重型运载火箭预设时间自适应控制

针对存在模型不确定性及未知外部干扰的重型运载火箭姿态控制问题，提出一种新型预设时间自适应控制方法，使得姿态控制误差收敛时间与系统初始状态无关且可预先设定。首先设计一种新型预设时间滑模面，采用滑模面切换的方法避免系统出现奇异；然后设计预设时间滑模控制器，采用神经网络估计系统集总扰动并在控制器中进行补偿，设计自适应律自适应调整神经网络权重系数，基于Lyapunov稳定性定理证明了所设计控制器的预设时间稳定性；最后通过数值仿真验证了所提方法的可行性及有效性。     

直升机航向鲁棒保性能控制

针对具有时变不确定性且不确定性界为椭球的线性系统提出了一种新的具有自适应机制的鲁棒保性能控制器设计方法.首先,引入一个具有可由自适应律在线调整的可调参数的目标模型,通过该参数来保证由目标模型与被控模型所获得的误差系统渐近稳定.结合保证目标模型稳定性的设计,最终形成保证闭环系统稳定且控制器增益仿射依赖于可调参数的鲁棒保性能跟踪控制器.应用于安装在试验平台上的小型直升机航向控制中,仿真试验表明了该方法的有效性.     

基于RBF网络的机械人鲁棒自适应控制与仿真分析

针对电机驱动机器人模型,设计了一种鲁棒自适应控制器.首先用动态RBF神经网络逼近机器人动态模型,然后设计了一个带积分器的滤波器,由滤波器系统推导出所需的理想输入电流,再以理想输入电流为目标设计电机控制器并得到最终控制律.基于Lyapunov稳定理论分析了鲁棒自适应控制器的稳定性,给出了稳定性充分条件.实例仿真结果表明,合理的选择控制器参数可使系统具有良好的动态特性和鲁棒稳定性.     

基于状态观测器的非线性系统神经网络自适应控制

结合高增益观测器,针对相对阶为n的非线性系统,设计了神经网络自适应控制器。利用Lyapnov定理获得了神经网络权值的更新律和控制器的控制律,从而确保了整个闭环系统的稳定性和有界性。由于神经网络不需任何的离线训练,因而该控制器能够广泛应用于一大类非线性性系统的控制中。仿真结果验证了控制方案的有效性。     

欠驱动平面机械手自适应模糊滑模控制

采用自适应模糊滑模控制策略来实现欠驱动平面机械手的位置控制，定义滑模面为模糊输入，减少了模糊规则数量，模糊输出为通过自适应律在线调整幅值的单值函数，利用李亚普诺夫稳定性理论推导出自适应调整律，保证了系统的稳定性，提出的控制器由一个模糊滑模控制器和一个辅助控制器构成，模糊滑模控制器用来实现与滑模控制相等的控制律，辅助控制器用来补偿两者的差值，仿真结果表明了提出控制器的有效性和可行性。     

多入多出非仿射系统的径向基网络逆控制方法

针对多入多出非仿射非线性系统, 提出了一种径向基网络补偿逆模型误差的自适应控制方法. 将难以求逆的非仿射项分解为可逆部分和不可逆部分, 可逆部分作为理想逆来近似系统的直接逆, 逆模型误差用径向基网络的自适应控制信号补偿, 网络权值利用不可逆部分非仿射信息更新, 应用均值理论和Lyapunov函数证明了自适应控制律的稳定性. 仿真结果验证了该方法的有效性.     

基于可变增益的翼伞自适应模糊反步降高控制

针对含模型不确定性的无人动力翼伞低空降高控制问题,提出了一种基于可变增益的自适应模糊反步法控制策略。首先,推导了稳定航速下翼伞尾沿偏转变增益反步控制律,通过设计增益参数简化了控制器形式。然后,利用模糊逻辑系统在线逼近系统的不确定性,并加入自适应鲁棒项对逼近误差进行消除,采用Lyapunov理论得出的模糊系统权值和逼近误差自适应律,保证了闭环系统的一致最终有界性和跟踪精度。最后,针对控制器增益的组合形式,采用单独的模糊系统对增益参数进行在线调节。仿真结果验证了所提方法的有效性。     

