首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到18条相似文献,搜索用时 234 毫秒
1.
针对电厂热力系统故障检测和定位准确性低的问题,提出了基于鲁棒输入训练网络的传感器故障检测模型;采用带参数限制项的目标函数对网络进行训练,并在测试目标函数中引入影响因子,增加了模型训练精度,抑制了网络计算过程故障数据对正常值的影响,减小了残差污染,提高了模型准确性;以某300 MW电厂热力系统20组测点为对象进行算例分析,通过反复的实验,结果表明,该模型能够更加准确地对非线性系统故障点进行检测和分离,并更加精确重构各变量真实值,验证了该模型用于非线性过程传感器故障检测的有效性和可靠性.  相似文献   

2.
一类非线性系统参数突变故障的检测与诊断   总被引:3,自引:1,他引:2       下载免费PDF全文
本文针对一类非线性系统提出了一种非线性自适应故障检测滤波器,可以实时检测并分离、估计出其参数的突变故障。仿真实例说明了本文方法的有效性。  相似文献   

3.
一类非线性系统参数偏差型故障的实时检测与诊断   总被引:18,自引:1,他引:18       下载免费PDF全文
本文针对一类较一般的多变量非线性时变随机系统,给出了一种全新的用于其参数偏差型故障的实时检测与诊断方法。这类故障包容了诸如部件参数的阶跃型和缓变型故障等,所给仿真实例证实了本文方法的有效性。  相似文献   

4.
非线性系统的鲁棒故障检测与诊断   总被引:5,自引:0,他引:5       下载免费PDF全文
魏晨  陈宗基 《自动化学报》2003,29(6):976-980
研究了一类具有未建模动态或扰动的非线性系统的鲁棒故障检测与诊断问题,利用神经网络、模糊系统或小波网络等对非线性故障模式进行在线逼近的方法进行故障诊断.第一步,对用于鲁棒故障检测的观测器,建立了保证观测器稳定的增益阵的选择条件;第二步,若检测出发生故障,则用神经网络、模糊系统或小波网络进行故障的在线估计,建立了估计误差界,结果显示输出估计误差将收敛到由扰动上界或建模误差上界线性确定的范围内.  相似文献   

5.
空调系统中传感器故障检测与诊断方法的研究   总被引:5,自引:0,他引:5  
提出了空调系统传感器故障检测,故障识别、故障重构的主成分分析方法。主成分分析法将测量空间分为主成分子空间和残差子空间。SPE指数和SVI指标分别用来检测和识别故障,沿着故障方向,测量数据逐步逼近主成分子空间可以实现数据的重构,通过对空调监测系统的传感器故障检测与诊断结果展示出PCA方法具有良好的故障检测,识别和重构建能力。  相似文献   

6.
一类非线性系统的故障检测与容错控制算法   总被引:4,自引:0,他引:4  
针对仿射非线性系统提出了一种稳定的故障检测及容错控制算法.该算法利用神经网络对系统故障进行建模,在线估计故障向量,监测系统运行情况;在反馈回路中引用故障辅助反馈控制回路,实现容错控制;并基于Lyapunov方法进行了稳定性分析.控制系统可运行于两种模式:系统正常时,采用常规反馈控制器(CC);有故障发生时,引入补偿控制来削弱故障影响,保障系统的正常运行.最后对一类非线性电机的仿真控制结果表明了此容错控制方法的有效性.  相似文献   

7.
一种基于小波分析的故障检测与诊断   总被引:3,自引:0,他引:3  
程耕国  周凤星 《控制与决策》2001,16(11):828-830
小波分析是一种时变信号时-频两维分析方法。根据小波分析的思想,构造出一种新型机械设备故障诊断装置,使得机械故障的诊断晚加准确,并在实际应用中取得了良好效果。实践证明这种拟小波理论的信号处理方法在故障诊断中是十分有效的。  相似文献   

8.
一类基于神经网络非线性观测器的鲁棒故障检测和诊断   总被引:4,自引:1,他引:4  
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。  相似文献   

9.
为实现直流供电系统中的绝缘故障检测,研制了一种以AVR单片机为核心的智能传感器系统。该系统利用电磁感应原理检测直流供电系统中电气负载馈电回路的不平衡电流,实现了对电气负载绝缘故障的检测。经过现场测试,该智能传感器系统具有低功耗、高可靠性和易使用的特点,试验结果表明:系统达到了检测准确度要求。  相似文献   

10.
非线性系统传感器偏差故障的UKF递推检测方法   总被引:2,自引:0,他引:2  
针对传统的推广卡尔曼滤波器方法(EKF)的不足,为检测非线性系统传感器的偏差型故障,提出了一种新的基于unscented卡尔曼滤波(UKF)的实时递推检测算法,该方法应用UKF作为传感器故障残差发生器,并利用残差加权平方和检测策略进行故障的检测.仿真结果表明,与基于EKF的传感器故障检测方法相比,该方法有更好的故障预示能力,并提高了故障检测的准确率.  相似文献   

11.
基于模型的控制系统故障诊断技术的最新进展   总被引:13,自引:2,他引:11       下载免费PDF全文
评述了近三年来基于模型的控制系统故障诊断技术的发展状况.介绍了这一技术在九个方面的最新进展及十一项最新的应用.对故障诊断技术目前的状况进行了分析和总结,给出了这一领域中值得进一步研究的一些问题和可能的发展方向.  相似文献   

12.
    
