期刊文献+
共找到87篇文章
< 1 2 5 >
每页显示 20 50 100
神经网络数据融合机动目标跟踪算法 被引量:11
1
作者 毕靖 王青 石晓荣 《北京航空航天大学学报》 EI CAS CSCD 北大核心 2002年第6期692-694,共3页
利用神经网络方法解决雷达 /红外双模制导中的数据融合问题 .红外数据经过异步数据融合处理与经过卡尔曼滤波处理后的雷达数据同步 ,共同作为神经网络的输入 ,神经网络作为同步融合中心 ,输出为目标的最优融合估计 .研究结果表明这种方... 利用神经网络方法解决雷达 /红外双模制导中的数据融合问题 .红外数据经过异步数据融合处理与经过卡尔曼滤波处理后的雷达数据同步 ,共同作为神经网络的输入 ,神经网络作为同步融合中心 ,输出为目标的最优融合估计 .研究结果表明这种方法可以在融合中心不知道协方差信息的情况下进行数据融合 . 展开更多
关键词 卡尔曼滤波 神经网络 雷达制导 红外制导 数据融合
下载PDF
Finite Time Convergent Wavelet Neural Network Sliding Mode Control Guidance Law with Impact Angle Constraint 被引量:12
2
作者 Qing-Chun Li Wen-Sheng Zhang +1 位作者 Gang Han Ying-Hua Zhang 《International Journal of Automation and computing》 EI CSCD 2015年第6期588-599,共12页
This paper presents a novel guidance law to intercept non-maneuvering targets with impact angle and lateral acceleration command constraints. Firstly, we formulate the impact angle control to track the desired line-of... This paper presents a novel guidance law to intercept non-maneuvering targets with impact angle and lateral acceleration command constraints. Firstly, we formulate the impact angle control to track the desired line-of-sight(LOS) angle, which is achieved by selecting the missile s lateral acceleration to enforce the sliding mode on a sliding surface at impact time. Secondly, we use the Lyapunov stability theory to prove the stability and finite time convergence of the proposed nonlinear sliding surface. Thirdly, we introduce the wavelet neural network(WNN) to adaptively update the additional control command and reduce the high-frequency chattering of sliding mode control(SMC). The proposed guidance law, denoted WNNSMC guidance law with impact angle constraint,combines the SMC methodology with WNN to improve the robustness and reduce the chattering of the system. Finally, numerical simulations are performed to demonstrate the validity and effectiveness of the WNNSMC guidance law. 展开更多
关键词 guidance law sliding mode control wavelet neural n
原文传递
基于最优制导模板的神经网络预测制导方法 被引量:11
3
作者 曾庆华 董荣华 皮术武 《国防科技大学学报》 EI CAS CSCD 北大核心 2014年第1期137-141,共5页
针对传统预测制导方法中高精度制导与快速实时解算之间的矛盾,提出了一种基于最优制导模板的神经网络预测制导方法。该方法采用基于高置信度飞行器运动模型仿真计算预测弹道落点,利用优化理论进行迭代解算制导变量,以此为基础离线生成... 针对传统预测制导方法中高精度制导与快速实时解算之间的矛盾,提出了一种基于最优制导模板的神经网络预测制导方法。该方法采用基于高置信度飞行器运动模型仿真计算预测弹道落点,利用优化理论进行迭代解算制导变量,以此为基础离线生成样本数据;通过选择合适的多结构模态神经网络,进行基于调度管理的神经网络训练,完成神经网络控制器的设计。针对CAV进行了算例设计,结果表明:该制导方法在线计算量少,制导解算速度快,制导精度高,综合性能远优于传统的预测制导方法。 展开更多
关键词 最优制导模板 神经网络 预测制导
下载PDF
强化学习在导弹制导中的应用 被引量:6
4
作者 周锐 陈宗基 《控制理论与应用》 EI CAS CSCD 北大核心 2001年第5期748-750,共3页
简述了强化学习的基本原理和特点 ,讨论了强化学习中评价函数的神经网络近似问题 ,重点分析了采用多神经网络近似评价函数的学习问题 ,实现了状态空间或任务的自动分解 ,提高了评价函数的推广能力 .网络的学习是离线进行 ,并作为反馈控... 简述了强化学习的基本原理和特点 ,讨论了强化学习中评价函数的神经网络近似问题 ,重点分析了采用多神经网络近似评价函数的学习问题 ,实现了状态空间或任务的自动分解 ,提高了评价函数的推广能力 .网络的学习是离线进行 ,并作为反馈控制器在线应用 .并以A 学习为例 ,将强化学习应用于导弹的制导问题 ,仿真结果表明了强化学习在导弹制导或控制问题中的应用前景和有效性 . 展开更多
