Fault Diagnosis And Isolation Research Articles

Data Acquiring System for Gas Turbine Engine’s Dynamic Performance; Build and Validate

ABSTRACT Gas Turbine Engines (GTE) have the highest power-to-weight ratio among Internal Combustion Engines (ICE). Its modularity and ability to utilize various types of fuel make it highly recommended in power plants, naval transportation, and, of course, the most equipped in aviation. The lack of GTEs’ real data is increasing a recognized need for collecting informative real data sets from GTEs for modeling, monitoring, and fault diagnosis and isolation (FDI). In the present article, a robust versatile data acquisition measuring system has been built to collect real-time data from an axial turboshaft GTE. The system facilitates connectivity and integrity by means of two wiring harnesses connecting the data acquisition card (DAQ), the engine’s control unit, and the operator’s control console. Mobility is guaranteed using a wireless connection between DAQ and a customized programmable LabVIEW interface application. Many experiments have been conducted in different operating conditions to collect the engine and controller’s data in different regimes. The measured signals have been filtered using software-implemented filters and transformed into the right measurement quantities. The experiment data have been analyzed for different regimes, and the milestone documented readings were compared with the measured ones to validate the accuracy and precision of the measuring system. The system is valid for collecting informative data sets that are usable for modeling the engine’s dynamic performance and fault detection.

Investigations on Using Intelligent Learning Techniques for Anomaly Detection and Diagnosis in Sensors Signals in Li-Ion Battery—Case Study

This research paper aims to design and implement an intelligent least short time memory (LSTM) deep learning classification technique to detect possible anomalies in measurements dataset within a particular Li-ion battery type. For the state of charge (SOC) and battery faults estimation, a Joint State and Parameter Extended Kalman Filter (JEKF) estimator is developed. The SOC accuracy performance is excellent, with less than 0.5% error during steady-state, compared to the 2% error reported in the literature. For the design and implementation of JEKF SOC and parameter estimation is chosen a preset Li-ion battery Simulink Simscape generic model. It is also helpful to generate the healthy and faulty measurement dataset to design and implement the proposed intelligent LSTM classifier deep learning technique. The generic Li-ion battery model is wisely selected for the “proof concept” purpose, model validation, and algorithms’ robustness, accuracy, and effectiveness. Compared to the traditional EKF fault diagnosis and isolation (FDI), a model-based estimation strategy, the proposed classification LSTM technique is an intelligent data-driven-based deep learning algorithm of high accuracy (around 80%) and loss performance close to zero. Therefore, this feature makes data collection of dataset measurements directly from Li-ion battery sensors possible, which is beneficial for generating online fault scenarios. Additionally, the LSTM deep learning technique can remarkably classify all detected anomalies with high accuracy, independent of battery model accuracy, uncertainties, and unmodeled dynamics. Also, high-performance accuracy root mean square error (RMSE) of 0.0588 (voltage fault), approximately 5.5×10−7 (healthy) and 8.87 × 10−6 (current fault) for deep learning shallow neural network (DLSNN) reveals an obvious superiority of both compared to the traditional FDI estimation strategies.

상호 다중 모델을 이용한 멀티로터 프로펠러 고장 감지

Many studies are being promoted due to the miniaturization of equipment installed in the UAV(Unmanned Aerial Vehicle). Among them, the quadrotor of MAV(Multirotor Aerial vehicle) is the most popular UAV and has been developed in various fields. Practical utilization of UAV requires stable flight or emergency action in fault of UAV parts, but a quadrotor with one motor damaged cannot perform stable flight due to unbalanced force applied to the quadrotor frame. For this reason the development of hexa- or octorotor with more motors is underway and the need to develop FDI(Fault Diagnosis and Isolation) algorithms to use with MAV is increasing. In this paper we designed a simulation based on MAV dynamic and FDI used to classify fault that occurred in the simulation. For fault diagnosis the model based FDI algorithm IMM(Interacting Multiple Model) was applied because the fault affects the system dynamic and output. IMM uses multiple filter models in simultaneously and then compare to the filters estimation and target system output to give weight to suitable filter model. IMM showed accurate and fast fault perceive and classification performance when a fault occurred in the MAV simulation.

On-board Fault Diagnosis of a Laboratory Mini SR-30 Gas Turbine Engine

Inspired by recent progress in machine learning, a data-driven fault diagnosis and isolation (FDI) scheme is explicitly developed for failure in the fuel supply system and sensor measurements of the laboratory gas turbine system. A passive approach to fault diagnosis is implemented where a model is trained using machine learning classifiers to detect a given set of faults in real-time on which it is trained. Towards the end, a comparative study is presented using well-known classification techniques, namely Support Vector Machine, Linear Discriminant Analysis, K-Neighbors, and Decision Trees. Several simulation studies were carried out to demonstrate the proposed fault diagnosis scheme's advantages, capabilities, and performance.

