检索结果-南通市图书馆

Choice of discount rate in reinforcement learning with long-delay rewards

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2022年第2期33卷 381-392页

作者： LIN Xiangyang XING Qinghua liu fuxian Department of Air Defense and Anti-Missile Air Force Engineering UniversityXi’an 710051China

In the world, most of the successes are results of longterm efforts. The reward of success is extremely high, but before that, a long-term investment process is required. People who are “myopic” only value short-term rewards and are unwilling to make early-stage investments, so they hardly get the ultimate success and the corresponding high rewards. Similarly, for a reinforcement learning(RL) model with long-delay rewards, the discount rate determines the strength of agent’s “farsightedness”.In order to enable the trained agent to make a chain of correct choices and succeed finally, the feasible region of the discount rate is obtained through mathematical derivation in this paper firstly. It satisfies the “farsightedness” requirement of agent. Afterwards, in order to avoid the complicated problem of solving implicit equations in the process of choosing feasible solutions,a simple method is explored and verified by theoreti cal demonstration and mathematical experiments. Then, a series of RL experiments are designed and implemented to verify the validity of theory. Finally, the model is extended from the finite process to the infinite process. The validity of the extended model is verified by theories and experiments. The whole research not only reveals the significance of the discount rate, but also provides a theoretical basis as well as a practical method for the choice of discount rate in future researches.

关键词： reinforcement learning(RL) discount rate longdelay reward Q-learning treasure-detecting model feasible solution

Dynamic Recrystallization Behavior of a Heat-resistant Martensitic Stainless Steel 403Nb during Hot Deformation

在线全文

学校读者我要写书评

暂无评论

Journal of Materials Science & Technology 2011年第10期27卷 913-919页

作者： Zhouyu Zeng Liqing Chen fuxian Zhu Xianghua liu State Key Laboratory of Rolling and Automation Northeastern University 3-11 Wenhua Road Shenyang 110819 China

Dynamic recrystallization （DRX） behaviors of a heat-resistant martensitic stainless steel 403Nb during hot deformation have been investigated by single-pass thermo-mechanical simulative experiment at temperatures of 900-1150℃ and strain rates of 0.01-1 s-1 The results show that the true stress-true strain curves of this alloy can be classified into two types, one is of dynamic recovery and the other is of dynamic recrystallization. The DRX in 403Nb alloy is easy to occur at strain rates lower than 0.5 s-1 and deformation temperatures higher than 1000℃. Using regression analysis, the stress multiplier （a） and apparent stress exponent （n） were calculated to be 0.0153 and 3.22, respectively, while the activation energy （Qd） for DRX of 403Nb was calculated to be 367.293 kJ/mol. The constitutive equation of peak stress for DRX was also obtained. Based on P-J method, the critical strain for DRX was accurately determined. The mathematical models of peak strain and kinetic equation for DRX of 403Nb steel were finally established.

关键词： 403Nb steel Dynamic recrystallization Hot deformation Critical strain

Static recrystallization behavior of a martensitic heat-resistant stainless steel 403Nb

在线全文

学校读者我要写书评

暂无评论

Acta Metallurgica Sinica(English Letters) 2011年第5期24卷 381-389页

作者： Zhouyu ZENG Liqing CHEN fuxian ZHU Xianghua liu State Key Laboratory of Rolling and Automation Northeastern University Shenyang 110819 China

A static recrystallization behavior between the roiling passes of a martensitic heatresistant stainless steel 403Nb has been studied by OM, TEM and double-hit thermomechanical simulator to explore the effects of deformation temperature, strain rate, strain and the prior austenite grain size. The results show that increases of deformation temperature and strain rate and strain can promote the static recrystallization of 403Nb steel. Static recrystallization also proceeds faster when the prior austenite grain size is smaller. Microstructural observation indicates that the volume fraction of static recrystallization increases with prolonged interval of the rolling passes. Straininduced precipitation can lead to an appearance of a platform in the kinetic curve of static recrystallization. Different from the conventional micro-alloying steel, the strain-induced precipitates in 403Nb steel during hot rolling are carbides containing Nb and Cr.

