检索结果-南通市图书馆

基于CNN-STLSTM-CNN模型的有效波高预测

在线全文

学校读者我要写书评

暂无评论

海洋环境科学 2024年第3期43卷 417-429页

作者：王丽娜齐致远张红春董昌明南京信息工程大学人工智能学院(未来技术学院) 江苏南京210044 南方海洋科学与工程广东省实验室(珠海) 广东珠海519080 南京信息工程大学长望学院江苏南京210044 南京信息工程大学海洋科学学院江苏南京210044

有效波高(significant wave height,SWH)是海洋的重要参数之一,对其的精确预测对渔业发展、海上交通和海洋生态系统具有重要意义。为了提高有效波高的预测精度,本文提出了一种基于卷积神经网络-时空长短时记忆神经网络-卷积神经网络(con... 详细信息

有效波高(significant wave height,SWH)是海洋的重要参数之一,对其的精确预测对渔业发展、海上交通和海洋生态系统具有重要意义。为了提高有效波高的预测精度,本文提出了一种基于卷积神经网络-时空长短时记忆神经网络-卷积神经网络(convolutional neural network-spatiotemporal long short-term memory-convolutional neural network,CNN-STLSTM-CNN)的有效波高预测模型。该模型由编码器(Encoder)、解释器(Translator)和解码器(Decoder)构成。Encoder通过卷积神经网络提取SWH数据的空间特征,Translator通过时空长短时记忆神经网络(spatiotemporallongshort-term memory,STLSTM)提取SWH数据的空间特征在时间上的变化特性,Decoder通过卷积神经网络的转置卷积模块重建预测结果。对东海和南海海域的二维有效波高数据进行建模,实验结果表明CNNSTLSTM-CNN模型的均方根误差(root mean squared error,RMSE)、平均绝对误差(mean absolute error,MAE)、均方根误差均值(mean of root mean squared error,M_RMSE)和平均绝对误差均值(mean of mean absolute error,M_MAE)等指标值均低于已有的方法,验证了CNN-STLSTM-CNN模型的有效性。

关键词：有效波高卷积神经网络时空长短时记忆神经网络转置卷积

在线全文

学校读者我要写书评

暂无评论

父母控制同伴关系与初中生攻击行为的关系

中国学校卫生 2024年第4期45卷 530-534页

作者：韩文耕戚志远赵继利倪虹程耀慧韩慧蚌埠医科大学公共卫生学院安徽233030

目的了解父母控制水平、同伴关系和初中生攻击行为的关系,为预防青少年攻击行为的发生提供理论依据。方法于2022年6—7月,采用方便整群随机抽样方法,选取安徽省宿州市、宣城市6所初中学校中初一至初三的2564名学生为研究对象,采用父母... 详细信息

目的了解父母控制水平、同伴关系和初中生攻击行为的关系,为预防青少年攻击行为的发生提供理论依据。方法于2022年6—7月,采用方便整群随机抽样方法,选取安徽省宿州市、宣城市6所初中学校中初一至初三的2564名学生为研究对象,采用父母控制问卷、Buss和Perry攻击问卷中文版和初中生同伴关系量表进行问卷调查。结果男生在父母控制、父亲心理控制、母亲心理控制、父亲行为控制、母亲行为控制中得分(185.31±27.49,21.65±7.43,21.77±8.18,69.50±11.41,72.39±11.53)均高于女生(178.21±25.13,20.08±7.09,20.61±7.62,66.56±11.14,70.95±11.84)(t值分别为8.63,5.47,3.70,6.60,3.12),女生的同伴关系得分(48.41±11.26)高于男生(47.13±10.84)(t=2.95);初一年级学生在父母控制、父亲心理控制、母亲心理控制、父亲行为控制、同伴关系和攻击行为维度的得分(184.67±27.18,21.83±7.29,22.15±8.07,68.81±10.95,50.21±9.57,80.23±17.66)均高于初二(180.98±25.46,20.16±7.82,20.21±7.55,68.29±11.69,45.47±11.67,74.08±17.70)和初三(179.21±26.79,20.53±7.22,21.17±8.06,66.81±11.39,47.54±11.43,75.75±16.29)年级(F值分别为9.44,12.87,13.61,6.84,42.85,30.40)(P值均<0.01)。父母控制、同伴关系得分均与攻击行为得分呈正相关(r值分别为0.22,0.47,P值均<0.01)。同伴关系在父母控制和攻击行为之间起部分中介作用,中介效应值为0.04,占父母控制对攻击行为总效应的26.39%。结论父母控制高及同伴关系差与攻击行为水平均呈正相关。应通过建立良好的家庭教养模式,抵制校园暴力、维护良好社会准则等方式改善初中生的同伴关系,以减少攻击行为的发生。

