With the condition monitoring system on airplanes, failures can be predicted before they occur. Performance deterioration of aircraft engines is monitored by parameters such as fuel flow, exhaust gas temperature, engine fan speeds, vibration, oil pressure and oil temperature. The vibration parameter allows us to easily detect any existing or possible faults. The purpose of this paper is to develop a new model to estimate the low pressure turbine (LPT) vibration parameter of an aircraft engine by using the data of an aircraft’s actual flight from flight data recorder (FDR).

    Design/methodology/approach

    First, statistical regression analysis is used to determine the parameters related to LPT. Then, the selected parameters were applied as an input to the developed Levenberg–Marquardt feedforward neural network and the output LPT vibration parameter was estimated with a small error. Analyses were performed on MATLAB and SPSS Statistics 22 package program. Finally, the confidence interval method is used to check the accuracy of the estimated results of artificial neural networks (ANNs).

    Findings

    This study shows that the health conditions of an aircraft engine can be evaluated in terms of this paper by using confidence interval prediction of ANN-estimated LPT vibration parameters without dismantling and expert knowledge.

    Practical implications

    With this study, it has been shown that faults that may occur during flight can be easily detected using the data of a flight without expert evaluation.

    Originality/value

    The health condition of the turbofan engine was evaluated using the confidence interval prediction of ANN-estimated LPT vibration parameters.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Confidence interval prediction of ANN estimated LPT parameters


    Contributors:

    Published in:

    Publication date :

    2019-10-01


    Size :

    1 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Improving Accuracy and Confidence Interval of Camera Parameters Estimated with a Planar Pattern

    Ricolfe-Viala, C. / Sanchez-Salmeron, A.-J. | British Library Conference Proceedings | 2005



    CONFIDENCE-ESTIMATED DOMAIN ADAPTATION

    ROSMAN GUY | European Patent Office | 2021

    Free access

    CONFIDENCE LEVEL DETERMINATION FOR ESTIMATED ROAD GEOMETRIES

    CARLSSON NIKLAS / SORSTEDT JOAKIM | European Patent Office | 2015

    Free access

    Confidence level determination for estimated road geometries

    CARLSSON NIKLAS / LIN-SÖRSTEDT JOAKIM | European Patent Office | 2015

    Free access