期刊文献+
共找到4,767篇文章
< 1 2 239 >
每页显示 20 50 100
Deep Synchronization Control of Grid-Forming Converters:A Reinforcement Learning Approach
1
作者 Zhuorui Wu Meng Zhang +2 位作者 Bo Fan Yang Shi Xiaohong Guan 《IEEE/CAA Journal of Automatica Sinica》 2025年第1期273-275,共3页
Dear Editor,This letter proposes a deep synchronization control(DSC) method to synchronize grid-forming converters with power grids. The method involves constructing a novel controller for grid-forming converters base... Dear Editor,This letter proposes a deep synchronization control(DSC) method to synchronize grid-forming converters with power grids. The method involves constructing a novel controller for grid-forming converters based on the stable deep dynamics model. To enhance the performance of the controller, the dynamics model is optimized within the deep reinforcement learning(DRL) framework. Simulation results verify that the proposed method can reduce frequency deviation and improve active power responses. 展开更多
关键词 reduce frequency deviation enhance performance stable deep dynamics model improve active power responses deep reinforcement learning drl dynamics model deep synchronization control dsc deep synchronization control
在线阅读 下载PDF
Researches on the PAM/Cr^3+ Gel for Deep Profile Control 被引量:1
2
作者 ChangXuejun LiuXuejun +1 位作者 WangQunyi GaoShusheng 《Petroleum Science》 SCIE CAS CSCD 2004年第1期65-69,共5页
The profile control hard-gel is composed of polyarylamide (5-6g/L), whose molecular weight is 4,000,000 - 7,000,000 and hydrolysis degree is 17.6%, and cross-linking oxidation-reduction agent (Na2Cr2O7 + NH4Cl), with ... The profile control hard-gel is composed of polyarylamide (5-6g/L), whose molecular weight is 4,000,000 - 7,000,000 and hydrolysis degree is 17.6%, and cross-linking oxidation-reduction agent (Na2Cr2O7 + NH4Cl), with an delayed organic acid crosslinker which contains lactic acid/propionic acid/ethanoic acid and ethylene glycol. After research of the influence factors, such as pH, temperature, salinity and the dosage of delayed crosslinker, the optimum condition(pH 5.2, temperature 55℃, salinity < 7g/L) was found. Gelation time (12-144h) can be controlled by adjusting the dosage of the delayed crosslinker. Deep profile control experiments are carried out on heterogeneous models, which contains three serial high permeable and low permeable cores arranged in a parallel. After water flooding (total recovery, 24.3%), the first, second and third high-permeable cores each are sealed in turn by the profile control agent, and the total displacement recovery increases to 46.8%, 62.2% and 69.1% respectively. So, the greater the sealed depth, the larger the enhancing recovery will be. Finally, the oil displacement mechanisms of deep profile control are discussed. 展开更多
关键词 deep profile control hard-gel delayed cross-linker gelation time heterogeneous model sealed depth
原文传递
PREDICTION AND CONTROL OF ROCKBURST DURING DEEP EXCAVATION OF A GOLD MINE IN CHINA 被引量:2
3
作者 Zhang Guang,Chen Jingxi,Hu Bin (Institute of Rock and Soil Mechanics,The Chinese Academy of Sciences, Wuhan 430071 China) 《岩石力学与工程学报》 EI CAS CSCD 北大核心 2003年第10期1607-1612,共6页
