基于概率神经网络的故障诊断方法及应用

针对智能大厦空调系统中发生的各种传感器故障问题 ,提出了一种基于概率神经网络 (PNN)的传感器故障诊断改进方法。该方法采用贝叶斯分类决策理论建立系统的数学模型 ,以高斯函数作为激励函数 ,具有非线性处理和抗干扰能力强等特点 ,可获得对空调系统中各种传感器硬故障和软故障的有效识别和诊断。给出了该方法的理论分析 ,故障特征量的选取 ,神经网络设置和训练的具体步骤。通过仿真和空调系统模型试验证明了该方法在网络训练速度 ,抗干扰能力及各种传感器故障识别准确率等方面的有效性。     

Diagnosis of process faults and sensor faults in a class of nonlinear uncertain systems

This paper presents a fault diagnosis method for process faults and sensor faults in a class of nonlinear uncertain systems.The fault detection and isolation architecture consists of a fault detection estimator and a bank of adaptive isolation estimators,each corresponding to a particular fault type.Adaptive thresholds for fault detection and isolation are presented.Fault detectability conditions characterizing the class of process faults and sensor faults that are detectable by the presented method are derived.A simulation example of robotic arm is used to illustrate the effectiveness of the fault diagnosis method.     

基于神经网络的飞控系统实时容错设计与仿真

为了提高系统的可靠性与容错能力,提出了基于径向基神经网络的飞行控制系统传感器实时容错策略.利用改进的梯度下降优化算法来设计神经网络,以提高网络的学习速度和映射能力;基于网络的逼近性能,建立在线神经网络辨识模型;考虑到系统闭环反馈与实时控制的特性,使用多个辨识模型的信息进行传感器故障的定位和信号重构.应用某型飞机进行仿真,在保证闭环系统稳定的前提下,实现了传感器的在线故障隔离与信号重构,达到了预期的效果.     

空调箱传感器故障在线检测和诊断新方法

针对空调箱的温度、流量等传感器进行固定偏差和漂移故障的检测与诊断,提出了一种基于统计学的方法进行在线的故障检测和诊断。主成分分析法根据系统正常的历史数据建立数理统计模型,通过传感器实际测量数据与正常数据在故障子空间投影的比较,对传感器的故障进行在线检测。联合角度法改进了传统的贡献图的诊断方法,通过对故障库中的故障知识的利用,能够在线的分离出发生故障的传感器。     

Multiobjective fault detection and isolation for flexible air-breathing hypersonic vehicle

An application of the multiobjective fault detection and isolation (FDI) approach to an air-breathing hypersonic vehicle (HSV) longitudinal dynamics subject to disturbances is presented. Maintaining sustainable and safe flight of HSV is a challenging task due to its strong coupling effects, variable operating conditions and possible failures of system components. A common type of system faults for aircraft including HSV is the loss of effectiveness of its actuators and sensors. To detect and isolate multiple actuator/sensor failures, a faulty linear parameter-varying (LPV) model of HSV is derived by converting actuator/system component faults into equivalent sensor faults. Then a bank of LPV FDI observers is designed to track individual fault with minimum error and suppress the effects of disturbances and other fault signals. The simulation results based on the nonlinear flexible HSV model and a nominal LPV controller demonstrate the effectiveness of the fault estimation technique for HSV.     

线性时滞系统的鲁棒故障诊断

研究了一类含有未知输入干扰和模型不确定性的时滞系统故障诊断问题。通过变换,原系统被分成两个子系统,一个子系统不受故障的影响,可以设计鲁棒观测器;另一个子系统受到故障的影响,但是它的状态可以通过测量得到。设计的观测器利用解析冗余方法能够对执行器故障和传感器故障进行诊断。仿真结果表明,算法具有良好的诊断性能。     

神经网络主元分析的传感器故障诊断方法

针对多传感器故障诊断问题，将神经网络引入主元分析(principal component analysis, PCA)模型之中，提出一基于主元分析的多传感器故障诊断模型。首先，应用传感器正常工作时测量的历史数据，由PCA模型得到所有传感器的预测值。其次，计算传感器系统的平方预期误差值(squared prediction error, SPE),根据系统的SPE值是否跳变，判定有无故障发生。通过分别重构单个传感器信号的SPE值来确定发生故障的传感器。最后,应用一个多传感器故障诊断仿真实例证明了该方案的可行性。     

基于T-S模糊模型的鲁棒故障诊断

针对T-S模糊模型描述的具有外部干扰的非线性不确定系统,构造了相应的测量冗余方程和模糊奇偶方程,给出并证明了对特定传感器和执行器故障敏感的最优奇偶向量的存在条件和求解定理,采用奇偶方程故障检测与诊断方法,研究了非线性不确定系统的鲁棒故障检测和诊断.最后,通过仿真示例说明了所提出的方法是有效的.     

