Effects of Slow-release Nitrogen on Dry Matter Accumulation,Translocation and Yield of Summer Maize

[Objectives]This study was conducted to investigate the effects of slow-release nitrogen fertilizer on dry matter accumulation and translocation of summer maize.[Methods]With Zhoudan 9 as the test variety,six different treatment were set up:blank control(CK1),slow-release urea 75 kg/hm^(2)(C1),slow-release urea 150 kg/hm^(2)(C2),slow-release urea 225 kg/hm^(2)(C3),slow-release urea 300 kg/hm^(2)(C4)and ordinary urea 300 kg/hm^(2)(CK2),to study the change law of dry matter accumulation and translocation in summer maize.[Results]Treatment slow-release urea 225 kg/hm^(2)(C4)showed summer maize yield,dry matter translocation between organs,grain contribution rate and proportion of grain dry matter in the full ripe stage higher than other treatments.Considering the weight loss and cost factors,slow-release urea 225 kg/hm^(2)(C3)could be recommended as the fertilizing amount for summer maize.[Conclusions]This study provides theoretical reference for rational selection of fertilizers for reducing fertilizer application and increasing fertilizer efficiency,and for production of summer maize in Shajiang black soil region.

Effects of Slow-release Nitrogen Fertilizer on Yield and Nitrogen Accumulation of Summer Maize in Shajiang Black Soil Area

[Objectives] This study was conducted to verify the field application effect of slow-release nitrogen fertilizer on summer maize in Shajiang black soil area by simultaneous sowing and fertilization, and explore the application scope and nitrogen metabolism mechanism, so as to lay a foundation for fertilizer reduction and efficiency improvement. [Methods] With maize variety Beiqing 340 and sulfur-coated urea as experimental materials, five nitrogen application levels were set, namely, control (C0), slow-release nitrogen 70 kg/hm^(2) (C70), slow-release nitrogen 140 kg/hm^(2) (C140), slow-release nitrogen 210 kg/hm^(2) (C210) and slow-release nitrogen 280 kg/hm^(2) (C280). The phosphorus and potassium fertilizers were all in accordance with the unified standard. [Results] With the application rate of slow-release nitrogen increasing, the nitrogen accumulation in organs increased first and then decreased after tasseling stage of maize. In order to reduce the fertilizing amount and increase efficiency, 210 kg/hm^(2) of slow-release nitrogen fertilizer was the best fertilizing amount for summer maize in Shajiang black soil area. [Conclusions] This study provides reference for fertilizer reduction, efficiency improvement and sustainable development of summer maize in Shajiang black soil area.

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的服装可持续消费行为建模与仿真

“双碳”目标下,随着服装消费引起的气候变化和环境污染等生态问题日益严重,迫切需要重新思考和重塑服装消费模式,推动服装消费向质量型、低碳化转变,从而实现服装产业的绿色转型。文章运用多Agent建模方法,构建服装可持续消费行为仿真模型,采用Netlogo平台进行仿真实验,探求服装可持续消费行为的影响机理。结果表明,消费者可持续消费认知、产品可持续性和设施供应条件均显著促进可持续消费行为;但不同强度下,产品可持续性和设施供应条件的推动作用存在差异。基于此,从可持续消费认知和供应条件两方面提出了引导中国消费者服装可持续消费行为的建议和对策。

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。

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。

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.

The dynamic response of a high-density polyethylene slow-release structure under launching overload

Based on the 60 mm artillery grenade,a slow-release structure was designed to reduce the severity of ammunitions response to accidental thermal stimulation and improve the thermal stability of ammunitions.The slow-release structure was made of high-density polyethylene(HDPE) and connected the fuse and the projectile body through internal and external threads.To study the safety of the slowrelease structure under artillery launching overload,mechanical analysis of the slow-release structure was simulated via finite element analysis(FEA).The impacts of various factors(e.g.,fuse mass,number of threads,and nominal diameter of internal threads of the slow-release structure) on the connection strength of the slow-release structure were studied.A strength-prediction model based on the fuse mass and internal thread parameters was established by fitting the maximum effective stress of the slowrelease structure.This led to good prediction results.In conclusion,this study provides references and theoretical support for the design of thermal protection structures insensitive to ammunition.

