A neuro-fuzzy online fault detection and diagnosis algorithm for nonlinear and dynamic systems

This paper presents a new fault detection and diagnosis approach for nonlinear dynamic plant systems with a neuro-fuzzy based approach to prevent developing of fault as soon as possible. By comparison of plants and neuro-fuzzy estimator outputs in the presence of noise, residual signal is generated and compared with a predefined threshold, the fault can be detected. To diagnose the type, size, time and fault conditions, are used analytical approach and neural network for tracking fault developing online. The neuro-fuzzy nets are compared with some other identification methods in application of power plant gas turbine. Faults are considered in two forms, step, and ramp shape. This work was implemented with real data from gas turbine of Kazeroun (Iran) power plant (Mitsubishi unit) and result is presented to demonstrate the benefits of the proposed method.     

A novel approach to fault diagnosis for time-delay systems

In this paper, a novel fault detection and identification (FDI) scheme for time-delay systems is presented. Different from the existing FDI design methods, the proposed approach utilizes fault tracking approximator (FTA) and iterative learning algorithm to obtain estimates of the fault functions. Performance of the FTA is rigorously analyzed by investigating its stability and fault tracking sensitivity properties in the presence of slowly developing or abrupt faults for state delayed dynamic systems. A novel feature of the FTA is that it can simultaneously detect and identify the shape and magnitude of the faults. Additionally, an extension to a class of nonlinear time-delay systems is made by using nonlinear control theories. Finally, the applicability and effectiveness of the proposed FDI scheme is illustrated by a practical industrial process.     

A novel fault diagnosis method based on CNN and LSTM and its application in fault diagnosis for complex systems

Fault diagnosis plays an important role in actual production activities. As large amounts of data can be collected efficiently and economically, data-driven methods based on deep learning have achieved remarkable results of fault diagnosis of complex systems due to their superiority in feature extraction. However, existing techniques rarely consider time delay of occurrence of faults, which affects the performance of fault diagnosis. In this paper, by synthetically considering feature extraction and time delay of occurrence of faults, we propose a novel fault diagnosis method that consists of two parts, namely, sliding window processing and CNN-LSTM model based on a combination of Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM). Firstly, samples obtained from multivariate time series by the sliding window processing integrates feature information and time delay information. Then, the obtained samples are fed into the proposed CNN-LSTM model including CNN layers and LSTM layers. The CNN layers perform feature learning without relying on prior knowledge. Time delay information is captured with the use of the LSTM layers. The fault diagnosis of the Tennessee Eastman chemical process is addressed, and it is verified that the predictive accuracy and noise sensitivity of fault diagnosis can be greatly improved when the proposed method is applied. Comparisons with five existing fault diagnosis methods show the superiority of the proposed method.

     

导航系统故障检测与诊断技术综述

导航系统的故障检测与诊断技术受到理论界的广泛重视,总结了国内外应用于导航系统的故障检测与诊断方法:基于硬件冗余方法、基于χ2检验方法、基于奇偶空间方法、基于小波变换方法、基于神经网络方法、基于联邦滤波器方法和一些其他方法.讨论了导航系统的故障检测与诊断发展趋势.     

Robust fault diagnosis for non-linear difference-algebraic systems

A new robust fault diagnosis method based on linear matrix inequality (LMI) for non-linear difference-algebraic systems (DAS) with uncertainties is proposed. Based on the known nominal model of DAS, it firstly constructs an auxiliary system consisting of a difference equation and an algebraic equation, then converts the problem of fault identification into the problem of parameter estimation, and finally realizes fault identification using an LMI method. This method can not only detect, isolate and identify faults for DAS, but also give the upper bounds of fault identification error. Simulation indicates that it can give satisfactory diagnostic results for both abrupt and incipient faults.     

非线性系统的故障诊断技术

文中对非线性系统的故障诊断方面问题给予了归纳总结,指出了基于数学模型方法,基于信号处理方法和基于知识的方法在实现非线性系统故障诊断的基本思想,并进一步指出了各各非线性系统故障诊断方法及可能的发展方向。     

LMI-based sensor fault diagnosis for nonlinear Lipschitz systems

The problem of sensor fault diagnosis in the class of nonlinear Lipschitz systems is considered. A dynamic observer structure is used with the objective to make the residual converge to the faults vector achieving detection and estimation at the same time. It is shown that, unlike the classical constant gain structure, this objective is achievable by minimizing the faults effect on the estimation error of the dynamic observer. The use of appropriate weightings to solve the design problem in a standard convex optimization framework is also demonstrated. An LMI design procedure solvable using commercially available software is presented.     

