航空机电作动器神经网络快速终端滑模控制

目前机电作动器由于具有干净、维护方便等优点,越来越受到航空业的青睐。航空机电作动器的特点是控制精度、稳定性和响应速度要求高,针对以上特点,提出了一种基于多层神经网络的快速终端滑模控制策略。为了提高航空作动器响应速度和跟踪精度,设计了快速终端滑模控制策略,不仅可以加快系统响应而且可以在无扰动情况下实现系统的有限时间稳定。针对系统参数不确定性和外部扰动,设计多层神经网络进行估计并通过前馈方法加以补偿。针对神经网络的重构误差,设计了非线性鲁棒项加以克服。利用李亚普洛夫稳定性定理证明了控制系统在有扰动情况下可以实现有界稳定。实验结果表明：所设计的控制器具有良好的参数自适应和抗干扰能力,同时具有更高的跟踪精度和更快的响应速度。     

基于BP网络的光纤陀螺刻度因子建模研究

针对光纤陀螺(FOG)随温度呈非线性变化的特性,提出了采用BP神经网络对刻度因子的温度误差建模的方法,以减小光纤陀螺输出误差;用BP网络对其建模的结果和传统的建模结果进行了比较,结果表明采用BP神经网络对刻度因子的建模是非常有效的.     

基于自适应神经网络的非线性飞行控制

结合反馈线性化和神经网络提出了一种新的飞行控制系统设计方法,通过反馈线性化将非线性耦合系统等效转换为线性解耦系统,利用具有在线学习能力的神经网络补偿反馈线性化的误差,建立了基于自适应神经网络的控制结构,并利用李亚普诺夫函数导出了网络权值的自适应调整规则。在巡航弹地形跟踪应用中的结果表明,该控制系统不仅具有精确的跟踪性能而且具有良好的鲁棒性。     

漂浮基空间机器人捕获卫星过程动力学模拟及捕获后混合体运动的RBF神经网络控制

 讨论了漂浮基空间机器人在轨捕获目标卫星过程的碰撞动力学建模,以及捕获操作结束后空间机器人与卫星混合体的稳定控制问题。首先采用多刚体动力学建模方法并结合空间机器人捕获目标卫星过程中的碰撞动力学特性,建立了漂浮基空间机器人在轨捕获漂浮卫星过程的动力学模型,并在此基础上计算出完成捕获操作后空间机器人与目标卫星混合体关节的运动速度。然后针对卫星及空间机器人系统惯性参数均是未知的复杂情况,应用上述模型、神经网络控制理论和Lyapunov稳定性理论,设计了空间机器人与卫星混合体在捕获过程碰撞冲击影响下稳定运动的高斯径向基函数神经网络控制方案,以达到对捕获卫星的有效控制。此外,高斯径向基函数神经网络控制方案具有不需要测量和反馈载体位置、移动速度与加速度的显著优点。系统数值仿真证实了上述控制方案的有效性。     

超低空空投航迹倾角自适应跟踪控制

针对超低空空投下滑阶段考虑执行器输入死区、不确定性大气扰动以及模型存在未知非线性等因素干扰轨迹精确跟踪等问题,提出了一种自适应神经网络动态面跟踪控制方法.建立了含执行器输入死区的超低空空投载机纵向非线性模型,采用神经网络逼近模型中未知非线性函数,引入非线性鲁棒补偿项消除了执行器死区建模误差和外界扰动.应用Lyapunov稳定性理论证明了闭环系统所有信号均是有界收敛的.仿真验证表明,所提方法既保证了轨迹跟踪的精确性,又具有强鲁棒性.     

基于反馈误差学习的神经网络控制

研究了应用神经网络和ＰＤ反馈控制实现非线性系统的自适应跟踪问题。ＰＤ反馈控制器不但保证闭环系统的稳定性,同时其输出又作为训练神网络的参考信号。证明了通过选择适当的初始加权和加权的调节速率可以实现非线性系统的固定点跟踪。     

无人直升机的自适应非线性控制

最近几年，许多仿真结果都揭示了基于神经网络的直接自适应控制在飞行控制系统设计中的发展潜力。其中最重要的一点就是显著降低了对系统动态模型的要求。本文把该方法应用于无人直升机，给出了自适应姿态控制系统和跟踪控制器的设计方法。通过，数字仿真表明该控制方法有良好的跟踪控制性能。     

Robust control for an unmanned helicopter with constrained flapping dynamics

In this paper, a neural network based adaptive prescribed performance control scheme is proposed for the altitude and attitude tracking system of the unmanned helicopter in the presence of state and output constraints. For handling the state constraints, the barrier Lyapunov function and the saturation function are employed. And, the prescribed performance method is used to deal with the flapping angle constraints for the unmanned helicopter. It is proved that the proposed control approach can ensure that all the signals of the resulting closed-loop system are bounded, and the tracking errors are within the prescribed performance bounds for all time. The numerical simulation is given to illustrate the performance of the proposed scheme.     

