检索结果-南通市图书馆

Mixed Deep Reinforcement Learning Considering Discrete-continuous Hybrid Action Space for Smart Home Energy Management

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Modern Power Systems and Clean Energy 2022年第3期10卷 743-754页

作者： Chao Huang Hongcai Zhang Long Wang xiong Luo yonghua Song IEEE State Key Laboratory of Internet of Things for Smart City University of MacaoMacao S.A.R.China School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China Shunde Graduate School University of Science and Technology BeijingFoshan 528399China State Key Laboratory of Internet of Things for Smart City and Department of Electrical and Computer Engineering University of MacaoMacao S.A.R.China

This paper develops deep reinforcement learning(DRL)algorithms for optimizing the operation of home energy system which consists of photovoltaic(PV)panels,battery energy storage system,and household appliances.Model-free DRL algorithms can efficiently handle the difficulty of energy system modeling and uncertainty of PV generation.However,discretecontinuous hybrid action space of the considered home energy system challenges existing DRL algorithms for either discrete actions or continuous actions.Thus,a mixed deep reinforcement learning(MDRL)algorithm is proposed,which integrates deep Q-learning(DQL)algorithm and deep deterministic policy gradient(DDPG)algorithm.The DQL algorithm deals with discrete actions,while the DDPG algorithm handles continuous actions.The MDRL algorithm learns optimal strategy by trialand-error interactions with the environment.However,unsafe actions,which violate system constraints,can give rise to great cost.To handle such problem,a safe-MDRL algorithm is further proposed.Simulation studies demonstrate that the proposed MDRL algorithm can efficiently handle the challenge from discrete-continuous hybrid action space for home energy management.The proposed MDRL algorithm reduces the operation cost while maintaining the human thermal comfort by comparing with benchmark algorithms on the test dataset.Moreover,the safe-MDRL algorithm greatly reduces the loss of thermal comfort in the learning stage by the proposed MDRL algorithm.

关键词： Demand response deep reinforcement learning discrete-continuous action space home energy management safe reinforcement learning

Identification and application of nonlinear dynamic load models

在线全文

学校读者我要写书评

暂无评论

控制理论与应用（英文版） 2013年第2期11卷 173-179页

作者： Jing YANG Min WU Yong HE Yonghua XIONG School of Information Science and Engineering Central South University and Hunan Engineering Laboratory for Advanced Control and Intelligent Automation

An alternating least squares approach is developed in this paper to identify the exponential recovery dy- namic load model of wide-area power systems. The nonlinear optimization problem is decomposed to two linear least squares problems, and solved in an alternating way. Then, a new algorithm for numerical derivative calculation using dis- crete Fourier transform is proposed to attenuate the effect of noises in the process of parameter estimation. Based on the estimated dynamic load characteristics, the application on voltage stability is analyzed. Finally, numerical and laboratory examples are conducted to demonstrate the effectiveness of the orooosed methods.

关键词： Dynamic load models Parameter estimation Alternating least squares approach Numerical derivativetechnique Voltage stability

Modeling and Maximizing Angle Coverage in Visual Sensor Networks

在线全文

学校读者我要写书评

暂无评论

Modeling and Maximizing Angle Coverage in Visual Sensor Netw...

Efficacy of Shouzhangshen(Rhizoma Gymnadeniae Crassinervidis)extract against acute high altitude hypoxia-induced brain injury in mice

第37届中国控制会议

作者： Yonghua XIONG Manjie Lu Wei Chen School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Guizhou Tobacco Science Institute

Maintaining the quality of network coverage is a major concern in visual sensor networks. In this paper, we study the angle coverage problem in visual sensor networks, considering the target is very large, and each camera node can only monitor a portion of its perimeter. The goal of the proposed work is to schedule camera nodes to achieve maximum angle coverage in different period. Firstly, we establish a novel coverage model and formally prove that the problem is NP-hard in general.Next, we present a scheduling scheme based on greedy algorithm, to schedule camera nodes into disjoint cover sets working in turn.Then, we conclude that the approximate ratio of the proposed algorithm is k, theoretically, and the time complexity of the algorithm is O（n）. Finally, extensive simulations have been conducted to evaluate the performance of the proposed algorithm.

