Influence ofβ-nucleating Compound Agents on the Mechanical Properties and Crystallization Behavior of Polypropylene Random Copolymer

A novel polypropylene random(PPR)composite materials with optimized properties was developed by addingβ-nucleating compound agents(rare earth complex WBG-2 and aryl amide derivative TMB-5)and ternary compound modifier(TPE/WBG-2/CaCO_(3)).The effects of differentβ-nucleating agents and ternary compound modifier on the mechanical properties and crystallization behavior of PPR were analyzed.The results show that,compared with pure PPR materials,both WBG-2 and TMB-5 could significantly improve the impact strength of PPR.The crystallization temperature of PPR increased with the addition ofβ-nucleating agent.The modified PPR prepared with ternary compound modifier showed the most excellent comprehensive properties.

流程型生产安全数据流的多Agent节点协同分流优化方法

为实现流程型生产安全监测系统的及时、准确决策,结合数据流采集与隐患识别过程,分析非关键数据的冗余、关键数据的缺失和数据计算时延较大的问题,提出基于多Agent的流程型生产安全数据流网络分流调度规划方法和节点流量划分识别机制。研究结果表明:相较于分簇传输方法,数据流网络分流调度方法可以实现关键隐患数据更高的传输成功率;相较于常规的复杂事件处理方法,本文提出的流量划分识别机制在2种类型数据集上实现隐患事件识别均有更低的计算时延。研究结果可为流程行业安全生产数字化管控模式和数据高质量获取提供参考。

基于多Agent深度强化学习的无人机协作规划方法

人机协作控制是多无人机任务规划的重要方式。考虑多无人机任务环境协同解释和策略控制一致性需求,提出基于多Agent深度强化学习的无人机协作规划方法。依据任务知识和行为状态,构建基于任务分配Agent的任务规划器,生成人机交互的相互依赖关系;设计一种深度学习强化方法,解决群体行为最优策略和协同控制方法,并利用混合主动行为选择机制评估学习策略。实验结果表明:作为人机交互实例,所提方法通过深度强化学习使群体全局联合动作表现较好,学习速度和稳定性均能优于确定性策略梯度方法。同时,在跟随、自主和混合主动3种模式比较下,可以较好地控制无人机飞行路径和任务,为无人机集群任务执行提供了智能决策依据。

基于免疫Agent的电力电缆线路故障检测系统

为区别故障信号、非故障信号,实现对电缆线路故障的准确检测,设计了基于免疫Agent的电力电缆线路故障检测系统。利用前端检测电路为故障分析模块、测距方式切换模块提供电量传输信号,完成系统前端检测装置的连接。按照免疫Agent检测原理提取电力电缆线路故障信号的特征,联合已获取信号对象,求解检测插值指标的具体数值。结合各级硬件设备结构,完成系统设计。实验结果表明,该系统可同时检测波频为10~20 Hz、40~50 Hz、60~70 Hz的故障信号与波频为20~30 Hz、30~40 Hz、50~60 Hz的非故障信号,可以在精准辨别故障与非故障信号的同时,实现对电力电缆线路故障的准确检测。

基于Agent人工智能的异构网络多重覆盖节点入侵检测系统设计

异构网络具有结构复杂、多重覆盖面积大等特征,使得网络入侵检测较为隐蔽,威胁网络运行的安全性;为此,对基于Agent人工智能的异构网络多重覆盖节点入侵检测系统进行了研究;通过检测Agent和通信Agent装设主机Agent,以Cisco Stealthwatch流量传感器作为异构网络传感器检测攻击行为,采用STM32L151RDT664位微控制器传输批量数据,由MAX3232芯片实现系统电平转化,实现硬件系统设计;软件部分设计入侵检测标准,采用传感器设备捕获网络实时数据,通过Agent技术解析异构网络协议并提取数据运行特征,综合考虑协议解析结果及与检测标准匹配度,实现异构网络多重覆盖节点入侵检测;经实验测试表明,基于Agent人工智能的异构网络多重覆盖节点入侵检测系统入侵行为的漏检率和入侵类型误检率的平均值仅为6%和5%,能够有效提高检测精度,减小检测误差。