关键词：人际关系攻击精神卫生法定监护人学生

Power Control Based on Microcomputer for Small Wind Power System

在线全文

学校读者我要写书评

暂无评论

Power Control Based on Microcomputer for Small Wind Power Sy...

Combat data shift in few-shot learning with knowledge graph

第25届中国控制与决策会议

作者： qi zhiyuan Wang Liang College of Electronic Information Engineering Inner Mongolia University

ISBN: (纸本)9781467355339

A power controller is designed to improve the efficiency and enhance the reliability for small wind power system （SWPS） in this paper. A Buck converter is employed as main power circuit and a single-chip microcomputer C8051F410 is used as control unit in the designed power controller. The detailed introduction of the controller including the hardware circuits and the software flow of the related code are given. The performance of the controller is tested on the experimental platform for SWPS, and test results indicate that the proposed controller can automatically regulates the working modes of the wind turbine as well the battery at different condition, so that the optimal and reliable operation of the SWPS is obtained. The Results obtained in this paper provide practical guidance to design power controller for SWPS in engineering.

关键词： Small wind power system Power control Buck converter Microcontroller

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2023年第1期17卷 101-111页

作者： Yongchun ZHU Fuzhen ZHUANG Xiangliang ZHANG zhiyuan qi Zhiping SHI Juan CAO qing HE Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China Institute of Artificial Intelligence Beihang UniversityBeijing 100191China Xiamen Institute of Data Intelligence Xiamen 361021China Computer Science and Engineering University of Notre DameIN 46556USA University of California San Diego La JollaCA 92093USA College of Information Engineering&Academy for Multidisciplinary Studies Capital Normal UniversityBeijing 100089China

Many few-shot learning approaches have been designed under the meta-learning framework, which learns from a variety of learning tasks and generalizes to new tasks. These meta-learning approaches achieve the expected performance in the scenario where all samples are drawn from the same distributions (i.i.d. observations). However, in real-world applications, few-shot learning paradigm often suffers from data shift, i.e., samples in different tasks, even in the same task, could be drawn from various data distributions. Most existing few-shot learning approaches are not designed with the consideration of data shift, and thus show downgraded performance when data distribution shifts. However, it is non-trivial to address the data shift problem in few-shot learning, due to the limited number of labeled samples in each task. Targeting at addressing this problem, we propose a novel metric-based meta-learning framework to extract task-specific representations and task-shared representations with the help of knowledge graph. The data shift within/between tasks can thus be combated by the combination of task-shared and task-specific representations. The proposed model is evaluated on popular benchmarks and two constructed new challenging datasets. The evaluation results demonstrate its remarkable performance.

关键词： few-shot data shift knowledge graph

Sine Wave Inverter of Small Wind Power Based on Genetic Algorithm Optimize BP Neural Network

在线全文

学校读者我要写书评

暂无评论

Sine Wave Inverter of Small Wind Power Based on Genetic Algo...