关键词 神经网络 强化学习 微分对策 导弹制导 人工智能
下载PDF
Extracellular matrix and biomimetic engineering microenvironment for neuronal differentiation 被引量:4
5
作者 Deepak Jain Sabrina Mattiassi +1 位作者 Eyleen L.Goh Evelyn K.F.Yim 《Neural Regeneration Research》 SCIE CAS CSCD 2020年第4期573-585,共13页
Extracellular matrix(ECM)influences cell differentiation through its structural and biochemical properties.In nervous system,neuronal behavior is influenced by these ECMs structures which are present in a meshwork,fib... Extracellular matrix(ECM)influences cell differentiation through its structural and biochemical properties.In nervous system,neuronal behavior is influenced by these ECMs structures which are present in a meshwork,fibrous,or tubular forms encompassing specific molecular compositions.In addition to contact guidance,ECM composition and structures also exert its effect on neuronal differentiation.This short report reviewed the native ECM structure and composition in central nervous system and peripheral nervous system,and their impact on neural regeneration and neuronal differentiation.Using topographies,stem cells have been differentiated to neurons.Further,focussing on engineered biomimicking topographies,we highlighted the role of anisotropic topographies in stem cell differentiation to neurons and its recent temporal application for efficient neuronal differentiation. 展开更多
关键词 BIOMIMETIC platforms biophysical cues contact guidance extracellular matrix NEURONAL development neural regeneration neural STEM CELL niche NEURONAL differentiation NEURONAL maturation STEM CELL topography
下载PDF
基于神经网络的实时滚动追逃博弈导弹制导律 被引量:6
6
作者 朱强 邵之江 《系统工程与电子技术》 EI CSCD 北大核心 2019年第7期1597-1605,共9页
针对导弹实时滚动追逃博弈对抗双方制导律求解问题,设置了若干组对抗双方初始状态,采用分解正交配置法分别离线求解双边开环最优控制,并组成神经网络训练数据集。基于数据集将所有短周期初始和终止时刻对抗双方的状态和控制变量作为输... 针对导弹实时滚动追逃博弈对抗双方制导律求解问题,设置了若干组对抗双方初始状态,采用分解正交配置法分别离线求解双边开环最优控制,并组成神经网络训练数据集。基于数据集将所有短周期初始和终止时刻对抗双方的状态和控制变量作为输入和输出,采用反向传播(back propagation,BP)算法训练神经网络。然后分别在简单、复杂和不确定环境下,基于滚动时域优化框架使用BP神经网络估计短优化周期内双边开环最优控制,反馈更新对抗双方状态并重复上述过程,进而实时滚动求解导弹追逃博弈双边闭环最优控制。最后将上述方法和直接法得到的优化结果进行比较,捕捉点位置和博弈时间最大误差分别为0.554%和0.097%,两种方法的优化结果吻合较好。同时本文方法计算耗时明显下降,有效提高了导弹滚动追逃博弈制导律求解的实时性。 展开更多
关键词 神经网络 追逃博弈 导弹制导律 滚动时域优化
下载PDF
基于神经网络的鲁棒制导律设计 被引量:4
7
作者 周锐 张鹏 《航空学报》 EI CAS CSCD 北大核心 2002年第3期262-264,共3页
基于神经网络理论对寻的导弹鲁棒制导律进行了优化设计。建立了制导系统非线性运动学方程和鲁棒性能函数 ,并将鲁棒性能函数转化成了微分对策的极小极大化问题。采用伴随 BP技术 ,将微分对策的两点边值求解问题转化为 2个神经网络的学... 基于神经网络理论对寻的导弹鲁棒制导律进行了优化设计。建立了制导系统非线性运动学方程和鲁棒性能函数 ,并将鲁棒性能函数转化成了微分对策的极小极大化问题。采用伴随 BP技术 ,将微分对策的两点边值求解问题转化为 2个神经网络的学习问题 ,训练后的 2个神经网络分别作为对策双方的最优控制器在线使用 ,避免了直接求解复杂的鲁棒制导律问题 。 展开更多
关键词 微分对策 神经网络 导弹制导 鲁棒控制
下载PDF
基于神经网络航程估算模型的预测校正切换再入制导方法 被引量:5
8
作者 章吉力 刘凯 +1 位作者 樊雅卓 佘智勇 《战术导弹技术》 北大核心 2020年第5期93-100,164,共9页