关键词： 403Nb Static recrystallization Microstructural evolution Strain-induced precipitation

Ripple-effect analysis for operational architecture of air defense systems with supernetwork modeling

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2014年第2期25卷 249-264页

作者： Zhigang Zou fuxian liu Shiman Sun Lu Xia Chengli Fan School of Air and Missile Defense Air Force Engineering University Research & Development Center China Airport Construction Group Corporation

In order to solve the problem that the ripple-effect analy- sis for the operational architecture of air defense systems （OAADS） is hardly described in quantity with previous modeling approaches, a supernetwork modeling approach for the OAADS is put for- ward by extending granular computing. Based on that operational units and links are equal to different information granularities, the supernetwork framework of the OAADS is constructed as a “four- network within two-layer” structure by forming dynamic operating coalitions, and measuring indexes of the ripple-effect analysis for the OAADS are given combining with Laplace spectral radius. In this framework, via analyzing multidimensional attributes which inherit relations between operational units in different granular scales, an extended granular computing is put forward integrating with a topological structure. Then the operation process within the supernetwork framework, including transformation relations be- tween two layers in the vertical view and mapping relations among functional networks in the horizontal view, is studied in quantity. As the application case shows, comparing with previous modeling approaches, the supernetwork model can validate and analyze the operation mechanism in the air defense architecture, and the ripple-effect analysis can be used to confirm the key operational unit with micro and macro viewpoints.

关键词： operational architecture air defense system super-network model Laplace spectral radius ripple-effect analysis.

Intercepts allocation for layered defense

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2016年第3期27卷 602-611页

作者： Longyue Li fuxian liu Guangzheng Long Pengsong Guo Yingying Mei Air and Missile Defense College Air Force Engineering UniversityXi'an 710051China Chongqing Nankai Secondary School Chongqing 400030China

One important mission of the strategic defense is to develop an integrated, layered ballistic missile defense system（BMDS）. Considering the problem of assigning limited defense weapons to incoming ballistic missiles, we illustrate how defense weapons, ballistic missiles, kill probability and effectiveness of defense（ED） are interrelated and how to understand this relationship for achieving the best allocation plan. Motivated by the queueing theory, in which the available resources are not sufficient to satisfy the demands placed upon them at all times, the layered deployed defense weapon is modeled as a queueing system to shoot Poisson arrived targets. Simultaneously, examples, of optimum intercepts allocation problems under different constraints are presented. The four theorems determine the allocation rules of intercepts to targets that maximize ED or minimize the cost to achieve a required ED.

关键词： intercepts allocation layered defense queueing theory effectiveness of defense

西南乡村振兴示范村空间分布特征及影响因素分析

在线全文

学校读者我要写书评

暂无评论

安徽农学通报 2024年第8期30卷 138-144页

作者：刘富仙王佑汉廖琴曾琨李谦丘陵地区国土资源统筹利用工程实验室四川南充637009 西华师范大学地理科学学院四川南充637009 西华师范大学商学院四川南充637009

村庄是乡村地区最普遍的空间表征和县域乡村振兴规划最基本的组织单元之一,本研究旨在通过分析乡村振兴示范村的空间分布特征和影响因素,为其示范村建设提供参考。本研究采用最近邻指数、地理集中指数、基尼系数、核密度分析、地理探测... 详细信息

村庄是乡村地区最普遍的空间表征和县域乡村振兴规划最基本的组织单元之一,本研究旨在通过分析乡村振兴示范村的空间分布特征和影响因素,为其示范村建设提供参考。本研究采用最近邻指数、地理集中指数、基尼系数、核密度分析、地理探测器和地理联系率,对西南某地1 947个乡村振兴示范村的空间分布特征和影响因素进行了探讨。结果表明,该地乡村振兴示范村空间分布类型为集聚型,且在市州内部表现为非均衡集聚,整体呈“东密西疏”,并在该地东部形成了“一带四点”的分布格局。自然环境、人口、社会经济、交通及资源禀赋对乡村振兴示范村的空间分布均有一定影响,经过因子探测分析发现,高程和坡度对乡村振兴示范村的空间分布影响较大,而交通条件、资源禀赋及河流水系对乡村振兴示范村空间分布影响较小。

