Fault detection for turbine engine disk using adaptive Gaussian mixture model

Abstract

Rotating turbine engine disk is one of the most critical components of the aircraft engine. Therefore, fault detection for rotating turbine engine disk is particularly significant. An adaptive Gaussian mixture model is put forward to deal with the dynamic working process of rotating turbine engine disk. Different from the standard expectation–maximization algorithm, the criterion based on minimum within-cluster distance and maximum between-cluster distance is used to update the weight of each Gaussian component. The incoming samples obtained by a forgetting mechanism are adopted to modify the fault detection model by exponentially weighted algorithm, which improves the ability of fault detection model to accommodate the actual situation of turbine engine disk. The comparison results between the multiple principal component analysis, the classical Gaussian mixture model, and the proposed algorithm show that the proposed approach has much superiority on the fault detection of turbine engine disk.

Keywords

Fault detection Gaussian mixture model expectation–maximization incremental forgetting mechanism turbine engine disk

Get full access to this article

View all access options for this article.

References

Abdul-Aziz

Woike

Oza

et al . Propulsion health monitoring of a turbine engine disk using spin test data. In: Proceedings of the SPIE smart structures and materials & nondestructive evaluation and health monitoring, San Diego, CA, 7–11 March 2010. Bellingham, WA: SPIE.

Abdul-Aziz

Woike

Oza

et al . Rotor health monitoring combining spin tests and data-driven anomaly detection methods. Struct Health Monit 2011; 11(1): 3–12.

Pourbabaee

Meskin

Khorasani

Sensor fault detection, isolation, and identification using multiple-model-based hybrid Kalman filter for gas turbine engines. IEEE T Contr Syst T 2015; 24(4): 1184–1200.

Poon

Jain

Konstantakopoulos

et al . Model-based fault detection and identification for switching power converters. IEEE T Power Electr 2017; 32(2): 1419–1430.

Chen

Zhang

Gao

Fault detection for turbine engine disk based on an adaptive kernel principal component analysis algorithm. Proc IMechE, Part I: J Systems and Control Engineering 2016; 230(7): 651–660.

Yin

Chen

et al . An efficient multi-PCA based on-line monitoring scheme for multi-stages imperial smelting process. Int J Control Autom 2013; 11(2): 317–324.

Fault prediction algorithm for multiple mode process based on reconstruction technique. Math Probl Eng 2015; 2015: 348729.1–348729.8.

Zhang

Wang

Tan

et al . Novel monitoring strategy combining the advantages of the multiple modeling strategy and Gaussian mixture model for multimode processes. Ind Eng Chem Res 2015; 54(47): 11866–11880.

Cai

Tian

Chen

Monitoring nonlinear and non-Gaussian processes using Gaussian mixture model-based weighted Kernel independent component analysis. IEEE T Neur Net Lear 2015; 28(1): 122–135.

10.

Jiang

Huang

Yan

XF.

GMM and optimal principal components-based Bayesian method for multimode fault diagnosis. Comput Chem Eng 2016; 84: 338–349.

11.

Qiu

Yuan

Mei

et al . An improved Gaussian mixture model for damage propagation monitoring of an aircraft wing spar under changing structural boundary conditions. Sensors 2016; 16(3): 291.

12.

Yan

Zhou

Pang

CK.

Gaussian mixture model using semisupervised learning for probabilistic fault diagnosis under new data categories. IEEE T Instrum Meas 2017; 66(4): 723–733.

13.

Jiang

Zhao

Jin

Multimode process monitoring based on sparse principal component selection and Bayesian inference-based probability. Math Probl Eng 2015; 2015(1): 465372.1–465372.13.

14.

Xie

Shi

Dynamic multimode process modeling and monitoring using adaptive Gaussian mixture models. Ind Eng Chem Res 2012; 51(15): 5497–5505.

15.

Grbić

Slišković

Kadlec

Adaptive soft sensor for online prediction and process monitoring based on a mixture of Gaussian process models. Comput Chem Eng 2013; 58: 84–97.

16.

Qiu

Yuan

Chang

et al . On-line updating Gaussian mixture model for aircraft wing spar damage evaluation under time-varying boundary condition. Smart Mater Struct 2014; 23(12): 1–14.

17.

Reynolds

Gaussian mixture models. In: Li

Jain

(eds) Encyclopedia of biometrics. New York: Springer Science + Business Media, 2015, pp.827–832.

18.

Hansman

Palacios

et al . Anomaly detection via a Gaussian Mixture Model for flight operation and safety monitoring. Transport Res C: Emer 2016; 64: 45–57.

19.

Zhang

Bingham

Martinez-Garcia

et al . Detection of emerging faults on industrial gas turbines using extended Gaussian mixture models. Int J Rotat Mach 2017; 2017: 5435794.

20.

Vila

Schniter

Expectation-maximization Gaussian-mixture approximate message passing. IEEE T Signal Proces 2013; 61(19): 4658–4672.

21.

Zhang

Gonzalez

Huang

et al . Expectation–maximization approach to fault diagnosis with missing data. IEEE T Ind Electron 2015; 62(2): 1231–1240.

22.

A new fault diagnosis method of multimode processes using Bayesian inference based Gaussian mixture contribution decomposition. Eng Appl Artif Intel 2013; 26(1): 456–466.

23.

Zhou

Deng

Xia

et al . A new sampling method in particle filter based on Pearson correlation coefficient. Neurocomputing 2016; 216: 208–215.