针对升力式飞行器再入制导问题提出了一种智能预测校正制导方法。首先,以数值预测校正制导为出发点,考虑预测环节计算时间过长的问题,通过引入神经网络航程估算模型代替动力学积分过程,快速计算剩余飞行航程。然后,为了进一步降低神经... 针对升力式飞行器再入制导问题提出了一种智能预测校正制导方法。首先,以数值预测校正制导为出发点,考虑预测环节计算时间过长的问题,通过引入神经网络航程估算模型代替动力学积分过程,快速计算剩余飞行航程。然后,为了进一步降低神经网络训练数据规模,分析了飞行状态参数对剩余飞行航程的影响规律,对神经网络的结构进行了优化,设计了用于航程估算的全连接神经网络模型。最后,将训练好的神经网络模型应用于再入制导前中期,结合分段目标函数设计,在再入后期使用等距试探确定制导指令。蒙特卡罗仿真结果表明,所提出的基于神经网络航程估算模型的预测校正再入制导算法具有良好的鲁棒性,在保证精度的前提下提升了计算效率。 展开更多
关键词 神经网络 再入制导 预测校正 智能制导
原文传递
智能制导律研究综述 被引量:5
9
作者 方洋旺 邓天博 符文星 《无人系统技术》 2020年第6期36-42,共7页
制导律设计的优劣是导弹打击目标、执行其任务的关键,而随着人工智能技术的不断发展,设计智能化的制导律已经成为了学者们研究的热点问题。介绍美国远程反舰导弹LRASM、俄罗斯锆石高超声速反舰导弹以及挪威反舰导弹NSM等几种外军智能化... 制导律设计的优劣是导弹打击目标、执行其任务的关键,而随着人工智能技术的不断发展,设计智能化的制导律已经成为了学者们研究的热点问题。介绍美国远程反舰导弹LRASM、俄罗斯锆石高超声速反舰导弹以及挪威反舰导弹NSM等几种外军智能化导弹的发展现状,重点论述了当前国内外基于神经网络、模糊理论、强化学习等智能方法在制导律设计中的应用。对未来智能制导律的研究进行了展望,提出了在分布式多源异构信息融合条件下或是多约束和不确定条件下的单智能体智能制导律,以及协同智能制导律等多智能体智能制导律,为今后制导律的发展提供了切实可行的方向。 展开更多
关键词 智能制导律 神经网络 模糊理论 强化学习 多智能体 协同制导
下载PDF
RACK1 regulates neural development 被引量:4
10
作者 Leah Kershner Kristy Welshhans 《Neural Regeneration Research》 SCIE CAS CSCD 2017年第7期1036-1039,共4页
Receptor for activated C kinase 1(RACK1)is an evolutionarily conserved scaffolding protein within the tryptophan-aspartate(WD)repeat family of proteins.RACK1 can bind multiple signaling molecules concurrently,as w... Receptor for activated C kinase 1(RACK1)is an evolutionarily conserved scaffolding protein within the tryptophan-aspartate(WD)repeat family of proteins.RACK1 can bind multiple signaling molecules concurrently,as well as stabilize and anchor proteins.RACK1 also plays an important role at focal adhesions,where it acts to regulate cell migration.In addition,RACK1 is a ribosomal binding protein and thus,regulates translation.Despite these numerous functions,little is known about how RACK1 regulates nervous system development.Here,we review three studies that examine the role of RACK1 in neural development.In brief,these papers demonstrate that(1)RACK-1,the C.elegans homolog of mammalian RACK1,is required for axon guidance;(2)RACK1 is required for neurite extension of neuronally differentiated rat PC12cells;and(3)RACK1 is required for axon outgrowth of primary mouse cortical neurons.Thus,it is evident that RACK1 is critical for appropriate neural development in a wide range of species,and future discoveries could reveal whether RACK1 and its signaling partners are potential targets for treatment of neurodevelopmental disorders or a therapeutic approach for axonal regeneration. 展开更多
关键词 RACK1 RACK-1 neural development neurite outgrowth axon outgrowth axon guidance
下载PDF
visual bone marrow mesenchymal stem cell transplantation in the repair of spinal cord injury 被引量:4
11
作者 Rui-ping Zhang Cheng Xu +2 位作者 Yin Liu Jian-ding Li Jun Xie 《Neural Regeneration Research》 SCIE CAS CSCD 2015年第3期404-411,共8页
