Gas Turbine Engine Condition Monitoring Using Gaussian Mixture and Hidden Markov Models

This paper investigates the problem of condition monitoring of complex dynamic systems, specifically the detection, localisation and quantification of transient faults. A data driven approach is developed for fault detection where the multidimensional data sequence is viewed as a stochastic process whose behaviour can be described by a hidden Markov model with two hidden states --- i.e. `healthy / nominal' and `unhealthy / faulty'. The fault detection is performed by first clustering in a multidimensional data space to define normal operating behaviour using a Gaussian-Uniform mixture model. The health status of the system at each data point is then determined by evaluating the posterior probabilities of the hidden states of a hidden Markov model. This allows the temporal relationship between sequential data points to be incorporated into the fault detection scheme. The proposed scheme is robust to noise and requires minimal tuning. A real-world case study is performed based on the detection of transient faults in the variable stator vane actuator of a gas turbine engine to demonstrate the successful application of the scheme. The results are used to demonstrate the generation of simple and easily interpretable analytics that can be used to monitor the evolution of the fault across time.

[1]  Sergei Vassilvitskii,et al.  k-means++: the advantages of careful seeding , 2007, SODA '07.

[2]  Rolf Isermann,et al.  Fault-Diagnosis Applications , 2011 .

[3]  Jie Chen,et al.  Robust Model-Based Fault Diagnosis for Dynamic Systems , 1998, The International Series on Asian Studies in Computer and Information Science.

[4]  Padhraic J. Smyth,et al.  Hidden Markov models for fault detection in dynamic systems , 1993 .

[5]  Witold Pedrycz,et al.  Multivariate time series anomaly detection: A framework of Hidden Markov Models , 2017, Appl. Soft Comput..

[6]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.

[7]  Vic Barnett,et al.  Outliers in Statistical Data , 1980 .

[8]  N. Nasios,et al.  Variational learning for Gaussian mixture models , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[9]  Weizhong Yan,et al.  On Accurate and Reliable Anomaly Detection for Gas Turbine Combustors: A Deep Learning Approach , 2019, ArXiv.

[10]  Pascal Vincent,et al.  Manifold Parzen Windows , 2002, NIPS.

[11]  Michael I. Jordan,et al.  On Convergence Properties of the EM Algorithm for Gaussian Mixtures , 1996, Neural Computation.

[12]  Geoffrey J. McLachlan,et al.  Robust mixture modelling using the t distribution , 2000, Stat. Comput..

[13]  Van Nostrand,et al.  Error Bounds for Convolutional Codes and an Asymptotically Optimum Decoding Algorithm , 1967 .

[14]  Johannes Blömer,et al.  Adaptive Seeding for Gaussian Mixture Models , 2013, PAKDD.

[15]  Furong Gao,et al.  Review of Recent Research on Data-Based Process Monitoring , 2013 .

[16]  Geoffrey J. McLachlan,et al.  Finite Mixture Models , 2019, Annual Review of Statistics and Its Application.

[17]  Seungjin Choi,et al.  Echo-state conditional variational autoencoder for anomaly detection , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[18]  Pierre Baldi,et al.  Bioinformatics - the machine learning approach (2. ed.) , 2000 .

[19]  B. Ripley,et al.  Robust Statistics , 2018, Wiley Series in Probability and Statistics.

[20]  P. McKenzie,et al.  Selecting the optimal number of components for a Gaussian mixture model , 1994, Proceedings of 1994 IEEE International Symposium on Information Theory.

[21]  Visakan Kadirkamanathan,et al.  Particle filtering based likelihood ratio approach to fault diagnosis in nonlinear stochastic systems , 2001, IEEE Trans. Syst. Man Cybern. Part C.

[22]  Marius Kloft,et al.  Hidden Markov Anomaly Detection , 2015, ICML.

[23]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[24]  David A. Clifton,et al.  A review of novelty detection , 2014, Signal Process..

[25]  Fu Xiao,et al.  Analytical investigation of autoencoder-based methods for unsupervised anomaly detection in building energy data , 2018 .

[26]  S. N. Panigrahi,et al.  Motor bike piston-bore fault identification from engine noise signature analysis , 2014 .

[27]  Daeyoung Kim,et al.  Assessment of the number of components in Gaussian mixture models in the presence of multiple local maximizers , 2014, J. Multivar. Anal..

[28]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[29]  Shinichi Nakajima,et al.  Support Vector Data Descriptions and $k$ -Means Clustering: One Class? , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[30]  Ying Peng,et al.  A novel method for online health prognosis of equipment based on hidden semi-Markov model using sequential Monte Carlo methods , 2012 .

[31]  R. Redner,et al.  Mixture densities, maximum likelihood, and the EM algorithm , 1984 .

[32]  Wenjing Jin,et al.  Enhanced Restricted Boltzmann Machine With Prognosability Regularization for Prognostics and Health Assessment , 2016, IEEE Transactions on Industrial Electronics.

[33]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.