly,the vibration signals are transformed into 2D images by taking advantage of the GAF,which preserves the temporal correlation.The raw signals can be mapped to 2D image features such as texture and color.To integrate the feature information,the images of the Gramian angular summation field(GASF)and Gramian angular difference field(GADF)are fused by the weighted average fusion method.Secondly,the channel attention mechanism and temporal attention mechanism are introduced in the CNN model to optimize the CNN learning mechanism.Introducing the concept of residuals in the attention mechanism improves the feasibility of optimization.Finally,the weighted average fused images are fed into the CNN for feature extraction and fault diagnosis.The validity of the proposed method is verified by experiments with abnormal valve clearance.The average diagnostic accuracy is 98.40%.When−20 dB≤signal-to-noise ratio(SNR)≤20 dB,the diagnostic accuracy of the proposed method is higher than 94.00%.The proposed method has superior diagnostic performance.Moreover,it has a certain anti-noise capability and variable-load adaptive capability.

关键词： Multi-attention mechanisms(MAM) Convolutional neural network(CNN) Gramian angular field(GAF) Image fusion Marine power-generation diesel engine Fault diagnosis

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

Influence of soil to structure stiffness on the accuracy of the pushover method for underground structures

引用

Earthquake Research Advances 2022年第4期2卷 22-27页

作者： Qi Wu Yifeng Zhou jiawei jiang Wuxi Institute of Technology Wuxi214021China Institute of Geotechnical Engineering Nanjing Tech UniversityNanjing210009China

The pushover method for underground structures is a seismic analysis method featured by high calculation accuracy and a simple implementation process.The method has been widely used in seismic design and other related scientific research;however,the influence of different soil-structure flexibility ratios on the accuracy of this method is still not well understood.In this study,we select the cross-section structures beneath the Daikai subway station as the research object and establish 12 finite element analysis models with different soil-structure flexibility ratios using ABAQUS.All models are computed by the dynamic time-history method or the pushover method.Furthermore,the dynamic time-history solution result is taken as the standard solution,and the precision and application of the pushover analysis method are discussed based on the parameters of peak interlayer displacement and peak internal force of the middle column section.The results show that the soil-structure flexibility ratio has a significant influence on the calculation accuracy of the pushover method,and the calculation accuracy of this method is the most ideal when the soil-structure flexibility is equal to 1.The research results can provide significant references for the seismic design of underground structures or the improvement of simplified seismic analysis methods.

关键词： Underground structure Pushover Soil to structure flexibility Accuracy

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

Drag Reduction Characteristics of Microstructure Inspired by the Cross Section of Barchan Dunes under High Speed Flow Condition

引用

Journal of Renewable Materials 2022年第3期10卷 781-797页

作者： jiawei jiang Yizhou Shen Jie Tao Zhenfeng Jia Xinyu Xie Chaojiao Zeng College of Materials Science and Technology Nanjing University of Aeronautics and AstronauticsNanjing210016China

A new type of microstructure inspired by the cross section of barchan dunes was proposed to reduce windage,which was considered as a passive drag reduction technology in aerospace manufacturing field.Computational fluid dynamics method was carried out to discuss the effect of the microstructure on the skin friction reduction under high velocity flow condition.Different microstructure heights were employed to survey the reduction of drag.The results illustrated that the appearance of microstructure led to a generation of pressure drag in non-smooth model(with microstructures inspired by cross section of barchan dune)in contrast to smooth model.However,the microstructure significantly increased the thickness of the low-speed fluid by 11.4%in the near-wall flow field,causing the low-speed fluid to rise and decreasing the velocity gradient near the wall,thereby reducing viscous resistance.In addition,high-speed fluid flowed above the microstructure units instead of along the inner side of the units due to the influence of micro-vortex,resulting in a reduction of friction near the surface.Further-more,micro-vortex was considered to be the significant internal factor to achieve turbulent drag reduction since it could not only reduce the viscous resistance by promoting the fluid flow above the microstructure but also pro-vide a reverse thrust force.The understanding of the mechanism of drag reduction provides theoretical guidance for further fabrication of drag reduction coatings using renewable materials.