Flexible neuro-fuzzy systems

In this paper, we derive new neuro-fuzzy structures called flexible neuro-fuzzy inference systems or FLEXNFIS. Based on the input-output data, we learn not only the parameters of the membership functions but also the type of the systems (Mamdani or logical). Moreover, we introduce: 1) softness to fuzzy implication operators, to aggregation of rules and to connectives of antecedents; 2) certainty weights to aggregation of rules and to connectives of antecedents; and 3) parameterized families of T-norms and S-norms to fuzzy implication operators, to aggregation of rules and to connectives of antecedents. Our approach introduces more flexibility to the structure and design of neuro-fuzzy systems. Through computer simulations, we show that Mamdani-type systems are more suitable to approximation problems, whereas logical-type systems may be preferred for classification problems.     

A knowledge-based system for fault diagnosis and maintenance of advanced automated systems

A knowledge-based system for diagnosis & maintenance of robotic systems has been designed which may also serve as a training tool for maintenance personnel. The system uses a Group Technology (GT) approach for fault classification and analysis. A simple user interface leads the user through a consultation phase in order to arrive at a diagnosis. It then recommends corrective actions and a simple test procedure to verify that the robot will perform satisfactorily after the repairs.     

基于故障跟踪估计器的非线性时滞系统故障诊断

提出一种可有效检测和估计一类非线性时滞系统故障的故障跟踪估计器.根据预测控制和迭代学习控制的思想,在所选取的优化时域长度内,通过迭代算法调节故障跟踪估计器中的可调参数,使之逼近系统中实际发生的故障.与以往基于观测器的故障诊断方法不同的是,故障跟踪估计器可同时检测和估计系统中发生的故障,而且针对不同类型的故障亦有很好的适应性.仿真结果表明了所提出算法的可行性和有效性.     

Robust fault diagnosis for a class of nonlinear systems

Robust fault diagnosis based on adaptive observer is studied for a class of nonlinear systems up to output injection. Adaptive fault updating laws are designed to guarantee the stability of the diagnosis system. The upper bounds of the state estimation error and fault estimation error of the adaptive observer are given respectively and the effects of parameter in the adaptive updating laws on fault estimation accuracy are also discussed. Simulation example demonstrates the effectiveness of the proposed methods and the analysis results.     

A genetic-based neuro-fuzzy approach for modeling and control ofdynamical systems

Linguistic modeling of complex irregular systems constitutes the heart of many control and decision making systems, and fuzzy logic represents one of the most effective algorithms to build such linguistic models. In this paper, a linguistic (qualitative) modeling approach is proposed. The approach combines the merits of the fuzzy logic theory, neural networks, and genetic algorithms (GAs). The proposed model is presented in a fuzzy-neural network (FNN) form which can handle both quantitative (numerical) and qualitative (linguistic) knowledge. The learning algorithm of a FNN is composed of three phases. The first phase is used to find the initial membership functions of the fuzzy model. In the second phase, a new algorithm is developed and used to extract the linguistic-fuzzy rules. In the third phase, a multiresolutional dynamic genetic algorithm (MRD-GA) is proposed and used for optimized tuning of membership functions of the proposed model. Two well-known benchmarks are used to evaluate the performance of the proposed modeling approach, and compare it with other modeling approaches.     

Residual generation for fault diagnosis in linear time-varying systems

A residual generation method for fault diagnosis in deterministic and stochastic linear time-varying systems is proposed in this note. Based on appropriate assumptions on the monitored faults and on some persistent excitation condition, it enables complete diagnosis of any number of faults, regardless of the number of output sensors. In order to generate residuals for fault diagnosis, part of the possible faults are estimated with a recently developed technique of adaptive observer. The sensitivity of the residuals to the monitored faults is rigorously analyzed, as well as their insensitivity to the faults to be ignored.     