The studies of prediction and control of rockburst are presented during deep excavation in a gold mine in China. Firstly,the stress-relief method is used to obtain a vast amount of data about initial geostress. Second... The studies of prediction and control of rockburst are presented during deep excavation in a gold mine in China. Firstly,the stress-relief method is used to obtain a vast amount of data about initial geostress. Secondly,3D FEM analyses of large scale are performed to find out the law of geostress distribution at various excavation levels of the mining area. At the same time,as an equally important measure,six typical kinds of rock blocks are sampled for the experimental study of rockburst tendency. According to the synthesized results of the theoretical and testing results,the methods of brittleness coefficient,brittle index and stress,and so on,are adopted. Finally,the evaluation on the possibility of rockbursts is given that may take place at the deep mining area and some effective measures are put forward to prevent and control the rockburst. 展开更多
关键词 中国 金矿 开挖 岩爆预报 控制
在线阅读 下载PDF
Double-directional control bolt support technology and engineering application at large span Y-type intersections in deep coal mines 被引量:13
4
作者 GUO, Zhibiao SHI, Jianjun +2 位作者 WANG, Jiong CAI, Feng WANG, Fuqiang 《Mining Science and Technology》 EI CAS 2010年第2期254-259,共6页
Under deep and complex geological conditions,severe deformation occurs at intersection points of Y-type roadways with large cross sections during engineering projects in coal mines,especially at junction arches.Based ... Under deep and complex geological conditions,severe deformation occurs at intersection points of Y-type roadways with large cross sections during engineering projects in coal mines,especially at junction arches.Based on in-situ investigations and theoretical studies,we have summarized typical forms of destruction and identified high stress and unrestricted support at both sides of junction arch as its main causes.In this study,we also presented double-directional control bolt support technology for a large Y-type span intersection,applied to deep intersection engineering in the Jiahe Coal Mine,which has proved effective. 展开更多
关键词 Y-type intersection double-directional control bolt support deep coal mines
在线阅读 下载PDF
Tunnel Surrounding Rock Deformation Characteristics and Control in Deep Coal Mining 被引量:2
5
作者 Zhiqiang Zhao Housheng Jia +1 位作者 Bo Peng Yangyang Dong 《Geomaterials》 2013年第1期24-27,共4页
In order to study the failure characteristics and control method of deep tunnel surrounding rock, based on the stress test, the structure and stress state of the main transportation tunnel surrounding rock in Mine Zha... In order to study the failure characteristics and control method of deep tunnel surrounding rock, based on the stress test, the structure and stress state of the main transportation tunnel surrounding rock in Mine Zhaogezhuang level 14 was analyzed, and it shows that the surrounding rock is exposed to an interphase hard and soft disadvantageous structure state and complex high stress repeated addition area;Through the theoretical analysis and the statistical data, the relation between the tunnel stress transformation and the surrounding rock deformation was proposed;Through the numerical simulation of the tunnel surrounding rock failure process with the help of RFPA procedure, the results show that the damage of the transportation tunnel level 14 mainly occurs in the bottom and the two coal ribs, and the failure process is spreading from the bottom to the two coal ribs, and the effect of the surrounding rock deformation control is obvious by using the way of 2.5 m anchor with 1.0 m grouting strengthening. 展开更多
