Nonlinear Fault Diagnosis of Jet Engines by Using a Multiple Model-Based Approach

Naderi, E.; Meskin, Nader; Khorasani, K.

doi:10.1115/1.4004152

Cited by 62 publications

(42 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data used in this work are generated by using the MATLAB/Simulink model based on the equations described in the previous section as well as those in [7]. The engine model is operating in its takeoff mode when the fuel usage is in its maximum value and maximum thrust is provided.…”

Section: Engine Data Generationmentioning

confidence: 99%

“…Based on the work of Naderi et al [7] on modelling of an aircraft gas turbine engine, a MATLAB/Simulink model for a single spool gas turbine engine is developed. The simulation model was constructed by using mechanical, aerodynamic and thermodynamic relationships between the components of the system.…”

Section: Gas Turbine Engine Mathematical Modelmentioning

confidence: 99%

“…3. The set of nonlinear equations corresponding to a single spool gas turbine engine is also obtained in [7] as follows:…”

Section: Gas Turbine Engine Mathematical Modelmentioning

confidence: 99%

“…The interest in application and use of neural networks in health monitoring and prognosis is mainly due to their capability in modelling nonlinearities of dynamical systems. The aircraft gas turbine engine is a highly nonlinear dynamical system [1,2,[4][5][6][7][8][9], and therefore, in order to model time delays and memory associated with the dynamics of the system, a dynamic neural network should be required for learning its dynamics.…”

Section: Introductionmentioning

confidence: 99%

“…-(7). The percentage of changes in the turbine temperature, rotor speed and fuel flow rate under the presence of different compressor fouling indices in our model and the GSP software are compared together, where it follows that the changes in the measurements follow the same pattern for the model and the GSP software.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Dynamic neural networks for gas turbine engine degradation prediction, health monitoring and prognosis

Kiakojoori

Khorasani

2015

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

In this paper, the problem of health monitoring and prognosis of aircraft gas turbine engines is considered by using computationally intelligent methodologies. Two different dynamic neural networks, namely the nonlinear autoregressive with exogenous input neural networks and the Elman neural networks, are developed and designed for this purpose. The proposed dynamic neural networks are designed to capture the dynamics of two main degradations in the gas turbine engine, namely the compressor fouling and the turbine erosion. The health status and condition of the engine in terms of the turbine output temperature (TT) are then predicted subject to occurrence of these deteriorations. Various scenarios consisting of fouling and erosion separately as well as combined are considered. For each scenario, several neural networks are trained and their performance in predicting multiple flights ahead TTs is evaluated. Finally, the most suitable neural networks for achieving the best prediction are selected by using the normalized Bayesian information criterion model selection. Simulation results presented demonstrate and illustrate the effective performance of our proposed neural networkbased prediction and prognosis strategies.

show abstract

Section: Engine Data Generationmentioning

confidence: 99%

Section: Gas Turbine Engine Mathematical Modelmentioning

confidence: 99%

“…3. The set of nonlinear equations corresponding to a single spool gas turbine engine is also obtained in [7] as follows:…”

Section: Gas Turbine Engine Mathematical Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Dynamic neural networks for gas turbine engine degradation prediction, health monitoring and prognosis

Kiakojoori

Khorasani

2015

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

show abstract

A Model‐Based Approach for Gas Turbine Engine Performance Optimal Estimation

Lü¹,

Lv²,

Huang³

et al. 2013

Asian Journal of Control

View full text Add to dashboard Cite

Kalman filters (KF) are widely used in model‐based fault diagnosis designs for aircraft engine health management purposes. Nevertheless, health parameter estimation based on KF in the self‐tuning on‐board real‐time model (STORM) cannot always achieve sufficient health monitoring due to the interrelation of different types of sensors and the number of sensors usually being less than the number of health parameters on the aircraft engine. In order to mitigate this problem, one must accomplish two things: the sensor measurements for fault diagnosis should be analyzed and determined and a health parameter vector in STORM of lower dimension should be acquired. In this paper, a measurement vector for STORM is selected by the concept of sensor condition number and the sensor similarity is used for validation. A transformation matrix for the health parameter vector is introduced, and quantum particle swarm optimization (QPSO) is employed to produce a health parameter subset with appropriate dimensions to enable KF based estimation. Simulations on this method are carried out on a turbofan engine, and the results show that the proposed method for health parameters estimation is efficient.

show abstract