Najmeh Daroogheh

A novel particle filter parameter prediction scheme for failure prognosis

Particle filters are well-known as powerful tools for accomplishing state and parameter estimation and their propagation prediction in nonlinear dynamical systems. Their ability to include system model parameters as part of the system state vector is among one of the key factors for their use in prognostics. Estimation of system parameters along with the states produces an updated model that can be used for long-term prediction. This paper presents a novel method for uncertainty management in long-term prediction using particle filters. In our proposed approach, the observation prediction concept is applied in order to extend the system observation profiles (as time series) for future. Next, particles are propagated to future time instants according to the resampling algorithm instead of considering constant weights for their propagation in the prediction step. The uncertainty in the long-term prediction of system states and parameters are managed by utilizing fixed-lag dynamic linear models. The observation prediction is achieved along with an outer adjustment loop to change the observation injection window adaptively based on the Mahalanobis distance criteria. The proposed approach is applied to predict the health of a gas turbine system that is affected by the degradation in the system health parameters.

Particle filtering for state and parameter estimation in gas turbine engine fault diagnostics

In this paper, a novel method for a time-varying parameter estimation technique using particle filters is proposed based on the concept of Recursive Prediction Error (RPE). According to the proposed method, a parallel structure for both state and parameter estimation in a nonlinear non-Gaussian system is developed. The performance of the developed framework is evaluated in an application to the gas turbine engine state and health parameters estimation by using different scenarios. The developed method is identified to be applicable for fault diagnosis of an engine system while it is subjected to concurrent and simultaneous loss of effectiveness faults in the system components.

A hybrid prognosis and health monitoring strategy by integrating particle filters and neural networks for gas turbine engines

In this paper, a novel hybrid structure is proposed for the development of health monitoring techniques of nonlinear systems by integration of model-based and computationally intelligent and data-driven techniques. In our proposed health monitoring framework, the well-known particle filtering method is utilized to estimate the states as well as the health parameters of the system. Simultaneously, the system observations are predicted through an observation forecasting scheme which is developed based on artificial neural networks to construct observation profiles for future time horizons. As a case study, the proposed approach is applied to predict the health condition of a gas turbine engine when it is affected by degradation damage.

Prognosis and Health Monitoring of Nonlinear Systems Using a Hybrid Scheme Through Integration of PFs and Neural Networks

In this paper, a novel hybrid architecture is proposed for developing a prognosis and health monitoring methodology for nonlinear systems through integration of model-based and computationally intelligent-based techniques. In our proposed framework, the well-known particle filters (PFs) method is utilized to estimate the states as well as the health parameters of the system. Simultaneously, the system observations are predicted through an observation forecasting scheme that is developed based on neural networks (NNs) paradigms. The objective is to construct observation profiles that are to be used in future time horizons. Our proposed online training that is utilized for observation forecasting enables the NNs models to track nonergodic changes in the profiles that are present due to presence of hidden damage affecting the system health parameters. The forecasted observations are then utilized in the PFs to predict the evolution of the system states as well as the health parameters (which are considered to be time-varying due to effects of degradation and damage) into future time horizons. Our proposed hybrid architecture enables one to select health signatures for determining the remaining useful life of the system or its components not only based on the system observations but also by taking into account the system health parameters that are not physically measurable. Our proposed hybrid health monitoring methodology is constructed and developed by invoking a special framework where implementation of the observation forecasting scheme is not dependent on the structure of the utilized NNs model. In other words, changing the network structure will not significantly affect the prediction accuracy associated with the entire health prediction scheme. To verify and validate the above results and as a case study, our proposed hybrid approach is applied to predict the health condition of a gas turbine engine when it is affected by and subjected to fouling and erosion degradation and fault damages.

Engine Life Evaluation Based on a Probabilistic Approach

In this paper Fouling and Erosion damages as two main sources of deterioration in the engine performance are modelled for a single spool engine. The effects of these phenomena on the Low Cycle Fatigue (LCF) and Creep status of the engine turbine blades are studied. A Matlab/Simulink model is developed for the LCF and Creep damages evaluation based on the available measured outputs. Several simulations are performed to investigate the effects of different levels of the Fouling and the Erosion degradations on the LCF and Creep damages propagation in the take-off mode of the flight. The probability of failure is calculated in each simulation scenario according to the Weibull distribution. The obtained results can be used as a prognostic tool to predict an appropriate next cycle for the engine maintenance schedule.Copyright

