基于自校正模糊神经控制的无刷直流传动系统

提出了一种自校正模糊神经网络控制器(SCFNNC)来实现无刷直流电动机起动、调速、制动等各运行阶段的性能指标.该SCFNNC是采用调整系统增益参数的方法完成较完善的控制规则的.重点研究了系统自校正增益参数的确定方法,模糊控制器的设计,人工神经网络实现模糊控制规则的方法等.自校正增益参数是根据系统对超调量、转速稳态误差、动态速降的期望值来确定的.设计模糊控制器时是根据系统的性能指标,确定出合适的模糊控制规则表,用于训练神经网络.为使系统的性能达到最佳,采用了自校正模糊神经控制、开关控制和比例控制相结合的复合控制方法,通过数学仿真证实配备SCFNNC的系统具有优良的动、静态特性,及较强的鲁棒性.     

基于PNN与FNN模型神经网络控制器设计与分析

模糊神经网络和预测神经网络分别是基于经验和学习的新型神经网络控制系统,通过在卧式电液仿真转台中框控制器上分别采用这2种控制方法来研究它们的控制特性和应用范围.其中,模糊神经网络结合了模糊控制的经验和神经网络的学习能力,但控制精度取决于人为经验;所研究的预测神经网络采用了基于非线性自回归滑动平均模型建立预测模型,实现在线学习和在线控制,但初始阶段控制精度不高.仿真研究证明,根据具体的控制对象采用适当的控制方法或是将2种方法合理地结合起来将会达到较高的控制精度.      

一种新的模糊控制方法及其仿真

提出了在难以精确描述控制对象数学模型的情况下,通过建立控制对象的模糊模型来确定系统的模糊控制规则,并对模糊系统进行仿真分析的思想。利用连续系统定性分析的思想,提出一种对模糊系统进行定性分析的可行方法,在相平面内较为准确地刻画模糊系统的动态行为。在模糊控制器的设计中,引入动态调节因子来提高模糊控制的精度,并采用了一种便于实际运算操作的解模糊运算方法。在一种简单的控制对象情况下进行了具体的仿真计算,得     

液压飞行仿真转台外框FNN控制器设计及仿真

以液压转台外框为控制对象,根据模糊控制理论,设计出直接自适应模糊控制器(DAFC,Direct Adaptive Fuzzy Controller)和同步模糊控制器(SFC,Synchronizing Fuzzy Controller)来解决外框负载干扰和双液压马达同步驱动这2个影响转台控制性能的主要问题;其中直接自适应模糊控制器还与PID控制器一起组成并行控制系统来抑制系统静态误差和动态干扰.针对模糊控制器自学习能力较差等缺陷,在模糊控制的基础上,根据模糊神经网络(FNN,Fuzzy Neural Net)模型设计出多输入多输出(MIMO,Multi-Input Multi-Output)的FNN控制器.软件仿真结果表明,当转台外框负载发生变化或外框两马达转速相差较大时,使用FNN模型的智能控制系统仍具有较高的位置跟踪精度和动态性能.      

无刷直流电动机的新型自适应模糊神经控制

 为无刷直流电动机提出了一种自适应模糊神经控制方法.这是一种建立在开关控制、模糊控制和自适应控制相结合基础上的控制方法,并用神经网络实现了模糊控制器和自适应机构.在无刷直流电动机的双闭环调速系统中,电流控制器是PI控制器;转速控制器是由1个开关控制器和1个包括自适应机构在内的模糊控制器相结合组成的,且用1个3层前向神经网络离线学习实现了模糊控制器,学习算法采用的是改进的BP算法.用1个单神经元通过在系统运行过程中的动态学习实现了自适应机构,学习算法选用了有监督的Hebb学习算法.由电机所处的运行阶段决定哪一个控制器工作.此控制算法的仿真结果说明,它使系统具有良好的动、静态特性和自适应性.     

