沙尘暴对Q/V高通量卫星通信系统的影响研究

为缓解通信卫星频谱资源紧张程度,高通量卫星通信系统正向Q/V频段发展,毫米波在空间传播过程中容易受到沙尘粒子的散射和吸收作用而产生衰减,论述了电磁波在沙尘天气中传播的衰减模型,通过MATLAB编程利用电磁波在沙质媒介中传播的衰减模型进行仿真计算,得到不同仰角、不同频率下电磁波衰减量对能见度的依赖关系,量化了高频电磁波在沙尘天气中的传输损耗,为未来国内Q/V高频段卫星通信系统建设提供理论依据。

基于Q学习的高超声速飞行器自抗扰控制研究

为实现高超声速飞行器姿态自抗扰控制的参数整定,提出一种模糊Q学习算法。首先,采用强化学习中的Q学习算法来实现姿态自抗扰控制参数的离线闭环快速自适应整定;然后,根据模糊控制的思路,将控制参数划分为不同区域,通过设定奖励,不断更新Q表;最后,将训练好的Q表用于飞行器的控制。仿真结果表明,相对于传统的线性自抗扰控制(linear active disturbance rejection control,LADRC)和滑模控制,基于Q学习的LADRC省去了人工调试参数的繁琐过程,且仍具有良好的跟踪效果。蒙特卡罗仿真测试结果验证了基于Q学习的LADRC的鲁棒性。

演化算法的DQN网络参数优化方法

为了解决DQN(Deep Q Network)在早期会出现盲目搜索、勘探利用不均并导致整个算法收敛过慢的问题,从探索前期有利于算法训练的有效信息获取与利用的角度出发,以差分演化(Differential Evolution)算法为例,提出了一种基于演化算法优化DQN网络参数以加快其收敛速度的方法(DE-DQN)。首先,将DQN的网络参数编码为演化个体;其次,分别采用“运行步长”和“平均回报”两种适应度函数评价方式;利用CartPole控制问题进行仿真对比,验证了两种评价方式的有效性。最后,实验结果表明,在智能体训练5 000代时所提出的改进算法,以“运行步长”为适应度函数时,在运行步长、平均回报和累计回报上分别提高了82.7%,18.1%和25.1%,并优于改进DQN算法;以“平均回报”为适应度函数时,在运行步长、平均回报和累计回报上分别提高了74.9%,18.5%和13.3%并优于改进DQN算法。这说明了DE-DQN算法相较于传统的DQN及其改进算法前期能获得更多有用信息,加快收敛速度。

Q/V频段电磁波在等离子体鞘套下的传输特性

高超声速飞行器再入地面时,由于飞行器表面等离子体电子密度分布不均匀,因此从背风面向天基中继卫星传输,可避开迎风面的高电子密度,并以Q/V频段为测控频段,经中继卫星转发至地面测控站。本文以波阻抗方法为基础,分析了Q/V频段在不同等离子体参数下的传输特性,并仿真了等离子体对Q/V频段天线波束指向的影响。结果表明:Q/V频段在等离子体中穿透性更好,可在更高的等离子体电子密度和碰撞频率下保持较低的衰减值。但Q/V频段下的天线波束指向偏差较大,随着频段的提高和入射角度的减小,偏差值逐渐减小。因此,应用Q/V频段,通过中继卫星转发实现实时通信,有利于缓解再入飞行器“黑障”现象。

基于Q学习的超超临界机组协调系统模型预测控制研究

超超临界机组具有多输入多输出、非线性严重、耦合强、时滞大的特点,其控制系统的设计要求是在保证系统稳定运行的同时,最大限度地提高机组的热效率和功率输出、快速准确地调节机组负荷、确保机组主蒸汽压力和温度在允许范围。通过调整系统模型以及阶段成本,进而获取最优策略。选取强化学习中的Q学习方法。将参数化模型预测控制作为Q学习中的一种新型函数逼近器,通过调整模型预测控制的参数来获取近似最优闭环控制策略以及最优的值函数。将该方法应用到1 GW超超临界锅炉汽轮机协调系统的控制中。在升负荷以及小范围升负荷变化情况下进行仿真。仿真结果表明,与传统模型预测控制方法对比,该方法可以在满足约束的情况下使系统输出值更加准确地到达设定值。

