检索结果-南通市图书馆

Robust state of charge estimation of lithium-ion battery via mixture kernel mean p-power error loss LSTM with heap-based-optimizer

引用

Journal of Energy Chemistry 2023年第5期80卷 768-784,I0016页

作者： Wentao Ma yiming lei Xiaofei Wang Badong Chen School of Electrical Engineering Xi'an University of TechnologyXi’an 710048ShaanxiChina School of Microelectronics Xi'an Jiaotong UniversityXi’an 710049ShaanxiChina Institute of Artificial Intelligence and Robotics(IAIR) Xi'an Jiaotong UniversityXi’an 710049ShaanxiChina

The state of charge(SOC)estimation of lithium-ion battery is an important function in the battery management system(BMS)of electric *** long short term memory(LSTM)model can be employed for SOC estimation,which is capable of estimating the future changing states of a nonlinear *** the BMS usually works under complicated operating conditions,i.e the real measurement data used for model training may be corrupted by non-Gaussian noise,and thus the performance of the original LSTM with the mean square error(MSE)loss may ***,a novel LSTM with mixture kernel mean p-power error(MKMPE)loss,called MKMPE-LSTM,is developed by using the MKMPE loss to replace the MSE as the learning criterion in LSTM framework,which can achieve robust SOC estimation under the measurement data contaminated with non-Gaussian noises(or outliers)because of the MKMPE containing the p-order moments of the error *** addition,a meta-heuristic algorithm,called heap-based-optimizer(HBO),is employed to optimize the hyper-parameters(mainly including learning rate,number of hidden layer neuron and value of p in MKMPE)of the proposed MKMPE-LSTM model to further improve its flexibility and generalization performance,and a novel hybrid model(HBO-MKMPE-LSTM)is established for SOC estimation under non-Gaussian noise ***,several tests are performed under various cases through a benchmark to evaluate the performance of the proposed HBO-MKMPE-LSTM model,and the results demonstrate that the proposed hybrid method can provide a good robustness and accuracy under different non-Gaussian measurement noises,and the SOC estimation results in terms of mean square error(MSE),root MSE(RMSE),mean absolute relative error(MARE),and determination coefficient R2are less than 0.05%,3%,3%,and above 99.8%at 25℃,respectively.

关键词： SOC estimation Long short term memory model Mixture kernel mean p-power error Heap-based-optimizer Lithium-ion battery Non-Gaussian noisy measurement data

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

Meta Ordinal Regression Forest for Medical Image Classification With Ordinal Labels

引用

IEEE/CAA Journal of Automatica Sinica 2022年第7期9卷 1233-1247页

作者： yiming lei Haiping Zhu Junping Zhang Hongming Shan Shanghai Key Laboratory of Intelligent Information Processing the School of Computer ScienceFudan UniversityShanghai 200433China with Huawei Shanghai 200120China Institute of Science and Technology for Brain-Inspired Intelligence and MOE Frontiers Center for Brain Science Fudan UniversityShanghai 200433 Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai 200031China IEEE

The performance of medical image classification has been enhanced by deep convolutional neural networks(CNNs),which are typically trained with cross-entropy(CE)***,when the label presents an intrinsic ordinal property in nature,e.g.,the development from benign to malignant tumor,CE loss cannot take into account such ordinal information to allow for better *** improve model generalization with ordinal information,we propose a novel meta ordinal regression forest(MORF)method for medical image classification with ordinal labels,which learns the ordinal relationship through the combination of convolutional neural network and differential forest in a meta-learning *** merits of the proposed MORF come from the following two components:A tree-wise weighting net(TWW-Net)and a grouped feature selection(GFS)***,the TWW-Net assigns each tree in the forest with a specific weight that is mapped from the classification loss of the corresponding ***,all the trees possess varying weights,which is helpful for alleviating the tree-wise prediction ***,the GFS module enables a dynamic forest rather than a fixed one that was previously used,allowing for random feature *** training,we alternatively optimize the parameters of the CNN backbone and TWW-Net in the meta-learning framework through calculating the Hessian *** results on two medical image classification datasets with ordinal labels,i.e.,LIDC-IDRI and Breast Ultrasound datasets,demonstrate the superior performances of our MORF method over existing state-of-the-art methods.

