A deep reinforcement learning approach to gasoline blending real-time optimization under uncertainty

The gasoline inline blending process has widely used real-time optimization techniques to achieve optimization objectives,such as minimizing the cost of production.However,the effectiveness of real-time optimization in gasoline blending relies on accurate blending models and is challenged by stochastic disturbances.Thus,we propose a real-time optimization algorithm based on the soft actor-critic(SAC)deep reinforcement learning strategy to optimize gasoline blending without relying on a single blending model and to be robust against disturbances.Our approach constructs the environment using nonlinear blending models and feedstocks with disturbances.The algorithm incorporates the Lagrange multiplier and path constraints in reward design to manage sparse product constraints.Carefully abstracted states facilitate algorithm convergence,and the normalized action vector in each optimization period allows the agent to generalize to some extent across different target production scenarios.Through these well-designed components,the algorithm based on the SAC outperforms real-time optimization methods based on either nonlinear or linear programming.It even demonstrates comparable performance with the time-horizon based real-time optimization method,which requires knowledge of uncertainty models,confirming its capability to handle uncertainty without accurate models.Our simulation illustrates a promising approach to free real-time optimization of the gasoline blending process from uncertainty models that are difficult to acquire in practice.

Full Dynamic Model for Liquid Sloshing Simulation in Cylindrical Tank Shape

This study presents a comprehensive full dynamic model designed for simulating liquid sloshing behavior within cylindrical tank structures. The model employs a discretization approach, representing the liquid as a network of interconnected spring-damper-mass systems. Key aspects include the adaptation of liquid discretization techniques to cylindrical lateral cross-sections and the calculation of stiffness and damping coefficients. External forces, simulating various vehicle maneuvers, are also integrated into the model. The resulting system of equations is solved using Maple Software with the Runge-Kutta-Fehlberg method. This model enables accurate prediction of liquid displacement and pressure forces, offering valuable insights for tank design and fluid dynamics applications. Ongoing refinement aims to broaden its applicability across different liquid types and tank geometries.

Analysis of Commuting Modal Shift in Consideration of Social Interaction of Consciousness for Environment

It is the matter for achievement of the low carbon transport system that the excessive use of private vehicles can be controlled appropriately.Not only improvement of service level of modes except private vehicle,but also consciousness for environmental problem of individual trip maker is important for eco-commuting promotion.On the other hand,consciousness for environment would be changed by influence of other person.Accordingly,it is aimed in the study that the structure of decision-making process for modal shift to the eco-commuting mode in the local city is described considering environmental consciousness and social interaction.For the purpose,the consciousness for the environment problem and the travel behavior of the commuter at the suburban area in the local city are investigated by the questionnaire survey.The covariance structure about the eco-consciousness is analyzed with the database of the questionnaire survey by structural equation modeling.As the result,it can be confirmed with the structural equation model that the individual environmental consciousness is strongly related with the intention of self-sacrifice and is influenced with the local interaction of the individual connections.On the other hand,the intention of modal shift for the commuting mode is analyzed with the database of the questionnaire survey.It can be found out that the environmental consciousness is not statistically significant for commuting mode choice with the present poor level of service of public transport.However,the intention of self-sacrifice for the prevention of the global warming is statistically confirmed as the factor of modal shift with the operation of eco-commuting bus service with the RP/SP integrated estimation method.As the result,the multi-agent simulation system with social interaction model for eco consciousness is developed to measure the effect of the eco-commuting promotion.For the purpose,the carbon dioxide emission is estimated based on traffic demand and road network condition in the traffic environment model.On the other hand,the relation between agents is defined based on the small world network.The proposed multi-agent simulation is applied to measure the effect of the eco-commuting promotion such as improvement of level of service on the public transport or education of eco-consciousness.The effect of the promotion plan can be observed with the proposed multi-agent system.Finally,it can be concluded that the proposed multi-agent simulation with social interaction for eco-consciousness is useful for planning of eco-commuting promotion.

面向Link16的QualNet与虚拟机信息交互接口设计与实现

Link16是美国国防部采用的高速视距战术数据链,广泛应用于美国海军、联合部队和北约部队,针对其开展测试评估具有重要军事意义。通过硬件在环技术将Link16实物设备接入到仿真测试中,可有效提高测试结果的真实性和准确性。然而当测试场景需要进行实物设备组网测试时,仍会带来成本问题。为此,提出一种面向QualNet MAC层的Link16专属模型以及与之匹配的虚拟机信息交互接口。该模型可高逼真模拟Link16通信行为,实现Link16节点竞争接入、时隙划分、NPG分组等功能。并基于数据分布式服务实现了虚拟机交互接口,将运行在虚拟机的Link16设备模型接入QualNet测试场景。实验测试结果表明,所设计模型具有较高真实性和准确性且接口引入延时不超过1 ms,为大规模数据链网络测试提供一种新方法。

