Fault Detection and Diagnosis Based on Modeling and Estimation Methods

This paper investigates the problem of fault detection and diagnosis in a class of nonlinear systems with modeling uncertainties. A nonlinear observer is first designed for monitoring fault. Radial basis function (RBF) neural network is used in this observer to approximate the unknown nonlinear dynamics. When a fault occurs, another RBF is triggered to capture the nonlinear characteristics of the fault function. The fault model obtained by the second neural network (NN) can be used for identifying the failure mode by comparing it with any known failure modes. Finally, a simulation example is presented to illustrate the effectiveness of the proposed scheme.     

Sensor fault diagnosis for a class of time delay uncertain nonlinear systems using neural network

In this paper, a sliding mode observer scheme of sensor fault diagnosis is proposed for a class of time delay nonlinear systems with input uncertainty based on neural network. The sensor fault and the system input uncertainty are assumed to be unknown but bounded. The radial basis function (RBF) neural network is used to approximate the sensor fault. Based on the output of the RBF neural network, the sliding mode observer is presented. Using the Lyapunov method, a criterion for stability is given in terms of matrix inequality. Finally, an example is given for illustrating the availability of the fault diagnosis based on the proposed sliding mode observer.     

Intelligent adaptive observer-based optimal control of overhead transmission line de-icing robot manipulator

In cold season, wet snow ice accretion on overhead transmission lines increases wind load effects which in turn increases line tension. This increased line tension causes undesirable effects in power systems. This paper discusses the design of an observer-based boundary sliding mode control (BSMC) for 3 DOF overhead transmission line de-icing robot manipulator (OTDIRM). A robust radial basis functional neural network (RBFNN) observer-based neural network (NN) controller is developed for the motion control of OTDIRM, which is a combination of BSMC, NN approximation and adaptation law. The RBFNN-based adaptive observer is designed to estimate the positions and velocities. The weights of both NN observer and NN approximator are tuned off-line using particle swarm optimization. Using Lyapunov analysis the closed loop tracking error was verified for a 3 DOF OTDIRM. Finally, the robustness of the proposed neural network-based adaptive observer boundary sliding mode control (NNAOBSMC) was verified against the input disturbances and uncertainties.     

Neural network-based sliding mode adaptive control for robot manipulators

This paper addresses the robust trajectory tracking problem for a robot manipulator in the presence of uncertainties and disturbances. First, a neural network-based sliding mode adaptive control (NNSMAC), which is a combination of sliding mode technique, neural network (NN) approximation and adaptive technique, is designed to ensure trajectory tracking by the robot manipulator. It is shown using the Lyapunov theory that the tracking error asymptotically converge to zero. However, the assumption on the availability of the robot manipulator dynamics is not always practical. So, an NN-based adaptive observer is designed to estimate the velocities of the links. Next, based on the observer, a neural network-based sliding mode adaptive output feedback control (NNSMAOFC) is designed. Then it is shown by the Lyapunov theory that the trajectory tracking errors, the observer estimation errors asymptotically converge to zero. The effectiveness of the designed NNSMAC, the NN-based adaptive observer and the NNSMAOFC is illustrated by simulations.     

An online fault tolerant actor-critic neuro-control for a class of nonlinear systems using neural network HJB approach

In this paper, we propose an actor-critic neuro-control for a class of continuous-time nonlinear systems under nonlinear abrupt faults, which is combined with an adaptive fault diagnosis observer (AFDO). Together with its estimation laws, an AFDO scheme, which estimates the faults in real time, is designed based on Lyapunov analysis. Then, based on the designed AFDO, a fault tolerant actor- critic control scheme is proposed where the critic neural network (NN) is used to approximate the value function and the actor NN updates the fault tolerant policy based on the approximated value function in the critic NN. The weight update laws for critic NN and actor NN are designed using the gradient descent method. By Lyapunov analysis, we prove the uniform ultimately boundedness (UUB) of all the states, their estimation errors, and NN weights of the fault tolerant system under the unpredictable faults. Finally, we verify the effectiveness of the proposed method through numerical simulations.     

