For Fault Detection And Diagnosis Research Articles

Designing supervised local neural network classifiers based on EM clustering for fault diagnosis of Tennessee Eastman process

This paper proposes a supervised local multilayer perceptron (SLMLP) classifier integrated with independent component analysis (ICA) models for fault detection and diagnosis (FDD) of industrial systems. The interest of this paper is to improve the performance of single neural network (SNN) by dividing the fault pattern space into a few smaller sub-spaces using Expectation-Maximization (EM) clustering technique and triggering the right local classifier by designing a supervisor agent. To detect both known and new faults of the system, two ICA models are integrated with the proposed classifier. The performances of this method are evaluated on the data of Tennessee Eastman (TE) process, a benchmark chemical engineering problem. The results from the experiments show the superiority of the proposed method compared to other well-known published works.

Double-model adaptive fault detection and diagnosis applied to real flight data

The existing multiple model-based estimation algorithms for Fault Detection and Diagnosis (FDD) require the design of a model set, which contains a number of models matching different fault scenarios. To cope with partial faults or simultaneous faults, the model set can be even larger. A large model set makes the computational load intensive and can lead to performance deterioration of the algorithms. In this paper, a novel Double-Model Adaptive Estimation (DMAE) approach for output FDD is proposed, which reduces the number of models to only two, even for the FDD of partial and simultaneous output faults. Two Selective-Reinitialization (SR) algorithms are proposed which can both guarantee the FDD performance of the DMAE. The performance is tested using a simulated aircraft model with the objective of Air Data Sensors (ADS) FDD. Another contribution is that the ADS FDD using real flight data is addressed. Issues related to the FDD using real flight test data are identified. The proposed approaches are validated using real flight data of the Cessna Citation II aircraft, which verified their effectiveness in practice.

Fault Detection and Diagnosis in a Bayesian Network classifier incorporating probabilistic boundary1

The purpose of this article is to present a method for Fault Detection and Diagnosis (FDD) with Bayesian network, and more particularly with Conditional Gaussian Network (CGN). A classical problem of FDD with supervised classification is when Normal Operating Conditions class is integrated, the false alarm rate is not guarantee by the classifier. The interest of the proposed method is to introduce a probabilistic limit on the Normal Operating Conditions class, allowing to respect a given false alarm rate. Performances of this method are evaluated on data of a benchmark example: the Tennessee Eastman Process. Three kinds of faults are taken into account on this complex process.

Takagi Sugeno fuzzy expert model based soft fault diagnosis for two tank interacting system

Abstract The inherent characteristics of fuzzy logic theory make it suitable for fault detection and diagnosis (FDI). Fault detection can benefit from nonlinear fuzzy modeling and fault diagnosis can profit from a transparent reasoning system, which can embed operator experience, but also learn from experimental and/or simulation data. Thus, fuzzy logic-based diagnostic is advantageous since it allows the incorporation of a-priori knowledge and lets the user understand the inference of the system. In this paper, the successful use of a fuzzy FDI based system, based on dynamic fuzzy models for fault detection and diagnosis of an industrial two tank system is presented. The plant data is used for the design and validation of the fuzzy FDI system. The validation results show the effectiveness of this approach.

Study on Linear Vibration Model of Shield TBM Cutterhead Driving System

In this paper, a general linear time-varying multiple-axis (LTVMA) vibration model of shield tunnel boring machine (TBM) cutterhead driving system is established. The corresponding multiple inputs and multiple outputs (MIMO) state-space model is also presented. The linear vibration model is analysed, and the vibration-torque transfer function matrix and the vibration-torque static gain matrix are obtained. The linear vibration model is simulated, and the physical parameters' effects on the vibration response are investigated. A preliminary approach is proposed to reduce vibration by increasing motor rotor inertia and viscous damped. The LTVMA vibration model provides a solid foundation for fault detection and diagnosis (FDD), as long as the health monitoring of cutterhead driving system.