Real-time control for fuel-optimal Moon landing based on an interactive deep reinforcement learning algorithm

In this study,a real-time optimal control approach is proposed using an interactive deep reinforcement learning algorithm for the Moon fuel-optimal landing problem.Considering the remote communication restrictions and environmental uncertainties,advanced landing control techniques are demanded to meet the high requirements of real-time performance and autonomy in the Moon landing missions.Deep reinforcement learning(DRL)algorithms have been recently developed for real-time optimal control but suffer the obstacles of slow convergence and difficult reward function design.To address these problems,a DRL algorithm is developed using an actor-indirect method architecture to achieve the optimal control of the Moon landing mission.In this DRL algorithm,an indirect method is employed to generate the optimal control actions for the deep neural network(DNN)learning,while the trained DNNs provide good initial guesses for the indirect method to promote the efficiency of training data generation.Through sufficient learning of the state-action relationship,the trained DNNs can approximate the optimal actions and steer the spacecraft to the target in real time.Additionally,a nonlinear feedback controller is developed to improve the terminal landing accuracy.Numerical simulations are given to verify the effectiveness of the proposed DRL algorithm and demonstrate the performance of the developed optimal landing controller.

Molecular mechanisms of Biyu decoction as treatment for psoriasis:A network pharmacology and molecular docking study

BACKGROUND The therapeutic effects of a combination of Chinese medicines called Biyu decoction have been clinically verified,although its molecular targets in psoriasis remain unknown.AIM To explore the molecular mechanisms of Biyu decoction for psoriasis treatment.METHODS In this network pharmacology and molecular docking study,the Traditional Chinese Medicine Systems Pharmacology database was searched for Biyu decoction active ingredients.GeneCards,Online Mendelian Inheritance in Man,PharmGkb,Therapeutic Target Database,and DrugBank databases were searched for psoriasis-related genes.The genes targeted by the decoction’s active ingredient and disease genes were intersected to obtain predictive targets of the drug during psoriasis treatment.Cytoscape 3.8.0 was used to construct a drug component/target disease network.The The functional protein association networks database and Cytoscape were used to construct a protein-protein interaction network and streamline the core network.The Gene Ontology and Kyoto Encyclopedia of Genes and Genomes were used for pathway enrichment analysis.Molecular docking technology was used to verify the drug component/target disease network.RESULTS We screened 117 major active ingredients,including quercetin,kaempferol,naringenin,and acetyl-shikonin,and identified 213 gene targets,such as MAPK3,JUN,FOS,MYC,MAPK8,STAT3,and NFKBIA.Using a molecular docking analysis,the main active ingredients demonstrated good binding to the core targets.The Gene Ontology analysis showed that these ingredients were significantly associated with biological activities,such as transcription factor DNA binding,RNA polymerase II-specific DNA binding of transcription factors,and cytokine receptor binding;responses to lipopolysaccharides,molecules of bacterial origin,and oxidative stress;and were mainly distributed in membrane rafts,microdomains,and regions.The Kyoto Encyclopedia of Genes and Genomes analysis showed that decoction ingredients act on Th17 cell differentiation,tumor necrosis factor and mitogen-activated protein signaling pathways,the interleukin-17 signaling pathway,and the PI3K-Akt signaling pathway.CONCLUSION Biyu decoction may be effective against psoriasis through multi-component,multi-target,and multi-channel synergy.

供水管网大口径管道爆管事件形成机理与精细模拟

近年来城市供水管网爆管事件频发对城市的运行安全造成直接影响。结合2017年上海“11·16”溧阳路四平路爆管事件,系统介绍了本次爆管事件概况,同时,利用本次爆管事件现场调查数据,采用3D激光扫描技术和三维数值建模方法,对本次爆管管道进行了建模分析,研究了供水管道在存在初期裂缝情况下,裂缝末端应力集中与管内水压力和裂缝长度发展变化影响关系,采用动力分析方法模拟了管道从裂缝发展到管体破坏形成爆管的物理全过程。结果表明:在供水管网管道早期裂缝末端,由于应力集中管体裂缝继续发展,且随管道水压增大而增大,其增速与裂缝长度密切相关;管道发生开裂后其临界破坏水压随早期裂缝长度的增加而降低,结合本次爆管事件周边获得的3个测点实测水压分析可知,爆管管道早期裂缝断面圆心角应大于26°;管道爆管破坏过程模拟显示,管道残片随裂缝开展向管顶转动,直至形成贯通裂缝完全脱离管道,脱落管片在内水压及外部荷载作用下会发生剧烈的转动和向外弹射,从而形成爆管并产生极大的瞬间破坏作用。