An important factor in improving functional recovery from spinal cord injury using stem cells is maximizing the number of transplanted cells at the lesion site. Here, we established a contusion model of spinal cord in... An important factor in improving functional recovery from spinal cord injury using stem cells is maximizing the number of transplanted cells at the lesion site. Here, we established a contusion model of spinal cord injury by dropping a weight onto the spinal cord at T7_8. Superparamagnet- ic iron oxide-labeled bone marrow mesenchymal stem cells were transplanted into the injured spinal cord via the subarachnoid space. An outer magnetic field was used to successfully guide the labeled cells to the lesion site. Prussian blue staining showed that more bone marrow mesen- chymal stem cells reached the lesion site in these rats than in those without magnetic guidance or snperparamagnetic iron oxide labeling, and immunofluorescence revealed a greater number of complete axons at the lesion site. Moreover, the Basso, Beattie and Bresnahan (BBB) locomotor rating scale scores were the highest in rats with superparamagnetic labeling and magnetic guid- ance. Our data confirm that superparamagnetic iron oxide nanoparticles effectively label bone marrow mesenchymal stem cells and impart sufficient magnetism to respond to the external magnetic field guides. More importantly, superparamagnetic iron oxide-labeled bone marrow mesenchymal stem cells can be dynamically and non-invasively tracked in vivo using magnetic resonance imaging. Superparamagnetic iron oxide labeling of bone marrow mesenchymal stem cells coupled with magnetic guidance offers a promising avenue for the clinical treatment of spinal cord injury. 展开更多
关键词 nerve regeneration superparamagnetic iron oxide magnetic guidance bone marrowmesenchymal stem cells spinal cord injury cell transplantation magnetic resonance image lumbarpuncture neural regeneration
下载PDF
基于神经网络的工业机器人视觉抓取系统设计 被引量:1
12
作者 燕硕 李建松 唐昌松 《计算机测量与控制》 2024年第4期201-209,共9页
针对机器人示教编程方法导致的工件位置固定、抓取效率低下的问题,研究神经网络在机器人视觉识别与抓取规划中的应用,建立了视觉引导方案,通过YOLOV5神经网络模型开发视觉识别系统,识别物体的种类,同时获取待抓取物体定位点坐标;提出了... 针对机器人示教编程方法导致的工件位置固定、抓取效率低下的问题,研究神经网络在机器人视觉识别与抓取规划中的应用,建立了视觉引导方案,通过YOLOV5神经网络模型开发视觉识别系统,识别物体的种类,同时获取待抓取物体定位点坐标;提出了机器人六点手眼标定原理并进行标定实验,提出了针对俯视图为圆形或长方形物体的定位方法;最后针对3种物体进行了180次的抓取实验,实验的综合平均抓取成功率约为92.8%,验证了视觉识别和抓取机器人系统具备实际应用的可能性,有效提高了抓取效率。 展开更多
关键词 神经网络 目标定位 机器人抓取 机器人标定 视觉引导
下载PDF
Trajectory tracking guidance of interceptor via prescribed performance integral sliding mode with neural network disturbance observer 被引量:1
13
作者 Wenxue Chen Yudong Hu +1 位作者 Changsheng Gao Ruoming An 《Defence Technology(防务技术)》 SCIE EI CAS CSCD 2024年第2期412-429,共18页