局部凸起在V形钝前缘模型中的降热特性研究

三维内转式进气道的唇口结构通常存在复杂的激波干扰及严酷的气动热载荷,严重威胁高超声速飞行器的性能与安全.在6.0马赫的高超声速流动中,以V形钝前缘模型为研究对象,设计了局部凸起的被动流动控制降热方案.采用数值模拟手段,首先研究了局部凸起方案的降热能力以及降热原理,然后初步优化了局部凸起的位置、高度以及宽度等关键设计参数,最后分析了优化后的局部凸起方案的攻角、侧滑角及马赫数的适用性.研究结果表明:上游凸起边缘形成的斜激波与主马赫反射结构形成的透射激波发生干扰,能够减弱其冲击壁面的强度,实现降热的目的;驻点凸起通过改变超声速射流的对撞角度,能够降低其对撞的强度,实现降热的目的.原始方案的降热能力约为37.75%,在对局部凸起的关键设计参数进行初步优化后,优化方案的降热能力将提升至44.60%.设计工况下的优化方案具有良好的攻角适用性,而高度可变的优化方案可以较好地适用于有侧滑角及高马赫数的流动.在研究范围内,高度可变的优化局部凸起方案的降热能力均高于20%.

双波长LD泵浦Nd^(3+)∶YAG免温控被动调Q激光器的研究

传统的固体激光器体积、重量大,功耗高,限制了其在空间受限设备中的应用。被动调Q的LD泵浦免温控固体激光器省去了复杂的温度控制装置,调Q机构简单,能够满足复杂温度环境的特殊应用场景的小型化、低功耗要求。提出了基于双波长LD泵浦实现宽温度范围免温控阈值自适应的1.06μm激光脉冲输出方法。基于Nd∶YAG晶体设计了角锥棱镜谐振腔,仿真分析了LD泵浦源到激光棒的面心距对热负载的影响,并确定4 mm的最佳面心距。数值分析了相同泵浦功率下-40~60℃温度范围内激光静态能量输出变化,以及不同初始透过率的可饱和吸收体对激光阈值脉宽的影响。计算结果表明在-37℃~60℃范围内,阈值脉宽都在200μs以下,阈值脉宽最低点达到了29.4μs。构建主波实时探测的阈值自适应调节装置并搭建实验系统,实验结果表明,在温度范围为-35~60℃时,阈值脉宽变化范围为40~180μs。采用激光腔体一体加工成型,应用轻量化的铝合金材料,实现工程化应用,体积83.5 mm×44 mm×29.5 mm,重量约为230 g。在23.8%初始透过率的饱和吸收体条件下实现单脉冲输出能量42 mJ,脉冲宽度5.2 ns。

A UAV-Assisted V2X Network Architecture with Separated Data Transmission and Network Control

With the explosive increasing number of connecting devices such as smart phones, vehicles,drones, and satellites in the wireless networks, how to manage and control such a huge number of networking nodes has become a great challenge. In this paper, we combine the advantages of centralized networks and distributed networks approaches for vehicular networks with the aid of Unmanned Aerial Vehicle(UAV), and propose a Center-controlled Multihop Wireless(CMW) networking scheme consisting of data transmission plane performed by vehicles and the network control plane implemented by the UAV.Besides, we jointly explore the advantages of Medium Access Control(MAC) protocols in the link layer and routing schemes in the network layer to facilitate the multi-hop data transmission for the ground vehicles.Particularly, the network control plane in the UAV can manage the whole network effectively via fully exploiting the acquired network topology information and traffic requests from each vehicle, and implements various kinds of control based on different traffic demands, which can enhance the networking flexibility and scalability significantly in vehicular networks.Simulation results validate the advantages of the proposed scheme compared with existing methods.

