A robust fault diagnosis and accommodation scheme for robot manipulators

This paper investigates an algorithm for robust fault diagnosis (FD) in uncertain robotic systems by using a neural sliding mode (NSM) based observer strategy. A step by step design procedure will be discussed to determine the accuracy of fault estimation. First, an uncertainty observer is designed to estimate the uncertainties based on a first neural network (NN1). Then, based on the estimated uncertainties, a fault diagnosis scheme will be designed by using a NSM observer which consists of both a second neural network (NN2) and a second order sliding mode (SOSM), connected serially. This type of observer scheme can reduce the chattering of sliding mode (SM) and guarantee finite time convergence of the neural network (NN). The obtained fault estimations are used for fault isolation as well as fault accommodation to self-correct the failure systems. The computer simulation results for a PUMA560 robot are shown to verify the effectiveness of the proposed strategy.     

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。     

Fault Diagnosis and Fault Tolerant Control for Manipulator with Actuator Multiplicative Fault

In this paper, a new fault diagnosis and fault tolerant control algorithm for manipulators with actuator multiplicative fault is proposed. The dynamic model of the manipulator with disturbance is taken as the research object. When faults occur in the actuator, a nonlinear observer based on radial basis function (RBF) neural network is used to estimate the fault information. After the fault information is obtained, an adaptive back-stepping sliding mode controller is used to control the manipulator to reach the desired trajectory. At last, an illustrated example is given to demonstrate the efficiency of the proposed algorithm, and satisfactory results have been obtained.

     

基于小波包神经网络的传感器故障诊断方法

讨论了小波包神经网络在传感器故障诊断中的应用问题.文中提出了将小波包分解提取各个节点特征能量与RBF神经网络进行模式分类的传感器故障诊断方法.通过三层小波包分解得到各个节点的分解系数,通过一定的削减算法使得故障的瞬态信号的特征得到加强,再根据重构的时域信号计算各个节点对应的能量,作为特征向量训练RBF神经网络.通过各种故障模式特征数据的训练,RBF网络具有了传感器故障诊断的功能.最后,通过工业锅炉流量传感器数据对训练之后的RBF神经网络进行检验,验证了这种方法的实用性和有效性.     

基于神经网络观测器的飞控传感器在线故障诊断

为提高无人机飞行安全可靠性,针对飞行控制系统中常出现的传感器故障以及非线性气动力模型参数难以确定的问题,提出了基于BP神经网络观测器估计的故障诊断方法;引用LM改进算法对网络参数进行调整,构造了神经网络观测器模型逼近非线性系统,并运用于飞行控制系统进行在线数字仿真,对垂直陀螺输出卡死故障、恒偏差故障和恒增益故障分别进行仿真分析;仿真结果表明,所设计神经网络观测器可以有效估计系统输出,在线诊断传感器故障。     

基于RBF终端滑模观测器的电机转子位置估计

无刷直流电机常采用位置传感器来检测转子位置,这会影响系统的可靠性,增加电机体积和成本。采用无位置传感器控制技术:引入终端滑模面,其具有快速收敛性和良好观测精度,可减少相位滞后问题;采用RBF神经网络来设计观测器的控制策略,将滑模变量作为神经网络输入,输出即为控制策略,简化控制结构。RBF终端滑模观测器将RBF控制与终端滑模控制的优点紧密结合,优化了控制信号,削弱了抖振现象。仿真结果表明,该观测器能快速准确地估计电机的线反电势及电机转速,系统具有良好性能,满足无刷直流电机的工作要求。     

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．     

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.     