This paper investigates interception missiles’trajectory tracking guidance problem under wind field and external disturbances in the boost phase.Indeed,the velocity control in such trajectory tracking guidance system... This paper investigates interception missiles’trajectory tracking guidance problem under wind field and external disturbances in the boost phase.Indeed,the velocity control in such trajectory tracking guidance systems of missiles is challenging.As our contribution,the velocity control channel is designed to deal with the intractable velocity problem and improve tracking accuracy.The global prescribed performance function,which guarantees the tracking error within the set range and the global convergence of the tracking guidance system,is first proposed based on the traditional PPF.Then,a tracking guidance strategy is derived using the integral sliding mode control techniques to make the sliding manifold and tracking errors converge to zero and avoid singularities.Meanwhile,an improved switching control law is introduced into the designed tracking guidance algorithm to deal with the chattering problem.A back propagation neural network(BPNN)extended state observer(BPNNESO)is employed in the inner loop to identify disturbances.The obtained results indicate that the proposed tracking guidance approach achieves the trajectory tracking guidance objective without and with disturbances and outperforms the existing tracking guidance schemes with the lowest tracking errors,convergence times,and overshoots. 展开更多
关键词 BP network neural Integral sliding mode control(ISMC) Missile defense Prescribed performance function(PPF) State observer Tracking guidance system
下载PDF
Optimal predictive sliding-mode guidance law for intercepting near-space hypersonic maneuvering target 被引量:5
14
作者 Bolun ZHANG Di ZHOU 《Chinese Journal of Aeronautics》 SCIE EI CAS CSCD 2022年第4期320-331,共12页
The design of optimal guidance law for intercepting a near-space hypersonic maneuvering target with bounded inputs is considered. Firstly, a maneuvering model for near-space hypersonic aircraft is given. Then, the air... The design of optimal guidance law for intercepting a near-space hypersonic maneuvering target with bounded inputs is considered. Firstly, a maneuvering model for near-space hypersonic aircraft is given. Then, the aircraft acceleration prediction can be obtained using this model with two neural networks. By using the target acceleration prediction, which is taken into account when calculating the Zero Effort Miss(ZEM), an optimal sliding-mode guidance law is proposed to fulfill the guidance task. An adaptive sliding-mode switch term is designed to deal with actuator saturation and prediction errors. Finally, numerical simulations show that the proposed guidance law can reduce the energy consumption and the terminal acceleration command of the interceptor effectively. 展开更多