关键词： Barchan dunes microstructure high-speed flow micro-vortex

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

Bioadaptable bioactive glass-β-tricalcium phosphate scaffolds with TPMS-gyroid structure by stereolithography for bone regeneration

引用

Journal of Materials Science & Technology 2023年第24期155卷 54-65页

作者： Meng Li jiawei jiang Wenbin Liu Xiaolong Huang Xiaopei Wu Wenying Wei Hao Zhu Jinyong Zhang Jun Xiao Honglian Dai State Key Laboratory of Advanced Technology for Materials Synthesis and Processing Wuhan University of Technology Biomedical Materials and Engineering Research Center of Hubei Province Wuhan 430070 China Department of Orthopedics Tongji Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan 430030 China Department of Orthopaedics The Third Xiangya Hospital Central South University Changsha 410008 China Foshan Xianhu Laboratory of the Advanced Energy Science and Technology Guangdong Laboratory Xianhu Hydrogen Valley Foshan 528200 China

Bone defect repair remains a troubling problem in clinical orthopedics,which involves complex biological processes.Calcium phosphates(CaPs)have been widely used owing to their advantage of biocompatibility.However,single component and traditional fabrication methods cannot meet the requirements of bioadaptability during the tissue repair process.In this work,0%,5%,15%,25%wt%of BG-TCP(bioactive glass-β-tricalcium phosphate)bioresorbable scaffolds with triply-periodic minimal surfaces(TPMS)-gyroid structure were prepared by the stereolithography(SLA)technology.TPMS-gyroid structure provided an accurate mimicry of natural bone tissue,and the incorporation of BG improved the compressive strength ofβ-TCP matrix,matched with the defective bone(2–12 MPa).Rapid but tunable degradation kinetics(compared with pure TCP)of BG enabled the BG-TCP system to sh8ow adaptable biodegradability to new bone generation.In vitro studies have shown that composite scaffolds have better mechanical properties(7.82 MPa),and can released appropriate contents of calcium,phosphorous,and magnesium ions,which promoted the osteogenic differentiation of bone marrow mesenchymal stem cells(BMSCs)and angiogenic ability of endothelial progenitor cells(EPCs).Moreover,the in vivo assessment of rat femoral defect revealed that TPMS-structure-based TCP scaffolds accelerated bone ingrowth to the pores.Moreover,BG-TCP scaffolds,especially 15BG-TCP group,exhibited superior bone regeneration capacity at both 4 and 8 weeks,which achieved an optimal match between the rate of material degradation and tissue regeneration.In summary,this study provides insight into influences of bioactive components(BG)and bionic structures(TPMS)on the physical-chemical properties of materials,cell behavior and tissue regeneration,which offers a promising strategy to design bioadaptive ceramic scaffolds in the clinical treatment of bone defects.

关键词： Bioactive glass Tricalcium phosphate Triply periodic minimal surfaces Stereolithography Osteogenesis

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

基于多源数据的山区小流域降水融合模型

引用

水科学进展 2024年第1期35卷 74-84页

作者：詹昌洵张挺蒋嘉伟福州大学土木工程学院福建福州350116

为准确获取山区小流域的降水空间分布及其资源量,采用Kriging插值法对低分辨率卫星数据进行空间降尺度处理,通过长短期记忆网络(Long Short-Term Memory,LSTM)将局部卫星与观测数据进行降水融合,引入前期降水信息加强卫星与观测降水之... 详细信息