一种基于Agent的任务自生成方法

任务自生成是基于预先设定的业务工作流完成任务执行流程制定的一个过程,任务执行流程制定主要包括任务执行步骤选取与任务执行步骤相应的解决方案选取。提出一种基于Agent的任务自生成方法来解决基于传统的业务工作流的流程制定机制,在面对有差异性需求的不同任务时,因其不能做出任务执行流程制定的自适应性改变而在处理任务时出现处理速度慢、结果不准确等问题。利用Agent的环境感知能力实现对任务需求信息和任务自生成系统环境的感知,利用Agent的自主行为决策能力结合感知的信息实现对任务执行流程制定工作的自主管理,在真实应用场景测试中,通过一系列比较实验验证了这种方法在处理速度和准确度方面具有明显优势。

基于Multi-Agent的无人机集群体系自主作战系统设计

针对无人集群自主作战体系设计中的关键问题,提出基于Multi-Agent的无人集群自主作战系统设计方法。建立无人集群各节点的Agent模型及其推演规则;对于仿真系统模块化和通用化的需求,设计系统互操作式接口和无人集群自主作战的交互关系;开展无人集群系统仿真推演验证。仿真结果表明,所提设计方案不仅能够有效开展并完成自主作战网络生成-集群演化-效能评估的全过程动态演示验证,而且能够通过重复随机试验进一步评估无人集群的协同作战效能,最后总结了集群协同作战的策略和经验。

基于Multi-Agent的水电站变压器故障诊断系统

为了精准、快速完成水电站变压器的故障诊断,设计基于Multi-Agent的水电站变压器故障诊断系统。变压器状态监控agent将检测到的变压器故障信息发送给系统管理agent,系统管理agent通过通信agent将变压器故障信息发送给变压器故障诊断agent,变压器故障诊断agent利用小波变换方法提取变压器故障特征,并将其作为IFOA-SVM模型输入,完成变压器故障分类后,获取变压器故障诊断结果,该结果通过通信agent显示给用户。实验表明,该系统可有效诊断变压器故障诊断,诊断成功率受系统故障信息丢失率的影响较小,诊断耗时、耗能小,并具有较高故障诊断成功率。

基于多Agent传动关系的股市趋势预测

股市趋势预测是机器学习领域中一个具有挑战性的任务。由于一些因素对于股市的影响是动态且不确定的,导致股市趋势难以预测。针对已有方法在股市预测时存在的灵敏性差、适应力弱等问题,从快变量和慢变量的传动关系出发,利用Agent技术对股市中的快周期和慢周期进行联合建模,提出一种多Agent传动影响图(MATID)股市趋势预测方法。给出股市中快周期和慢周期的划分标准,并引入周期能量的概念;通过对相关趋势指标的特征融合,给出周期能量的量化计算方法;通过分析快周期和慢周期的动态作用过程,给出传动因子的表示方法;将快周期和慢周期分别对应成不同的Agent,利用多Agent影响图模型建模快周期和慢周期的传动过程;利用股市振子模型表示快Agent和慢Agent之间的传动效用,利用联合树的自动推理技术对股市趋势进行预测。在不同样本数量和不同股市趋势下进行实验,结果表明,与门控循环单元、S-LSTM和Hybrid-RNN预测方法相比,MATID方法预测精确率提升1.5%~7.0%,召回率提升5.4%~6.7%,F1值提升3.7%~6.2%,具有良好的灵敏性和适应力。

Effect of Nucleating Agents and Heat Treatments on the Crystallization of Magnesium Aluminosilicate Transparent Glass-ceramics

The crystallization behavior and transparent property of MgO-A1203-SiO2 （MAS） glasses with TiO2 and TiO2＋ZrO2 as nucleating agents were discussed by differential thermal analysis, X-ray diffraction, field emission-environment scanning electron microscope, energy dispersive spectrum and UV-VIS-NIR scanning spectrophotometer. It was found that the glass crystallized at 950 ℃ with ZrO2 less than 3% could obtain transparent glass ceramic, which presented purple to colorless. With the nucleating agent additives （5% TIO2＋3% ZrO2）, the colorless transparent glass-ceramics with spinel as the main crystal phase could be prepared, and the transmittance reached about 80%. As the crystallized temperature increase to 1 000 ℃, besides spinel（MgA1204）, sapphirine （Mg3.5A19Si1.5O20） and ZrTiO4 precipitated from matrix glass, and the transmitance of glass-ceramic decreased.

