Application of neural networks for the design of flight control algorithms. II Adaptive tuning of neural network control law

In this paper, we consider different approaches for the neural network controller tuning in the flight control system. Two of the most common tuning approaches in the adaptive control theory are applied. The first one uses parameter identification technique and consists in solving a real-time regression problem for the control law. The second approach is based on the Lyapunov direct method, which utilizes a tracking error as an absolute measure of tuning performance. The neural network control law are designed for the three-axis flight control problem and tested on the full nonlinear model of a fighter aircraft. Closed loop simulation results are presented and two adaptation algorithms are compared in the case of abrupt change of aircraft dynamics.     

Neural networks in nonlinear aircraft flight control

This paper describes an approach for incorporating a neural network with real-time learning capability in a flight control architecture. The architecture is also applicable, in general, for the control of processes described by nonlinear differential equations of motion in which there exists a control for each degree of freedom. The main features are that the defining equations of motion for the process to be controlled are poorly known with respect to their functional forms, and that the functional forms, themselves, may undergo sudden and unexpected variation. It is well known that such systems are difficult to control, particularly when the effect of the control action enters nonlinearly. Numerical results based on 6DOF simulations of a high performance aircraft are presented to illustrate the potential benefits of incorporating neural networks as a part of a flight control system architecture     

Neural network modeling of flight control system

Modeling of angle tracking systems in the presence of actuator non-linearity such as angle, position and rate limits is a very significant and difficult task in the design and implementation of aircraft, target-tracking, and missile guided systems. A new recurrent neural network with time-delayed inputs and output feedback is used for the modeling of angle tracking systems, with emphasis on the neural network architecture, principles and algorithms. The neural network controller with modeling units for angle tracking is designed by using TMS320C25 processors. For time and size requirements, limited precision technology and look-up table technology are used in the design of the hardware and software systems. Given a set of input commands, the network is trained to control the system within the constraints imposed by actuators. The results show that the proposed networks are able to model the angle tracking system through learning without separate consideration of the non-linearity of actuators     

Electromechanical flight actuators for advanced flight vehicles

The aircraft flight quantities and success of the mission depend to a great extent upon the actuator performance, and flight actuators must be designed to achieve the specified criteria. Electromechanical flight actuators driven by electric motors have begun to displace hydraulic technology in advanced flight vehicles. In aerospace application, permanent-magnet stepper motors are perfectly suited due to their efficiency and reliability, low volume-, weight-, and size-to-torque ratios, high power and torque densities, low cost and maintenance, simplicity and ruggedness, etc. Conventional open-loop stepper motor servos do not ensure the required accuracy and dynamic performance. An innovative method in motion control of advanced electromechanical flight actuators is developed, and nonlinear controllers are designed. The specified tracking accuracy, desired stability margins, microstepping capabilities, and disturbance attenuation are ensured by the robust nonlinear controllers synthesized. Analytical, numerical, and experimental results are documented to study the performance of flight actuators directly driven by stepper motors and to demonstrate the efficiency of control algorithms     

基于数字虚拟飞行的民用飞机纵向地面操稳特性评估

针对民用飞机设计方案纵向地面操稳特性的评估需求,面向适航标准的要求,提出了一种基于数字虚拟飞行的评估方法。基于适航条例要求提出了纵向地面操稳特性的量化判定准则,建立了飞机的地面运动模型和驾驶员操纵模型,以实现起降等特定地面运行任务的数字虚拟飞行,最终依据数字虚拟飞行结果和判定准则对飞机设计方案的地面操稳特性做出评估。应用此方法研究了某大型运输类飞机的纵向地面操稳特性。数字虚拟飞行结果表明:前翻倾向的严重情况发生在起降过程的高速滑行段,主轮刹车引起的机身前翻倾向是显著的,起落架纵向定位参数设计以及飞行进近参数选择均会对飞机的纵向地面操稳特性产生影响。     

一种针对结构损伤的非线性容错飞行控制方法

飞机结构损伤会引起气动参数变化,进而影响系统的静稳定性和控制精度。针对具有多输入的非线性飞机模型,利用带有二阶命令滤波器的自适应反步控制方法在线估计飞机气动参数,补偿结构损伤导致的气动参数变化对控制系统的影响,以实现容错飞行控制功能;引入的命令滤波器可以避免反步控制中复杂的求导运算。从理论上分析证明了带有二阶命令滤波器的自适应反步控制的闭环系统稳定性,并给出了控制跟踪误差的理论上界和二阶命令滤波器频率参数选取的下界。通过一个大型客机垂直尾翼脱落场景的仿真实验,验证了所提容错控制方法的有效性。     

模糊自适应过失速飞行控制

研究了带推力矢量飞机过失速非线性飞机控制问题。根据奇异摄动理论将受控变量分为快变量和慢变量，然后分别对内环和外环进行设计，外环利用滑动面控制进行设计，内环利用模糊逻辑系统的万能特性来抵消近似非线性动态逆所带来的误差，根据李亚谱诺夫稳定性理论了模糊系统权值的自适应调整规律，从而保证闭环系统的稳定性。数字仿真结果表明：在存在较大的模型不确定性以及飞机动力学对状态和控制输入均为非线性的情况下，该控制方案能对指令进行良好的跟踪。     