关键词 deep TUNNEL SURROUNDING ROCK control Stress TRANSFORMATION DEFORMATION Characteristics
暂未订购
Adaptability Analysis of Deep Profile Control and Flooding Formula System in Water Injection Oilfield
6
作者 GUO Lina 《外文科技期刊数据库(文摘版)工程技术》 2021年第12期867-870,共6页
Affected by reservoir heterogeneity, there is often a serious problem of water channeling in the late stage of water injection oilfield development. Conventional water injection adjustment is difficult to further impr... Affected by reservoir heterogeneity, there is often a serious problem of water channeling in the late stage of water injection oilfield development. Conventional water injection adjustment is difficult to further improve water drive recovery. It is necessary to adopt deep profile control and displacement technology to block water channeling channel and improve water drive efficiency.Based on the analysis of deep profile control and flooding mechanism, this paper analyzes the composition, technical indexes and adaptive conditions of seven types of profile control and flooding agent formula system, and takes block J as an example to analyze the deep adjustment effect in detail, including profile control and flooding agent system, injection volume and changes of various indexes after profile control and flooding. The effect of increasing oil and controlling water is remarkable, with an efficiency of 36.148 million yuan and an input-output ratio of 1:2.81,To achieve the purpose of cost reduction and efficiency increase under low oil prices, the achievements and understanding can provide reference experience for peers. 展开更多
关键词 water injection oilfield deep profile control and flooding formulation system adaptability analysis
原文传递
Research and Application of Deep Profile Control and Flooding Technology in Water Flooding Reservoir
7
作者 ZHANGMengmeng 《外文科技期刊数据库(文摘版)工程技术》 2022年第5期173-177,共5页
Affected by factors such as rapid change of sedimentary microfacies in plane, serious reservoir heterogeneity in vertical direction and perfection of injection-production well pattern, low utilization rate of injected... Affected by factors such as rapid change of sedimentary microfacies in plane, serious reservoir heterogeneity in vertical direction and perfection of injection-production well pattern, low utilization rate of injected water exists in water injection development of block S, which results in serious water flooding, low water flooding efficiency and high dispersion of remaining oil, as well as poor downhole technical conditions, so it is difficult to further improve oil recovery by conventional water injection adjustment. Including chemical agent system optimization design, pilot test well group optimization, injection volume design, development index prediction, etc. Five well groups were implemented on site. Two wells were sidetracked in the old wells, with an average daily oil production of 43 tons, comprehensive water cut of 4.2%, cumulative oil production of 25,200 tons in stages, improvement in water injection pressure, waterline propulsion speed, formation water absorption status, etc. The purpose of cost reduction and efficiency enhancement was achieved under low oil price. The results and understanding provided reference experience for similar reservoirs. 展开更多