This paper presents an observer‐based robust fault estimation scheme for a class of nonlinear systems. We consider the system where the fault enters both the state and output equations via unmeasurable nonlinear functions, for which currently no fault estimation scheme exists. The proposed scheme exploits the special structures and information embedded in the fault‐dependent nonlinear functions. We propose a design method to minimize the ?2 gain from the disturbances to the fault estimation, and provide conditions for the existence of such observers. The effectiveness of this scheme is demonstrated on a nonlinear single‐link flexible joint robot system with disturbances.  相似文献   

13.
    
This article considers the fault detection (FD) problem for a class of Itô-type stochastic time-delay systems subject to external disturbances and sensor faults. The main objective is to design a fault detection filter (FDF) such that it has prescribed levels of disturbance attenuation and fault sensitivity. Sufficient conditions for guaranteeing these levels are formulated in terms of linear matrix inequalities (LMIs), and the corresponding fault detection filter design is cast into a convex optimisation problem which can be efficiently handled by using standard numerical algorithms. In order to reduce the conservatism of filter design with mixed objectives, multi-Lyapunov functions approach is used via Projection Lemma. In addition, it is shown that our results not only include some previous conditions characterising H performance and H ? performance defined for linear time-invariant (LTI) systems as special cases but also improve these conditions. Finally, two examples are employed to illustrate the effectiveness of the proposed design scheme.  相似文献   

14.
    
In this paper, the detection problem of intermittent multiplicative sensor fault is investigated for stochastic uncertain systems. A robust optimal filter is designed according to the criterion of minimum estimation error covariance. Then, based on this, a residual generator is constructed, and the quantitative effect of the fault on it is discussed in detail. After that we design the evaluation function and detection threshold to achieve intermittent fault detection. Our proposed strategy has a recursive form and only includes simple arithmetic operations, thus it is suitable for real‐time online applications. Finally, a simulation example is given to demonstrate the effectiveness of the proposed strategy.  相似文献   

15.
This paper is concerned with the fault detection and estimation for nonlinear stochastic system with additive multi-faults. The states of system are estimated by the improved particle filter which composed of basic particle filter and preliminary fault estimation. Since the preliminary fault estimation contains noise, the faults are detected by the method of hypothesis testing, while the amplitude of each fault is estimated by the average of the sample of preliminary fault estimation. Meanwhile, the relationship of the sample size, the significance level of two types of error, the amplitude of fault and the variance of the error of preliminary fault estimation are also given. The effectiveness of the proposed method is verified by the simulation of three-vessel water tank system.  相似文献   

16.
The problem of robust analytical redundancy relations design for fault diagnosis in nonlinear systems is investigated. An approach is proposed to solve this problem through an extension of the system state‐space by means of constant (or slow varying) unknown parameters, followed by designing analytical redundancy relations that are insensitive both to state variables and unknown parameters. To make the design practicable, some problems related to nonlinear transformation of the extended system model into observable one are considered. The quasi‐linear computational form for robust analytical redundancy relations is described. Fault detectability and distinguishability conditions are formulated, and a recommendation for choosing the size of the moving time window is made. The results are demonstrated through an example involving an SISO nonlinear model of an underwater vehicle.  相似文献   

17.
    
This article outlines the formulation of a robust fault detection and isolation (FDI) scheme that can precisely detect and isolate simultaneous actuator and sensor faults for uncertain linear stochastic systems. The given robust fault detection scheme based on the discontinuous robust observer approach would be able to distinguish between model uncertainties and actuator failures and therefore eliminate the problem of false alarms. Since the proposed approach involves estimating sensor faults, it can also be used for sensor fault identification and the reconstruction of true outputs from faulty sensor outputs. Simulation results presented here validate the effectiveness of the proposed robust FDI system.  相似文献   

18.
    
This paper deals with fault detection and identification in dynamic systems when the system dynamics can be modeled by smooth nonlinear differential equations including affine, bilinear or linear parameter varying (LPV) systems. Two basic approaches will be considered, these apply differential algebraic and differential geometric tools.In the differential algebraic approach the state elimination methods will be used to derive nonlinear parity relations. In the specific case when a reconstruction of the fault signal is needed the dynamic inversion based approach will be investigated. This approach will also be studied from geometric point of view. The geometric approach, as proposed by Isidori and De Persis, is suitable to extend the detection filter and unknown input observer design approaches (well elaborated for LTI systems) to affine nonlinear systems.Beyond the development of the theory of fault detection and identification it is equally important to offer computable methods and to analyze the robustness properties against uncertainties. Both the observer based and the inversion based approaches will be elaborated for LPV systems that may offer computational tools inherited from linear systems and also allow to design for robustness utilizing results from robust filtering and disturbance attenuation.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号