基于神经网络自适应动态逆的结冰飞机飞行安全边界保护方法

考虑到飞机带冰飞行的安全问题，对结冰飞机进行安全边界保护成为一种有效的解决手段。基于神经网络自适应动态逆跟踪性能好、鲁棒性强的优点，提出了以安全关键飞行参数限制值作为神经网络自适应动态逆的输入，获取可用舵面偏转角的边界保护方法。建立了飞机本体动力学模型，采用高精度的数值模拟方法获得结冰数据库。设计了神经网络自适应动态逆控制律，通过在动态逆环节引入单隐层神经网络，对不确定性逆误差进行自适应补偿，增强了控制系统的鲁棒性。以俯仰姿态保持模式为例设计了结冰飞行闭环安全边界保护系统。以结冰飞机最小平飞速度的估算值作为飞机最低飞行速度，设计自动油门控制系统，实现对飞行速度的保护。通过仿真验证了设计的控制律具有较强的鲁棒性。对结冰严重程度线性增加情形下飞机状态参数的动态响应进行了分析。仿真结果表明，所设计的结冰边界保护系统，能够实现飞机在容冰飞行过程中对安全关键参数如迎角、飞行速度的实时保护。     

滚珠旋摆作动器的优化设计

提出了一种新型液压执行机构--滚珠螺旋液压旋摆作动器,建立了一套伺服动态优化设计理论及分析方法。在结构上,采用了多头大升角的滚珠螺旋副、滚珠花键副、滚珠卸荷副、活塞式液压缸等结构,以保证作动器受力特性好、传动平稳、效率高、且输出扭矩大,适应于低、中、高压任何压力的液压系统;在理论上,导出了滚珠螺旋液压旋摆作动器优化参数的设计计算公式,分析了优化参数与系统效率、频宽之间的关系。按照该理论设计的滚珠螺旋液压旋摆作动器,系统耗能最小、效率最高、频带最宽。     

神经网络在直升机对地攻击中的应用研究

应用神经网络方法研究了直升机对地射击的一些技术问题。文中首先介绍了直升机对地攻击的火控系统原理;其次,对复杂又不稳定的直升机飞行运动模型设计了模糊神经网络控制器;然后,设计了综合火/飞控制系统,并对所设计的整个攻击系统进行了仿真,通过仿真证明满足系统设计要求。在神经网络设计中,采用了变尺度优化算法,提高了算法的速度和精度,直升机对地攻击的实时应用提供了重要的参数价值。     

基于自适应神经网络的非线性飞控系统设计

将动态逆理论、神经网络和自适应控制相结合应用于非线性飞行控制系统设计中，通过动态逆控制律将非线性耦合系统转换为线性解耦系统，采用具有在线学习能力的神经网络来补偿反馈线性化中存在的逆误差，最后利用李亚普诺夫稳定性理论推导了在线网络权值的自适应调整规则。仿真结果表明，这种控制结构具有良好的跟踪能力和极强的鲁棒性。     

非线性自适应控制理论在无人直升机飞行控制系统设计中的应用

最近，国内外很多研究结果表明，基于神经网络的直接自适应控制方法，在飞行器控制系统设计中有着诸多优点。其中最重要的是它减少了设计对飞机动态特性高保真建模的依赖。这种设计方法在某无人直升机上得以实际飞行验证。本文主要介绍这种非线性自适应控制系统及其外回路航迹跟踪器的设计问题。     