基于触发同步的配电网信息物理系统实时仿真方法

配电网信息物理系统(CPS)仿真需要实现电力物理系统与信息通信系统的联合仿真,同步接口是实现两者之间联合仿真的关键。配电网CPS实时仿真的精度高,但容易因计算规模过大、交互频率过高导致仿真产生“超时”现象,从而降低仿真精度。为了提升配电网CPS实时仿真的效率,建立了有源配电网的物理系统模型与信息通信系统模型,考虑物理、信息通信、信控3个仿真子系统的仿真交互需求,提出了包含管理层、仿真层、交互层的配电网CPS实时仿真架构。针对信息通信仿真子系统与物理仿真子系统之间的数据交互问题,通过事件触发下调节信息通信与物理仿真子系统之间数据交互的周期步长,提出了基于触发同步的有源配电网CPS的实时交互仿真方法,在保证精度的前提下,降低了配电网信息物理仿真接口所需的交互频次,提升了配电网CPS实时仿真的效率。算例分析结果表明,所提有源配电网信息物理交互同步方法能够有效保证配电网CPS仿真的精度,避免无效的交互计算,提高CPS联合仿真的效率。

拥挤传播对汽车共享系统运行影响的仿真分析

随着共享汽车渗透率的不断增加,站点、路段层面的车辆溢出和拥挤传播现象日趋严重.为刻画拥挤传播对汽车共享系统运行的影响机理,首先,搭建具有时变性和状态相关性的汽车共享系统排队网络;其次,基于C#语言和O2DES离散事件仿真框架,提出并设计考虑车路交互影响和拥挤传播现象的汽车共享系统仿真模型,分析动态随机环境下站点与路段层面的拥挤传播现象对汽车共享系统运行的影响;最后,以成都市三站点的小规模汽车共享系统为例,在不同转运比例、需求和道路拥堵场景下,将该模型与引入虚拟空间的无穷排队模型进行对比分析.研究结果表明:站点和路段层面的拥挤传播现象会导致系统服务率下降9.3%~16.9%,相比无穷排队模型,考虑拥挤传播现象的排队模型更能反映汽车共享系统的实际运营过程;当路网的道路占用率为70%(路网处于中度拥堵)时,考虑拥挤传播现象的汽车共享系统可实现最大收益;汽车共享系统的引入会为道路资源的动态分配带来新变化,当公共交通转向汽车共享系统的用户占比超过70%时,路网拥堵加剧,不利于汽车共享系统的有效运营和可持续发展.

新型电力负荷管理系统发展的关键支撑技术研究

针对新型负荷管理系统对规模化需求侧资源控制能力较弱问题,基于新型电力负荷管理系统大规模负荷调控的不同场景需求,提出灵活组网技术,以支撑需求侧P2P分布式交易、虚拟用电权交易等多业务通信要求,实现新型电力负荷管理系统灵活互动。为预防高并发控制信息导致的网络阻塞等危害并精确掌握需求侧资源的响应能力,提出构建适用于新型电力负荷管理系统多模态灵活组网的半实物实时仿真内核,并建立在环测试机制,做到动态调整控制策略,从而实现对分布式客户侧资源的优化管理和精准服务。

基于ABM建模的农业创新技术扩散仿真研究

借助基于主体建模方法(agent-based-modeling,ABM)建立农户决策的演化博弈模型,以社会网络为技术扩散载体并假设社会网络中的农户全部采纳传统技术,设计4组控制变量实验仿真研究个体学习、社会效应和两者耦合作用对农业创新技术扩散的影响,并进一步通过改变参数探究农户平均交流人数、创新技术理论收益和两者耦合作用的影响。研究发现,仅存在个体学习时农业创新技术扩散效率大幅度增长,仅存在社会效应时扩散效率有所下降,同时存在个体学习和社会效应产生的耦合作用并非二者净作用的简单相加,而是产生了部分促进作用;农户平均交流人数的增长产生了阻碍作用,且创新技术理论收益的增长可以消除不同农户平均交流人数的差异;创新技术理论收益的增长产生了促进作用,促进效果呈非线性特征,且具有产生影响的起飞点。最后根据研究结论提出相应的政策建议。

网络化弹药起爆控制半实物仿真测试方法

针对网络化弹药起爆控制功能靶场测试成本高、可重复性差等问题,提出一种基于QualNet仿真平台的网络化弹药动态起爆控制半实物仿真测试方法。基于该测试方法架构,设计了联通真实网络与仿真网络的半实物交互接口,实现了实物原理样机与网络化弹药仿真模型间的实时数据交互;开发了安全系统动态运行监控软件,通过该界面指挥中心可对弹药节点进行远程动态控制与状态信息监测;为保证控制指令等数据报文的可靠实时传输,定义了监控软件与安全起爆控制模块间的应用层通信协议;对网络化弹药远程解保、远程动态起爆控制功能及半实物交互接口时延进行了测试。研究结果表明:该测试方法不仅具有较强的可行性和有效性,而且具有良好的实时性。