关键词： Terms-Convolutional neural network(CNNs) medical image classification meta-learning ordinal regression random forest

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

Mechanical and thermal properties of RE4Hf3O12（RE=Ho,Er, Tm） ceramics with defect fluorite structure

引用

Journal of Materials Science & Technology 2019年第9期35卷 2064-2069页

作者： Wanpeng Hu yiming lei Jie Zhang Jingyang Wang Advanced Ceramics and Composites Division Shenyang National Laboratory for Materials ScienceInstitute of Metal ResearchChinese Academy of SciencesShenyang 110016China School of Materials Science and Engineering University of Science and Technology of ChinaShenyang 110016China

The thermal and environmental barrier coatings (T/EBC) are technologically important for advanced propulsion engine system. In this study, RE4Hf3Oi2 (RE=Ho, Er, Tm) with defect fluorite structure was investigated for potential use as top TBC layer. Dense pellets were fabricated via a hot pressing method and the mechanical and thermal properties were characterized. RE4Hf3Oi2 (RE=Ho, Er, Tm) possessed a high Vickers hardness of 11 GFa. The material retained high elastic modulus at elevated temperatures up to 1773 K, which made it attractive for high temperature application. The coefficient of thermal expansion (CTE) of RE4Hf3Oi2 (RE = Ho, Er, Tm) laid in the range between 7× 10^-6K^-1 to 10×10^16K^-1 from 473 K to 1673 K. In addition, the rare earth hafnates exhibited lower thermal conductivity which rendered it a good candidate material for thermal barrier applications.

关键词： Rare earth hafnate Thermal/environmental barrier coating Mechanical property Thermal property

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

Accelerating the design of multicomponent rare earth silicates for SiC_(f)/SiC CMC by combinatorial material chip design and high throughput screening

引用

Journal of Materials Science & Technology 2023年第19期150卷 96-103页

作者： Xirui Lv yiming lei Zhao Zhang Jie Zhang Jingyang Wang Shenyang National Laboratory for Materials Science Institute of Metal ResearchChinese Academy of SciencesShenyang 110016China School of Materials Science and Engineering University of Science and Technology of ChinaShenyang 110016China

High throughput experimentation is employed to establish a ternary system with the compositional range of 30.8 mol.%-75.7 mol.%SiO_(2),16.6 mol.%-61.7 mol.%Yb_(2)O_(3),and 6.3 mol.%-4.1 moll.%Ho_(2)O_(3) through co-sputtering deposition on one combinatorial material *** their application in advanced SiC_(f)/SiC CMC,the phase composition and mechanical properties of samples with various RE/Si ratios and Yb/Ho ratios are comprehensively *** stability and thermal expansion compatibility between SiC and RE silicates with different compositions are also *** materials for the application of environmental barrier coating and interphase for SiC_(f)/SiC CMC are screened respectively according to the above trends and *** work is a case study to establish a composition-property library for RE_(2)O_(3)-SiO_(2) *** is inspired more complicated multicomponent RE silicates could be prepared and characterized by high throughput experimentation,accelerating the design and screening of promising optimal candidates.

关键词： High throughput experimentation RE silicates Phase stability Mechanical properties

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

A Networking Solution on Uplink Channel of CoFrequency and Co-Time System

引用

China Communications 2016年第S2期13卷 183-188页

作者： Bingli Jiao Sanjun Liu yiming lei Meng Ma School of Electronics Engineering & Computer Science Peking University

Co-frequency and co-time full duplex(CCFD) is an attractive technology for the future wireless communication because of its high spectral ***,applications of CCFD to mobile network can suffer from strong base station to base station(B2B)*** this paper,the authors proposed a design that uses centralized base station(BS)transmit antenna and distributed BS receive antennas,each of which consists of an antennary to perform beamforming that can nullify the B2 B *** addition,we proposed a combination algorithm that uses the zero forcing method to cascade the recursive least square(RLS) method for reducing the necessary number of the bits taken to the digital *** enables the faster convergence and,thus,allows the transmission of more information bits,compared to the conventional method,for mobile *** simulation results confirm this approach for practical application.