Effect of a Novel Nucleating Agent on Isothermal Crystallization of Poly（L-lactic acid）

The effect of a novel active nucleating agent(TBC8-eb) on the isothermal crystallization of poly(L-lactic acid) (PLLA) was studied by differential scanning calorimetry(DSC) and Fourier transform infrared spectroscopy(FTIR) . The analysis on kinetics demonstrates that TBC8-eb can not only accelerate the crystallization rate but also transform most of the original spherulite crystals of PLLA into sheaf-like crystals. Furthermore,the free energy of folding(σe) of PLLA and PLLA with TBC8-eb is 0.15 and 0.06 J·m-2,respectively,which suggests that the addition of TBC8-eb favors the regular folding of molecule chains in the crystallization of PLLA,improv-ing its crystallization rate. The FTIR results show that TBC8-eb can accelerate the conformational ordering of PLLA in the isothermal crystallization. The conformational ordering of PLLA nucleated with TBC8-eb begins with the interchain interaction of CH3,and then a short helix emerges where a couple of CH3 groups interact.

THERMODYNAMIC STUDY OF NUCLEATION PROPERTY OF NUCLEATING AGENT

It is deduced from thermodynamic relations and confirmed by experiment results that the nucleation rate and nucleation temperature of nucleating agents in the glass are dependent upon their melting entropy Delta S//m melting temperature T//m and crystal - type transition in terms of some mathematical expressions. (Author abstract) 10 Refs.

基于AI agent的6G内生智能技术框架及其应用

未来6G网络将内生支持通信和AI一体化服务,赋能丰富多彩的新业务,支撑社会高效可持续发展。为此,借鉴了IT行业AI Agent的应用范式,基于电信应用场景创新地提出了6G AI Agent技术框架的三大设计理念,包括多模型融合、定制化Agent和插件式环境交互,并基于该理念构建了6G AI Agent技术框架。通过环境交互层、Agent引擎层、模型调度层、模型基座层交互协同,实现了自主环境感知、自主任务生成和自主执行任务的能力。此外,以移动网络的智能感知任务为例,探索了AI Agent的使用场景及价值,为AI新技术在电信领域发展提供了新的思路和技术支撑。

MELTING BEHAVIOR OF LOW ETHYLENE CONTENT POLYPROPYLENE COPOLYMERS WITH AND WITHOUT NUCLEATING AGENTS

The melting behavior of polypropylene (PP) and low ethylene content polypropylenecopolymer with and without nucleating agent samples crystallized under both isothermal and non-isothermal conditions were studied by Differential Scanning Calorimeter (DSC) and X-raydiffraction. Multiple melting behavior were observed depending on the existence of nucleatingagent and crystallization conditions. The observed phenomena have been discussed by the effect ofnucleating agent on perfection of crystal and the melting and recrystallization of imperfect crystalto a more perfect crystal during the heating process of samples.

Preliminary Study on the Characteristics of Isotactic Polypropylene with Nucleating Agent Swollen by Supercritical Carbon Dioxide

Impregnation of isotactic polypropylene (iPP) with nucleating agent (NA21) using supercritical carbon dioxide as the swelling agent at different temperature and pressure and its non-isothermal crystallization kinetics were investigated. The results showed that NA21 was dispersed at a nanometer-scale in the PP matrix, resulting in the formation of different typesof crystal phases of iPP and the enhancement of its mechanical properties.

竞争与合作视角下的多Agent强化学习研究进展

随着深度学习和强化学习研究取得长足的进展,多Agent强化学习已成为解决大规模复杂序贯决策问题的通用方法。为了推动该领域的发展,从竞争与合作的视角收集并总结近期相关的研究成果。该文介绍单Agent强化学习;分别介绍多Agent强化学习的基本理论框架——马尔可夫博弈以及扩展式博弈,并重点阐述了其在竞争、合作和混合三种场景下经典算法及其近期研究进展;讨论多Agent强化学习面临的核心挑战——环境的不稳定性,并通过一个例子对其解决思路进行总结与展望。

Patent-based technological developments and surfactants application of lithium-ion batteries fire-extinguishing agent