基于滑模观测器和神经网络的传感器故障诊断方法比较研究

针对航空发动机传感器故障诊断中各种方法的优势和劣势,选择滑模观测器和神经网络这两种故障诊断方法分别对航空发动机转速传感器进行故障诊断研究,采用实验室搭建的发动机实验台DGEN380的实验数据,选择对航空发动机控制系统影响较大的偏置故障、漂移故障、脉冲故障、周期性干扰故障这四类传感器故障进行诊断。研究结果表明,滑模观测器和IPSO-BP神经网络都能实现航空发动机传感器的故障诊断;滑模观测器方法可以诊断出偏置故障、脉冲故障和周期性干扰故障,但不能诊断出传感器发生的漂移故障; IPSO-BP神经网络方法可以诊断出偏置故障、漂移故障、脉冲故障和周期性干扰故障。因此,滑模观测器在故障诊断中可能会出现漏诊的现象,IPSO-BP神经网络相对滑模观测器而言不会出现漏诊的现象。     

High-order sliding mode observers and integral backstepping sensorless control of IPMS motor

This paper presents a robust high-order sliding mode interconnected observer and an integral backstepping controller for a sensorless interior permanent magnet synchronous motor. To limit the chattering phenomenon on the observed state, a super twisting algorithm is combined with an interconnected observer to design a new high-order sliding mode observer which will be used for multiple-input multiple-output systems. The proposed observer is used to estimate in finite time the rotor position, the speed and the stator resistance. Moreover, a robust nonlinear controller based on the backstepping algorithm is designed where integral actions are introduced step by step. This controller allows to track a desired reference which is computed by using a maximum-torque-per-ampere strategy. Simulation results are shown to illustrate the performance of the proposed scheme by using significant trajectories including the zero speed and under parametric uncertainties.     

双电机同步驱动伺服系统故障诊断与容错控制

本文针对双电机同步驱动伺服系统中执行器失效会导致系统性能下降甚至失稳的情况,提出了一种基于自适应滑模的故障诊断和容错控制策略.该方法通过设计各电机转速的自适应滑模状态观测器,在线估计各执行器的失效因子:当单个执行器部分失效时,通过自适应的方法调整控制器增益;当单个执行器全部失效时,重构系统的控制律.对于系统中存在非匹配不确定项的情况,提出在期望虚拟信号中引入基于扩张状态观测器的补偿项抑制方案;利用Lyapunov理论证明了闭环系统在正常和故障状况下的稳定性以及观测器的收敛性;仿真结果表明,所设计的控制策略能保证系统稳定跟踪指令信号,在单个执行器失效的情况下系统跟踪性能基本不下降.     

Observer‐Based Multiple Faults Diagnosis Scheme for Satellite Attitude Control System

This paper proposes a multiple fault diagnosis (MFD) scheme based on an observer method for satellite attitude control systems (ACSs) subject to nonlinearity and external disturbances of the system. The essential idea is to develop a fault diagnosis scheme and design the corresponding observers for satellite ACSs. The nonlinearity, space external disturbances, sensor uncertainties, and multiple faults problem of the satellite ACS are all taken into account. The proposed MFD scheme is developed at two different levels. First, at the system level, two nonlinear observers based on analytical redundancy are designed for the MFD of the satellite ACS; this level roughly reveals the fault source. Then, at the component level, a bank of sliding mode observers activated by the results of the previous diagnosis is designed to precisely diagnose multiple faults of actuators in the satellite ACS; this level further precisely reveals the fault source. Both the nonlinear observers and the sliding mode observers are confirmed to be asymptotically stable via Lyapunov stability theory. Finally, numerical simulations of a satellite ACS are performed to illustrate the effectiveness of the proposed MFD scheme.     