关键词 Adaptive sliding-mode control Near-space hypersonic aircraft neural networks Optimal control Predictive guidance law
原文传递
Single injection of platelet-rich plasma as a novel treatment of carpal tunnel syndrome 被引量:3
15
作者 Michael Alexander Malahias Elizabeth O.Johnson +1 位作者 George C.Babis Vasileios S.Nikolaou 《Neural Regeneration Research》 SCIE CAS CSCD 2015年第11期1856-1859,共4页
Both in vitro and in vivo experiments have confirmed that platelet-rich plasma has therapeutic effects on many neuropathies, but its effects on carpal tunnel syndrome remain poorly understood. We aimed to investigate ... Both in vitro and in vivo experiments have confirmed that platelet-rich plasma has therapeutic effects on many neuropathies, but its effects on carpal tunnel syndrome remain poorly understood. We aimed to investigate whether single injection of platelet-rich plasma can improve the clinical symptoms of carpal tunnel syndrome. Fourteen patients presenting with median nerve injury who had suffered from mild carpal tunnel syndrome for over 3 months were included in this study. Under ultrasound guidance, 1-2 m L of platelet-rich plasma was injected into the region around the median nerve at the proximal edge of the carpal tunnel. At 1 month after single injection of platelet-rich plasma, Visual Analogue Scale results showed that pain almost disappeared in eight patients and it was obviously alleviated in three patients. Simultaneously, the disabilities of the arm, shoulder and hand questionnaire showed that upper limb function was obviously improved. In addition, no ultrasonographic manifestation of the carpal tunnel syndrome was found in five patients during ultrasonographic measurement of the width of the median nerve. During 3-month follow-up, the pain was not greatly alleviated in three patients. These findings show very encouraging mid-term outcomes regarding use of platelet-rich plasma for the treatment of carpal tunnel syndrome. 展开更多
关键词 nerve regeneration carpal tunnel syndrome platelet-rich plasma ultrasound guidance pilot study neural regeneration
下载PDF
组合动作空间深度强化学习的人群疏散引导方法 被引量:4
16
作者 薛怡然 吴锐 刘家锋 《哈尔滨工业大学学报》 EI CAS CSCD 北大核心 2021年第8期29-38,共10页
人群疏散引导系统可在建筑物内发生灾害时有效保护生命安全,减少人员财产损失。针对现有人群疏散引导系统需要人工设计模型和输入参数,工作量大且容易造成误差的问题,本文提出了基于深度强化学习的端到端智能疏散引导方法,设计了基于社... 人群疏散引导系统可在建筑物内发生灾害时有效保护生命安全,减少人员财产损失。针对现有人群疏散引导系统需要人工设计模型和输入参数,工作量大且容易造成误差的问题,本文提出了基于深度强化学习的端到端智能疏散引导方法,设计了基于社会力模型的强化学习智能体仿真交互环境。使智能体可以仅以场景图像为输入,通过与仿真环境的交互和试错自主学习场景模型,探索路径规划策略,直接输出动态引导标志信息,指引人群有效疏散。针对强化学习深度Q网络(DQN)算法在人群疏散问题中因为动作空间维度较高,导致神经网络复杂度指数增长的“维度灾难”现象,本文提出了将Q网络输出层按动作维度分组的组合动作空间DQN算法,显著降低了网络结构复杂度,提高了系统在多个引导标志复杂场景中的实用性。在不同场景的仿真实验表明本文方法在逃生时间指标上优于静态引导方法,达到人工构造模型方法的相同水平。说明本文方法可以有效引导人群,提高疏散效率,同时降低人工构造模型的工作量并减小人为误差。 展开更多