While newer,more efficient Lithium-ion batteries(LIBs)and extinguishing agents have been developed to reduce the occurrence of thermal runaway accidents,there is still a scarcity of research focused on the application of surfactants in different LIBs extinguishing agents,particularly in terms of patented technologies.The aim of this review paper is to provide an overview of the technological progress of LIBs and LIBs extinguishing agents in terms of patents in Korea,Japan,Europe,the United States,China,etc.The initial part of this review paper is sort out LIBs technology development in different regions.In addition,to compare LIBs extinguishing agent progress and challenges of liquid,solid,combination of multiple,and microencapsulated.The subsequent section of this review focuses on an in-depth analysis dedicated to the efficiency and challenges faced by the surfactants corresponding design principles of LIBs extinguishing agents,such as nonionic and anionic surfactants.A total of 451,760 LIBs-related patent and 20 LIBs-fire-extinguishing agent-related patent were included in the analyses.The extinguishing effect,cooling performance,and anti-recombustion on different agents have been highlighted.After a comprehensive comparison of these agents,this review suggests that temperature-sensitive hydrogel extinguishing agent is ideal for the effective control of LIBs fire.The progress and challenges of surfactants have been extensively examined,focusing on key factors such as surface activity,thermal stability,foaming properties,environmental friendliness,and electrical conductivity.Moreover,it is crucial to emphasize that the selection of a suitable surfactant must align with the extinguishing strategy of the extinguishing agent for optimal firefighting effectiveness.

Non-isothermal crystallization kinetics of wood-flour/polypropylene composites in the presence of b-nucleating agent

The influence of aryl amide compounds（TMB）as b-nucleating agents, on the non-isothermal crystallization of a wood-flour/polypropylene composite（WF/PP）prepared by compression molding was investigated by wide-angle X-ray diffraction and differential scanning calorimetry. TMB was proved to be an effective b-crystalline nucleating agent for WF/PP. The DSC data showed that the crystallization peak temperature（Tp） increased and the half-time（t1/2） decreased with the addition of TMB.Three theoretical models were used to analyze the nonisothermal crystallization process. The modified Avrami method and Mo method successfully explained the nonisothermal crystallization behavior of PP and its composites. Their activation energies for non-isothermal crystallization were determined basing on the Kissinger method.

General anesthetic agents induce neurotoxicity through oligodendrocytes in the developing brain

General anesthetic agents can impact brain function through interactions with neurons and their effects on glial cells.Oligodendrocytes perform essential roles in the central nervous system,including myelin sheath formation,axonal metabolism,and neuroplasticity regulation.They are particularly vulnerable to the effects of general anesthetic agents resulting in impaired proliferation,differentiation,and apoptosis.Neurologists are increasingly interested in the effects of general anesthetic agents on oligodendrocytes.These agents not only act on the surface receptors of oligodendrocytes to elicit neuroinflammation through modulation of signaling pathways,but also disrupt metabolic processes and alter the expression of genes involved in oligodendrocyte development and function.In this review,we summarize the effects of general anesthetic agents on oligodendrocytes.We anticipate that future research will continue to explore these effects and develop strategies to decrease the incidence of adverse reactions associated with the use of general anesthetic agents.

Sn nucleation and growth from Sn(II)dissolved in ethylene glycol:Electrochemical behavior and temperature effect

Thermodynamic and kinetic aspects of Sn nucleation and growth processes onto a glassy carbon electrode from SnCl2·2H2O dissolved in ethylene glycol solutions were studied.Typical reduction and oxidation peaks observed in voltammograms have demonstrated the capability of ethylene glycol solutions to electrodeposit Sn.The temperature-dependence of diffusion coefficient values derived from potentiodynamic and potentiostatic studies helped to determine and validate estimations of the activation energy for Sn(II)bulk diffusion.Chronoamperometric results have identified that,the suitable model to describe the early stage of Sn electrodeposition could be composed of Sn three-dimensional nucleation and diffusion-controlled growth and water reduction contributions,which was duly validated by theoretical and experimental approaches.From the model,typical kinetic parameters such as the nucleation frequency of Sn(A),number density of Sn nuclei(N0),and diffusion coefficient of Sn(II)ions(D),were determined.The presence of Sn nuclei with excellent quality and their structures were verified using SEM,EDX,and XRD techniques.