Synchronization and Tracking Control for Dual‐motor Driving Servo Systems with Friction Compensation

A nonsingular fast terminal sliding mode (NFTSM) controller is designed by incorporating the variable gain neural network (NN) observer, which is utilized to guarantee motor speed synchronization and load position tracking of dual‐motor driving servo systems. By designing the variable gain NN observer, the states and uncertain nonlinearities of servo systems are estimated with fast convergence rate and small steady‐state error, where the effects from external disturbance are suppressed as well. Based on the estimated states, the cross‐coupling synchronization strategy and NFTSM tracking scheme are designed to achieve the rapid speed synchronization and precise load tracking, where the NNs are introduced to approximate and compensate friction nonlinearities. In particular, a novel nonlinear synchronization factor characterizing the degree of speed synchronization is proposed to achieve switching between synchronization control and tracking control, which is proven to deal with the coupling problem of synchronization and tracking. Finally, the comparative simulations and experiments are included to verify the reliability and effectiveness.     

基于自适应滑模的欠驱动无人艇轨迹跟踪控制算法

针对欠驱动水面无人艇在航行过程中存在的海洋环境干扰、数学模型参数不确定、执行器故障等问题,提出了一种基于扰动观测器与神经网络技术的自适应滑模轨迹跟踪策略。在无人艇三自由度模型的基础上,结合视线制导率,提出了一种新的轨迹跟踪制导策略。采用自适应滑模控制技术设计了欠驱动无人艇轨迹跟踪控制器,有效地抑制了执行器衰减故障对无人艇控制系统的影响;同时运用了非线性扰动观测器和自适应径向基函数神经网络分别对无人艇受到的外界干扰和模型参数不确定性进行补偿和拟合,提高了控制系统的抗干扰能力。基于Lyapunov定理证明了所设计的控制系统的稳定性,并在MATLAB中进行了仿真测试。仿真结果表明,所提出的轨迹跟踪控制算法可以在较为复杂的环境下实现对欠驱动无人艇的精准控制;相较于对比算法,位置的平均跟踪误差减小了80%以上,具备较高的稳定性和鲁棒性。     

Extended observer-based hybrid tracking control strategy for networked system with FDI attacks

This paper studies the speed tracking control of networked control systems (NCSs) with external disturbance and false data injection (FDI) attacks. First, the system model with external disturbances and FDI attacks is built. Then, an extended observer based on discrete time sliding function and neural network (NN) is proposed to observe the extended states and suppress the effect of external disturbance and FDI attacks. Furthermore, a novel hybrid discrete-time sliding mode control (HDSMC) strategy combining discrete time sliding mode control with super-twisting control is designed to perform closed-loop control of the system, in which the exponential term and nonlinear term are constructed to restrain the jitters. The convergence and reachability of the sliding motion are proofed. Finally, the validity and feasibility of the proposed methods are proved by simulations and experiments.     

Optimal State Estimation and Fault Diagnosis for a Class of Nonlinear Systems

This study proposes a scheme for state estimation and,consequently,fault diagnosis in nonlinear systems.Initially,an optimal nonlinear observer is designed for nonlinear systems subject to an actuator or plant fault.By utilizing Lyapunov's direct method,the observer is proved to be optimal with respect to a performance function,including the magnitude of the observer gain and the convergence time.The observer gain is obtained by using approximation of Hamilton-Jacobi-Bellman(HJB)equation.The approximation is determined via an online trained neural network(NN).Next a class of affine nonlinear systems is considered which is subject to unknown disturbances in addition to fault signals.In this case,for each fault the original system is transformed to a new form in which the proposed optimal observer can be applied for state estimation and fault detection and isolation(FDI).Simulation results of a singlelink flexible joint robot(SLFJR)electric drive system show the effectiveness of the proposed methodology.     