Robust fault diagnosis and fault‐tolerant control for non‐Gaussian uncertain stochastic distribution control systems

The purpose of fault diagnosis of stochastic distribution control systems is to use the measured input and the system output probability density function to obtain the fault estimation information. A fault diagnosis and sliding mode fault‐tolerant control algorithms are proposed for non‐Gaussian uncertain stochastic distribution control systems with probability density function approximation error. The unknown input caused by model uncertainty can be considered as an exogenous disturbance, and the augmented observation error dynamic system is constructed using the thought of unknown input observer. Stability analysis is performed for the observation error dynamic system, and the H_∞ performance is guaranteed. Based on the information of fault estimation and the desired output probability density function, the sliding mode fault‐tolerant controller is designed to make the post‐fault output probability density function still track the desired distribution. This method avoids the difficulties of design of fault diagnosis observer caused by the uncertain input, and fault diagnosis and fault‐tolerant control are integrated. Two different illustrated examples are given to demonstrate the effectiveness of the proposed algorithm. Copyright © 2016 John Wiley & Sons, Ltd.     

基于RBF神经网络的多关节机器人固定时间滑模控制

针对具有典型非线性特性的多关节机器人轨迹跟踪控制问题,提出一种基于径向基函数(RBF)神经网络的固定时间滑模控制方法.首先,基于凯恩方法建立包括系统模型不确定性以及外部干扰在内的多关节机器人动力学模型;然后,根据机器人动力学模型设计一种固定时间收敛的滑模控制器,RBF神经网络用来逼近系统模型中的不确定性项,并利用Lyapunov理论证明该系统跟踪误差能在固定时间内收敛;最后,对特定型号的多关节机器人虚拟样机进行仿真分析,结果表明:与基于RBF神经网络的有限时间滑模控制器相比,所提出控制器具有良好的跟踪性能且能保证系统状态在固定时间内收敛.     

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.     

一类仿射型非线性系统智能故障诊断

针对一类仿射型非线性系统,在状态不完全可观测的条件下,研究其智能故障诊断问题.首先,利用微分同胚,提出系统观测器设计问题;然后针对该系统提出基于RBF神经网络逼近故障特性函数的故障诊断方法.所设计的观测器不仅能保证观测器稳定,而且通过观测误差信号识别系统故障的发生,保证了故障检测算法的鲁棒性和故障系统的稳定性;同时该设计方法对于设计常规的高增益观测器有一定帮助.最后通过仿真示例表明了所设计方法的有效性.     

Aero‐Engine DCS Fault‐Tolerant Control with Markov Time Delay Based On Augmented Adaptive Sliding Mode Observer

With a focus on aero‐engine distributed control systems (DCSs) with Markov time delay, unknown input disturbance, and sensor and actuator simultaneous faults, a combined fault tolerant algorithm based on the adaptive sliding mode observer is studied. First, an uncertain augmented model of distributed control system is established under the condition of simultaneous sensor and actuator faults, which also considers the influence of the output disturbances. Second, an augmented adaptive sliding mode observer is designed and the linear matrix inequality (LMI) form stability condition of the combined closed‐loop system is deduced. Third, a robust sliding mode fault tolerant controller is designed based on fault estimation of the sliding mode observer, where the theory of predictive control is adopted to suppress the influence of random time delay on system stability. Simulation results indicate that the proposed sliding mode fault tolerant controller can be very effective despite the existence of faults and output disturbances, and is suitable for the simultaneous sensor and actuator faults condition.     

基于RBF神经网络观测器飞控系统故障诊断

为了解决非线性系统采用解析方法进行故障诊断困难的问题,利用神经网络可逼近任意连续有界非线性函数的能力,提出了一种基于RBF神经网络观测器的故障检测与诊断方法,并详细论述了该故障诊断方法的构造原理。以含有非线性项的飞行控制系统的作动器模型为例,仅作动器的输入输出可测量,通过构造RBF神经网络观测器来拟合作动器系统模型,逼近其在正常情况下的输出。最后在飞控系统的闭环控制环境下,对作动器的三种典型故障进行了计算机仿真诊断,结果表明故障诊断方法是有效的。     

Fault tolerant sliding mode control for T-S fuzzy stochastic time-delay system via a novel sliding mode observer approach

In this paper, a fault estimation and fault-tolerant control problem for a class of T-S fuzzy stochastic time-delay systems with actuator and sensor faults is investigated. A novel sliding mode observer is proposed, which can simultaneously estimate the system states, actuator and sensor faults with good accuracy. Based on the state and actuator fault estimation, a new sliding mode control scheme is developed, which can effectively eliminate the influence of actuator fault. Sufficient conditions for the existence of the proposed observer and fault-tolerant sliding mode controller are provided in terms of linear matrix inequality, and moreover, the reachability of the sliding mode surface can be guaranteed under the proposed control scheme. The propose sliding mode observer and fault-tolerant sliding mode controller can overcome the restrictive assumption that the input matrix of all local modes is the same. Finally, a numerical example is provided to verify the effectiveness of the proposed sliding mode observer and fault-tolerant sliding mode control technique.     

