A possibilistic clustering approach to novel fault detection and isolation

In this paper, a new approach for fault detection and isolation that is based on the possibilistic clustering algorithm is proposed. Fault detection and isolation (FDI) is shown here to be a pattern classification problem, which can be solved using clustering and classification techniques. A possibilistic clustering based approach is proposed here to address some of the shortcomings of the fuzzy c-means (FCM) algorithm. The probabilistic constraint imposed on the membership value in the FCM algorithm is relaxed in the possibilistic clustering algorithm. Because of this relaxation, the possibilistic approach is shown in this paper to give more consistent results in the context of the FDI tasks. The possibilistic clustering approach has also been used to detect novel fault scenarios, for which the data was not available while training. Fault signatures that change as a function of the fault intensities are represented as fault lines, which have been shown to be useful to classify faults that can manifest with different intensities. The proposed approach has been validated here through simulations involving a benchmark quadruple tank process and also through experimental case studies on the same setup. For large scale systems, it is proposed to use the possibilistic clustering based approach in the lower dimensional approximations generated by algorithms such as PCA. Towards this end, finally, we also demonstrate the key merits of the algorithm for plant wide monitoring study using a simulation of the benchmark Tennessee Eastman problem.     

Passive robust fault detection using interval observers: Application to the DAMADICS benchmark problem

In this paper, the “passive approach” to robust fault detection and isolation (FDI) is presented in the context of observer methodology, when a model with parameters bounded in intervals (“interval model”) is used, deriving the interval version corresponding to the classical use of observers. The passive approach is based on allowing the effect of the uncertainties to propagate into the residuals and then the principle of adaptive thresholds is used to achieve robustness. Finally, the approach proposed is applied to detect some of the faults proposed in an industrial actuator used as an FDI benchmark in the European RTN DAMADICS.     

Set-theoretic methods in robust detection and isolation of sensor faults

This paper proposes a sensorfault detection and isolation (FDI) approach based on interval observers and invariant sets. In fault detection (FD), both interval observer-based and invariant set-based mechanisms are used to provide real-time fault alarms. In fault isolation (FI), the proposed approach also uses these two different mechanisms. The former, based on interval observers, aims to isolate faults during the transient-state operation induced by faults. If the former does not succeed, the latter, based on both interval observers and invariant sets, is started to guarantee FI after the system enters into steady state. Besides, a collection of invariant set-based FDI conditions are established by using all available system-operating information provided by all interval observers. In order to reduce computational complexity, a method to remove all available but redundant/unnecessary system-operating information is incorporated into this approach. If the considered faults satisfy the proposed FDI conditions, it can be guaranteed that they are detectable and isolable after their occurrences. This paper concludes with a case study based on a subsystem of a wind turbine benchmark, which can illustrate the effectiveness of this FDI technique.     

模糊方向神经网络及其在故障检测与分离中的应用

提出一种用于我工况对象系统故障检测与的模糊方向神经网络，神经网络用模糊集表示故障模式，模糊集是由模糊超体聚集形成的集合体，模糊超体是由单位方向、夹角和两个半径确定，模糊方向神经网络能在一次循环学习中形成非线性方向边界，并不断融合新样本信息和精炼已存在的故障模式。发动机故障检测与分离的仿真研究验证了模糊方向神经网络分类器的优越性能。     

Fault tolerant control using a fuzzy predictive approach

This paper proposes the application of fault-tolerant control (FTC) using fuzzy predictive control. The FTC approach is based on two steps, fault detection and isolation (FDI) and fault accommodation. The fault detection is performed by a model-based approach using fuzzy modeling and fault isolation uses a fuzzy decision making approach. The information obtained on the FDI step is used to select the model to be used in fault accommodation, in a model predictive control (MPC) scheme. The fault accommodation is performed with one fuzzy model for each identified fault. The FTC scheme is used to accommodate the faults of two systems a container gantry crane and three tank benchmark system. The fuzzy FTC scheme proposed in this paper was able to detect, isolate and accommodate correctly the considered faults of both systems.     

Model-free direct fault detection and classification

The present paper deals with the problem of fault detection and diagnosis in large scale engineering processes. These processes are typically equipped with database management systems and data logging servers whereby the measurement data is cleaned and stored. The expert knowledge of engineers and technicians as well as historical data records about abnormal scenarios experienced in the past is often available at hand. In this work we propose a framework where fault detection and classification can be done online directly on new data record without dimensionality reduction or any distributional assumptions. The proposed algorithm is based on a two-sample test via kernel mean embeddings of probability distributions. The Tennessee Eastman benchmark process is used to assess this new data-driven approach on different simulated faults.     