关键词 神经网络 强化学习 疏散引导 人群仿真 深度Q网络
下载PDF
Design of Closed Loop Optimal Guidance Law Using Neural Networks 被引量:1
17
作者 ZHOU Rui 《Chinese Journal of Aeronautics》 SCIE EI CAS CSCD 2002年第2期98-102,共5页
It is generally impossible to obtain the analytic optimal guidance law for complex nonlinear guidance systems of homing missiles,and the open loop optimal guidance law is often obtained by numerical methods,which can ... It is generally impossible to obtain the analytic optimal guidance law for complex nonlinear guidance systems of homing missiles,and the open loop optimal guidance law is often obtained by numerical methods,which can not be used directly in practice.The neural networks are trained off line using the optimal trajectory of the missile produced by the numerical open loop optimal guidance law,and then,the converged neural networks are used on line as the feedback optimal guidance law in real time.The research shows that different selections of the neural networks inputs,such as the system state variables or the rate of LOS(line of sight),may have great effect on the performances of the guidance systems for homing missiles.The robustness for several guidance laws is investigated by simulations,and the modular neural networks architectures are used to increase the approximating and generalizing abilities in the large state space.Some useful conclusions are obtained by simulation results. 展开更多
关键词 neural networks missile guidance optimal guidance law proportional navigation guidance
下载PDF
基于神经网络的轨道武器再入制导研究 被引量:3
18
作者 杨兴宝 毕开波 《战术导弹技术》 2009年第2期45-49,共5页
将神经网络应用于轨道武器的弹道式再入制导中,实时得到所需航迹角,以此形成制导信号.对于具有较大再入初始误差及再入过程干扰、机动能力又不大的弹道式再入飞行器,可以给出满意的制导效果,而并不增加制导系统的复杂性.
关键词 神经网络 弹道式再入 再入制导
下载PDF
基于FCMAC干扰观测器的动态逆再入制导 被引量:3
19
作者 郑总准 王永骥 +1 位作者 吴浩 李传锋 《华中科技大学学报(自然科学版)》 EI CAS CSCD 北大核心 2010年第1期96-100,共5页
针对升力式飞行器不确定的非线性模型,提出了基于模糊小脑模型神经网络(FCMAC)干扰观测器的动态逆再入轨迹跟踪制导律.首先采用非线性动态逆设计阻力加速度-能量标准轨迹的跟踪方法;然后利用FCMAC网络良好的非线性逼近能力、泛化能力和... 针对升力式飞行器不确定的非线性模型,提出了基于模糊小脑模型神经网络(FCMAC)干扰观测器的动态逆再入轨迹跟踪制导律.首先采用非线性动态逆设计阻力加速度-能量标准轨迹的跟踪方法;然后利用FCMAC网络良好的非线性逼近能力、泛化能力和自学习能力,设计干扰观测器对模型的不确定性和外部干扰进行在线补偿;最后给出了闭环误差系统的鲁棒稳定性证明.仿真结果表明:FCMAC干扰观测器通过在线重构逆误差,降低了动态逆方法对模型的依赖,增强了跟踪系统的鲁棒性. 展开更多
关键词 神经网络 干扰观测器 再入制导 轨迹跟踪 动态逆
原文传递
针对过载控制的神经网络制导律研究 被引量:1
20
作者 王欣 赵云凯 王育欣 《兵器装备工程学报》 CAS CSCD 北大核心 2023年第10期139-146,共8页
针对高机动高突防能力目标的拦截问题,通过对比例导引律导引过程中过载与比例系数、视线角速率关系的分析,建立基于视线坐标系的三维弹-目相对运动模型,研究在该坐标系下的比例导引律加速度表现形式,据此设计实现K值自适应调整的RBF神... 针对高机动高突防能力目标的拦截问题,通过对比例导引律导引过程中过载与比例系数、视线角速率关系的分析,建立基于视线坐标系的三维弹-目相对运动模型,研究在该坐标系下的比例导引律加速度表现形式,据此设计实现K值自适应调整的RBF神经网络模型。通过与纯比例导引律的法向过载以及攻击时间对比,验证了RBF神经网络导引律在降低制导性能的前提下抑制视线角速率抖振、过载控制方面的有效性。 展开更多
关键词 神经网络 末制导 比例导引律 过载控制
下载PDF
上一页 1 2 5 下一页 到第
使用帮助 返回顶部