基于UHPLC-Q-Exactive Orbitrap/MS技术的血平片化学成分及指纹图谱的研究

目的基于超高效液相色谱-四级杆静电场轨道阱质谱(UHPLC-Q-Exactive Orbitrap/MS)技术快速分析鉴定血平片的化学成分,根据质谱鉴定结果与对照品比对建立指纹图谱方法并对血平片进行质量控制。方法采用XBridge BEH C18色谱柱(2.1 mm×150 mm,2.5μm),以乙腈-0.1%甲酸溶液为流动相梯度洗脱,质谱在正负离子切换扫描的模式下采集数据,结合数据库检索和对照品比对等方法分析血平片的主要化学成分。采用ODS C18色谱柱(4.6mm×250 mm,5μm),以甲醇-0.1%甲酸溶液为流动相梯度洗脱,分别使用紫外检测和蒸发光散射检测技术,建立血平片指纹图谱。结果从血平片中共鉴定出41种主要化学成分,并建立了血平片HPLC指纹图谱,13批样品的相似度均>0.90,标定了23个共有峰。结论该研究基本阐明了血平片的主要化学成分,建立的指纹图谱方法精密度、稳定性、重复性良好,结果准确可靠,可为血平片的质量控制提供客观有效的评价方法。

Evaluation of Malaria Transmission and Vector Control Strategies in the Dry Season in the Cotonou V Health Zone, Benin, West Africa

The anarchic urbanization of certain African cities favors the multiplication of the malaria parasite. Thus, the urgent mobilization of African cities is essential to combat this health risk. It is, therefore, with the objective of contributing to the investigation of problem areas that the present study evaluates malaria transmission and vector control strategies in the Cotonou V health zone in particular. This is a cross-sectional study taking into account four neighborhoods, including Wologuèdè, Sainte Rita, Gbèdjromèdé and the area around Etoile Rouge. Two nocturnal captures on voluntary humans and the method of spray were carried out in the dry season from December 2021 to February 2022. On the captured Anopheles, the ELISA Circum-Sporozoite Protein test was performed to determine the infectivity and calculate some transmission parameters. Finally, we conducted a survey using the second stage sampling method with one step to ask selected households about their knowledge of vector control methods, their use and the physical integrity of LLINs. We collected 2386 culicidae of which the majority was Culex quinquefasciatus. After the ELISA test, the 29 Anopheles tested, showed no infectivity, i.e. an EIR of 0 pi/h/n. In addition, 99% of the populations in the Cotonou V area use LLINs to protect themselves. However, coils, door and window screens, aerosol sprays, skin and household repellents, and periodic indoor spraying were used. Finally, the majority of nets observed had T1 tears, but there were also T2, T3 and T4 nets (P-value = 0.0). This study confirms that malaria transmission during the dry season in the Cotonou V health zone is almost negligible but not non-existent. Also, populations are exposed to the nuisance of Culex quinquefasciatus mosquitoes continuously throughout the year.

Research on V2G Control Strategy for EV Charge and Discharge Equipmen

In this paper, the fundamental structure of charge and discharge device of V2G is analyzed. As for three phase voltage source PWM converter’s control, this paper presents that the control strategy of direct power control PWM rectifier is adopted under charging operation and constant power control strategy is used under discharging operation. For bidirectional DC/DC converter control strategy, dual closed-loop control of external voltage loop and internal current loop is put into use. The whole system of charge and discharge device of V2G is modeled and simulated by using the toolbox of PSCAD/EMTDC. Two-way power energy and information interaction of electric vehicle and power grid has been realized, current harmonic on grid side is decreased, power factor and power quality are improved.