基于神经网络的反步自适应大机动飞行控制

针对飞机大机动飞行时模型非线性和参数不确定性的特点,提出了一种基于全调节神经网络的反步自适应控制方法。飞机模型不确定部分由全调节径向基函数(radical basis function, RBF)神经网络在线补偿,控制律及神经网络参数自适应律由反步法回馈递推得到,并利用一种自适应参数策略的混沌粒子群算法优化控制器固定参数,改善动态性能,最后通过加权伪逆控制分配方法得到最终控制信号。仿真结果表明：在较大的模型气动参数不确定及控制增益矩阵未知时,所设计的控制律仍能理想地跟踪飞机大机动指令飞行,神经网络参数估计误差指数收敛到有界紧集,系统具有快速的收敛性和良好的鲁棒性。     

一种时变非线性系统的自适应逆控制仿真

对一种非线性时变系统提出了基于神经网络的自适应逆控制方案。该方案中用两个动态神经网络分别作为模型辨识器和自适应逆控制器,详细推导了在线训练自适应逆控制器的BPTM(backpropagationthroughmodel)和RTRL(realtimerecursivelearning)算法。根据大幅面喷墨打印机的结构特点,建立了打印头车架系统的时变非线性动力学模型作为仿真对象,在Matlab/Simulink平台下进行了算法仿真验证。结果表明了该方案收敛快,能有效控制该时变非线性对象。     

基于GA的非线性电机自适应模糊滑模控制器设计

提出一种基于GA的自适应模糊积分型滑模控制策略,并将其用于具有非线性动态摩擦力的单轴运动控制系统中.控制器由自适应模糊控制项和补偿控制项组成,自适应模糊控制项用来逼近理想滑模控制律,补偿控制项用来补偿逼近偏差,利用李亚普诺夫稳定性理论推导出模糊规则和补偿控制项中逼近偏差边界在线自适应律,采用遗传算法优化自适应律中参数.仿真和实验结果表明了该控制策略的有效性.     

Direct adaptive control for a class of MIMO nonlinear discrete-time systems

This paper considers the problem of adaptive con-trol for a class of multiple input multiple output （MIMO） nonlinear discrete-time systems based on input-output model with unknown interconnections between subsystems. Based on the Taylor ex-pand technology, an equivalent model in affine-like form is derived for the original nonaffine nonlinear system. Then a direct adap-tive neural network （NN） control er is implemented based on the affine-like model. By finding an orthogonal matrix to tune the NN weights, the closed-loop system is proven to be semiglobal y uni-formly ultimately bounded. The σ-modification technique is used to remove the requirement of persistence excitation during the adaptation. The control performance of the closed-loop system is guaranteed by suitably choosing the design parameters.     

Cooperative Neuro Adaptive Control of Leader Following Uncertain Multi-Agent Systems with Unknown Hysteresis and Dead-Zone

In this paper, a cooperative adaptive control of leader-following uncertain nonlinear multiagent systems is proposed. The communication network is weighted undirected graph with fixed topology. The uncertain nonlinear model for each agent is a higher-order integrator with unknown nonlinear functions, unknown disturbances and unknown input actuators. Meanwhile, the gains of input actuators are unknown nonlinear functions with unknown sign. Two most common behaviors of input actuators in practical applications are hysteresis and dead-zone. In this paper, backlash-like hysteresis and dead-zone are used to model the input actuators. Using universal approximation theorem proved for neural networks, the unknown nonlinear functions are tackled. The unknown weights of neural networks are derived by proposing appropriate adaptive laws. To cope with modeling errors and disturbances an adaptive robust structure is proposed. Considering Lyapunov synthesis approach not only all the adaptive laws are derived but also it is proved that the closed-loop network is cooperatively semi-globally uniformly ultimately bounded(CSUUB). In order to investigate the effectiveness of the proposed method, it is applied to agents modeled with highly nonlinear mathematical equations and inverted pendulums. Simulation results demonstrate the effectiveness and applicability of the proposed method in dealing with both numerical and practical multi-agent systems.     