ToMFIR-based fault detection approach in frequency domain

This paper is to explore further results for total measurable fault information-based residual (ToMFIR) approach to fault detection in dynamic systems. The ToMFIR contains the essential fault information and remains unaffected by control actions in a closed-loop system. It is composed of controller residual and output residual and some of further results are developed in frequency domain. Besides the ability of detecting actuator and sensor faults, it is able to detect faults/failures resulting from the computer used for control purpose that generates control signals. Currently, all of existing fault detection schemes cannot achieve the same task at all. A practical DC motor example, with a PID controller, is used to demonstrate the effectiveness of the ToMFIR-based fault detection. A comparison with the standard observer-based technique is also provided.     

基于AR模型和支持向量机的转子系统故障诊断方法

提出了基于AR模型和支持向量机的转子系统故障诊断方法.该方法对转子系统的振动信号建立AR模型,以AR模型主要的自回归参数和残差的方差作为特征向量,然后建立支持向量机分类器,进而判断转子系统的工作状态和故障类型.实验结果分析表明,该方法能有效地应用于转子系统的故障诊断.并通过支持向量机与BP神经网络的性能比较,说明了支持向量机的优点.     

Sensor fault-tolerant observer applied in satellite attitude control

The observing failure and feedback instability might happen when the partial sensors of a satellite attitude control sys- tem (SACS) go wrong. A fault diagnosis and isolation (FDI) method based on a fault observer is introduced to detect and isolate the fault sensor at first. Based on the FDI result, the object system state-space equation is transformed and divided into a corresponsive triangular canonical form to decouple the normal subsystem from the fault subsystem. And then the KX fault-tolerant observers of the system in different modes are designed and embedded into online monitoring. The outputs of all KX fault-tolerant observers are selected by the control switch process. That can make sense that the SACS is part-observed and in stable when the partial sensors break down. Simulation results demonstrate the effectiveness and superiority of the proposed method.     

Fault tolerant navigation method for satellite based on information fusion and unscented Kalman filter

An effective autonomous navigation system for the integration of star sensor, infrared horizon sensor, magnetometer, radar altimeter and ultraviolet sensor is developed. The requirements of the integrated navigation system manager make optimum use of the various navigation sensors and allow rapid fault detection, isolation and recovery. The normal full fusion feedback method of federated unscented Kalman filter (UKF) cannot meet the needs of it. So a no-reset feedback federated Kalman filter architecture is developed and used in the autonomous navigation system. The minimal skew sigma points are chosen to improve the calculation speed. Simulation results are presented to demonstrate the advantages of the algorithm. These advantages include improved failure detection and correction, improved computational efficiency, and reliability. Additionally, its’ accuracy is higher than that of the full fusion feedback method.     

Distributed event region fault-tolerance based on weighted distance for wireless sensor networks

Event region detection is the important application for wireless sensor networks (WSNs), where the existing faulty sensors would lead to drastic deterioration of network quality of service. Considering single-moment nodes fault-tolerance, a novel distributed fault-tolerant detection algorithm named distributed fault-tolerance based on weighted distance (DFWD) is proposed, which exploits the spatial correlation among sensor nodes and their redundant information. In sensor networks, neighborhood sensor nodes will be endowed with different relative weights respectively according to the distances between them and the central node. Having syncretized the weighted information of dual-neighborhood nodes appropriately, it is reasonable to decide the ultimate status of the central sensor node. Simultaneously, readings of faulty sensors would be corrected during this process. Simulation results demonstrate that the DFWD has a higher fault detection accuracy compared with other algorithms, and when the sensor fault probability is 10%, the DFWD can still correct more than 91% faulty sensor nodes, which significantly improves the performance of the whole sensor network.     