关键词： Visual sensor network angle coverage camera node scheduling greedy 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

Journal of Traditional Chinese Medicine 2021年第4期41卷 546-555页

作者： ZHANG Yongcang LIU Tonghua LIU Lan ZONG yonghua LI Yu xiong Hai WU Lili Medical College Tibet UniversityLhasa 850000China Department of Chemical Biology School of Pharmaceutical SciencesPeking UniversityBeijing 100191China Tibetan Traditional Medical College Lhasa 850000China Key Laboratory of Health Cultivation of the Ministry of Education Beijing University of Chinese MedicineBeijing 100029China College of Life Sciences Shandong Normal UniversityJinan 250014China

OBJECTIVE:To evaluate the protective effect of Shouzhangshen(Rhizoma Gymnadeniae Crassinervidis)extract against acute high altitude hypoxia-induced brain injury in mice.METHODS:Sixty C57BL/6J mice were selected and assigned to six groups(n=10):normal control group,low-pressure hypoxia group,positive control group(dexamethasone 500 mg/kg),and three groups treated with Shouzhangshen extract(250,500,and 750 mg/kg,respectively).The Morris water maze test was performed to evaluate alterations in spatial learning and memory deficits.Nissl staining was performed to detect Nissl bodies and neuron damage.Hypoxia-inducible factor(HIF)-1α,interleukin(IL)-1β,tumor necrosis factor(TNF)-α,vascular endothelial growth factor(VEGF),and malondialdehyde(MDA)expression in brain tissue and serum,as well as superoxide dismutase(SOD)and glutathione(GSH)activity in brain tissues were measured by enzyme-linked immunosorbent assays,quantitative real-time-polymerase chain reaction and western blots.RESULTS:The Morris water maze test results showed that Shouzhangshen extract can significantly reduce the latency and swimming distance to escape onto a visible platform,increase neuron density and hierarchy and the number of pyramidal neurons,and decrease the expression of HIF-1α,IL-1β,TNF-α,and VEGF mRNAs and proteins in both brain tissue and serum(P0.05).CONCLUSION:Our findings suggest that Shouzhangshen extract may have a significant effect on acute high altitude hypoxia-induced brain injury in mice.

关键词： altitude sickness neuro-protective effect Hypoxia-Inducible Factor 1 alpha Subunit interleukin-1beta tumor necrosis factor-alpha vascular endothelial growth factors Shouzhangshen

Efficient generation of zebrafish maternal-zygotic mutants through transplantation of ectopically induced and Cas9/gRNA targeted primordial germ cells

在线全文

学校读者我要写书评

暂无评论

Journal of Genetics and Genomics 2020年第1期47卷 37-47页

作者： Fenghua Zhang Xianmei Li Mudan He Ding Ye Feng xiong Golpour Amin Zuoyan Zhu yonghua Sun State Key Laboratory of Freshwater Ecology and Biotechnology Innovation Academy for Seed DesignInstitute of HydrobiologyChinese Academy of SciencesWuhan430072China College o f Advanced Agricultural Sciences University of Chinese Academy of SciencesBeijing100049China

The clustered regularly interspaced short palindromic repeats(CRISPR)/Cas9 technology has been widely utilized for knocking out genes involved in various biological processes in zebrafish. Despite this technology is efficient for generating different mutations, one of the main drawbacks is low survival rate during embryogenesis when knocking out some embryonic lethal genes. To overcome this problem, we developed a novel strategy using a combination of CRISPR/Cas9 mediated gene knockout with primordial germ cell(PGC) transplantation(PGCT) to facilitate and speed up the process of zebrafish mutant generation, particularly for embryonic lethal genes. Firstly, we optimized the procedure for CRISPR/Cas9 targeted PGCT by increasing the efficiencies of genome mutation in PGCs and induction of PGC fates in donor embryos for PGCT. Secondly, the optimized CRISPR/Cas9 targeted PGCT was utilized for generation of maternal-zygotic(MZ) mutants of tcf7l1a(gene essential for head development), pou5f3(gene essential for zygotic genome activation) and chd(gene essential for dorsal development) at F1 generation with relatively high efficiency. Finally, we revealed some novel phenotypes in MZ mutants of tcf7l1 a and chd, as MZtcf7l1 a showed elevated neural crest development while MZchd had much severer ventralization than its zygotic counterparts. Therefore, this study presents an efficient and powerful method for generating MZ mutants of embryonic lethal genes in zebrafish. It is also feasible to speed up the genome editing in commercial fishes by utilizing a similar approach by surrogate production of CRISPR/Cas9 targeted germ cells.

