基于互信息的缺陷定位方法

为充分挖掘执行结果与程序频谱的潜在关系,提出基于互信息的可疑度计算公式MIStar(mutual information star).通过分析程序在不同测试用例下的执行信息,引用互信息对传统的怀疑度公式进行优化,给每条语句赋予权重值,不断修正不确定性参数Star,获得良好的定位效果.实验结果表明,该方法较其它可疑度算法...     

Fault detection,location and classification of a transmission line

Neural Computing and Applications - Transient stability is very important in power system. Large disturbances like fault in a transmission line are a concern which needs to be disconnected as...     

Fault detection and isolation in transient states using principal component analysis

This paper proposes the use of principal component analysis (PCA) for process monitoring and fault detection and isolation in processes with several operation modes and long transient states and start-ups. The principal aspects of the PCA approach and the necessary transformations for dealing with this type of processes are presented. In this paper a classical PCA model is used for each steady state of the process and a modification of a batch PCA approach is applied to the transient states of the continuous process. So, in this last case, the PCA model is performed over a three way matrix arranged with the values of the measured variables of several past transitions with a nominal behaviour. This approach presents some problems, such as the unfolding, alignment and imputation. The methods proposed to deal with these problems are explained in detail and compared in order to design a fault detection and isolation method. Two examples are considered to perform the tasks explained. In both cases good results are obtained.     

基于颜色和几何关系的人脸检测方法

针对复杂背景下的彩色图像提出了一种基于颜色和几何关系的人脸检测方法.选择YCbCr色彩空间进行肤色分割,在候选人脸区域的灰度图像中进行图像复杂度的计算以确定眼睛区域的大致位置,并利用嘴巴的红色特性在候选人脸区域的YIQ色彩空间中确定嘴巴的大致位置,最后利用眼睛、嘴巴的几何关系精确定位人脸.实验结果表明,该方法速度快、检测率高,与其它算法相比有很好的检测效果.     

Fault location using digraph and inverse direction search with application

A fault location method for large-scale plants is described. Fault location is executed using the following procedure: first, a digraph which indicates the failure propagation network of a plant is drawn using nodes corresponding to the devices of the plant or failure modes of the devices. Arrows which correspond to the direction of failure propagation between adjacent nodes are drawn in. Second, some nodes are chosen as candidates of the failure origin by back-tracing, using the arrows, starting from the nodes which indicate abnormal states such as rapidly rising pressure. Third, the candidates are screened by using failure propagation probabilities between adjacent nodes, failure propagation time between adjacent nodes, and back-tracing, starting from the nodes which indicate normal states. Finally, the failure propagation probabilities and the failure rates of the devices are used to evaluate the priority ranking among the screened candidates. This method is applied to pump and evaporation plants.     

基于电气介数的电网故障无功规划选址与定容

无功补偿对电网减少线路损耗、提高故障应对能力和稳定性等有着显著作用.为此,基于电网拓扑电气介数模型,针对有限经济约束的电网输电线路N-1故障,考虑电网系统无功补偿的经济性约束和潮流方程电气约束,建立包括最小发电费用、最大网损降幅和最优裕度提升为目标函数的优化模型,求解输电线路N-1故障情况下的无功补偿策略的最优选址定容.最后,考虑到构建的混合整数非线性模型的复杂性与难以凸化松弛,通过改进的精英策略的自适应遗传算法求解最优潮流问题,并通过IEEE-14节点标准测试系统进行算法验证,从而表明所提出算法的有效性以及策略的可行性.     

Fault detection and isolation of the three-tank system using the modal interval analysis

Analytical redundancy is a widely used technique for fault detection. It consists of comparing the behaviour of a real system with a reference obtained by simulation of its model. The main problem is that there are always imprecisions and uncertainties which are not represented in the model so the behaviour of the real system and the behaviour of the model are not exactly the same. One way to represent these uncertainties in the model is using interval models. The results of the simulation of these types of models may be represented by envelopes. This paper proposes an approach to generate envelopes based on interval techniques of the modal interval analysis. As an example, this approach is used to detect and isolate faults in a physical system formed by three interconnected tanks.     