基于神经网络的自动着陆飞行鲁棒自适应逆控制

针对飞机自动着陆飞行提出了基于神经网络的鲁棒自适应非线性动态逆控制器设计方案。首先采用非线性动态逆方法设计着陆飞行的基本控制律,再利用多层感知器神经网络设计适当的权值调整规则使其能够自适应地逼近和补偿逆误差。仿真结果表明,所设计的飞行控制系统是有效的,系统能够克服动态逆误差对着陆飞行控制带来的不利影响。     

复杂结冰环境下飞机鲁棒飞行安全包线分析

结冰是威胁飞行安全的重要环境因素,研究复杂结冰环境下飞机的飞行安全包线对于飞行安全边界保护,确保飞机飞行安全具有重要意义。以RCAM为研究对象,利用时间尺度分离原则将飞机解耦成两个子系统,建立了考虑飞机横向运动的纵向运动模型和复杂结冰环境下鲁棒气动导数模型。基于可达集最优控制理论,以反向可达集作为飞机复杂结冰环境下的飞行安全包线,利用可达性分析研究结冰及横向滚转运动对飞行安全包线的影响,在此基础上,进一步分析考虑不同结冰程度下结冰位置、冰型及分布等不确定性结冰情况时飞机的鲁棒飞行安全包线。仿真结果表明,随着结冰程度增加,飞行安全包线不断收缩,当考虑结冰不确定性因素时,轻度结冰条件下的鲁棒飞行安全包线较重度结冰条件下收缩更为严重。因此,即使飞机只是遭遇轻度结冰,但当存在不确定性因素时,飞行风险仍然较大,飞行员应该保持警惕。研究结果可为飞机在复杂结冰环境下的边界保护提供支撑和参考。     

Conceptual design and flight test of two wingtip-docked multi-body aircraft

To overcome the drawbacks such as large wing deformations, poor performance encountering gusts, limits in taking off and landing, inconvenience of transportation of High-Altitude Long-Endurance (HALE) Unmanned Aerial Vehicles (UAVs), a new conceptual aircraft called wingtip-docked Multi-Body Aircraft (MBA) has attracted lots of attentions. Aiming to investigate the feasibility of this concept, two UAV models were designed, manufactured and connected by a wingtip-docking mechanism, which only allows the relative roll motion between the two aircraft. The trim solution of the two connected aircraft is firstly obtained by solving the developed nonlinear flight dynamic equations, followed by the stability analysis based on the linearized model. The results show that the connected aircraft is inherently unstable and cannot fly without a reasonable flight control system. A set of Proportional-Integral-Derivative (PID) control laws was then developed and implemented in the two experimental aircraft. The success of the flight tests show that the flight control can effectively eliminate the unstable motion and the wingtip-docked MBA is controllable and feasible.     

超机动飞行非线性动态逆 - 模糊自适应控制

对带推力矢量飞机的飞控设计问题进行了研究。根据奇异摄动理论将受控状态变量分为快变量和慢变量，然后根据非线性动态逆理论分别对内环和外环进行设计。针对非线笥动态逆要求准确的数学模型的特点，引入模糊自适应控制以考虑模型的不确定性,最后对所设计的飞控规律进行过失速机动仿真。结果表明，在存在较大模型误差的情况下，所设计的飞控规律安全能在过失速机动条件下控制飞机跟踪指令飞行。     

Design of safety monitor schemes for a fault tolerant flight control system

For a research aircraft, "conventional" control laws (CLs) are implemented on a "baseline" flight computer (FC) while research CLs are typically housed on a dedicated research computer. Therefore, for an experimental aircraft used to test specific fault tolerant flight control systems, a safety logic scheme is needed to ensure a safe transition from conventional to research CLs (while at nominal conditions) as well as from research CLs at nominal conditions to conditions with "simulated" failures on specific control surfaces. This paper describes the design of such a safety scheme for the NASA Intelligent Flight Control System (IFCS) F-15 Program. The goals of the IFCS F-15 program are to investigate the performance of a set of fault tolerant CLs based on the use of dynamic inversion with neural augmentation. The different transitions are monitored using information relative to flight conditions and controller-related performance criteria. The testing of the scheme is performed with a Simulink-based flight simulation code and interface developed at West Virginia University for the NASA IFCS F-15 aircraft.     