关键词：乡村振兴示范村空间分布影响因素最近邻指数乡村规划

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

一种面向多属性不确定数据流的模体发现算法

电子与信息学报 2017年第1期39卷 159-166页

作者：王菊刘付显空军工程大学防空反导学院西安710051

该文针对多属性不确定数据流的频繁模式发现问题,借鉴生物信息学中的模体发现思想,提出了一种基于MEME(Multiple Expectation-maximization for Motif Elicitation)的多属性不确定数据流模体发现算法。该算法根据不确定数据流的特点,设... 详细信息

该文针对多属性不确定数据流的频繁模式发现问题,借鉴生物信息学中的模体发现思想,提出了一种基于MEME(Multiple Expectation-maximization for Motif Elicitation)的多属性不确定数据流模体发现算法。该算法根据不确定数据流的特点,设计了基于混合型模型的不确定滑动窗口更新计算方法,改进了SAX(Symbolic Aggregate appro Ximation)的符号化策略,提出了不同滑动窗口下多属性模体的相似性分析方法。在实验当中,用防空反导情报传感器网络中的一组不确定数据流验证了其功能,通过植入不同数目的模体测试了其发现准确率,并在元组有效概率设置为1的条件下与已有算法进行了比较,结果表明:该算法可以较准确地发现多属性不确定数据流中的频繁模式。

关键词：数据挖掘模体发现不确定数据流 MEME(Multiple Expectation-maximization for Motif Elicitation) 算法

在线全文

学校读者我要写书评

暂无评论

多射击模式多目标类型下防御效率分析

系统工程理论与实践 2017年第8期37卷 2200-2208页

作者：李龙跃刘付显空军工程大学防空反导学院西安710051

在军事对抗中,将作战双方抽象为防御方(红方)和进攻方(蓝方),研究红方的射击战斗问题.本文讨论蓝方目标无差别和目标多类型两种情况下的射击战斗,解决以下三个问题:一是在射击-射击策略下,基于给定的射弹和目标数,给出了红方获得最大防... 详细信息

在军事对抗中,将作战双方抽象为防御方(红方)和进攻方(蓝方),研究红方的射击战斗问题.本文讨论蓝方目标无差别和目标多类型两种情况下的射击战斗,解决以下三个问题:一是在射击-射击策略下,基于给定的射弹和目标数,给出了红方获得最大防御效率(defense effectiveness,DE)时射弹的分配方法;二是在射击-观察-射击策略下,考虑射击次数和齐射弹数等因素,给出了红方多次射击的DE迭代递推生成方法;三是给出了影响DE两个重要基础因素(射弹需求量和射击次数)的通用计算方法.通过仿真分析对本文给出的方法验证,保证了方法的可行性.

关键词：射击模式齐射-观察-齐射防御效率生成函数

在线全文

学校读者我要写书评

暂无评论

基于PSO的不确定时间序列模体发现算法

系统工程与电子技术 2018年第7期40卷 1639-1645页

作者：王菊刘付显靳春杰空军工程大学防空反导学院陕西西安710051 中国人民解放军93527部队河北张家口075000

针对不确定时间序列(uncertain time series,UTS)的模体发现(motif discovery,MD)问题,提出了基于粒子群(particle swarm optimization,PSO)的UTS MD算法。该算法根据UTS的特点,设计了基于PSO的UTS MD的研究框架,并通过对时间序列片段的起始时刻和持续时间进行编码和修正,实现了在该框架下对UTS的MD。在实验中,针对所提出的算法,验证了其可行性,比较了其与MK、MOEN算法在运行时间、占用内存和收敛性方面的性能,并分析了其MD准确率,结果表明所提方法占用较少内存与运行时间,可以发现不同长度的模体,且具有收敛性和较高的准确率。

关键词：不确定时间序列粒子群模体发现