Unknown input modeling and robust fault diagnosis using black box observers

A key issue that needs to be addressed while performing fault diagnosis using black box models is that of robustness against abrupt changes in unknown inputs. A fundamental difficulty with the robust FDI design approaches available in the literature is that they require some a priori knowledge of the model for unmeasured disturbances or modeling uncertainty. In this work, we propose a novel approach for modeling abrupt changes in unmeasured disturbances when innovation form of state space model (i.e. black box observer) is used for fault diagnosis. A disturbance coupling matrix is developed using singular value decomposition of the extended observability matrix and further used to formulate a robust fault diagnosis scheme based on generalized likelihood ratio test. The proposed modeling approach does not require any a priori knowledge of how these faults affect the system dynamics. To isolate sensor and actuator biases from step jumps in unmeasured disturbances, a statistically rigorous method is developed for distinguishing between faults modeled using different number of parameters. Simulation studies on a heavy oil fractionator example show that the proposed FDI methodology based on identified models can be used to effectively distinguish between sensor biases, actuator biases and other soft faults caused by changes in unmeasured disturbance variables. The fault tolerant control scheme, which makes use of the proposed robust FDI methodology, gives significantly better control performance than conventional controllers when soft faults occur. The experimental evaluation of the proposed FDI methodology on a laboratory scale stirred tank temperature control set-up corroborates these conclusions.     

Fault diagnosis and accommodation of nonlinear systems based on multiple-model adaptive unscented Kalman filter and switched MPC and H-infinity loop-shaping controller

In this paper, a new active fault tolerant control (AFTC) methodology is proposed based on a state estimation scheme for fault detection and identification (FDI) to deal with the potential problems due to possible fault scenarios. A bank of adaptive unscented Kalman filters (AUKFs) is used as a core of FDI module. The AUKF approach alleviates the inflexibility of the conventional UKF due to constant covariance set up, leading to probable divergence. A fuzzy-based decision making (FDM) algorithm is introduced to diagnose sensor and/or actuator faults. The proposed FDI approach is utilized to recursively correct the measurement vector and the model used for both state estimation and output prediction in a model predictive control (MPC) formulation. Robustness of the proposed FTC system, H_∞ optimal robust controller and MPC are combined via a fuzzy switch that is used for switching between MPC and robust controller such that FTC system is able to maintain the offset free behavior in the face of abrupt changes in model parameters and unmeasured disturbances. This methodology is applied on benchmark three-tank system; the proposed FTC approach facilitates recovery of the closed loop performance after the faults have been isolated leading to an offset free behavior in the presence of sensor/actuator faults that can be either abrupt or drift change in biases. Analysis of the simulation results reveals that the proposed approach provides an effective method for treating faults (biases/drifts in sensors/actuators, changes in model parameters and unmeasured disturbances) under the unified framework of robust fault tolerant control.     

Isolation of parametric faults in continuous-time multivariable systems: a sampled data-based approach

A novel approach is proposed towards on-line and real-time detection and isolation of parametric faults in a multivariable linear continuous-time (CT) system. The problem of fault detection and isolation (FDI) is formulated in terms of a CT state space model. Since parameters in a CT model usually have simple relationships with physical parameters of the system, isolating parametric faults in the CT model can lead to the isolation of undesired changes in the physical parameters. Isolating parametric faults is very challenging, because even in a linear time-invariant system, the fault model can be time-varying and random. To obtain a constant fault model, many existing parametric FDI schemes have to make unrealistical assumptions. Our proposed FDI approach can generate an optimal primary residual vector (PRV), in which the fault model is constant without making any assumptions. To isolate faults, the PRV is transformed into a set of structured residual vectors (SRVs), where one SRV is made insensitive to a specified subset of faults, but most sensitive to other faults. The proposed approach is successfully applied to detection and isolation of undesired changes in the physical parameters of a simulated continuously stirred tank process.     

基于模糊贴近度的粒子滤波故障预测

复杂设备的故障特征具有不确定性,非线性等特点,为预防故障可能造成的严重后果,提高故障预测准确性是非常必要的.针对故障预测具有不确定性的特点,本文将模糊数学中的模糊贴近度和粒子滤波算法相结合设计故障预测的方法.新方法利用隶属度函数设计了描述系统运行正常的正常模糊子集和运行异常的异常模糊子集,利用粒子滤波算法计算系统运行的预测值,并计算预测值的正常隶属度;再分别计算预测值的正常隶属度与正常模糊子集和异常模糊子集的贴近程度来实现故障预报.该方法通过三容水箱系统T2水箱水位变化预测三容水箱系统是否出现故障和通过UH-60行星齿轮盘裂纹何时开始增大的故障进行实验,并同基于改进余弦相似度的粒子滤波故障预报、基于随机摄动粒子滤波器的故障预报算法和基于粒子滤波的FDI方法进行了对比.实验验证了该方法的可行性,可及时准确地预测出系统故障.     