基于可传递置信模型的模拟电路融合诊断方法研究

本文提出了一种有效的基于可转移置信模型的模拟电路故障融合诊断方法,解决模拟电路诊断中故障特征信息缺乏和决策融合中异质信息不相容等问题。该法首先采用所提出的电路温度故障信息的提取规则,将获得的温度故障信息输入隶属度函数进行故障预识别,再结合基于可测点电压神经网络故障预识别结果,利用可传递置信模型进行电路融合诊断。通过具体电路实验仿真,表明了该方法的有效性,提高了模拟电路融合诊断准确率。     

Fault detection using robust multivariate control chart

We introduce a new multivariate statistical process control chart for fault detection using robust statistics and principal component analysis. The proposed approach consists of two main steps. In the first step, a robust covariance matrix is determined using the minimum covariance determinant algorithm. In the second step, an eigen-analysis of the robust correlation matrix is performed to derive the robust control limits of the proposed multivariate chart. Our experimental results illustrate the much better fault detection performance of the proposed method in comparison with existing statistical monitoring and process controlling charts.     

WSN中基于端到端的贪婪故障定位算法

为了维持无线传感器网络的正常运行,所有的故障链路需要被精确定位。将该问题转换为基于端到端的数据引导,以减少主动监测次数为目的的最优监测序列的问题。提出了通过拓扑拆分得到故障子图,并通过子图的概率集进一步计算节省主动探测次数的基于节点监测多条链路的启发式贪婪算法NTHG(node testing using heuristic greedy)。仿真结果表明仅需要监测小部分的节点,就可以定位网络中所有的故障链路。与该问题最新的解决算法LTHG(link testing using heristic greedy)相比,新算法需要更少的监测次数和平均CPU耗时,从而很好地降低了网络能耗,缩短了故障定位耗时。     

Fault detection and isolation using viability theory and interval observers

This paper proposes the use of interval observers and viability theory in fault detection and isolation (FDI). Viability theory develops mathematical and algorithmic methods for investigating the viability constraints characterisation of dynamic evolutions of complex systems under uncertainty. These methods can be used for checking the consistency between observed and predicted behaviour by using simple sets that approximate the exact set of possible behaviour (in the parameter or state space). In this paper, FDI is based on checking for an inconsistency between the measured and predicted behaviours using viability theory concepts and sets. Finally, an example is provided in order to show the usefulness of the proposed approach.     

基于概率模型的遗传规划在故障诊断中的应用

采用在遗传规划中使用概率模型的新方法采解决一系列故障诊断问题。故障诊断可被看为是一个多级分类问题。遗传规划在解决复杂问题上有很大的优势,而这种优势在故障诊断中仍然显著。而且,使用概率模型作为适应函数能提高诊断的精确性,最后用这种方法解决机电设备的故障诊断。结果显示,使用基于概率模型的遗传规划解决机电设备的故障诊断比人工神经网络优越。     

Fault detection using multiscale PCA-based moving window GLRT

The presence of measurement errors (noise) in the data and mode l uncertainties degrade the performance quality of fault detection (FD) techniques. Therefore, an objective of this paper is to enhance the quality of FD by suppressing the effect of these errors using wavelet-based multiscale representation of data, which is a powerful feature extraction tool. Multiscale representation of data has been used to improve the FD abilities of principal component analysis. Thus, combining the advantages of multiscale representation with those of hypothesis testing should provide further improvements in FD. To do that, a moving window generalized likelihood ratio test (MW-GLRT) method based on multiscale principal component analysis (MSPCA) is proposed for FD. The dynamical multiscale representation is proposed to extract the deterministic features and decorrelate autocorrelated measurements. An extension of the popular hypothesis testing GLRT method is applied on the residuals from the MSPCA model, in order to further enhance the fault detection performance. In the proposed MW-GLRT method, the detection statistic equals the norm of the residuals in that window, which is equivalent to applying a mean filter on the squares of the residuals. This means that a proper moving window length needs to be selected, which is similar to estimating the mean filter length in data filtering. The fault detection performance of the MSPCA-based MW-GLRT chart is illustrated through two examples, one using synthetic data, and the other using simulated Tennessee Eastman Process (TEP) data. The results demonstrate the effectiveness of the MSPCA-based MW-GLRT method over the conventional PCA-based and MSPCA-based GLRT methods, and both of them provide better performance results when compared with the conventional PCA and MSPCA methods, through their respective charts T² and Q charts.     