关键词： co-frequency and co-time full duplex cellular networks beamform RLS

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

Strided Self-Supervised Low-Dose CT Denoising for Lung Nodule Classification

引用

Phenomics 2021年第6期1卷 257-268页

作者： yiming lei Junping Zhang Hongming Shan Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China Institute of Science and Technology for Brain-Inspired Intelligence and MOE Frontiers Center for Brain Science Fudan UniversityShanghai 200433China Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai 201210China Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence(Fudan University) Ministry of EducationShanghai 201210China

Lung nodule classification based on low-dose computed tomography(LDCT)images has attracted major attention thanks to the reduced radiation dose and its potential for early diagnosis of lung cancer from LDCT-based lung cancer ***,LDCT images suffer from severe noise,largely influencing the performance of lung nodule *** methods combining denoising and classification tasks typically require the corresponding normal-dose CT(NDCT)images as the supervision for the denoising task,which is impractical in the context of clinical diagnosis using *** jointly train these two tasks in a unified framework without the NDCT images,this paper introduces a novel self-supervised method,termed strided Noise2Neighbors or SN2N,for blind medical image denoising and lung nodule classification,where the supervision is generated from noisy input *** specifically,the proposed SN2N can construct the supervision infor-mation from its neighbors for LDCT denoising,which does not need NDCT images *** proposed SN2N method enables joint training of LDCT denoising and lung nodule classification tasks by using self-supervised loss for denoising and cross-entropy loss for *** experimental results on the Mayo LDCT dataset demonstrate that our SN2N achieves competitive performance compared with the supervised learning methods that have paired NDCT images as ***,our results on the LIDC-IDRI dataset show that the joint training of LDCT denoising and lung nodule classification significantly improves the performance of LDCT-based lung nodule classification.

关键词： Convolutional neural network Medical image classification Self-supervised denoising Low-dose CT

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

High porosity and low thermal conductivity high entropy(Zr0.2Hf0.2Ti0.2Nb0.2Ta0.2C

引用

Journal of Materials Science & Technology 2019年第8期35卷 1700-1705页

作者： Heng Chen Huimin Xiang Fu-Zhi Dai Jiachen Liu yiming lei Jie Zhang Yanchun Zhou Science and Technology on Advanced Functional Composite Laboratory Aerospace Research Institute of Materials & Processing Technology Beijing 100076 China Key Laboratory of Advanced Ceramics and Machining Technology of Ministry of Education School of Materials Science and Engineering Tianjin University Tianjin 300072 China Shenyang National Laboratory for Materials Science Institute of Metal Research Chinese Academy of Sciences Shenyang 110016 China

Porous ultra-high temperature ceramics(UHTCs)are promising for ultrahigh-temperature thermal insulation ***,the main limitations for their applications are the high thermal conductivity and densification of porous structure at high *** order to overcome these obstacles,herein,porous high entropy(Zr(0.2)Hf(0.2)Ti(0.2)Nb(0.2)Ta(0.2))C was prepared by a simple method combing in-situ reaction and partial *** high entropy(Zr(0.2)Hf(0.2)Ti(0.2)Nb(0.2)Ta(0.2))C possesses homogeneous microstructure with grain size in the range of 100–500 nm and pore size in the range of 0.2–1μm,which exhibits high porosity of 80.99%,high compressive strength of 3.45 MPa,low room temperature thermal conductivity of 0.39 W·m^-1K^-1,low thermal diffusivity of 0.74 mm^2·s^-1and good high temperature *** combination of these properties renders porous high entropy(Zr(0.2)Hf(0.2)Ti(0.2)Nb(0.2)Ta(0.2))Cpromising as light-weight ultrahigh temperature thermal insulation materials.