LPV Model Based Sensor Fault Diagnosis and Isolation for Permanent Magnet Synchronous Generator in Wind Energy Conversion Systems

This paper deals with the current sensor fault diagnosis and isolation (FDI) problem for a permanent magnet synchronous generator (PMSG) based wind system. An observer based scheme is presented to detect and isolate both additive and multiplicative faults in current sensors, under varying torque and speed. This scheme includes a robust residual generator and a fault estimation based isolator. First, the PMSG system model is reformulated as a linear parameter varying (LPV) model by incorporating the electromechanical dynamics into the current dynamics. Then, polytopic decomposition is introduced for H ∞ design of an LPV residual generator and fault estimator in the form of linear matrix inequalities (LMIs). The proposed gain-scheduled FDI is capable of online monitoring three-phase currents and isolating multiple sensor faults by comparing the diagnosis variables with the predefined thresholds. Finally, a MATLAB/SIMULINK model of wind conversion system is established to illustrate FDI performance of the proposed method. The results show that multiple sensor faults are isolated simultaneously with varying input torque and mechanical power.

Data‐driven fault diagnosis and robust control: Application to PEM fuel cell systems

SummaryA data‐driven methodology that includes the unfalsified control concept in the framework of fault diagnosis and isolation (FDI) and fault‐tolerant control (FTC) is presented. The selection of the appropriate controller from a bank of controllers in a switching supervisory control setting is performed by using an adequate FDI outcome. By combining simultaneous online performance assessment of multiple controllers with the fault diagnosis decision from structured hypothesis tests, a diagnosis statement regarding what controller is most suitable to deal with the current (nominal or faulty) mode of the plant is obtained. Switching strategies that use the diagnosis statement are also proposed. This approach is applied to a nonlinear experimentally validated model of the breathing system of a polymer electrolyte membrane fuel cell. The results show the effectiveness of this FDI–fault‐tolerant control data‐driven methodology. Copyright © 2017 John Wiley & Sons, Ltd.

Sensor fault-tolerant observer applied in UAV anti-skid braking control under control input constraint

This paper proposes a method for addressing the problem of sensor fault-tolerant control (FTC) for anti-skid braking systems (ABSs). When the wheel velocity sensor of the ABS for unmanned aerial vehicles (UAVs) becomes faulty, wheel velocity failure and feedback instability may occur. Firstly, a fault diagnosis and isolation (FDI) method based on a sliding mode observer approach is introduced to detect and isolate the fault of the sensor. When the wheel velocity sensor is in healthy conditions, the observer works in a diagnosis mode. If faults occur in the sensor, it acts as a wheel velocity estimator. Secondly, an FTC strategy, adopting a feedback compensation structure, is designed with input control constraints. In addition, based on the FDI result, a terminal sliding mode (TSM) controller is designed to guarantee that slip-ratio tracks its appropriate reference values in situations where runways change conditions during landing. The control system switches automatically from control using a wheel velocity sensor to sensorless control mode, so the observer-based FTC scheme is established. It is logical that the ABS keeps observed-state and remains stable when the wheel velocity sensor is broken and during external disturbance. Finally, simulation results show the effectiveness of the proposed method.

Design of a new nonlinear model predictive fault tolerant control system using multi-sensor data fusion technique based on UKF algorithm

Purpose– There are high expectations for reliability, safety and fault tolerance are high in chemical plants. Control systems are capable of potential faults in the plant processing systems. This paper proposes is a new Fault Tolerant Control (FTC) system to identify the probable fault occurrences in the plant.Design/methodology/approach– A Fault Diagnosis and Isolation (FDI) module has been devised based on the estimated state of system. An Unscented Kalman Filter (UKF) is the main innovation of the FDI module to identify the faults. A Multi-Sensor Data Fusion algorithm is utilized to integrate the UKF output data to enhance fault identification. The UKF employs an augmented state vector to estimate system states and faults simultaneously. A control mechanism is designed to compensate for the undesirable effects of the detected faults.Findings– The performance of the Nonlinear Model Predictive Controller (NMPC) without any fault compensation is compared with the proposed FTC scheme under different fault scenarios. Analysis of the simulation results indicates that the FDI method is able to identify the faults accurately. The proposed FTC approach facilitates recovery of the closed loop performance after the faults have been isolated.Originality/value– A significant contribution of the paper is the design of an FTC system by using UKF to estimate faults and enhance the accuracy of data. This is done by applying a data fusion algorithm and controlling the system by the NMPC after eliminating the effects of faults.