为准确获取山区小流域的降水空间分布及其资源量,采用Kriging插值法对低分辨率卫星数据进行空间降尺度处理,通过长短期记忆网络(Long Short-Term Memory,LSTM)将局部卫星与观测数据进行降水融合,引入前期降水信息加强卫星与观测降水之间的时间相关性,并利用该模型进行流域降水空间分布估计。结果表明:从空间分布来看,融合模型对暴雨中心位置的捕捉更加精确;从降水量来看,所提模型在短时强降水下的探测率和临界成功指数分别为0.60和0.50,能够改善原始低分辨率卫星降水数据,使其更接近实际情况;从雨量站数量来看,融合降水的精度随着站点数量的增加而提高,当站点数量达到某个临界值时,融合降水的精度趋于稳定。Kriging-LSTM模型为准确获取山区小流域的降水资源提供了新思路。

关键词：降水融合降水空间估计山区小流域 Kriging插值法长短期记忆网络(LSTM)

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

Angel: a new large-scale machine learning system

引用

National Science Review 2018年第2期5卷 216-236页

作者： Jie jiang Lele Yu jiawei jiang Yuhong Liu Bin Cui Key Lab of High Confidence Software Technologies (MOE) School of EECSPeking University

Machine Learning(ML) techniques now are ubiquitous tools to extract structural information from data collections. With the increasing volume of data, large-scale ML applications require an efficient implementation to accelerate the performance. Existing systems parallelize algorithms through either data parallelism or model parallelism. But data parallelism cannot obtain good statistical efficiency due to the conflicting updates to parameters while the performance is damaged by global barriers in model parallel methods. In this paper, we propose a new system, named Angel, to facilitate the development of large-scale ML applications in production environment. By allowing concurrent updates to model across different groups and scheduling the updates in each group, Angel can achieve a good balance between hardware efficiency and statistical efficiency. Besides, Angel reduces the network latency by overlapping the parameter pulling and update computing and also utilizes the sparseness of data to avoid the pulling of unnecessary parameters. We also enhance the usability of Angel by providing a set of efficient tools to integrate with application pipelines and provisioning efficient fault tolerance mechanisms. We conduct extensive experiments to demonstrate the superiority of Angel.

关键词： machine learning distributed system algorithms big data analytics

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

Snapshot boosting: a fast ensemble framework for deep neural networks

引用

Science China(Information Sciences) 2020年第1期63卷 77-88页

作者： Wentao ZHANG jiawei jiang Yingxia SHAO Bin CUI Center for Data Science Peking University National Engineering Laboratory for Big Data Analysis and Applications Department of Computer Science Beijing Key Lab of Intelligent Telecommunications Software and Multimedia School of Computer ScienceBeijing University of Posts and Telecommunications Key Lab of High Confidence Software Technologies Department of Computer SciencePeking University

Boosting has been proven to be effective in improving the generalization of machine learning models in many fields. It is capable of getting high-diversity base learners and getting an accurate ensemble model by combining a sufficient number of weak learners. However, it is rarely used in deep learning due to the high training budget of the neural network. Another method named snapshot ensemble can significantly reduce the training budget, but it is hard to balance the tradeoff between training costs and diversity. Inspired by the ideas of snapshot ensemble and boosting, we propose a method named snapshot boosting. A series of operations are performed to get many base models with high diversity and accuracy, such as the use of the validation set, the boosting-based training framework, and the effective ensemble strategy. Last, we evaluate our method on the computer vision(CV) and the natural language processing(NLP) tasks, and the results show that snapshot boosting can get a more balanced trade-off between training expenses and ensemble accuracy than other well-known ensemble methods.

关键词： ensemble learning deep learning boosting neural network snapshot ensemble

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

知识经济驱动高等教育发展的理论逻辑、现实图景与实践路径

引用

教育与考试 2024年第1期 71-77页

作者：姜嘉伟厦门大学教育研究院厦门361005 厦门大学教师发展中心厦门361005

21世纪是知识经济时代,知识经济因人的“在场”与“增值”与高等教育产生了天然联系。知识经济驱动下,高等教育的发展铺陈出一幅价值理念从保守到开放、人才培养从专业到创新、管理体制从集权到放权、科学研究从“产学研”到“学科-专业... 详细信息