随机傅里叶特征相异度的故障检测算法

针对大规模非线性动态过程故障检测问题, 提出随机傅里叶特征相异度(RFF–DISSIM)的故障检测方法.首先, 利用RFF对原始数据进行映射, 获得特征空间中的数据集; 然后, 在特征空间中应用滑动窗口技术并结合相异度指标对特征空间中的数据集进行过程状态监控. 本文方法通过RFF快速捕获数据的非线性结构并结合相异度指标消除样本间自相关性的影响, 有效地提高了过程监控性能. 通过一个数值例子和连续搅拌釜反应器(CSTR)的仿真实验并与传统的核主元分析、动态主元分析等方法对比分析, 仿真结果进一步证明了本文所提方法的有效性.     

Fast detection of impact location using kernel extreme learning machine

Damage location detection has direct relationship with the field of aerospace structure as the detection system can inspect any exterior damage that may affect the operations of the equipment. In the literature, several kinds of learning algorithms have been applied in this field to construct the detection system and some of them gave good results. However, most learning algorithms are time-consuming due to their computational complexity so that the real-time requirement in many practical applications cannot be fulfilled. Kernel extreme learning machine (kernel ELM) is a learning algorithm, which has good prediction performance while maintaining extremely fast learning speed. Kernel ELM is originally applied to this research to predict the location of impact event on a clamped aluminum plate that simulates the shell of aerospace structures. The results were compared with several previous work, including support vector machine (SVM), and conventional back-propagation neural networks (BPNN). The comparison result reveals the effectiveness of kernel ELM for impact detection, showing that kernel ELM has comparable accuracy to SVM but much faster speed on current application than SVM and BPNN.     

Fault detection and isolation for a wind turbine benchmark using a mixed Bayesian/Set-membership approach

This paper addresses the problem of fault detection and isolation of wind turbines using a mixed Bayesian/Set-membership approach. Modeling errors are assumed to be unknown but bounded, following the set-membership approach. On the other hand, measurement noise is also assumed to be bounded, but following a statistical distribution inside the bounds. To avoid false alarms, the fault detection problem is formulated in a set-membership context. Regarding fault isolation, a new fault isolation scheme that is inspired on the Bayesian fault isolation framework is developed. Faults are isolated by matching the fault detection test results, enhanced by a complementary consistency index that measures the certainty of not being in a fault situation, with the structural information about the faults stored in the theoretical fault signature matrix. The main difference with respect to the classical Bayesian approach is that only models of fault-free behavior are used. Finally, the proposed FDI method is assessed against the wind turbine FDI benchmark proposed in the literature, where a set of realistic fault scenarios in wind turbines are proposed.     

Fault analysis for networks with concurrent error detection

The authors propose an approach for fault analysis and simulation of networks designed to have concurrent detection properties. The analysis characterizes all faults that may affect a device and determines the coverage, extracting test vectors and other parameters for evaluating device quality     

Fault detection on robot manipulators using artificial neural networks

Nowadays, gas welding applications on vehicle’s parts with robot manipulators have increased in automobile industry. Therefore, the speed of end-effectors of robot manipulator is affected on each joint during the welding process with complex trajectory. For that reason, it is necessary to analyze the noise and vibration of robot’s joints for predicting faults. This paper presents an experimental investigation on a robot manipulator, using neural network for analyzing the vibration condition on joints. Firstly, robot manipulator’s joints are tested with prescribed of trajectory end-effectors for the different joints speeds. Furthermore, noise and vibration of each joint are measured. And then, the related parameters are tested with neural network predictor to predict servicing period. In order to find robust and adaptive neural network structure, two types of neural predictors are employed in this investigation. The results of two approaches improved that an RBNN type can be employed to predict the vibrations on industrial robots.     

Fault detection for discrete-time LPV systems using interval observers

This paper is concerned with the fault detection (FD) problem for discrete-time linear parameter-varying systems subject to bounded disturbances. A parameter-dependent FD interval observer is designed based on parameter-dependent Lyapunov and slack matrices. The design method is presented by translating the parameter-dependent linear matrix inequalities (LMIs) into finite ones. In contrast to the existing results based on parameter-independent and diagonal Lyapunov matrices, the derived disturbance attenuation, fault sensitivity and nonnegative conditions lead to less conservative LMI characterisations. Furthermore, without the need to design the residual evaluation functions and thresholds, the residual intervals generated by the interval observers are used directly for FD decision. Finally, simulation results are presented for showing the effectiveness and superiority of the proposed method.