关键词： Ultrahigh temperature ceramics (UHTCs) High entropy ceramics (Zr(0.2)Hf(0.2)Ti(0.2)Nb(0.2)Ta(0.2))C Thermal conductivity Porosity

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

Anisotropic shearing mechanism of Kangding slate:Experimental investigation and numerical analysis

引用

Journal of Rock Mechanics and Geotechnical Engineering 2024年第5期16卷 1487-1504页

作者： Ping Liu Quansheng Liu Penghai Deng Yucong Pan yiming lei Chenglei Du Xianqi Xie The Key Laboratory of Geotechnical and Structural Engineering Safety of Hubei Province School of Civil EngineeringWuhan UniversityWuhan430072China State Key Laboratory of Water Resources and Hydropower Engineering Science Wuhan UniversityWuhan430072China

The shear mechanical behavior is regarded as an essential factor affecting the stability of the surrounding rocks in underground *** shear strength and failure mechanisms of layered rock are significantly affected by the foliation *** shear tests were conducted on cubic slate samples with foliation angles of 0°,30°,45°,60°,and 90°.The effect of foliation angles on failure patterns,acoustic emission(AE)characteristics,and shear strength parameters was *** on AE characteristics,the slate failure process could be divided into four stages:quiet period,step-like increasing period,dramatic increasing period,and remission period.A new empirical expression of cohesion for layered rock was proposed,which was compared with linear and sinusoidal cohesion expressions based on the results made by this paper and previous *** comparative analysis demonstrated that the new expression has better prediction ability than other *** proposed empirical equation was used for direct shear simulations with the combined finite-discrete element method(FDEM),and it was found to align well with the experimental *** both computational efficiency and accuracy,it was recommended to use a shear rate of 0.01 m/s for FDEM to carry out direct shear *** balance the relationship between the number of elements and the simulation results in the direct shear simulations,the recommended element size is 1 mm.

关键词： Anisotropy Empirical expression of cohesion foliation angles Combined finite-discrete element method(FDEM) Shear rate Element size

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

Decomposing Complete 3-Uniform Hypergraphs into Cycles

引用

Journal of Mathematical Research with Applications 2016年第1期36卷 9-14页

作者： Guanru LI yiming lei Yuansheng YANG Jirimutu College of Mathematics Institute of Discrete Mathematics of Inner Mongolia University for the Nationalities School of Computer Science and Technology Dalian University of Technology

The problem of decomposing a complete 3-uniform hypergraph into Hamilton cycles was introduced by Bailey and Stevens using a generalization of Hamiltonian chain to uniform hypergraphs by Katona and Kierstead. Decomposing the complete 3-uniform hypergraphs K;into k-cycles（3 ≤ k < n） was then considered by Meszka and Rosa. This study investigates this problem using a difference pattern of combinatorics and shows that K;can be decomposed into 5-cycles for n ∈{5, 7, 10, 11, 16, 17, 20, 22, 26} using computer programming.

关键词： uniform hypergraph 5-cycle cycle decomposition

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

Prompt learning in computer vision: a survey

引用

Frontiers of Information Technology & Electronic Engineering 2024年第1期25卷 42-63页

作者： yiming lei Jingqi LI Zilong LI Yuan CAO Hongming SHAN Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200438China Institute of Science and Technology for Brain-Inspired Intelligence Fudan UniversityShanghai 200433China MOE Frontiers Center for Brain Science Fudan UniversityShanghai 200433China Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai 201210China

Prompt learning has attracted broad attention in computer vision since the large pre-trained visionlanguagemodels (VLMs) exploded. Based on the close relationship between vision and language information builtby VLM, prompt learning becomes a crucial technique in many important applications such as artificial intelligencegenerated content (AIGC). In this survey, we provide a progressive and comprehensive review of visual promptlearning as related to AIGC. We begin by introducing VLM, the foundation of visual prompt learning. Then, wereview the vision prompt learning methods and prompt-guided generative models, and discuss how to improve theefficiency of adapting AIGC models to specific downstream tasks. Finally, we provide some promising researchdirections concerning prompt learning.

关键词： Prompt learning Visual prompt tuning(VPT) Image generation Image classification Artificial intelligence generated content(AIGC)

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：