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。     

超机动飞行推进系统稳定性控制研究

研究了超机动飞行推进系统稳定性控制。为增强过失速机动飞行条件下发动机稳定性,提出了通过增加风扇压比控制回路的发动机稳定性控制方案,并给稳定控制压比指令算法,在已建立的飞机和发动机非线性模型的基础上,进行了系统仿真。结果检验了稳定性控制概念的合理性。     

Nonlinear adaptive and sliding mode flight path control of F/A-18 model

The question of inertial trajectory control of aircraft in the three-dimensional space is discussed. It is assumed that the nonlinear aircraft model has uncertain aerodynamic derivatives. The control system is decomposed into a variable structure outer loop and an adaptive inner loop. The outer-loop feedback control system accomplishes (x,y,z) position trajectory and sideslip angle control using the derivative of thrust and three angular velocity components (p,q,r) as virtual control inputs. Then an adaptive inner feedback loop is designed, which produces the desired angular rotations of aircraft using aileron, elevator, and rudder control surfaces to complete the maneuver. Simplification in the inner-loop design is obtained based on a two-time scale (singular perturbation) design approach by ignoring the derivative of the virtual angular velocity vector, which is a function of slow variables. These results are applied to a simplified F/A-18 model. Simulation results are presented which show that in the closed-loop system asymptotic trajectory control is accomplished in spite of uncertainties in the model at different flight conditions.     

一种动态面神经网络鲁棒飞行控制律设计

提出一种基于RBF(Radial Based Function)神经网络和动态面控制的飞行控制律设计方法。针对飞机气动参数变化引起的非线性和不确定性,通过RBF神经网络在线逼近。动态面飞行控制律消除了反推设计方法中由于对虚拟控制反复求导而导致的复杂性问题。同时,在控制律设计中引入一个鲁棒因子项来补偿外界干扰和神经网络的逼近误差,提高了系统的鲁棒性,使整个系统获得更好的跟踪控制性能。基于Lyapunov稳定性定理证明了闭环系统的所有信号半全局一致终结有界,并且通过适当选择设计参数,跟踪误差可收敛到原点的一个小邻域内。最后,通过飞机俯仰运动飞行的数值仿真验证了该方法的有效性。     

I-O map inversion, zero dynamics and flight control

The trajectory control of aircraft in rapid, nonlinear maneuvers is discussed. Based on nonlinear invertibility theory, a control law is derived to independently control roll, pitch, and sideslip angles using rudder, elevator, and aileron. Integral feedback is introduced in order to obtain robustness in the control system to parameter uncertainty. The stability of the zero dynamics is examined. Simulation results are presented to show that in a closed-loop system, precise simultaneous lateral and longitudinal maneuvers can be performed despite the presence of uncertainty in the stability derivatives     

基于隐模型跟踪的倾转旋翼机飞行控制

针对倾转旋翼机过渡阶段的强耦合性和快时变性,基于隐模型跟踪法设计了过渡阶段的自主飞行控制律。首先,考虑短舱和旋翼相对机身运动带来的额外惯性力,建立了倾转旋翼机的多体动力学模型;然后,通过飞行动力学特性分析发现倾转旋翼机过渡阶段具有强耦合性和快时变性;最后,针对强耦合性使用隐模型跟踪法实现了固定倾转角时的解耦控制,针对快时变性使用插值调用控制参数的方法实现了倾转旋翼机在整个过渡阶段的连续控制。仿真结果表明,隐模型跟踪控制系统能够达到良好的速度和轨迹跟踪效果,可以实现倾转旋翼机在过渡阶段的自主飞行仿真。     

高机动导弹气动／运动／控制耦合的风洞虚拟飞行试验技术

解决先进飞行器大迎角高机动飞行时的气动／运动非线性耦合问题,需要发展基于非线性理论的风洞试验技术,即风洞虚拟飞行试验技术。该试验能够实现较为逼真的模拟飞行器机动运动过程,气动和运动参数的实时同步测量,以及飞行控制律的集成验证与优化,从而达到探索气动／运动耦合特性和机理的目的。本文介绍了风洞虚拟飞行试验的模拟方法、关键技术及其解决措施,并针对典型导弹模型开展了虚拟飞行验证试验。试验结果表明：目前已经初步具备适用于导弹模型跨声速气动／运动／飞行控制一体化研究的风洞虚拟飞行试验能力。     

A two-stage approach for managing actuators redundancy and its application to fault tolerant flight control

In safety-critical systems such as transportation aircraft, redundancy of actuators is introduced to improve fault tolerance. How to make the best use of remaining actuators to allow the system to continue achieving a desired operation in the presence of some actuators failures is the main subject of this paper. Considering that many dynamical systems, including flight dynamics of a transportation aircraft, can be expressed as an input affine nonlinear system, a new state representation is adopted here where the output dynamics are related with virtual inputs associated with the intended operation. This representation, as well as the distribution matrix associated with the effectiveness of the remaining operational actuators, allows us to define different levels of fault tolerant governability with respect to actuators’ failures. Then, a two-stage control approach is developed, leading first to the inversion of the output dynamics to get nominal values for the virtual inputs and then to the solution of a linear quadratic(LQ) problem to compute the solicitation of each operational actuator. The proposed approach is applied to the control of a transportation aircraft which performs a stabilized roll maneuver while a partial failure appears. Two fault scenarios are considered and the resulting performance of the proposed approach is displayed and discussed.