用于卫星姿态机动控制的一种自适应模糊控制器

卫星的姿态机动控制要求机动快速和较强鲁棒性.纯模糊控制器响应快、鲁棒性好,能够方便地应用人的智能,但是模糊规则库的构建需要预先获取足够的语言信息.从Lyapunov函数出发设计了一个稳定的直接型自适应模糊姿态机动控制系统,控制器能够在初始语言信息很少的条件下通过自适应律调整语言信息参数而得到合适的模糊规则,使控制器具有更强的适应能力.数学仿真比较了在完全没有语言信息和有一条语言信息的情况下控制系统的表现,表明仅有一条语言信息时控制系统性能就能够显示得十分出色.最后,仿真结果证实了自适应模糊控制器良好的鲁棒性.      

机械臂的改进区间二型模糊神经网络控制

针对具有不确定性模型参数的双关节机械臂系统,提出基于改进区间二型模糊神经网络逼近器的自适应反演控制算法.相比于一型模糊系统,区间二型模糊系统由于自身的区间前件和隶属函数,更有效地处理高度非线性系统.然而现有的二型模糊寻找上下输出的交叉点过程中KM迭代算法计算量大、耗时高,使得传统的二型模糊系统不适用于实际控制应用.利用...     

自适应评判神经网络在微分对策中的应用

采用由3个神经网络组成的自适应评判神经网络结构求解微分对策的2点边值问题,其中2个 为控制神经网络,分别实现对微分对策系统中双边控制器的优化,一个为协 态神经网络,用于对2点边值问题中的协态变量进行求解,协态网络的输出对控制网络进行 校正,训练以后的2个控制网络作为双边的反馈控制器在线应用.并将神经网络结果与采用 Chebyshev技术的微分对策数字解进行了对比.追逃微分对策仿真结果表明了该方法的有效 性,并且对初始条件和测量噪声具有较强的鲁棒性.      

变结构航天器模糊神经网络滑模控制器设计

变结构航天器是目前航天领域的重要发展方向，航天器结构的变化将导致质量分布发生明显变化，这对航天器动力学建模和控制器设计都提出新的问题。针对这种情况，采用混合坐标法和拉格朗日方程建立了航天器刚柔耦合动力学模型，利用几种典型工况的参数近似得到变结构过程中动力学参数的变化规律。设计滑模控制器对航天器变结构过程进行姿态控制，为提高滑模控制器的适应性，设计模糊神经网络（FNN）自适应调节滑模控制器参数，并利用径向基函数（RBF）神经网络逼近动力学模型，得到控制力矩与姿态变化之间的近似关系，用于FNN的优化。通过仿真得到航天器变结构期间无控、滑模控制和模糊神经网络滑模控制的姿态变化，仿真结果对比验证了模糊神经网络滑模控制对于滑模控制的优势，证明了其在变结构航天器姿态控制方面的有效性。     

Mars entry fault-tolerant control via neural network and structure adaptive model inversion

The capability of autonomous fault detection and reconstruction is essential for future manned Mars exploration missions. Considering actuator failures and atmosphere uncertainties, we present a new active fault-tolerant control algorithm for Mars entry by use of neural network and structure adaptive model inversion. First, the online BP neural network is adopted to conduct the fault detection and isolation. Second, based on the structure adaptive model inversion, an adaptive neural network PID controller is developed for Mars entry fault-tolerant control. The normal PID controller will be automatically switched into neural network PID controller when an actuator fault is detected. Therefore, the error between the reference model and the output of the attitude control system would be adjusted to ensure the dynamic property of the entry vehicle. Finally, the effectiveness of the algorithm developed in this paper is confirmed by computer simulation.     

Adaptive neural network control of nonlinear systems with unknown dynamics

In this study, an adaptive neural network control approach is proposed to achieve accurate and robust control of nonlinear systems with unknown dynamics, wherein the neural network is innovatively used to learn the inverse problem of system dynamics with guaranteed convergence. This study focuses on the following three contributions. First, the considered system is transformed into a multi-integrator system using an input–output linearization technique, and an extended state observation technique is used to identify the transformed states. Second, an iterative control learning algorithm is proposed to achieve the neural network training, and stability analysis is given to prove that the network’s predictions converge to ideal control inputs with guaranteed convergence. Third, an adaptive neural network controller is developed by combining the trained network and a proportional-integral controller, and the long-standing challenge of model-based methods for control determination of unknown dynamics is resolved. Simulation results of a virtual control mission and an aerospace altitude tracking mission are provided to substantiate the effectiveness of the proposed techniques and illustrate the adaptability and robustness of the proposed controller.     