Model-Based Water Wall Fault Detection and Diagnosis of FBC Boiler Using Strong Tracking Filter

Fluidized bed combustion (FBC) boilers have received increasing attention in recent decades. The erosion issue on the water wall is one of the most common and serious faults for FBC boilers. Unlike direct measurement of tube thickness used by ultrasonic methods, the wastage of water wall is reconsidered equally as the variation of the overall heat transfer coefficient in the furnace. In this paper, a model-based approach is presented to estimate internal states and heat transfer coefficient dually from the noisy measurable outputs. The estimated parameter is compared with the normal value. Then the modified Bayesian algorithm is adopted for fault detection and diagnosis (FDD). The simulation results demonstrate that the approach is feasible and effective.

Bayesian network based FDD strategy for variable air volume terminals

Abstract This paper presents a diagnostic Bayesian network (DBN) for fault detection and diagnosis (FDD) of variable air volume (VAV) terminals. The structure of the DBN illustrates qualitatively the casual relationships between faults and symptoms. The parameters of the DBN describe quantitatively the probabilistic dependences between faults and evidence. The inputs of the DBN are the evidences which can be obtained from measurements in building management systems (BMSs) and manual tests. The outputs are the probabilities of faults concerned. Two rules are adopted to isolate the fault on the basis of the fault probabilities to improve the robustness of the method. Compared with conventional rule-based FDD methods, the proposed method can work well with uncertain and incomplete information, because the faults are reported with probabilities rather than in the Boolean format. Evaluations are made on a dynamic simulator of a VAV air-conditioning system serving an office space using TRNSYS. The results show that it can correctly diagnose ten typical VAV terminal faults.

An adaptive fault‐tolerant control framework with agent‐based systems

SUMMARYAn adaptive hierarchical framework for process supervision and fault‐tolerant control with agent‐based systems is presented. The framework consists of modules for fault detection and diagnosis (FDD), system identification and distributed control, and a hierarchical structure for performance‐based agent adaptation. Multivariate continuous process monitoring methodologies and several fault discrimination and classification techniques are implemented in the FDD modules to be used by multiple agents. In the process supervision layer, the continuous intramodular communication between FDD and control modules communicates the existence of an abnormality in the process, type of the abnormality, and affected process sections to the distributed model predictive control agents. In the agent management layer, the performances of all FDD and control agents are evaluated under specific process conditions. Performance‐based consensus criteria are used to prioritize the best‐performing agents in consensus decision making in every level of process supervision and fault‐tolerant control. The collective performance of the supervision system is improved via performance‐based consensus decision making and adaptation. The effectiveness of the proposed adaptive agent‐based framework for fault‐tolerant control is illustrated using a simulated continuous stirred‐tank reactor network. Copyright © 2011 John Wiley & Sons, Ltd.

Development of the reference model for a residential heat pump system for cooling mode fault detection and diagnosis

Development of a reference model to predict the value of system parameters during fault-free operation is a basic step for fault detection and diagnosis (FDD). In order to develop an accurate and effective reference model of a heat pump system, experimental data that cover a wide range of operating conditions are required. In this study, laboratory data were collected under various operating conditions and then filtered through a moving window steady-state detector. Over five thousand scans of steady-state data were used to develop polynomial regression models of seven system features. A reference model was also developed using an artificial neural network (ANN), and it is compared to the polynomial models.

A system-level fault detection and diagnosis strategy for HVAC systems involving sensor faults

This paper presents a strategy for fault detection and diagnosis (FDD) of HVAC systems involving sensor faults at the system level. Two schemes are involved in the system-level FDD strategy, i.e. system FDD scheme and sensor fault detection, diagnosis and estimation (FDD&E) scheme. In the system FDD scheme, one or more performance indices (PIs) are introduced to indicate the performance status (normal or faulty) of each system. Regression models are used as the benchmarks to validate the PIs computed from the actual measurements. The reliability of the system FDD is affected by the health of sensor measurements. A method based on principal component analysis (PCA) is used to detect and diagnose the sensor bias and to correct the sensor bias prior to the use of the system FDD scheme. Two interaction analyses are conducted. One is the impact of system faults on sensor FDD&E. The other is the impact of corrected sensor faults on the system FDD. It is found that the sensor FDD&E method can work well in identifying biased sensors and recovering biases even if system faults coexist, and the system FDD method is effective in diagnosing the system-level faults using processed measurements by the sensor FDD&E.