基于RMMAC的集成主动容错飞行控制

针对主动容错飞行控制系统设计问题,提出一种基于改进鲁棒多模型自适应控制(robust multiplemodel adaptive control,RMMAC)的故障检测与控制重构集成设计方法。建立了飞行器传感器和执行器故障的数学模型,介绍了改进鲁棒多模型自适应控制算法的结构和实现步骤。某无尾飞机重构飞行控制的仿真结果表明,在执行器故障情况下,基于改进RMMAC的集成主动容错飞行控制系统能够快速准确地辨识故障,并依据故障信息更新局部控制器权值,实现控制重构,提高了飞机可靠性、安全性和生存能力。     

基于多支持向量机的软测量模型

在许多工业过程控制系统中，软测量技术由于解决了输出变量难以测量的问题而被广泛应用。软测量技术的核心问题是建立优良的软测量数学模型，支持向量机（SVM）以其优良的泛化特性而被应用到建立软测量模型中。基于多个模型的组合可以提高模型精度和鲁棒性的思想，提出多支持向量机（MSVM）组合模型的软测量建模方法．该建模方法通过减聚类方法将输入空间划分为一些小的局部空间．在每个局部空间中用最小二乘支持向量机（LS-SVM）建立子模型．为解决子模型相互之间的严重相关问题，提高模型的精度和鲁棒性，各个子模型的预测输出通过主元递归（PCR）方法连接．仿真研究表明，采用该建模方法能够达到较好的建模效果。     

基于FWA-DBN的航空发电机偏心故障诊断

针对具有多并联支路绕组结构的航空发电机在偏心故障下的输出三相电压、电流故障特征差异小, 造成故障不易识别的问题, 提出一种基于烟花算法(fireworks algorithm, FWA)优化深度置信网络(deep belief network, DBN)的故障诊断方法。首先根据有限元法搭建航空发电机模型, 通过仿真获取不同静态、动态偏心故障输出数据; 然后运用FWA训练优化与极限学习机(extreme learning machine, ELM)相结合的DBN网络, 得到最佳DBN-ELM模型结构; 最后由ELM分类器进行故障诊断分类。诊断结果表明, 相较于传统的故障诊断方法, 应用所提方法进行航空发电机偏心故障诊断, 可以获得更高的准确率, 平均准确率达到99.203%。     

基于EEMD样本熵和SRC的自确认气体传感器故障诊断方法

针对非线性、非平稳情况下自确认气体传感器的故障诊断问题,提出了对传感器不同故障模式信号进行特征提取和智能识别的在线故障诊断方法。首先,该方法根据传感器信号的变化进行集合经验模态分解(ensemble empirical mode decomposition,EEMD),自适应地获得一组固有模态函数(intrinsic mode functions,IMFs),对每个IMF及残余分量进行样本熵分析,提取传感器输出信号的完备特征;然后,利用稀疏表示分类(sparse representation-based classification, SRC)将各故障模式下训练样本的特征向量构成超完备字典。为了提高故障诊断方法的自适应能力,对SRC分类器进行在线更新。通过求解最小1范数约束问题,获得测试样本的稀疏表示系数,再由不同故障类型的重构误差确定测试样本归属,进行传感器故障类型识别。实验结果表明,与目前其他传感器故障诊断方法比较,本文提出的方法能够更显著地提取传感器故障信号特征,故障识别率提高4%以上,达到97.14%。     

基于支持向量机的ESP系统传感器故障诊断方法

应用支持向量机(SVMs)回归估计方法建立ESP系统的传感器预测模型；将支持向量机模式分类方法应用于传感器的故障分离，用DAGSVM作为残差分类器获得故障结果。研究结果表明将支持向量机应用于ESP系统的传感器故障诊断是有效可行的。     

基于回归型支持向量机的液压舵机故障诊断

利用回归型支持向量机（SupportVectorRegression，SVR），设计了一个液压舵机的故障诊断系统。利用系统的可测参量，建立了基于SVR的液压舵机的全局故障检测模型。在仿真过程中发现，此方法能对电液伺服阀、位移传感器和伺服放大器的各种故障进行诊断，诊断准确度高，适用于闭环控制系统的故障检测，仿真结果验证了该方法的有效性。     

Satellite fault diagnosis method based on predictive filter and empirical mode decomposition

A novel satellite fault diagnosis scheme is presented based on the predictive filter and empirical mode composition(EMD).First,the predictive filter is utilized to obtain the fault estimation,which is corrupted by noise.Then the EMD method is introduced to decompose the fault estimation into a finite number of intrinsic mode functions and extract the trend of faults for fault diagnosis.The proposed scheme has the ability of diagnosing both abrupt and incipient faults of the actuator in a satellite attitude control subsystem.A mathematical simulation is given to illustrate the effectiveness of the proposed scheme.