ADO在故障诊断专家系统中的应用

作为新型的数据库访问技术,简要介绍了ADO技术及其特点,重点介绍了ADO技术在专家系统中的应用,利用ADPO技术实现了对两个数据源的访问,为建立在自动测试系统上的故障诊断专家系统提供了入口参数,最后用Visual C 语言实现了编程。     

Self-adaptive neuro-fuzzy inference systems for classification applications

This paper presents a self-adaptive neuro-fuzzy inference system (SANFIS) that is capable of self-adapting and self-organizing its internal structure to acquire a parsimonious rule-base for interpreting the embedded knowledge of a system from the given training data set. A connectionist topology of fuzzy basis functions with their universal approximation capability is served as a fundamental SANFIS architecture that provides an elasticity to be extended to all existing fuzzy models whose consequent could be fuzzy term sets, fuzzy singletons, or functions of linear combination of input variables. Without a priori knowledge of the distribution of the training data set, a novel mapping-constrained agglomerative clustering algorithm is devised to reveal the true cluster configuration in a single pass for an initial SANFIS construction, estimating the location and variance of each cluster. Subsequently, a fast recursive linear/nonlinear least-squares algorithm is performed to further accelerate the learning convergence and improve the system performance. Good generalization capability, fast learning convergence and compact comprehensible knowledge representation summarize the strength of SANFIS. Computer simulations for the Iris, Wisconsin breast cancer, and wine classifications show that SANFIS achieves significant improvements in terms of learning convergence, higher accuracy in recognition, and a parsimonious architecture.     

A review on the applications of neuro-fuzzy systems in business

This paper presents a review of the application of neuro-fuzzy systems (NFS) in business on the basis of the research articles issued in various reputed international journals and conferences during 2005–2015. The use of NFS for tackling various real world problems in different business domains has diversified significantly during this period. In effect NFS has emerged as a dominant technique for addressing various difficult research problems in business. Based on a detailed review of these research papers we have identified finance, marketing, distribution, business planning, information systems, production and operations as the main business application domains of NFS during this period. This paper also discusses the impact of NFS in various business domains and the trend of this application based research during this period. This paper also surveys the various innovations in NFS methodologies employed by the researchers to deal with different business problems in each of these years. Moreover the paper includes some articles published during 2016 in several international journals to present the latest progress in the application of NFS in various business domains.     

Neural-network-based robust fault diagnosis in robotic systems

Fault diagnosis plays an important role in the operation of modern robotic systems. A number of researchers have proposed fault diagnosis architectures for robotic manipulators using the model-based analytical redundancy approach. One of the key issues in the design of such fault diagnosis schemes is the effect of modeling uncertainties on their performance. This paper investigates the problem of fault diagnosis in rigid-link robotic manipulators with modeling uncertainties. A learning architecture with sigmoidal neural networks is used to monitor the robotic system for any off-nominal behavior due to faults. The robustness and stability properties of the fault diagnosis scheme are rigorously established. Simulation examples are presented to illustrate the ability of the neural-network-based robust fault diagnosis scheme to detect and accommodate faults in a two-link robotic manipulator.     

Application of knowledge-based systems for fault diagnosis and supply restoration

A knowledge-based system (KBS) for fault diagnosis and supply restoration in an electrical power distribution system is introduced to complement the teaching of the related theory in a senior-year course. The KBS communicates with a power-system simulator which enables the setup of various scenarios. Through the KBS, the students strengthen their understanding of generic diagnostic rules, restoration algorithms, knowledge acquisition and inference mechanisms. Six training scenarios are described to illustrate how the concepts of fault diagnosis, supply restoration and various features of the KBS can be taught.     

Observer-based residual generation for fault diagnosis for non-affine non-linear polynomial systems

This paper proposes an observer-based residual generator (OBRG) for diagnosing faults in a continuous non-affine system with polynomial non-linearities up to any finite degree where the fault and an unknown input affect both the system and part of the output. Firstly, given certain assumptions and the use of defined extended vectors, a parameterized polynomial system is considerred for which a compact set of sufficient conditions is given for the existence of a candidate OBRG. Conditions for error stability (by a Lyapunov method) and detectability are given. The calculation steps in the design of the OBRG are shown to involve the solution of three linear equations (with parameterizations) and the calculation of a set of constant matrices (for detectability of faults). A result is then given establishing that the design holds for a much wider class of systems. The residual design is applied to a real three-tank system.     

Error detection and diagnosis for fault tolerance in distributed systems

The early error detection and the understanding of the nature and conditions of an error occurrence can be useful to make an effective and efficient recovery in distributed systems. Various distributed system extensions were introduced for the implementation of fault tolerance in distributed software systems. These extensions rely mainly on the exchange of contextual information appended to every transmitted application specific message. Ideally, this information should be used for checkpointing, error detection, diagnosis and recovery should a transient failure occur later during the distributed program execution. In this paper, we present a generalized extension suitable for fault-tolerant distributed systems such as communication software systems and its detection capabilities are shown. Our extension is based on the execution of message validity test prior to the transmission of messages and the piggybacking of contextual information to facilitate the detection and diagnosis of transient faults in the distributed system.