Fault detection and diagnosis in a spacecraft attitude determination system

This paper presents a new scheme for fault detection and diagnosis (FDD) in spacecraft attitude determination (AD) sensors. An integrated attitude determination system, which includes measurements of rate and angular position using rate gyros and vector sensors, is developed. Measurement data from all sensors are fused by a linearized Kalman filter, which is designed based on the system kinematics, to provide attitude estimation and the values of the gyro bias. Using this information the erroneous sensor measurements are corrected, and unbounded sensor measurement errors are avoided. The resulting bias-free data are used in the FDD scheme. The FDD algorithm uses model-based state estimation, combining the information from the rotational dynamics and kinematics of a spacecraft with the sensor measurements to predict the future sensor outputs. Fault isolation is performed through extended Kalman filters (EKFs). The innovation sequences of EKFs are monitored by several statistical tests to detect the presence of a failure and to localize the failures in all AD sensors. The isolation procedure is developed in two phases. In the first phase, two EKFs are designed, which use subsets of measurements to provide state estimates and form residuals, which are used to verify the source of the fault. In the second phase of isolation, testing of multiple hypotheses is performed. The generalized likelihood ratio test is utilized to identify the faulty components. In the scheme developed in this paper a relatively small number of hypotheses is used, which results in faster isolation and highly distinguishable fault signatures. An important feature of the developed FDD scheme is that it can provide attitude estimations even if only one type of sensors is functioning properly.

Diagnosis of delay–deadline failures in real time discrete event models

In this paper a method for fault detection and diagnosis (FDD) of real time systems has been developed. A modeling framework termed as real time discrete event system (RTDES) model is presented and a mechanism for FDD of the same has been developed. The use of RTDES framework for FDD is an extension of the works reported in the discrete event system (DES) literature, which are based on finite state machines (FSM). FDD of RTDES models are suited for real time systems because of their capability of representing timing faults leading to failures in terms of erroneous delays and deadlines, which FSM-based ones cannot address. The concept of measurement restriction of variables is introduced for RTDES and the consequent equivalence of states and indistinguishability of transitions have been characterized. Faults are modeled in terms of an unmeasurable condition variable in the state map. Diagnosability is defined and the procedure of constructing a diagnoser is provided. A checkable property of the diagnoser is shown to be a necessary and sufficient condition for diagnosability. The methodology is illustrated with an example of a hydraulic cylinder.

An overall performance index for characterizing the economic impact of faults in direct expansion cooling equipment

Air conditioning is a non-critical application for fault detection and diagnosis (FDD) where decisions about servicing faults should involve the use of economics. Existing methods for evaluating impacts of faults on equipment performance only consider some individual factors such as the equipment coefficient of performance (COP) or cooling capacity. This paper develops an overall economic performance degradation index (EPDI) for air conditioning equipment that includes the combined effects of degradations in COP, cooling capacity, and sensible heat ratio (SHR). EPDI quantifies the performance degradation caused by faults based on economics so it can be used as part of the decision making process in an overall FDD system. Furthermore, EPDI can be used along with estimates of typical field performance degradations to assess the economic benefits associated with the application of automated FDD. A case study is presented where EPDI was applied to measurements for an existing unit where faults were artificially introduced.

Detection of Rooftop Cooling Unit Faults Based on Electrical Measurements

Nonintrusive load monitoring (NILM) is accomplished by sampling voltage and current at high rates and reducing the resulting start transients or harmonic contents to concise “signatures.” Changes in these signatures can be used to detect, and in many cases directly diagnose, equipment and component faults associated with rooftop cooling units. Use of the NILM for fault detection and diagnosis (FDD) is important because (1) it complements other FDD schemes that are based on thermo-fluid sensors and analyses and (2) it is minimally intrusive (one measuring point in the relatively protected confines of the control panel) and therefore inherently reliable. This paper describes changes in the power signatures of fans and compressors that were found, experimentally and theoretically, to be useful for fault detection.