Weighted and constrained possibilistic C-means clustering for online fault detection and isolation

In this paper, a new weighted and constrained possibilistic C-means clustering algorithm is proposed for process fault detection and diagnosis (FDI) in offline and online modes for both already known and novel faults. A possibilistic clustering based approach is utilized here to address some of the deficiencies of the fuzzy C-means (FCM) algorithm leading to more consistent results in the context of the FDI tasks by relaxing the probabilistic condition in FCM cost function. The proposed algorithm clusters the historical data set into C different dense regions without having precise knowledge about the number of the faults in the data set. The algorithm incorporates simultaneously possibilistic algorithm and local attribute weighting for time-series segmentation. This allows different weights to be allocated to different features responsible for the distinguished process faults which is an essential characteristic of proper FDI operations. A set of comparative studies have been carried out on the large-scale Tennessee Eastman industrial challenge problem and the DAMADICS actuator benchmark to demonstrate the superiority of the proposed algorithm in process FDI applications with respect to some available alternative approaches.     

On-line fault detection in uncertain nonlinear systems using diagnostic observers: a survey

The paper discusses the principles of model-based fault detection and isolation (FDI) in nonlinear and time-varying uncertain dynamic systems. Such systems are typical for such complex plants as, for example, in the chemical process industries or in advanced transportation technology. For a model-based fault diagnosis in such situations, robust or even adaptive strategies are needed. In this paper the theory of robust linear observer-based residual generation for FDI is reviewed from a general point of view. The structural equivalence between the parity space approach and observer-based approach is shown in a new simple graphical way by showing that the observer-based FDI concept can easily be transformed into an equivalent extended parity space configuration, without claiming, however, equivalence of the underlying design techniques. The unknown input observer approach known as a most powerful and comprehensive framework for robust residual generation for FDI in uncertain linear systems is extended to classes of nonlinear and time-varying systems. For such plants an adaptive nonlinear unknown input observer scheme is proposed. Finally, appropriate residual evaluation techniques are outlined and suggestions are made to increase the robustness, for instance by using adaptive thresholds.     

Actuator fault tolerant multi-controller scheme using set separation based diagnosis

We present a fault tolerant control strategy based on a new principle for actuator fault diagnosis. The scheme employs a standard bank of observers which match the different fault situations that can occur in the plant. Each of these observers has an associated estimation error with distinctive dynamics when an estimator matches the current fault situation of the plant. Based on the information from each observer, a fault detection and isolation (FDI) module is able to reconfigure the control loop by selecting the appropriate control law from a bank of controllers, each of them designed to stabilise and achieve reference tracking for one of the given fault models. The main contribution of this article is to propose a new FDI principle which exploits the separation of sets that characterise healthy system operation from sets that characterise transitions from healthy to faulty behaviour. The new principle allows to provide pre-checkable conditions for guaranteed fault tolerance of the overall multi-controller scheme.     

FDI approach to the DAMADICS benchmark problem based on qualitative reasoning coupled with fuzzy neural networks

A computer-assisted fault detection and isolation (FDI) based on a fuzzy qualitative simulation algorithm used for fault detection purposes, coupled with a hierarchical structure of fuzzy neural networks used to perform the fault isolation task, is presented. The DAMADICS benchmark actuator system has been used as test bed of the current FDI system. Single abrupt and incipient faults, as well as multiple simultaneous faults have been considered to test the overall system robustness. The results obtained prove the efficiency of the proposed FDI system.     

Design of an auto-associative neural network by using design of experiments approach

Advanced monitoring systems enable integration of data-driven algorithms for various tasks, for e.g., control, decision support, fault detection and isolation (FDI), etc. Due to improvement of monitoring systems, statistical or other computational methods can be implemented to real industrial systems. Algorithms which rely on process history data sets are promising for real-time operation especially for online process monitoring tasks, e.g., FDI. However, a reliable FDI system should be robust to uncertainties and small process deviations, thus, false alarms can be avoided. To achieve this, a good model for comparison between process and model is needed and for easier FDI implementation, the model has to be derived directly from process history data. In such cases, model-based FDI approaches are not very practical. In this paper a nonlinear statistical multivariate method (nonlinear principal component analysis) was used for modeling, and realized with auto-associative artificial neural network (AANN). A Taguchi design of experiments (DoE) technique was used and compared with a classic approach, where according to the analysis best AANN model structure was chosen for nonlinear model. Parameters that are important for neural network’s performance have been included into a joint orthogonal array to consider interactions between noise and control process variables. Results are compared to AANN design recommendations by other authors, where obtained nonlinear model was designed for reliable fault detection of very small faults under closed-loop conditions. By using Taguchi DoE robust design on AANN, an improved and reliable FDI scheme was achieved even in case of small faults introduced to the system. The accuracy and performance of AANN and FDI scheme were tested by experiments carried out on a real laboratory hydraulic system, to validate the proposed design for industrial cases.     