Adaptive control of system with hysteresis using neural networks

1.INTRODUCTIONThe piezoelectric actuators are well suited for micro-position devices in precision engineering because oftheir fast response,nanometer resolution and biggerdriving force[1].However,hysteresis inherent topiezoelectric actuator severely li mits system’s perfor-mance such as giving rise to undesirable accuracy oroscillations,even leading to instability.Hysteresischaracteristics are generally nondifferentiable andusually unknown.It is a difficult task to mitigate itsharmful ef…     

基于神经网络的自由漂浮空间机器人鲁棒控制

针对带有模型误差及外界扰动的自由漂浮空间机器人轨迹跟踪问题,提出了一种基于神经网络的自适应鲁棒控制策略。采用对神经网络状态空间进行划分后与滑模变结构结合的控制器,对不确定非线性进行自适应学习,逼近误差作为外部干扰由鲁棒控制器消除。该方法从整个闭环系统的稳定性出发,利用H_∞理论设计的鲁棒控制器及神经网络权值的在线调整规则保证了系统的稳定性,并能使系统L2增益小于给定的指标,具有较好的控制精度及动态特性。仿真分析进一步证明了该自适应鲁棒控制算法的有效性。     

基于遗传预估策略的智能主动队列管理

针对TCP传输过程中的典型时滞特性,提出了一种智能主动队列管理算法.该算法以自学习预估机制模型为核心来克服大时滞特征对网络稳定性能的影响,拥塞控制系统以两条信息通道分别实现模型补偿和预测控制功能.模型补偿通道采用了Smith预估嚣实现对网络时滞特征的动态补偿,并进一步设计迭代进化算法实现对Smith预估模型未建模特征的估计过程.预测控制通道采用基于神经网络的PID智能丢弃算法,通过神经网络的学习预测功能自适应调整预测控制通道的控制行为.通过仿真研究表明了提出的控制方法显著提高了拥塞控制机制的稳定性能和自适应性能.     

大型轮式工程车辆转向系统的神经网络PID控制

根据大型轮式工程车辆转向系统的对象特点和操纵方式，提出采用基于RBF神经网络控制器来改进常规PID控制器实现系统控制性能。该控制系统结构中，RBF神经网络辨识器(RBFNNI)实现对被控对象的Jacobian矩阵信息的辨识，神经网络控制器(NNC)是基于RBF神经网络实现的单神经元的PID控制器。在对算法进行改进的基础上设计了神经网络结构，并进行了被控对象的仿真分析。实际结果表明该控制方法具有较好的实用性和鲁棒性，可以用于多操纵模式工程车辆转向系统的控制。     

Neural network based adaptive sliding mode control of uncertain nonlinear systems

The purpose of this paper is the design of neural network-based adaptive sliding mode controller for uncertain unknown nonlinear systems. A special architecture adaptive neural network, with hyperbolic tangent activation functions, is used to emulate the equivalent and switching control terms of the classic sliding mode control (SMC). Lyapunov stability theory is used to guarantee a uniform ultimate boundedness property for the tracking error, as well as of all other signals in the closed loop. In addition to keeping the stability and robustness properties of the SMC, the neural network-based adaptive sliding mode controller exhibits perfect rejection of faults arising during the system operating. Simulation studies are used to illustrate and clarify the theoretical results.     

A new neural network-based adaptive ILC for nonlinear discrete-time systems with dead zone scheme

By introducing a dead-zone scheme, a new neural network based adaptive iterative learning control (ILC) (NN-AILC) scheme is presented for nonlinear discrete-time systems, where the NN weights are time-varying. The most distinct contribution of the proposed NN-AILC is the relaxation of the identical conditions of initial state and reference trajectory, which are common requirements in traditional ILC problems. Convergence analysis indicates that the tracking error converges to a bounded ball, whose size is determined by the dead-zone nonlinearity. Computer simulations verify the theoretical results. This research is supported by General Program (60774022) and State Key Program (60834001) of National Natural Science Foundation of China, and Doctoral Foundation of Qingdao University of Science & Technology (0022324).