High-torque density integrated electro-mechanical flight actuators

Electro-mechanical flight actuators (EMFAs) are core flight-critical vehicle components. Fly-by-wire or fly-by-light control of EMFAs is performed by flight management systems (flight, mission, propulsion, and integrated controls that manage any combination of specific flight, mission, and propulsion functions). Reported here are novel results in the analysis of EMFAs with permanent-magnet synchronous motors, with particular interest in the application of brushless high-torque density motors which have superior characteristics compared with other state-of-the-art motor technologies. It is shown that due to nonlinearities and bounds, new control algorithms must be developed and implemented to achieve a spectrum of performance and requirements for EMFAs. A number of important issues in control, analysis, model development, integration, and verification are studied. Tracking control algorithms are synthesized, stability studied, and novel analysis results are reported. Advanced computer-aided engineering software tools and emerging simulation-based design environments are used to guarantee high fidelity modeling and analysis within data intensive simulation. Proof-of-concept demonstration testbeds for the design of advanced EMFAs and their components are developed, and EMFA imitator performance thoroughly studied. Verification of the concepts reported are formed and documented. Precise tracking, disturbance attenuation, accuracy, stability, robustness, and excellent acceleration capabilities are reported. A demonstration is performed to substantiate the theoretical analyses to add credence to its applicability as an approach and method that the designer of future EMFAs can use to design a new class of actuators for aircraft flight control surfaces     

Robust dynamic output feedback control for switched polytopic systems under asynchronous switching

The robust controller design problem for switched polytopic systems under asynchronous switching is addressed.These systems exist in many aviation applications, such as dynamical systems involving rapid variations.A switched polytopic system is established to describe the highly maneuverable technology vehicle within the full flight envelope and a robust dynamic output feedback control method is designed for the switched polytopic system.Combining the Lyapunov-like function method and the average dwell time method, a sufficient condition is derived for the switched polytopic system with asynchronous switching and data dropout to be globally,uniformly and asymptotically stable in terms of linear matrix inequality.The robust dynamic output feedback controller is then applied to the highly maneuverable technology vehicle to illustrate the effectiveness of the proposed approach.The simulation results show that the angle of attack tracking performance is acceptable over the time history and the control surface responses are all satisfying along the full flight trajectory.     

多包传输网络控制系统的建模

作为系统分析和设计的基础,对网络控制系统建立合适的模型,意义尤显重要。本文对广义被控对象进行了分析,考虑了延时、系统噪声和数据包丢失的情况下,用一种统一的形式,建立了多包传输网络控制系统的模型。在系统中,传感器采用时间驱动方式,控制器和执行器采用事件驱动方式。这些模型的建立有利于网络控制系统的分析和网络控制系统控制器的设计。     

Closed-loop dynamic control allocation for aircraft with multiple actuators

A closed-loop control allocation method is proposed for a class of aircraft with multiple actuators. Nonlinear dynamic inversion is used to design the baseline attitude controller and derive the desired moment increment. And a feedback loop for the moment increment produced by the deflections of actuators is added to the angular rate loop, then the error between the desired and actual moment increment is the input of the dynamic control allocation. Subsequently, the stability of the closed-loop dynamic control allocation system is analyzed in detail. Especially, the closedloop system stability is also analyzed in the presence of two types of actuator failures: loss of effectiveness and lock-in-place actuator failures, where a fault detection subsystem to identify the actuator failures is absent. Finally, the proposed method is applied to a canard rotor/wing (CRW) aircraft model in fixed-wing mode, which has multiple actuators for flight control. The nonlinear simulation demonstrates that this method can guarantee the stability and tracking performance whether the actuators are healthy or fail.     

航空发动机多变量三层神经网络控制

提出了一种发动机多变量神经网络控制方法。采用三层前向神经网络对非线性项进行补偿,神经网络权重自适应律采用在线学习算法。控制系统的设计不需要知道精确模型,适应于全飞行包线。仿真研究表明发动机多变量神经网络控制具有良好的动、静态性能。      

适应型神经网络系统的控制

控制对象系统根据控制领域的不同，或多或少具有非线形特性。尤其汽车发动机系统中更具有很强的非线性。目前，三层构造的神经网络对于非线性系统的控制非常有效。     

Motion synchronization in a dual redundant HA/EHA system by using a hybrid integrated intelligent control design

This paper presents an integrated fuzzy controller design approach to synchronize a dis-similar redundant actuation system of a hydraulic actuator (HA) and an electro-hydrostatic actu-ator (EHA) with system uncertainties and disturbances. The motion synchronous control system consists of a trajectory generator, an individual position controller for each actuator, and a fuzzy force tracking controller (FFTC) for both actuators. The trajectory generator provides the desired motion dynamics and designing parameters of the trajectory which are taken according to the dynamic characteristics of the EHA. The position controller consists of a feed-forward controller and a fuzzy position tracking controller (FPTC) and acts as a decoupled controller, improving posi-tion tracking performance with the help of the feed-forward controller and the FPTC. The FFTC acts as a coupled controller and takes into account the inherent coupling effect. The simulation results show that the proposed controller not only eliminates initial force fighting by synchronizing the two actuators, but also improves disturbance rejection performance.