Adaptive fuzzy neural network control for a space manipulator in the presence of output constraints and input nonlinearities

Space manipulator is considered as one of the most promising technologies for future space activities owing to its important role in various on-orbit serving missions. In this paper, a novel adaptive fuzzy neural network (FNN) control scheme is proposed for the trajectory tracking control of an attitude-controlled free-flying space manipulator in the presence of output constraints and input nonlinearities. The parametric uncertainties and external disturbances are also taken into the consideration. First, a model-based controller is designed by using the barrier Lyapunov function (BLF) to prevent the position tracking errors from violating the predefined output constraints. Then, an adaptive FNN controller is designed by using two FNNs to compensate for the lumped uncertainties and input nonlinearities, respectively. Rigorous theoretical analysis for the semiglobal uniform ultimate boundedness of the whole closed-loop system is provided. The proposed adaptive FNN controller can guarantee the position and velocity tracking errors converge to the small neighborhoods about zero, while ensuring the position tracking errors within the output constraints even in the presence of input nonlinearities. To the best of the authors’ knowledge, there are relatively few existing controllers can achieve such excellent control performance in the same conditions. Numerical simulations illustrate the effectiveness and superiority of the proposed control scheme.     

基于模糊神经网络干扰观测器的组合体航天器姿态控制

针对非合作目标存在对抗性力矩输出情况下的组合体航天器姿态控制系统,提出了一种基于模糊神经网络干扰观测器（Fuzzy Neural Network Disturbance Observer,FNNDO）的非奇异终端滑模（Nonsingular Terminal Sliding Mode,NTSM）有限时间控制策略。首先以服务航天器为基准,建立组合体航天器姿态数学模型,然后针对包含惯量不确定性、目标对抗性力矩等的等效干扰力矩,设计了一种具有自适应能力的FNNDO,可以实现对等效干扰的有效跟踪。在FNNDO的基础上,设计NTSM控制器,利用Lyapunov理论证明闭环系统的有限时间稳定性。最后,仿真实验结果表明了控制策略的有效性和观测器在观测性能上的优越性。     

Stacked recurrent neural network based high precision pointing coupled control of the spacecraft and telescopes

In some space missions especially in the field of space gravitational wave detection, the telescope needs to point to a certain target through attitude movement and pointing control. In several mainstream gravitational wave detection missions, the detector usually consists of a cluster of three identical satellites, flying in a quasi-equilateral triangular formation with a big edge length, so every satellite needs two telescopes to point each other and constitute three giant Michelson-Type interferometers. Therefore, a satellite platform system with two telescopes is researched in this paper. This research helps to characterize the attitude motion of a telescope for space astronomical observation or space gravitational wave detection, provides new method on the telescope’s high-precision pointing control. For this purpose, we derive a satellite-telescope coupling attitude model, design the sliding mode controller for satellite and the stacked recurrent neural network adaptive controller for telescope. In the stacked recurrent neural network adaptive controller design, a sliding mode control technology is adopted. In addition, we propose a combinatorial optimization method for network weights in the stacked recurrent neural network training process, that is, the output layer is corrected by the adaptive law, and the correction of other layers adopt the error backpropagation method. Finally, a numerical simulation method verifies the effectiveness of the controller design.     

基于模糊控制的焊接机器人焊枪姿态规划

针对骑座式相贯线焊接机器人焊枪姿态的规划问题,提出了一种基于模糊控制的算法.以焊缝倾角、焊缝转角、坡口大小、被贯筒体厚度和相贯筒体厚度为输入变量,以焊接行走角和工作角为输出变量,建立多输入多输出系统模糊控制器;推导出各输入变量的隶属度函数;采用经验归纳法设计模糊控制规则,建立了相应的控制规则表;最后规划出焊枪的工作角和行走角.对不同的相贯筒体直径进行了仿真,结果表明,采用加权模糊专家系统对骑座式相贯线焊接机器人焊枪的工作角和行走角进行规划,可以有效的完成焊接过程焊枪的姿态控制.