21世纪是知识经济时代,知识经济因人的“在场”与“增值”与高等教育产生了天然联系。知识经济驱动下,高等教育的发展铺陈出一幅价值理念从保守到开放、人才培养从专业到创新、管理体制从集权到放权、科学研究从“产学研”到“学科-专业-产业链”、国际交流从合作到竞争的现实图景,进一步拓展和强化了高等教育的育人功能、科学研究功能和社会服务功能。知识经济驱动高等教育发展以高等教育机构为主体,紧扣国家与国际发展态势,通过培养创新型人才、把握普及化趋势、深化管理改革和关注国际形势等实践路径,不断推动高等教育高质量发展。

关键词：知识经济高等教育 “在场” 高质量发展

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

Green Synthesis of Mechanical Robust Superhydrophobic CNT@PU Coatings with High Flexibility for Extensive Applications

引用

Journal of Bionic Engineering 2021年第1期18卷 40-54页

作者： Zhengwei Wu Yizhou Shen Jie Tao Zhenfeng Jia Haifeng Chen jiawei jiang Zhen Wang College of Materials Science and Technology Nanjing University of Aeronauics and AstronauticsNanjing 210016China School of Engineering Huzhou UniversityHuzhou Centre HospitalHuzhou 313000China

Superhydrophobic coatings with high flexibility and mechanical durability can well address many practical application problems.To this end,we proposed and fabricated a kind of bio-based superhydrophobic(multi-walled carbon nanotubes)CNT@PU(polyurethane)coatings.It was demonstrated that the CNT@PU coatings with 64%soft segment content possessed the preferable bonding strength(5B)with metal substrates.The multi-walled carbon nanotubes,as additive materials,were used to construct the microscopic structures of the coating surfaces,which made polyurethane surface superhydrophobic(water contact angle being 156.9°,and water sliding angle being 4.3°).Furthermore,the high bonding strength between CNT and coating matrix led to robust mechanical durability of supertiydrophobic CNT@PU coatings,and the coatings remained superhydrophobicity after 10 cycles of abrasion under 100 g load pressure.Also,the superhydrophobic coatings could well resist 5 cycles of tape-peeling action,and presented outstanding flexibility.The supernydrophobic CNT@PU coatings with high flexibility and mechanical durability could be applied to various substrates suggesting their big potential in future real-world application.

关键词： bio-based PU superhydrophobic coatings high flexibility mechanical durability

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

场地均质性对浅埋地铁车站地下结构地震易损性的影响

引用

振动与冲击 2024年第6期43卷 151-156,178页

作者：蒋家卫李文彪赵雅芝陈国兴杜修力南京工业大学岩土工程研究所南京211816 北京工业大学城市与工程安全减灾教育部重点实验室北京100124

场地条件是影响地下结构地震响应的关键因素之一,该文旨在研究场地均质性对于地铁车站地下结构地震易损性的影响。以两层两跨地铁车站为研究对象,基于ABAQUS/Standard软件平台建立了考虑土-结构相互作用的二维有限元分析模型。模型考虑... 详细信息

场地条件是影响地下结构地震响应的关键因素之一,该文旨在研究场地均质性对于地铁车站地下结构地震易损性的影响。以两层两跨地铁车站为研究对象,基于ABAQUS/Standard软件平台建立了考虑土-结构相互作用的二维有限元分析模型。模型考虑了循环动力荷载作用下土体的非线性与钢筋混凝土的弹塑性力学行为。采用增量动力分析方法分别计算了结构在层层场地条件下与均质场地条件下结构的地震响应,并以层间位移角为损伤指标与地面峰值加速度为地震动强度指标绘制了地铁车站结构的地震易损性曲线。结果表明,层层场地条件下结构的响应均值要显著高于均质场地,但两者标准差一致。在地震动作用下,结构处于层层场地下的破坏概率要明显高于均质场地,这主要归因于层层场地中毗邻结构的土体产生了较大的剪切变形。上述结论可为地下结构基于性能的抗震设计提供科学参考。

关键词：地铁车站地下结构场地均质性地震易损性

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：