基于RBF网络的高炉热流分析传感器故障诊断

在炼铁高炉热流强度分析系统中要用到温度、流量等传感器,为确保热流分析系统中传感器数据的可靠性及系统的连续、稳定运行,诊断系统用径向基函数(RBF)神经网络对传感器进行故障判断。系统由上位机、温度及流量采集装置、传感器等组成,采用RBF神经网络为每一个传感器建立预测模型,网络的输入为传感器采集信号最近的n个值,输出为该传感器在n+1时刻的预测输出值。网络通过在线学习实现对传感器的在线故障监测,经仿真分析表明:用RBF神经网络构建预测模型可满足实时性的诊断要求,提高了诊断系统的诊断精度。     

基于RBF的传感器在线故障诊断和信号恢复

介绍利用径向基神经网络构造了一种在线故障诊断及信号恢复方法,给出了网络的连接结构和学习算法。采用RBF神经网络进行传感器在线故障诊断和信号恢复,其仿真结果表明,该方法具有收敛速度快、信号恢复准确度高、泛化能力强的特点,且可以诊断多种复杂工作系统的传感器在线故障信号,同时进行信号的恢复。实现传感器状态监测、故障诊断、分离和信号恢复。     

Integrated fault estimation and fault‐tolerant control for uncertain Lipschitz nonlinear systems

This paper proposes an integrated fault estimation and fault‐tolerant control (FTC) design for Lipschitz non‐linear systems subject to uncertainty, disturbance, and actuator/sensor faults. A non‐linear unknown input observer without rank requirement is developed to estimate the system state and fault simultaneously, and based on these estimates an adaptive sliding mode FTC system is constructed. The observer and controller gains are obtained together via H_∞ optimization with a single‐step linear matrix inequality (LMI) formulation so as to achieve overall optimal FTC system design. A single‐link manipulator example is given to illustrate the effectiveness of the proposed approach. Copyright © 2016 John Wiley & Sons, Ltd.     

基于神经网络的无人机滑模飞行控制设计

针对无人机受扰运动,基于Backstepping方法和非线性滑模控制提出了一种鲁棒神经网络飞行控制方案。对无人机姿态角速度层的系统不确定性项,采用径向基函数神经网络并对其权值进行在线调整,从而实现对其进行逼近。将回馈递推设计方法与滑模控制方法结合起来,基于神经网络的输出为无人机设计了一种回馈递推滑模飞行控制器。所设计的飞行控制器用于无人机的姿态控制,仿真结果表明所研究的无人机鲁棒神经网络飞行控制方案是有效的。     

多故障并发非线性系统一体化跟踪主动容错控制器设计

针对一类执行器及传感器同时发生故障的非线性系统,综合鲁棒滑模重构观测器及自适应滑模容错控制器设计技术,提出一体化跟踪主动容错控制方案.首先,将系统增维变换为广义系统,运用广义约束逆引入辅助矩阵,采用线性矩阵不等式设计观测器系数矩阵,综合自适应律给出广义鲁棒滑模观测器设计程式;在此基础之上,通过设计鲁棒滑模微分器估计输出向量微分,结合广义鲁棒滑模观测器状态估计结论,实现执行器及传感器故障同时重构.其次,基于故障重构及状态估计结论,提出自适应滑模的跟踪主动容错控制律设计程式.最后,通过开展飞行模拟转台伺服系统数值仿真,检验一体化跟踪主动容错控制器设计方法的有效性.