FAULT DETECTION AND ISOLATION USING CORRESPONDENCE ANALYSIS

In this paper, a new approach to Fault Detection and Diagnosis that is based on Correspondence Analysis is proposed. Correspondence analysis is a powerful multivariate technique based on the generalized singular value decomposition. The advantage of using correspondence analysis is that it depicts rows as well as columns as points in the dual lower dimensional vector space. Correspondence analysis has been shown to capture association between various features and events quite exoectively. In this paper, the correspondence analysis approach is used for Fault Detection and Diagnosis (FDD) and is validated on representative process systems.

사출 성형기 Barrel 온도에 관한 퍼지알고리즘 기반의 고장 검출 및 진단

We acquired data of injection molding machine in operation and stored the data in database. We acquired the data of injection molding machine for fault detection and diagnosis (FDD) continuously and estimated the fault results with a fuzzy algorithm. Many of FDD are applied to a huge system, nuclear power plant and a computer numerical control(CNC) machine for processing machinery. But, the research of FDD is rare in injection molding machine compare with computer numerical control machine. We appraise the accuracy of the FDD and the limit of the application to the injection molding machine. We construct the fault detection and diagnosis system based on fuzzy algorithm in the injection molding machine. Data of operating injection molding machine are acquired in order to improve the reliability of detection and diagnosis.

Bibliographical review on reconfigurable fault-tolerant control systems

In this paper, a bibliographical review on reconfigurable fault-tolerant control systems (FTCS) is presented. The existing approaches for fault detection and diagnosis (FDD) and reconfigurable control are considered with emphasis on the reconfigurable/restructurable controller design techniques. Several open problems and current research topics are addressed. 250 references in the open literature are listed to provide an outline of the historical and recent development in the field. The review reported in this paper is in no way to be complete, we apologize in advance if any of the existing works were left out. We encourage readers to communicate with us for any additional information.

Closed-loop fault diagnosis based on a nonlinear process model and automatic fuzzy rule generation

In this contribution a new approach for fault detection and diagnosis (FDD) for nonlinear processes is presented. A nonlinear fuzzy model with transparent inner structure is used for the generation of relevant symptoms. The resulting symptom patterns are classified with a new self-learning classification structure based on fuzzy rules. The approach is successfully applied to an electro-pneumatic valve in a closed control loop.

Fault detection and diagnosis using statistical control charts and artificial neural networks

In order to operate a successful plant or process, continuous improvement must be made in the areas of safety, quality and reliability. Central to this continuous improvement is the early or proactive detection and correct diagnosis of process faults. This research examines the feasibility of using cumulative summation (CUSUM) control charts and artificial neural networks together for fault detection and diagnosis (FDD). The proposed FDD strategy was tested on a model of the heat transport system of a CANDU nuclear reactor. The results of the investigation indicate that a FDD system using CUSUM control charts and a radial basis function (RBF) neural network is not only feasible but also of promising potential. The control charts and neural network are linked by using a characteristic fault signature pattern for each fault which is to be detected and diagnosed. When tested, the system was able to eliminate all false alarms at steady state, promptly detect six fault conditions, and correctly diagnose five out of the six faults. The diagnosis for the sixth fault was inconclusive.

A Comparative Study of Neural Networks Based Approach for Fault Detection

This paper deals with a comparative study of neural networks used for fault detection and diagnosis (FDD) in a wastewater plant. When a fault occurs the parameters in a non-lineal mathematical model of the process change. A method for detecting and tracking the different values of the parameters is proposed, with tries to be robust with respect to low frequency disturbances and modelling errors, the uncertainties, which can interfere seriously with the FDD performance, increasing the false and missed alarms. The method, using different neural networks, is applied to a wastewater plant, in order to compare and to prove the reliability of the algorithms.