Fuzzy Controller Based 3Phase 4Wire Shunt Active Filter for Mitigation of Current Harmonics with Combined p-q and Id-Iq Control Strategies

As more and more variable frequency drives (VFDs), electronic ballasts, battery chargers, and static Var compensators are installed in facilities, the problems related to harmonics are expected to get worse. As a result Active power filter (APF) gains much more attention due to excellent harmonic compensation. But still the performance of the active filter seems to be in contradictions with different control strategies. This paper presents detailed analysis to compare and elevate the performance of two control strategies for ex-tracting reference currents of shunt active filters under balanced, un-balanced and non-sinusoidal conditions by using Fuzzy controller. The well known methods, instantaneous real active and reactive power method (p-q) and active and reactive current method (id-iq) are two control methods which are extensively used in active filters. Extensive Simulations are carried out with fuzzy controller for both p-q and Id-Iq methods for different voltage conditions and adequate results were presented. Simulation results validate the superior per-formance of active and reactive current control strategy (id-iq) with fuzzy controller over active and reactive power control strategy (p-q) with fuzzy controller.

基于48V轻混重型汽车技术发展与趋势

针对当前化石燃料短缺,全球环境恶化,对国家及各科研机构的应对策略进行了分析。通过介绍研究48 V轻混动力技术与控制策略,提出了48 V轻混动力源混动机理和能量管理策略,阐述各主机厂对48 V轻混系统的应用发展与趋势,得出该48 V轻混动力技术的可行性。最后,分析了国家层面的GDP碳排放量总体规划,进行总结,提出展望。

双U/f下垂控制下双极MMC-HVDC系统交流阻抗建模及稳定性分析

基于模块化多电平换流器的高压柔性直流输电系统(modular multilevel converter-based high voltage direct current,MMC-HVDC)常采用双极接线方式以提高系统功率输送能力和可靠性。然而目前对于风电场经柔直外送系统的稳定性研究集中于单极接线方式,孤岛直驱风电场与采用不同双极协调控制的双极MMC-HVDC互联系统小信号稳定性问题还有待进一步探究。该文首先考虑频率耦合特性、参考系初相位和直流侧耦合特性的影响,分别建立了采用双U/f下垂控制和定U/f-P/Q控制的双极MMC-HVDC系统交流侧等效SISO阻抗模型,并详细分析了金属回线阻抗和双极间功率均分度对交流阻抗特性的影响。接着对比研究了两种协调控制中共有控制环路和特有控制环路对交流侧负电阻特性及互联系统稳定性的影响规律。最后,孤岛直驱风电场经两种双极协调控制下双极MMC-HVDC外送系统Matlab/Simulink时域仿真结果和硬件在环半实物实时仿真实验结果验证了所提出的小信号阻抗模型的精确性和稳定性分析结论的有效性。

基于改进多智能体Nash Q Learning的交通信号协调控制

为了优化区域交通信号配时方案,提升区域通行效率,文章提出一种基于改进多智能体Nash Q Learning的区域交通信号协调控制方法。首先,采用离散化编码方法,通过划分单元格将连续状态信息转化为离散形式。其次,在算法中融入长短时记忆网络(Long Short Term Memory,LSTM)模块,用于从状态数据中挖掘更多的隐藏信息,丰富Q值表中的状态数据。最后,基于微观交通仿真软件SUMO(Simulation of Urban Mobility)的仿真测试结果表明,相较于原始Nash Q Learning交通信号控制方法,所提方法在低、中、高流量下车辆的平均等待时间分别减少了11.5%、16.2%和10.0%,平均排队长度分别减少了9.1%、8.2%和7.6%,平均停车次数分别减少了18.3%、16.1%和10.0%。结果证明了该算法具有更好的控制效果。

Simultaneous Application of Controlled Availability Fertilizers to Seeding Furrows with Seeding Increases Grain Yield and Quality of No-Till Cultivated Common Wheat in Japan