第36届中国控制会议

作者： zhiyuan qi Guochen Yu Xiaoyu Liu College of Electronic Information Engineering Inner Mongolia University

ISBN: (纸本)9781538629185

In order to improve the power supply quality of sine wave inverter for small wind power system,a control method that combines BP neural network（BPNN） with genetic algorithm（GA） is proposed in this *** BPNN is optimized by means of the GA to avoid the BPNN falling into local optimum value,and the optimized BPNN can better control the power output of the designed sine wave *** study is done under MATLAB,and the results show that the proposed method of the GA optimize the BPNN can make the inverter to produce better waveform quality as well as adaptability under variable loads and wind *** the sine wave inverters with the GA optimizing the BPNN can meet the application requirements of small wind power system.

关键词： Small wind power Sine wave inverter BP neural network Genetic algorithm

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

海上油气田智能完井应用前景分析

海洋石油 2024年第2期44卷 51-56页

作者：邱浩文敏于继飞齐致远侯泽宁马楠中海油研究总院有限责任公司北京100028

智能完井技术为解决油气田开发难题、提高海上油气井生产及管理效率提供了全新的解决思路,但对于智能完井系统功能认识不全面及应用场景不明确导致目前海上智能完井应用普及程度不高。为有效提升智能完井技术工程应用普及程度,通过梳理... 详细信息

智能完井技术为解决油气田开发难题、提高海上油气井生产及管理效率提供了全新的解决思路,但对于智能完井系统功能认识不全面及应用场景不明确导致目前海上智能完井应用普及程度不高。为有效提升智能完井技术工程应用普及程度,通过梳理智能完井系统所涵盖的所有单元模块,全面分析了智能完井系统所能实现的功能构成,从而构建了功能完善的典型油气井智能完井工程方案,然后结合目前海上油气田开发可能存在的技术难点,有针对性地设计了6种典型的海上智能完井技术应用前景。研究海上智能完井技术应用普及程度,对推动海上智能油气田建设进程具有重要意义。

关键词：海上油气田智能完井智能控制在线监测应用前景

基于Maix-Ⅱ Dock摄像头的货运移动机器人的设计与实现

在线全文

学校读者我要写书评

暂无评论

沈阳工程学院学报（自然科学版） 2024年第2期20卷 42-47页

作者：龚明徐涢基齐志远林依婷王燊炀南昌交通学院交通运输学院江西南昌330100 南昌大学先进制造学院江西南昌330031

针对两地快速、高效地运输货物的问题,设计了一种货运移动机器人。货运移动机器人由STM32F103RCT6主控板、Maix-Ⅱ Dock(M2 dock)摄像头、OLED屏幕和XL4001可调降压模块等组成。货运移动机器人从地图“GO!”红色区域出发,到达红色“STOP... 详细信息

针对两地快速、高效地运输货物的问题,设计了一种货运移动机器人。货运移动机器人由STM32F103RCT6主控板、Maix-Ⅱ Dock(M2 dock)摄像头、OLED屏幕和XL4001可调降压模块等组成。货运移动机器人从地图“GO!”红色区域出发,到达红色“STOP!”区域停车,途中不得撞到路线外红色长方体障碍物。货运移动机器人主控板使用STM32F103RCT6,图像识别部分使用M2 dock摄像头。M2 dock摄像头可以稳定高效地识别红色区域。通过测试,货运移动机器人可以快速且稳定地行驶完全程,并能够处理复杂的路况。该货运移动机器人的理论研究与设计能够应用于多种路况。

关键词： STM32F103RCT6 M2 dock摄像头移动机器人五路灰度传感器 IIC通信 XL4001可调降压模块

Conversion of confined metal@ZIF-8 structures to intermetallic nanoparticles supported on nitrogen-doped carbon for electrocatalysis

在线全文

学校读者我要写书评

暂无评论

Nano Research 2018年第6期11卷 3469-3479页

作者： zhiyuan qi Yuchen Pei Tian Wei Goh Zhaoyi Wang Xinle Li Mary Lowe Raghu V. Maligal-Ganesh Wenyu Huang Department of Chemistry Iowa State University Ames Iowa 50011 USA Ames Laboratory U.S. Department of Energy Ames Iowa 50011 USA Department of Chemistry Beijing Normal University Beijing 100875 China