Robust control for a class of time-delay uncertain nonlinear systems based on sliding mode observer

In this paper, a robust control scheme is proposed for a class of time-delay uncertain nonlinear systems with unknown input using the sliding mode observer. The sliding mode state observer is given with radial basis function neural networks, and then the robust control scheme is presented based on the designed sliding mode observer. The developed observer-based control scheme consists of two parts. One term is a linear controller and the other term is a neural network controller. Using the Lyapunov method, a criterion for bounded stability of the closed-loop system is developed in terms of linear matrix inequalities. Finally, a simulation example is used to illustrate the effectiveness of the proposed robust control scheme.     

基于观测器的水下机器人神经网络稳定自适应控制

给出了基于观测器的水下机器人神经网络自适应控制算法．控制算法由3部分组成：输出反馈控制、神经网络以及滑模项，其中输出反馈控制为了保证系统的初始稳定性；神经网络用于逼近系统的非线性动力学；滑模项用于补偿和抑制系统的外部扰动、神经网络逼近误差等．控制算法中所需要的速度量由状态观测器来提供．基于Lyapunov稳定理论给出了系统闭环稳定条件和稳定域．水池试验结果验证了算法的有效性．     

基于神经网络观测器的飞行器传感器故障检测

为了避免传感器故障对飞控系统的影响,实现传感器故障的快速检测与隔离,提出了一种基于神经网络观测器(NNOB)的传感器故障检测方法。在建立四旋翼飞行器姿态故障模型的基础上,利用非线性观测器得到的期望输出和传感器测量值设计基于神经网络(NN)的传感器故障观测器,利用扩展卡尔曼滤波器(EKF)更新神经网络的权值参数,通过Lyapunov理论证明权值参数更新的收敛性,最终构建出一种基于神经网络观测器的传感器故障检测系统。数值仿真实验结果表明,与现有神经网络故障检测方法相比,所提方法具有更高的故障检出率与更好的跟踪性能。     

一种基于滑模—神经网络观测器的故障检测和诊断方法

本文针对一类非线性系统，提出了一种用于故障检测和诊断的滑模观测器方法．其 中，观测器中的滑模项保证了该系统在无故障情况时的鲁棒性，并且系统运行的滑动区域提供了故障检测的条件．当检测出故障之后，观测器中的故障估计部分被启动，利用RBF神经网络估计故障，从而能在线辨识故障的形态．仿真结果验证了该方法的有效性．     

不确定非线性系统的自适应反推高阶终端滑模控制

针对一类非匹配不确定非线性系统,提出一种神经网络自适应反推高阶终端滑模控制方案.反推设计的前1步利用神经网络逼近未知非线性函数,结合动态面控制设计虚拟控制律,避免传统反推设计存在的计算复杂性问题,并抑制非匹配不确定性的影响;第步结合非奇异终端滑模设计高阶滑模控制律,去除控制抖振,使系统对于匹配和非匹配不确定性均具有鲁棒性.理论分析证明了闭环系统状态半全局一致终结有界,仿真结果表明了所提出方法的有效性.     

Fault Detection, Isolation, and Accommodation Control in Robotic Systems

In this paper, fault diagnosis and accommodation control are developed for robotic systems. First, a nonlinear observer in the proposed method is designed based on the available model. The fault detection is carried out by comparing the observer states with their signatures. Secondly, state observers are constructed based on possible fault function sets. Thirdly, the accommodation control design is developed using a normal controller plus a neural network compensator to capture the nonlinear characteristics of faults. Finally, if the fault isolation is completed successfully, the second fault accommodation controller is presented based on the fault information obtained by the isolation scheme.      

一类基于神经网络非线性观测器的鲁棒故障检测和诊断

利用神经网络的非线性建模能力，对一类具有建模不确定项的非线性系统提出一种基于观测器的故障检测和诊断的方法。设计的观测器不仅能实现故障检测，而旦应用神经网络设计的故障估计器能在线估计系统中的故障向量。通过分析验证了该方法对系统中的建模误差和外部扰动具有良好的鲁棒性。仿真结果表明所提出的方法是有效的。