Limnimeter and rain gauge FDI in sewer networks using an interval parity equations based detection approach and an enhanced isolation scheme

In this paper, a methodology for limnimeter and rain-gauge fault detection and isolation (FDI) in sewer networks is presented. The proposed model based FDI approach uses interval parity equations for fault detection in order to enhance robustness against modelling errors and noise. They both are assumed unknown but bounded, following the so-called interval (or set-membership) approach. On the other hand, fault isolation relies on an algorithm that reasons using several fault signature matrices that store additional information to the typical binary one used in standard FDI approaches. More precisely, the considered fault signature matrices contain information about residual fault sign/sensitivity and time/order of activation. The paper also proposes an identification procedure to obtain the interval models used in fault detection that delivers the nominal model plus parameter uncertainty is proposed. To exemplify the proposed FDI methodology, a case study based on the Barcelona sewer network is used.     

Optimal sensor network design for multirate systems

A methodology for generating optimal sensor network design for multirate systems is presented. Location of sensors, cost of measurement and frequency of sampling are important factors that have been incorporated in the sensor network design formulation. The proposed methodology is based on evaluating trade-off (Pareto optimal) solutions between the quality of state estimation and the total measurement cost associated with the sensor network. To accommodate different sampling frequencies and evaluate their effect on state estimation accuracy, a generic multirate extension of the traditional Kalman filter is used. In general, higher accuracies of the state estimates are realizable at expense of higher measurement cost. Incorporation of these conflicting objectives of minimizing measurement cost and maximizing estimation accuracy results in a combinatorial, implicit multiobjective optimization problem, which is solved using the well-known non-dominated sorting genetic algorithm-II. The resulting solutions can be then analyzed by the process designer for determining an appropriate sensor network. The methodology is demonstrated by generating optimal sensor network design for the benchmark quadruple tank set up [K.H. Johansson, The quadruple-tank process: a multivariable laboratory process with an adjustable zero, IEEE Trans. Control Syst. Tech. 8 (3) (2000) 456–465] and the Tennessee Eastman challenge process [J.J. Downs, E.F. Vogel, A plant-wide industrial process control problem, Comput. Chem. Eng. 17 (3) (1993) 245–255].     

数字系统单加权集下随机测试生成方法

为在不引入额外的硬件开销以下较短的测试序列获得较高的故障覆盖率，提出一种基于细胞自动机（CA）的数字集成电路加权随机测试方法。该方法利用可测性测度建立反映故障侦查代价的可测性代价函数，对此函数的寻优得到被测电路主输入处的权值，再由一维混合型CA实现了该权值下的随机序列。对标准电路的实验验证了该方法是一种有效的、且便于BIST的应用的测试生成算法。     

Industrial actuator benchmark for fault detection and isolation

Feedback control systems are vulnerable to faults within the control loop, because feedback actions may cause abrupt responses and process damage when faults occur. Such faults can be detected by model-based methods for fault detection and isolation (FDI) but research results have not been widely accepted in industry. One reason has been a scarcity of realistic examples for testing FDI methods against industrial systems. These special section papers focus on a common benchmark example, an electro-mechanical position servo, used in speed control of large diesel engines. The result is a platform for comparison of FDI methods and a gathering together of design experience on a simple, yet very realistic, industrial example. This paper introduces the benchmark problem, overviews the FDI methods used within the papers and discusses the results.     

A pulsed plasma thruster fault detection and isolation strategy for formation flying of satellites

The main objective of this paper is to develop a dynamic neural network-based fault detection and isolation (FDI) scheme for pulsed plasma thrusters (PPTs) that are employed in the attitude control subsystem (ACS) of satellites tasked to perform formation flying (FF) missions. A hierarchical methodology is proposed that consists of three fault detection and isolation (FDI) approaches, namely (i) a “low-level” FDI scheme, (ii) a “high-level” FDI scheme, and (iii) an “integrated” FDI scheme. Based on the data from the electrical circuit of the PPTs, the proposed “low-level” FDI scheme can detect and isolate faults in the PPT actuators with a good level of accuracy, however the precision level is poor and below expectations with the misclassification rates as expressed by False Healthy and False Faulty parameters being too high. The proposed “high-level” FDI scheme utilizes data from the relative attitudes of the FF mission. This scheme has good detection capabilities, however its isolation capabilities are not adequate. Finally, the proposed “integrated” FDI scheme takes advantage of the strengths of each of the above two schemes while reducing their individual weaknesses. The results demonstrate a high level of accuracy (99.79%) and precision (99.94%) with a misclassification rates that are quite negligible (less than 1%). Furthermore, the proposed “integrated” FDI scheme provides additional and interesting information related to the effects of faults in the thrust production levels that would not have been available from simply using the low or the high level schemes alone.