关键词 water-injected reservoir serious water channeling deep profile control and flooding technical res
原文传递
Path Following Control of A Deep-Sea Manned Submersible Based upon NTSM 被引量:7
8
作者 马岭 崔维成 《China Ocean Engineering》 SCIE EI 2005年第4期625-636,共12页
In this paper, a robust path following control law is proposed for a deep-sea manned submersible maneuvering along a predeterminated path. Developed in China, the submersible is underactuated in the horizontal plane i... In this paper, a robust path following control law is proposed for a deep-sea manned submersible maneuvering along a predeterminated path. Developed in China, the submersible is underactuated in the horizontal plane in that it is actuated by two perpendicular thrusts in this plane. The advanced non-singular terminal sliding mode (NTSM) is implemented for the design of the path following controller, which can ensure the convergence of the motion system in finite time and improve its robustness against parametric uncertainties and environmental disturbances. In the process of controller design, the close-loop stability is considered and proved by Lyapunov' s stability theory. With the experimental data, numerical simulations are provided to verify the control law for path following of the deep-sea manned submersible. 展开更多
关键词 path following deep-sea manned submersible terminal sliding mode control ROBUSTNESS
在线阅读 下载PDF
KEY TECHNOLOGY IN INTELLIGENT CONTROL FOR SHEET METAL DEEP DRAWING
9
作者 罗亚军 赵军 +1 位作者 何丹农 张永清 《Journal of Shanghai Jiaotong university(Science)》 EI 2001年第1期27-30,共4页
Intellectualization of sheet metal in deep drawing is a new combined technology, which is concerned with control science and computer science and sheet metal forming theory. The intelligent control system for sheet me... Intellectualization of sheet metal in deep drawing is a new combined technology, which is concerned with control science and computer science and sheet metal forming theory. The intelligent control system for sheet metal deep drawing consists of four fundamental factors: real time measurement, identification, prediction and control. Real time identification of material properties and friction coefficient is the most important factor in the whole system. An artificial neural network model for identification of the material properties and friction coefficient was established according to deep drawing characteristics and more automation. The identification of the material properties and friction coefficient was realized. 展开更多
关键词 sheet metal forming intelligent control deep drawing neural network real time identification
在线阅读 下载PDF
Mechanism and practice of rock control in deep large span cut holes 被引量:2
10
作者 Li Chong Xu Jinhai +2 位作者 Fu Chunsheng Wu Rui Ma Qianqian 《Mining Science and Technology》 EI CAS 2011年第6期891-896,共6页
