Development and Application of Aero-engine Experimental Data Mining Algorithm Library

This paper presents the application of several anomaly detection algorithms in experiment data from engine test bed. Several anomaly detection algorithms are programmed in Python language and integrated into an algorithm library named PyPEFD (Python Package for Engine Fault Detection). The algorithm library includes Gaussian Mixture Model, Feature Weighted Fuzzy Compactness and Separation (WFCS), Sequential Probability Ratio Test (SPRT), Variational Autoencoder, Dynamic Time Warping, Mahalanobis Distance, Singular Value Thresholding, Random Forest and Multivariate State Estimation Technique. These algorithms can analyze the structure and characteristics of the engine test data, and mine the hidden fault information in the data, so as to detect the fault or fault trend of aero-engine test data. This paper also presents a preview of the algorithm library.

[1]  Inés Couso,et al.  Sequential pattern mining applied to aeroengine condition monitoring with uncertain health data , 2015, Eng. Appl. Artif. Intell..

[2]  Jian Peng,et al.  A Health Monitoring Method Based on Multivariate State Estimation Technique , 2013 .

[3]  Dong-Whan Choi,et al.  Defect diagnostics of gas turbine engine using hybrid SVM-ANN with module system in off-design condition , 2009 .

[4]  Pierre Dewallef,et al.  ON-LINE PERFORMANCE MONITORING AND ENGINE DIAGNOSTIC USING ROBUST KALMAN FILTERING TECHNIQUES , 2003 .

[5]  Holger Voos,et al.  Real time degradation identification of UAV using machine learning techniques , 2017, 2017 International Conference on Unmanned Aircraft Systems (ICUAS).

[6]  Zhang Yong Fuzzy c-means algorithm based on adaptive Mahalanobis distances , 2010 .

[7]  M. Pecht,et al.  Mahalanobis Distance and Projection Pursuit Analysis for Health Assessment of Electronic Systems , 2008, 2008 IEEE Aerospace Conference.

[8]  Jingchao Li,et al.  Nonlinear Steady-State Model Based Gas Turbine Health Status Estimation Approach with Improved Particle Swarm Optimization Algorithm , 2015 .

[9]  Lok Man Ho Application of Adaptive Thresholds in Robust Fault Detection of an Electro-Mechanical Single-Wheel Steering Actuator , 2012 .

[10]  Mehmet Karaköse,et al.  Random forest based diagnosis approach for rail fault inspection in railways , 2016, 2016 National Conference on Electrical, Electronics and Biomedical Engineering (ELECO).

[11]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[12]  Visakan Kadirkamanathan,et al.  Gas Turbine Engine Condition Monitoring Using Gaussian Mixture and Hidden Markov Models , 2020, International Journal of Prognostics and Health Management.

[13]  Mohamed Abdelrahman,et al.  A confidence-based approach to the self-validation, fusion and reconstruction of quasi-redundant sensor data , 2001, IEEE Trans. Instrum. Meas..

[14]  Jin Chen,et al.  Fault Detection for Air Conditioning System of Civil Aircraft Based on Multivariate State Estimation Technique , 2017, 2017 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC).

[15]  Roland Wilson Multiresolution Gaussian Mixture Models: Theory and Application , 2000 .

[16]  Weizhong Yan,et al.  Application of Random Forest to Aircraft Engine Fault Diagnosis , 2006, The Proceedings of the Multiconference on "Computational Engineering in Systems Applications".

[17]  Lok Man Ho Application of Adaptive Thresholds in Robust Fault Detection of an Electro-Mechanical Single-Wheel Steering Actuator , 2012 .

[18]  Seokwon Yeom Infrared image segmentation based on region of interest extraction with Gaussian mixture modeling , 2017, Defense + Security.

[19]  Valentina Zaccaria,et al.  Fleet Monitoring and Diagnostics Framework Based on Digital Twin of Aero-Engines , 2018, Volume 6: Ceramics; Controls, Diagnostics, and Instrumentation; Education; Manufacturing Materials and Metallurgy.