基于数字孪生技术的三维可视化网络仿真平台

实现复杂的网络系统代价往往较高或不现实,而传统的网络模拟仿真均使用二维界面,并利用抽象的命令行进行操作,可视化和交互性差。针对上述问题,将数字孪生技术作为网络技术研究的一种有效的现代化测试、评估和验证手段,便捷、可视化地针对现有网络系统进行模拟仿真,有效提高网络仿真平台的保真度与交互性,从而打破多数仿真工具的局限,提供更丰富的仿真服务,具有十分广阔的前景。

Review of Networked Microgrid Protection:Architectures,Challenges,Solutions,and Future Trends

Design and selection of advanced protection schemes have become essential for reliable and secure operation of networked microgrids.Various protection schemes that allow correct operation of microgrids have been proposed for individual systems in different topologies and connections.Nevertheless,protection schemes for networked microgrids are still in devel-opment,and further research is required to design and operate advanced protection in interconnected systems.Interconnection of these microgrids in different nodes with various intercon-nection technologies increases fault occurrence and complicates protection operation.This paper aims to point out challenges in developing protection for networked microgrids,potential solutions,and research areas that need to be addressed for their development.First,this article presents a systematic analysis of different microgrid clusters proposed since 2016,including several architectures of networked microgrids,operation modes,components,and utilization of renewable sources,which have not been widely explored in previous review papers.Second,the paper presents a discussion on protection systems currently available for microgrid clusters,current challenges,and solutions that have been proposed for these systems.Finally,it discusses the trend of protection schemes in networked microgrids and presents some conclusions related to implementation.IndexTerms—Adaptive eprotection,microgrid cluster,microgrid,multiple microgrid,networked microgrid,real-time simulation,smart grid.

基于基因优先级排序的活跃模块识别方法

随着高通量测序技术的快速发展,海量的多组学数据有助于从分子水平上研究癌症的致病机理。近年来,活跃模块的识别问题已成为生物信息学领域的主要研究方向。然而,许多现有方法往往无法识别与癌症密切相关的强连通模块。通过整合蛋白质-蛋白质相互作用网(PPI)和基因表达两种组学数据,提出一种活跃模块识别方法IdeMod。具体而言,IdeMod提出了基于p步随机游走核回归模型的基因活跃评分函数,结合帕累托最优共识(POC)方法中的支配关系得到基因优先级排序列表。通过引入一种模拟退火算法SA-PROX,寻找PPI网络中优先级高且连通性强的活跃模块。在真实的乳腺癌数据和宫颈癌数据下进行实验,与SigMod,LEAN,RegMod和ModFinder方法相比,IdeMod可以识别一个连通性强且包含大量癌症相关基因的活跃模块。因此,IdeMod方法可作为检测活跃模块的一种有效补充工具。

一种新的基于LSTM的航位推算算法

针对传统航位推算(DR)算法中构建的运动模型简化程度较高,对运动信息的预测精度有限,制约DR算法性能的问题,提出一种新的基于长短时记忆网络(Long Short Term Memory Network,LSTM)的DR算法,即LSTM-DR算法,该算法根据仿真实体的序列运动信息,以及仿真实体运动信息的预测误差,利用深度神经网络的表征能力,实现对仿真实体运动规律的拟合,从而提升仿真实体运动模型的预测精度。实验结果表明,所提出的LSTM-DR算法,使运动模型训练后能获得良好的预测精度,从而在保持仿真实体运动的连续性和平滑性的同时,大幅降低对通信资源的消耗。

配电网中多台并联逆变器之间的交互影响

多台DFACTS设备同时投入配电网时,设备的控制器之间存在交互影响,可建立并联逆变器的诺顿等效模型并利用RGA法定量分析多台并联逆变器之间的稳定性、网络参数及其交互影响的强弱关系。通过MATLAB仿真结果,可知逆变器的各控制参数对逆变器的交互影响具有不同程度的影响,因此,可通过协调控制各参数降低逆变器的交互影响。

分布交互仿真

为适应作战环境下武器群体或体系对抗的仿真，已由单武器平台的性能仿真发展为多武器平台在作战环境下体系对抗仿真。本文论述分布交互仿真的系统结构、特点和某些技术关键。

分布交互式仿真

该文对分布交互式仿真技术的发展及特点作了分析 ,并详细介绍了目前较为成熟的几种分布交互式仿真技术及其优缺点 ,最后对国内外利用分布式仿真技术开发的几个主要仿真系统进行了介绍。

基于Web的三维仿真虚拟实验室构建

讨论了虚拟实验室的内涵,对已开发完成的大学化学虚拟实验室的功能模块、三层系统结构作了简单介绍,具体设计采用VRML来建立三维仿真模型。实际应用表明该虚拟实验室具有很好的教学效果。