Deep large span cut holes are difficult to stabilize. The 7801 cut hole in the Lu'an Wuyang Mine was used as this project's background. The main factors affecting large span cut hole stability are analyzed. Pr... Deep large span cut holes are difficult to stabilize. The 7801 cut hole in the Lu'an Wuyang Mine was used as this project's background. The main factors affecting large span cut hole stability are analyzed. Pre- stressed bolting theory was used to design a roof control method for a large span roadway. By reducing the span and applying equal strength coordinated supports the rock could be stabilized. The control prin- ciples and methods are given herein along with the analysis. A double micro arch cross section roadway is defined and its use in solving the current problem is described. Beam arch theory was used to build a model of the double micro arch cross section roadway. A support reverse force model for the arch foot intersection was also derived. A support method based upon reducing the width of the large span in the cut hole is presented. These results show that the reduced span of the roadway roof plus the use of cable anchors and single supports gives an effective way to control the large span cut hole. On site monitoring showed that the reduced span support from the double micro arch cross section roadway design had a significant effect. The roadway surface displacement was small and harmful deformation of the cut hole was effectively controlled. This will ensure its long term stability. 展开更多
关键词 deep large span cut hole Double micro arch cross-section roadway Roof control by cross cut Equal strength coordinated support
在线阅读 下载PDF
Deformation Control of Deep Excavation Pit and Numerical Simulation with Finite Element Method
11
作者 Li Yun’an Engineering Faculty, China University of Geosciences, Wuhan 430074 School of Civil Engineering and Mechanics, Shanghai Jiaotong University, Shanghai 200030 Ge Xiurun School of Civil Engineering and Mechanics, Shanghai Jiaotong University, Shanghai 200030 Tang Huiming Engineering Faculty, China University of Geosciences, Wuhan 430074 《Journal of China University of Geosciences》 SCIE CSCD 2002年第3期278-288,共11页
The authors firstly introduce deformation control of deep excavation pit indetail, and then put forward new conceptions such as: effective coefficient of excavation pit,effective area, ineffective area and critical li... The authors firstly introduce deformation control of deep excavation pit indetail, and then put forward new conceptions such as: effective coefficient of excavation pit,effective area, ineffective area and critical line, and also put forward the referential criteria ofdeformation control. The System of Optimization Design with Deformation Control of Deep ExcavationPit and Numerical Simulation with Finite Element Method (SDCDEFEM) is also briefly introduced.Factors influencing deformation of excavation pit are analyzed by the system. The measured andsimulated data of maximum deformations (settlement, displacement and upheaval) and their positionsare analyzed and discussed. The statistic formula estimating maximum deformations and theirpositions was gained, and economical-effective measures of deformation control were brought forward. 展开更多
关键词 deep excavation pit deformation control finite element effectivecoefficient of excavation pit
在线阅读 下载PDF
基于PID搜索优化的CNN-LSTM-Attention铝电解槽电解温度预测方法研究 被引量:4
12
作者 尹刚 朱淼 +2 位作者 全鹏程 颜玥涵 刘期烈 《仪器仪表学报》 北大核心 2025年第1期324-337,共14页