We report a facile strategy to synthesize intermetallic nanoparticle （iNP） electrocatalysts via one-pot pyrolysis of a zeolitic imidazolate framework, ZIF-8, encapsulating precious metal nanoparticles （NPs）. ZIF-8 serves not only as precursor for N-doped carbon （NC）, but also as Zn source for the formation of intermetallic or alloy NPs with the encapsulated metals. The resulting sub-4 nm PtZn iNPs embedded in NC exhibit high sintering resistance up to 1,000℃. Importantly, the present methodology allows fine-tuning of both composition （e.g., PdZn and RhZn iNPs, as well as AuZn and RuZn alloy NPs） and size （2.4, 3.7, and 5.4 nm PtZn） of the as-formed bimetallic NPs. To the best of our knowledge, this is the first report of a metal-organic framework （MOF） with multiple functionalities, such as secondary metal source, carbon precursor, and size-regulating reagent, which promote the formation of iNPs. This work opens a new avenue for the synthesis of highly uniform and stable iNPs.

关键词： intermetallic compounds cage confinement pyrolysis electrocatalysis sintering resistance

Crystallization of RE_(2)(OH)_(2)CO_(3)SO_(4)·nH_(2)O as a new family of layered hydroxides(RE=Gd-Lu lanthanides and Y),derivation of RE_(2)O_(2)SO_(4),photoluminescence and optical thermometry

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

Journal of Rare Earths 2024年第8期42卷 1496-1506,I0003页

作者： Fan Li Zhenqi Song zhiyuan Pan Sihan Feng qi Zhu Ji-Guang Li Key Laboratory for Anisotropy and Texture of Materials(Ministry of Education) School of Materials Science and EngineeringNortheastern UniversityShenyang110819China Research Center for Functional Materials National Institute for Materials ScienceTSsukuboaIbaraki3050044Japan

Layered rare-earth hydroxides(LREHs) draw wide research interest because of their peculiar crystal structure,rich interlayer chemistry and abundant functionality of the RE element,but are limited to the two categories of RE_(2)(OH)_(5)A·nH_(2)O(A:typical of Cl^(-)or NO_(3)^(-)) and RE_(2)(OH)_(4)SO_(4)·nH_(2)*** the other hand,rare-earth oxysulfates(RE_(2)O_(2)SO_(4)) have attracted attention due to their properties of large-capacity oxygen storage,low-temperature magnetism and luminescence,but their preparation procedure mostly involves toxic SO_(x) gases and/or complicated *** this work,RE_(2)(OH)_(2)CO_(3)SO_(4)·nH_(2)O as a new family of LREHs(RE=Gd-Lu lanthanides and Y) were produced via hydrothermal reaction,from which phase-pure RE_(2)O_(2)SO_(4) was derived via subsequent annealing at 800℃ in air without the involvement of SO_(x),The compounds were thoroughly characterized to reveal the intrinsic influence of lanthanide contraction(RE^(3+) radius) on crystal structure,thermal behavior(dehydroxylation/decarbonation/desulfurization),vibrational property and crystallite *** analyzing the photoluminescence of Eu^(3+) and Sm^(3+)in the Gd_(2)O_(2)SO_(4) typical host it is found that the 617 nm(Eu^(3+),λ_(ex)=275 nm) and 608 nm(Sm^(3+),λ_(ex)=407 nm) main emissions can retain as high as ^(7)9.6% and 85.5%of their room-temperature intensities at 423 K,with activation energies of ~0.19 and 0.21 eV for thermal quenching,*** also indicates that both the phosphors have the potential for optical temperature sensing via the fluorescence intensity ratio(FIR) technology,whose maximum relative sensitivity reaches -2.70%/K for Eu^(3+)and 1.73%/K for Sm^(3+) at 298 K.

关键词： Layered hydroxide RE_(2)O_(2)SO_(4) Luminescence Optical temperature sensing Rare earths