Self-Repairing Control System for a Hybrid Underwater Vehicle

A novel remotely operated underwater vehicle-a hybrid remotely operated underwater vehicle (HROV) capable of working to the full ocean depth has been developed. The battery powered vehicle operates in two modes. For broad-area survey, the vehicle can operate as an autonomous underwater vehicle (AUV) capable of mapping the sea floor with sonars and cameras. For close up imaging and sampling, the vehicle can operate as a remotely operated underwater vehicle (ROV) employing a optic fiber tether for real-time telemetry of data and video to its operators on a surface ship. In order for the vehicle to achieve a certain survivability and reliability level, a self-repairing control system (SRCS) has been designed. This paper presents the two basic technologies in SRCS: fault diagnosis and isolation (FDI) and reconfigurable control. For FDI, a model-based hierarchical fault diagnosis system is designed for the HROV. Then, control strategies which reconfigure the control system at intervals according to information from the FDI system are presented. Combining the two technologies, we obtained the fundamental frame of SRCS for the HROV.

Sensor fault-tolerant observer applied in satellite attitude control

The observing failure and feedback instability might happen when the partial sensors of a satellite attitude control system (SACS) go wrong. A fault diagnosis and isolation (FDI) method based on a fault observer is introduced to detect and isolate the fault sensor at first. Based on the FDI result, the object system state-space equation is transformed and divided into a correspon-sive triangular canonical form to decouple the normal subsystem from the fault subsystem. And then the KX fault-tolerant observers of the system in different modes are designed and embedded into online monitoring. The outputs of all KX fault-tolerant observers are selected by the control switch process. That can make sense that the SACS is part-observed and in stable when the partial sensors break down. Simulation results demonstrate the effectiveness and superiority of the proposed method.

Actuator fault‐tolerant control based on set separation

AbstractIn this paper, an actuator fault‐tolerant control (FTC) strategy based on set separation is presented. The proposed scheme employs a standard configuration consisting of a 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 a distinctive behaviour when a estimator matches the current fault situation of the plant. With this information from each observer, a fault diagnosis and isolation (FDI) module is able to reconfigure the control loop by selecting the appropriate stabilising controller from a bank of precomputed control laws, each of them related to one of the considered fault models. The control law consists of a reference feedforward term and a feedback gain multiplying the state estimate provided by the matching observer. A novel feature of the proposed scheme resides in the decision criteria of the FDI, which is based on the computation of sets towards which the output estimation errors related to each fault scenario and for each control configuration converge. Conditions for the design of the FDI module and for fault tolerant closed‐loop stability are given, and the effectiveness of the approach is illustrated by means of a numerical example. Copyright © 2010 John Wiley & Sons, Ltd.

New Fusion Architectures for Performance Enhancement of a PCA-Based Fault Diagnosis and Isolation System

This paper proposes some new fusion architectures to enhance the diagnostic operation of a principal component analysis (PCA)-based fault diagnosis and isolation (FDI) system. The first approach presents a serial classifier fusion methodology by incorporating a support vector machine (SVM) classifier to diagnose PCA-based fault features. Then, parallel fusion architecture is proposed to fuse the fault diagnostics due to the individual SVM, Bayes and K-nearest neighbor (K-NN) classifiers. The two series and parallel fusion architectures are finally incorporated into a new combined framework to yield a more efficient and powerful diagnostic capabilities. Extensive simulation test experiments are conducted to demonstrate the comparative performances of the new proposed fusion-based FDI systems on the Tennessee Eastman (TE) process plant as a large-scale benchmark problem.

Actuator Fault-Tolerant Control based on Invariant Set Separation

Abstract In this paper an actuator fault-tolerant control (FTC) strategy based on invariant set computation is presented. The proposed scheme is based on a bank of observers which match different fault situations that can occur in the plant. Each of these observers produces an estimation error with a distinctive behavior when the observer matches the current fault situation in the plant. With the information of the estimation errors from each of the considered observers, a fault diagnosis and isolation (FDI) module is able to reconfigure the control loop by selecting the appropriate stabilising controller from a bank of precomputed control laws, each of them related to one of the considered fault models. The decision criteria of the FDI is based on the computation of invariant sets of the estimation errors for each fault scenario and for each control configuration. Conditions for the design of the FDI module and for fault-tolerant closed-loop stability are given, and the effectiveness of the approach is illustrated with an example.

Fault detection in electromagnetic suspension systems with state estimation methods

A procedure is presented for the design of a fault diagnosis and isolation (FDI) subsystem for electromagnetic suspension systems. This subsystem is based on the Luenberger observer and logical analysis. Using the position sensor output, the observer estimates the state variables. One critical feedback variable is the vertical acceleration of the suspended magnet. The fault of the accelerometer is detected by comparing its output with the estimated state variable. At the same time, a redundant accelerometer takes over to sustain stability. Experimental results illustrate the feasibility of this method. >