铝电解生产环境恶劣,受电场、磁场、流场、温度场等多物理场耦合影响,导致铝电解生产过程故障频发。铝电解温度是影响铝电解槽寿命和运行状态的重要参数,但由于槽内温度很高且具有强烈腐蚀性,至今尚未找到有效的电解温度在线检测与预测... 铝电解生产环境恶劣,受电场、磁场、流场、温度场等多物理场耦合影响,导致铝电解生产过程故障频发。铝电解温度是影响铝电解槽寿命和运行状态的重要参数,但由于槽内温度很高且具有强烈腐蚀性,至今尚未找到有效的电解温度在线检测与预测方法。为了解决这一技术难题,通过理论分析结合现场实验验证,揭示了铝电解槽电解温度与其工艺参数间的密切相关性,并据此提出一种基于深度学习的铝电解槽电解温度预测模型。考虑到铝电解槽工艺参数的复杂性、非线性、高维度、时序性等特征,采用卷积神经网络(CNN)用于提取数据的高维特征,长短期记忆网络用于建模(LSTM),处理铝电解生产过程中的时序数据,引入了注意力机制(Attention),学习输入参数不同部分之间的关联性,同时根据输入数据的重要程度进行加权处理,并采用PID搜索优化算法(PSA)对CNN-LSTM-Attention模型的参数进行寻优,减少训练时间并提高模型的性能。最后经铝电解实际生产数据进行现场实验验证,结果表明:提出的温度预测模型相关指数(R~2)为0.963 7,均方根误差(RMSE)和平均绝对误差(MAE)分别为5.417 6和3.382 5,与单一模型算法、其他预测算法和不同优化算法对比验证表明,该模型的性能更佳,能够准确预测铝电解槽电解温度,实现了铝电解槽电解温度的在线检测。 展开更多
关键词 铝电解 算法 电解温度 深度学习 过程控制
原文传递
Deep Learning Based Hand Gesture Recognition and UAV Flight Controls 被引量:11
13
作者 Bin Hu Jiacun Wang 《International Journal of Automation and computing》 EI CSCD 2020年第1期17-29,共13页
Dynamic hand gesture recognition is a desired alternative means for human-computer interactions.This paper presents a hand gesture recognition system that is designed for the control of flights of unmanned aerial vehi... Dynamic hand gesture recognition is a desired alternative means for human-computer interactions.This paper presents a hand gesture recognition system that is designed for the control of flights of unmanned aerial vehicles(UAV).A data representation model that represents a dynamic gesture sequence by converting the 4-D spatiotemporal data to 2-D matrix and a 1-D array is introduced.To train the system to recognize designed gestures,skeleton data collected from a Leap Motion Controller are converted to two different data models.As many as 9124 samples of the training dataset,1938 samples of the testing dataset are created to train and test the proposed three deep learning neural networks,which are a 2-layer fully connected neural network,a 5-layer fully connected neural network and an 8-layer convolutional neural network.The static testing results show that the 2-layer fully connected neural network achieves an average accuracy of 96.7%on scaled datasets and 12.3%on non-scaled datasets.The 5-layer fully connected neural network achieves an average accuracy of 98.0%on scaled datasets and 89.1%on non-scaled datasets.The 8-layer convolutional neural network achieves an average accuracy of 89.6%on scaled datasets and 96.9%on non-scaled datasets.Testing on a drone-kit simulator and a real drone shows that this system is feasible for drone flight controls. 展开更多
关键词 deep learning neural networks hand gesture recognition Leap Motion controllers DRONES
原文传递
基于深度强化学习的温室环境协调控制系统设计 被引量:2
14
作者 左志宇 牟晋东 +4 位作者 毛罕平 韩绿化 胡建平 张晓东 金文帅 《农机化研究》 北大核心 2025年第5期22-27,共6页
针对温室温度、光照、水肥控制不协调导致的能耗高、水肥利用率低的问题,提出了基于深度强化学习的温室环境协调控制方法。以能耗、光合速率为优化目标,采用深度强化学习算法训练模型,对温度、光照调控目标值进行优化;通过分析不同营养... 针对温室温度、光照、水肥控制不协调导致的能耗高、水肥利用率低的问题,提出了基于深度强化学习的温室环境协调控制方法。以能耗、光合速率为优化目标,采用深度强化学习算法训练模型,对温度、光照调控目标值进行优化;通过分析不同营养液灌溉量对作物长势的影响,确定灌溉量动态调整方法;开发了基于深度强化学习的温室环境协调控制系统软硬件。实验结果表明:该方法能够协调控制温室温度、光照和水肥环境因子,与传统控制方法相比,环境调控能耗降低8.1%,营养液灌溉量降低7.9%,光合速率提升2.7%,能够为温室环境高效控制提供决策支持。 展开更多
关键词 温室 深度强化学习 协调控制 光合速率 能耗
在线阅读 下载PDF
价值可持续太空探索的系统工程--理念、架构与实践 被引量:1
15
作者 党炜 许鹏程 +11 位作者 郑作环 张竞菲 王大辉 陈英武 张雯 骆军委 李京苑 宋恒旭 肖依永 熊盛阳 林宝军 任羿 《中国工程科学》 北大核心 2025年第3期229-246,共18页
太空探索活动进入价值可持续发展模式阶段,航天大国率先降低全生命周期成本以驱动可持续发展,以价值引领的“无人区”式目标强化驱动力,自然需要解决在探索性目标牵引下太空探索的任务宏观和微观、系统内部和外部存在未知状态的认知自... 太空探索活动进入价值可持续发展模式阶段,航天大国率先降低全生命周期成本以驱动可持续发展,以价值引领的“无人区”式目标强化驱动力,自然需要解决在探索性目标牵引下太空探索的任务宏观和微观、系统内部和外部存在未知状态的认知自适应可持续这一重要理论问题。本文基于钱学森工程控制论、系统工程、系统科学等学术发展逻辑和相关理论原理,结合中国载人航天工程在空间科学与应用领域超过30年的工程实践,从源头和底层出发总结规律、融合理论/原理、演绎发展;以系统论、大成智慧学思想为指导,构建了价值可持续太空探索的系统工程(TSE)方法体系,涵盖人工智能技术驱动的“物穷其理、宏微交替”理念,基于数据‒知识‒逻辑的认知三维结构和总体基本原理及其架构,三重嵌套自适应控制原理结构及其数学物理基础要点,针对存在未知状态的系统韧性构建原理。载人航天工程空间科学应用任务在降低成本、科学探索方面的全面实践以及月球相关探索项目中的前瞻应用,表明TSE方法体系能够显著提升太空探索活动的价值可持续性,为推进钱学森“创建系统学”进程、新时期航天强国建设提供了方法论与工程实践支撑。 展开更多