Optimization of slow-release fertilizer application improves lotus rhizome quality by affecting the physicochemical properties of starch

To achieve the dual goals of high yield and good quality with low environmental costs,slow-release fertilizer(SRF)has been widely used in lotus cultivation as new type of fertilizer instead of traditional nitrogen fertilizer.However,the optimal amount of SRF and how it would promote lotus rhizome quality remain unclear.This study was designed to investigate the photosynthetic characteristics and the synthesis,accumulation,and physicochemical properties of lotus rhizome starches under six SRF levels(CK,S1,S2,S3,S4,and S5).Compared with CK(0 kg ha^(–1)),the net photosynthetic rate(P_(n))and SPAD values of leaves remained at higher levels under SRF treatment.Further research showed that SRF increased the lotus rhizome yield,the contents of amylose,amylopectin,and total starch,and the number of starch granules.Among the six SRF levels,S3(1035 kg ha^(–1))showed the greatest difference from CK and produced the highest levels.With the increasing SRF levels,the peak,hot and final viscosities decreased at first and then increased,but the setback viscosity and pasting temperature increased.In order to interpret these changes at the molecular level,the activities of key enzymes and relative expression levels of starch accumulation related genes were analyzed.Each of these parameters also increased under SRF treatment,especially under the S3 treatment.The results of this study show that SRF,especially S3(1035 kg ha^(–1)),is a suitable fertilizer option for lotus planting which can improve lotus rhizome quality by affecting starch accumulations related enzymes and genes.These results will be useful for SRF application to high-quality lotus rhizome production with low environmental costs.

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。

Impacts and Demonstration Effects of Applying Long-acting Slow-release Fertilizer on Economic Yield of Peanut

[Objectives]To study the impacts and demonstration effects of long-acting slow-release fertilizer application on economic yield of peanut.[Methods]The 25,30,35,40,45,50 kg of long-acting slow-release fertilizers were applied to 667 m 2 of peanuts,and different amounts of urea were applied together.[Results]Applying 40 kg of long-acting slow-release fertilizer and 10.45 kg of urea had the best effect.Compared with the application of ordinary compound fertilizers,the plants did not age prematurely,the leaf diseases were mild,the stems and leaves remained dark green when harvested,and the stems and leaves had a longer functional period.Bearing shoots increased by 1.7,single-plant full pods increased by 2.4,double-seed peanuts increased by 3.2,empty pods decreased by 0.5,and single-seed peanuts decreased by 0.7.The experimental demonstration results show that the spring-sowed peanuts had an average yield increase of 29.0-67.2 kg/667 m 2,and the yield increase rate was 7.35%-16.89%,and the difference was extremely significant.[Conclusions]In the high-yield cultivation of peanuts,the application of long-acting slow-release fertilizer can be promoted to improve peanut production.

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.

基于Agent的跨境电子商务课程智能教学系统

当前,跨境电子商务课程智能教学系统功能模块多为单向形式,可控教学覆盖范围较小,导致平均成绩优化比下降,为此提出对基于Agent的跨境电子商务课程智能教学系统的设计与分析。首先,构建通信接口,并接入驱动装置,完成系统硬件的设计;其次,采用多目标的方式,扩大可控教学覆盖范围;最后,设计多目标Agent跨境电子商务课程教学功能模块,关联跨境电子商务教学知识库,完成系统软件设计。测试结果表明:针对选定的6个班级进行测试对比,最终得出的平均成绩优化比均可以达到20%以上,说明在Agent的辅助下,文章设计的系统应用效果更佳,具有实际的应用价值。

Fixed-Time Cluster Optimization for Multi-Agent Systems Based on Piecewise Power-Law Design

Dear Editor,This letter focuses on the fixed-time(FXT)cluster optimization problem of first-order multi-agent systems(FOMASs)in an undirected network,in which the optimization objective is the sum of the objective functions of all clusters.A novel piecewise power-law control protocol with cooperative-competition relations is proposed.Furthermore,a sufficient condition is obtained to ensure that the FOMASs achieve the cluster consensus within an FXT.