In Japan, common wheat is cultivated in upland fields converted from paddy fields, where poor drainage and high precipitation cause delay of sowing, lodging at the jointing stage, difficulty in topdressing at the ripening stage, and low yield. No-till cultivation has been promoted to overcome these problems but the yield is still low due to the lack of proper fertilizer application protocols. In this study, we determined whether an additional application of two kinds of Sigmoid coated urea as controlled availability fertilizers (CAFs) to the standard fertilization protocol for tillage cultivation can increase the yield and lodging resistance in no-till cultivated common wheat. Also, additional fertilization was applied to the seeding furrow simultaneously with seeding using a V-furrow no-till direct sowing (VFDS) machine. No-till cultivated plants had more tillers than tillage cultivated ones and consequently higher number of panicles and yield, caused by increased fertilizer application. The point-injected CAFs to the seeding furrow, which eluted at the jointing and ripening stages greatly increased the grain yield and protein content, respectively, compared to broadcast topdressing of ammonium sulfate at each stage. The simultaneous sowing and fertilization of additional CAFs using VFDS method in multi-year tests in farmers’ fields significantly increased the yield of no-till cultivated common wheat, and can be adopted by Japanese local farmers.

基于RISC-V的硬件管理控制器设计

随着云计算、大数据等先进计算产业的发展,基于硬件的管理模式实现智能化管理具有重要意义。基于RISC-V核心设计实现一种硬件管理控制芯片,利用网络通信工具,实现对应用系统的有效管理。基于UVM验证方法学构建验证平台进行仿真验证,基于FPGA构建芯片原型验证平台与上位机进行协同验证与稳定性测试。物理设计采用40 nm工艺,设计频率为250 MHz。

基于输出反馈逆强化Q学习的线性二次型最优控制方法

本文针对模型参数未知且状态不可测的线性离散系统的线性二次型最优控制问题,提出了一种数据驱动的基于输出反馈逆强化Q学习的最优控制方法,利用系统的输入输出数据同时确定合适的二次型性能指标权重和最优控制律,使得系统运行轨迹与参考轨迹一致.本文首先提出一个参数矫正方程并与逆最优控制相结合得到一种基于模型的逆强化学习最优控制框架,实现输出反馈控制律参数和性能指标加权项的矫正.在此基础上,本文引入强化Q学习思想提出了数据驱动的输出反馈逆强化Q学习最优控制方法,无需知道系统模型参数,仅利用历史输入输出数据对输出反馈控制律参数和性能指标加权项进行求解.理论分析与仿真实验验证了所提方法的有效性.

基于对决深度Q网络的机器人自适应PID恒力跟踪研究

为确保机器人与环境接触时能保持稳定的接触力,基于对决深度Q网络设计一种自适应PID控制恒力跟踪算法。分析机器人与外界的接触过程,并构建基于PID算法的机器人力控制器;提出基于对决深度Q网络的自适应PID算法,以适应外界环境的变化,该算法利用对决深度Q网络自主学习、寻找最优的控制参数;最后,通过Coopeliasim与MATLAB软件平台展开机器人恒力跟踪实验。仿真结果表明:提出的基于对决深度Q网络的自适应PID算法能够获得较好的力跟踪效果,验证了算法的可行性;相比于深度Q网络算法,力误差绝对值的平均值减少了51.6%,且收敛速度得到提升,使机器人能够更好地跟踪外界环境。

Walking Stability Control Method for Biped Robot on Uneven Ground Based on Deep Q-Network

A gait control method for a biped robot based on the deep Q-network (DQN) algorithm is proposed to enhance the stability of walking on uneven ground. This control strategy is an intelligent learning method of posture adjustment. A robot is taken as an agent and trained to walk steadily on an uneven surface with obstacles, using a simple reward function based on forward progress. The reward-punishment (RP) mechanism of the DQN algorithm is established after obtaining the offline gait which was generated in advance foot trajectory planning. Instead of implementing a complex dynamic model, the proposed method enables the biped robot to learn to adjust its posture on the uneven ground and ensures walking stability. The performance and effectiveness of the proposed algorithm was validated in the V-REP simulation environment. The results demonstrate that the biped robot's lateral tile angle is less than 3° after implementing the proposed method and the walking stability is obviously improved.