关键词 太空探索 价值可持续 系统工程 自适应控制 深空探测 航天强国
在线阅读 下载PDF
人工智能在气象数据集研制中的应用综述 被引量:3
16
作者 李波 潘勐 孙越 《人民长江》 北大核心 2025年第1期88-96,共9页
长序列、高时空分辨率气象数据集对气象业务和科研具有重要意义,但是应用过程中存在数据质量低、空间分辨率不足等问题。随着人工智能的发展,机器学习以及深度学习算法在气象领域逐步开展应用。针对气象数据集研制中的技术难点问题,梳... 长序列、高时空分辨率气象数据集对气象业务和科研具有重要意义,但是应用过程中存在数据质量低、空间分辨率不足等问题。随着人工智能的发展,机器学习以及深度学习算法在气象领域逐步开展应用。针对气象数据集研制中的技术难点问题,梳理了人工智能技术的4个关键应用场景,即观测数据的质量控制、缺测数据的插补和重构、多源数据的融合以及低分辨网格数据的降尺度,对各类机器学习模型在上述场景应用中的优势和不足进行了综述,并采用文献计量方法对研究前沿及发展趋势进行了定量分析。研究表明:相比传统方法,人工智能算法在计算效率、结果准确性、应用灵活性等方面更具竞争力。建议从建立高质量训练数据集、加强多源数据和异构数据的应用以及探索基于气象数据物理机制的建模等多个方面,进一步推动人工智能在气象数据产品研制中的应用。 展开更多
关键词 气象数据集 人工智能 机器学习 深度学习 质量控制 降尺度
在线阅读 下载PDF
基于深度强化学习的孤岛微电网二次频率控制
17
作者 王力 蒋宇翔 +2 位作者 曾祥君 赵斌 李均昊 《中国电力》 北大核心 2025年第5期176-188,共13页
随着分布式电源大量接入微电网,可再生能源发电波动性和系统随机扰动给孤岛微电网频率稳定和运行控制带来了严重威胁。为此,提出了基于深度强化学习的二次频率控制方法,分析孤岛微电网下垂控制特性,提出了基于深度Q网络的二次频率控制... 随着分布式电源大量接入微电网,可再生能源发电波动性和系统随机扰动给孤岛微电网频率稳定和运行控制带来了严重威胁。为此,提出了基于深度强化学习的二次频率控制方法,分析孤岛微电网下垂控制特性,提出了基于深度Q网络的二次频率控制器结构。将频率偏差作为状态输入变量,依次完成深度Q网络算法中状态空间、动作空间、奖励函数、神经网络和超参数的设计,其中奖励函数兼顾了频率恢复和各分布式电源功率分配的目标,实现各智能体动作选择一致性;通过离线学习训练生成深度强化学习二次频率控制器。在Matlab/Simulink中搭建孤岛微电网仿真模型,设置多场景源荷扰动验证控制器性能。结果表明,与传统PID控制和基于Q学习算法控制器相比,该控制方法能够快速实现更稳定的二次频率控制,并能自适应协调各分布式电源按自身容量进行功率分配,确保系统稳定运行。 展开更多
关键词 深度强化学习 孤岛微电网 下垂控制 深度Q网络 二次频率控制 功率分配
在线阅读 下载PDF
中低渗透油藏纳米级树脂颗粒分散体的调驱性能
18
作者 钱志鸿 余晓玲 +3 位作者 王磊 朱杰 戴志鹏 张贵才 《油田化学》 北大核心 2025年第2期269-274,322,共7页
现有调驱体系在中低渗透油藏中存在堵得住走不远或走得远堵不住的技术难题。文章通过高温高压熔融法,利用表面活性剂作为分散稳定剂,制备了适用于中低渗油藏深部调驱的纳米级树脂颗粒分散体(OSR);以驱替压力为指标,利用岩心驱替实验系... 现有调驱体系在中低渗透油藏中存在堵得住走不远或走得远堵不住的技术难题。文章通过高温高压熔融法,利用表面活性剂作为分散稳定剂,制备了适用于中低渗油藏深部调驱的纳米级树脂颗粒分散体(OSR);以驱替压力为指标,利用岩心驱替实验系统评价了OSR在中低渗透多孔介质中的注入性能和封堵能力。研究结果表明,OSR具有良好的注入性能及封堵能力。随着OSR中树脂含量的增大,注入压力有所增加,但仍处于较低水平。当树脂含量为5%时,OSR在不同渗透率岩心中均具有良好的注入性能,注入1 PV的OSR,最大注入压力小于0.25 MPa。OSR对岩心的封堵率随着树脂含量的增大而提高,当树脂含量超过5%后封堵率变化不再显著。在固定树脂含量为5%的情况下,OSR对岩心的封堵率随岩心渗透率的降低而提高,OSR对渗透率小于30×10^(-3)μm^(2)岩心的封堵率达90%以上。此外,OSR在不同渗透率岩心中均表现出良好的耐冲刷性能。 展开更多
关键词 纳米树脂颗粒分散体 深部调驱 注入性能 封堵能力
在线阅读 下载PDF
基于深度强化学习的城市交通信号分层协同控制方法 被引量:1
19
作者 代亮 杜鹏飞 +1 位作者 黄自彬 杨朋博 《交通运输系统工程与信息》 北大核心 2025年第4期63-72,95,共11页
强化学习具有强大的自适应性和学习能力,能够根据环境变化和反馈信号不断调整策略和行为,实现持续优化,为城市交通信号控制提供新的技术手段。针对现有强化学习方法在交通信号协同控制中存在的智能体协作效率低下与控制区域划分机制缺... 强化学习具有强大的自适应性和学习能力,能够根据环境变化和反馈信号不断调整策略和行为,实现持续优化,为城市交通信号控制提供新的技术手段。针对现有强化学习方法在交通信号协同控制中存在的智能体协作效率低下与控制区域划分机制缺失问题,本文提出一种交通信号分层协同控制架构,通过构建交叉口智能体,进行状态空间与回报函数的关联性协同设计,并建立基于拥堵扩散的交通控制子区划分模型,实现动态划分交通控制子区。最后,构建子区智能体协调子区内部交叉口智能体,交叉口智能体根据子区智能体提供的全局性建议以及所在交叉口情况完成信号控制方案的优化,实现区域交通信号分层协同控制。仿真结果表明,与现有定时控制与强化学习方法相比,本文方法平均行程时间分别降低56.78%和29.23%。相比MPLight(Max Pressure Light)方法,平均速度提升7.21%,平均行程时间与停车次数分别减少22.62%和3.98%。此外,通过对比在不同规模以及拓扑结构路网的性能表现,验证本文方法在同质交叉口路网中具有一定可移植性。 展开更多
关键词 智能交通 交通信号控制 深度强化学习 多智能体 子区划分
在线阅读 下载PDF
飞跃探测全过程最优轨迹设计及实时控制方法
20
作者 于萍 王浩帆 +1 位作者 王泽国 付仁皓 《中国空间科学技术(中英文)》 北大核心 2025年第5期110-120,共11页
飞跃探测是一种新颖的地外天体探测任务形式,是上升任务和着陆任务的复合过程。研究了兼具飞跃全程轨迹优化及实时性的控制方法。在标称轨迹优化方面,不同于传统的分段优化方法,从飞跃全程优化的视角出发,提出了解析与偏微分方法结合的... 飞跃探测是一种新颖的地外天体探测任务形式,是上升任务和着陆任务的复合过程。研究了兼具飞跃全程轨迹优化及实时性的控制方法。在标称轨迹优化方面,不同于传统的分段优化方法,从飞跃全程优化的视角出发,提出了解析与偏微分方法结合的全程轨迹设计方法。在实时轨迹控制方面,基于预测校正的思想,应用Jacobian矩阵,通过综合修正轨迹参数和推力方向,来确保终端状态的实现。实时轨迹控制中应用的Jacobian矩阵的计算公式均为显示解析形式,且仿真表明仅需2次迭代即可满足控制需求,说明了算法的实时性。在相同的仿真条件下,与离线的全程凸优化算法相比燃料仅相差20 g,说明了其燃料优化性能与全程凸优化算法相当。该方法可以适用于常推力飞跃全程轨迹优化及实时轨迹控制,能够保证飞跃任务轨迹的全程最优性和控制的实时性。 展开更多
关键词 飞跃转移 轨迹设计 解析控制 深空探测器
在线阅读 下载PDF
上一页 1 2 239 下一页 到第
使用帮助 返回顶部