关键词： Zebrafish CRISPR/Cas9 Primordial germ cells Transplantation Maternal zygotic mutant

复杂地层深基坑施工对邻近综合管廊影响的控制措施与评价

在线全文

学校读者我要写书评

暂无评论

市政技术 2023年第5期41卷 156-163页

作者：熊永华武汉市政工程设计研究院有限责任公司湖北武汉430023

针对深厚淤泥质软土区、高承压水等不利条件下的深基坑开挖对邻近综合管廊安全影响问题,以邻近武九线综合管廊的深基坑施工为背景,采用MIDAS/GTS NX软件构建了三维数值分析模型,基于修正的摩尔-库伦本构模型,模拟了基坑开挖过程对综合... 详细信息

针对深厚淤泥质软土区、高承压水等不利条件下的深基坑开挖对邻近综合管廊安全影响问题,以邻近武九线综合管廊的深基坑施工为背景,采用MIDAS/GTS NX软件构建了三维数值分析模型,基于修正的摩尔-库伦本构模型,模拟了基坑开挖过程对综合管廊的影响。研究结果表明:基坑开挖引起的围护结构变形和管廊结构变形均在规范限值以内;此外,与基坑开挖前相比,管廊结构轴力、剪力和弯矩最大值均有所上升,但变化较小,满足结构安全使用要求。因此,认为采用“围护桩+内支撑+TRD水泥土连续墙止水帷幕”基坑支护设计方案可行。该研究成果可为类似工程安全评估提供借鉴。

关键词：基坑施工综合管廊安全评估数值模拟

Design and Application of a Web-based Comprehensive Evaluation and Decision Support System for Tobacco Cultivation Process

在线全文

学校读者我要写书评

暂无评论

Design and Application of a Web-based Comprehensive Evaluati...

“社会性科学议题与建模教学”模式的缘起与内涵解读

第37届中国控制会议

作者： Gong Chen Yonghua XIONG Wei Chen Hao Zhou School of Automation China University of Geoscience Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Guizhou Tobacco Science Institute

The evaluation and decision support system are widely used in agriculture with the development of information technology. In this paper, a Web-based comprehensive evaluation and decision support system（WCEDSS） is designed for flue-cured tobacco cultivation process. Using the artificial neural networks and some image processing methods, WCEDSS can predict various indicators of tobacco such as yield and flue-cured score, or give decisions at different stages of tobacco cultivation. As the system is developed by the Browser/Server（B/S） architecture, it is possible to make full use of the Internet resources and to facilitate users at any place with access to the Internet. Test results indicates that WCEDSS can achieve good performance. With other auxiliary functions, the system shows potential and extensive practicality in agricultural information management and guidance.

关键词： tobacco Browser/Server architecture evaluate decision support

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

生物学教学 2024年第1期49卷 5-7页

作者：廖玮宁熊永华华中师范大学生命科学学院武汉430079 华中师范大学第一附属中学武汉430223

社会性科学议题是国际科学教育研究的热点,研究表明社会性科学议题教学能有效发展学生的科学素养,但在实施中出现了忽视科学概念学习的现象,“社会性科学议题与建模教学”模式便应运而生。本文对这一模式的缘起和内涵进行了解读。

关键词：社会性科学议题建模教学科学素养

ALGORITHM OF PRETREATMENT ON AUTOMOBILE BODY POINT CLOUD

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Mechanical Engineering 2007年第4期20卷 71-74页

作者： GAO Feng ZHOU Yu DU Farong QU Weiwei xiong yonghua Department of Automobile Engineering Beihang University Beijing 100083 China

As point cloud of one whole vehicle body has the traits of large geometric dimension, huge data and rigorous reverse precision, one pretreatment algorithm on automobile body point cloud is put forward. The basic idea of the registration algorithm based on the skeleton points is to construct the skeleton points of the whole vehicle model and the mark points of the separate point cloud, to search the mapped relationship between skeleton points and mark points using congruence triangle method and to match the whole vehicle point cloud using the improved iterative closed point （ICP） algorithm. The data reduction algorithm, based on average square root of distance, condenses data by three steps, computing datasets＇ average square root of distance in sampling cube grid, sorting order according to the value computed from the first step, choosing sampling percentage. The accuracy of the two algorithms above is proved by a registration and reduction example of whole vehicle point cloud of a certain light truck.

关键词： Reverse engineering Point cloud registration Skeleton point Iterative closed point（ICP） Data reduction