Deterioration Detection and Health Monitoring in Aircraft Jet Engines

In this paper the problem of jet engine deterioration detection and health monitoring is investigated by utilizing two methods. The first method is based on the fusion of the modified CUSUM (CUmulative SUM) method with the differential analysis approach. An enhanced differential analysis method is developed through which the degradation is captured from the unsymmetrical performance analysis of both engines on an aircraft. This is achieved by considering the effects of minor maintenance actions that are not reported. In the second approach, a statistical method based on the Hotelling’s T2-test approach is utilized to detect gradual degradations in the engine performance. The performance of our proposed approaches is evaluated by implementing them on a dual spool engine model that is developed by using the GSP software.Copyright

A Dual Particle Filter-Based Fault Diagnosis Scheme for Nonlinear Systems

In this paper, a dual estimation methodology is developed for both time-varying parameters and states of a nonlinear stochastic system based on the particle filtering scheme. Our developed methodology is based on a concurrent implementation of state and parameter estimation filters as opposed to using a single filter to simultaneously estimate the augmented states and parameters. The convergence and stability properties of our proposed dual estimation strategy are shown formally to be guaranteed under certain conditions. The advantage of our developed dual estimation method is justified by handling simultaneously and efficiently both the state and time-varying parameters of a nonlinear system. This is accomplished in the context of a health monitoring scheme that employs a unified approach to fault detection (FD), isolation, and identification in a single framework. The performance capabilities of our proposed FD methodology is demonstrated and evaluated by its application to a gas turbine engine through providing state and parameter estimation objectives under simultaneous and concurrent component fault scenarios. Extensive simulation results are provided to substantiate and justify the superiority of our proposed FD methodology when compared with another well-known alternative diagnostic technique that is available in the literature.

Prediction of the Jet Engine Performance Deterioration

This paper deals with performance deterioration modelling of a single spool gas turbine engine based on time-series methods. Towards this end, two univariate and multivariate methods, namely the Autoregressive Integrated Moving Average (ARIMA) and the Vector Autoregressive (VAR) schemes are applied to predict the Turbine Entry Temperature (TET) evolution during the flight cycles for maintenance purposes. In the VAR scheme, two engine process parameters i.e. the Turbine Entry Temperature (TET) and the Compressor Temperature are employed to achieve this prediction goal. The results show that employing multivariate modelling methods lead to better prediction horizons. For each method two scenarios are considered to demonstrate the effectiveness of the models.Copyright

An Improved Particle Filtering-based Approach for Health Prediction and Prognosis of Nonlinear Systems

Abstract Health monitoring of nonlinear systems is broadly concerned with the system health tracking and its prediction to future time horizons. Estimation and prediction schemes constitute as principle components of any health monitoring technique. Particle filter (PF) represents a powerful tool for performing state and parameter estimation as well as prediction of nonlinear dynamical systems. Estimation of the system parameters along with the states can yield an up-to-date and reliable model that can be used for long-term prediction problems through utilization of particle filters. This feature enables one to deal with uncertainty issues in the resulting prediction step as the time horizon is extended. Towards this end, this paper presents an improved method to achieve uncertainty management for long-term prediction of nonlinear systems by using particle filters. In our proposed approach, an observation forecasting scheme is developed to extend the system observation profiles (as time-series) to future time horizon. Particles are then propagated to future time instants according to a resampling algorithm instead of considering constant weights for the particles propagation in the prediction step. The uncertainty in the long-term prediction of the system states and parameters are managed by utilizing dynamic linear models for development of an observation forecasting scheme. This task is addressed through an outer adjustment loop for adaptively changing the sliding observation injection window based on the Mahalanobis distance criterion. Our proposed approach is then applied to predicting the health condition as well as the remaining useful life (RUL) of a gas turbine engine that is affected by degradations in the system health parameters. Extensive simulation and case studies are conducted to demonstrate and illustrate the capabilities and performance characteristics of our proposed and developed schemes.

Robust Hybrid EKF approach for state estimation in multi-scale nonlinear singularly perturbed systems

In this paper a general framework is developed for state estimation in a class of nonlinear continuous-time singularly perturbed systems. Our approach is based on the hybrid extended Kalman filter in which observations are originated from discrete measurements. The developed framework is also extended to include linearization error in the observation equation as uncertainty in the estimation filter design. The boundedness of both a priori and a posteriori estimation error covariance matrices is considered as a criterion for the algorithm to have bounded estimation errors. As an approximation method for the estimation covariance matrices in the singularly perturbed system, the matched asymptotic series method is utilized to include the effects of initial conditions by approximating the boundary layer solution in order to attain more accurate filter gain approximation. The developed Hybrid Robust EKF (HREKF) strategy can be used as an estimation method for tracking the effects of hidden damage in a nonlinear system.