0
Research Papers: Gas Turbines: Oil and Gas Applications

Optimization of Statistical Methodologies for Anomaly Detection in Gas Turbine Dynamic Time Series

[+] Author and Article Information
Giuseppe Fabio Ceschini, Thomas Hubauer

Siemens AG,
Nürnberg 90461, Germany

Nicolò Gatta, Mauro Venturini

Dipartimento di Ingegneria,
Università degli Studi di Ferrara,
Ferrara 44122, Italy

Alin Murarasu

Siemens AG,
Nürnberg 44122, Germany

Contributed by the Oil and Gas Applications Committee of ASME for publication in the JOURNAL OF ENGINEERING FOR GAS TURBINES AND POWER. Manuscript received July 14, 2017; final manuscript received July 30, 2017; published online October 25, 2017. Editor: David Wisler.

J. Eng. Gas Turbines Power 140(3), 032401 (Oct 25, 2017) (10 pages) Paper No: GTP-17-1359; doi: 10.1115/1.4037963 History: Received July 14, 2017; Revised July 30, 2017

Statistical parametric methodologies are widely employed in the analysis of time series of gas turbine (GT) sensor readings. These methodologies identify outliers as a consequence of excessive deviation from a statistical-based model, derived from available observations. Among parametric techniques, the k–σ methodology demonstrates its effectiveness in the analysis of stationary time series. Furthermore, the simplicity and the clarity of this approach justify its direct application to industry. On the other hand, the k–σ methodology usually proves to be unable to adapt to dynamic time series since it identifies observations in a transient as outliers. As this limitation is caused by the nature of the methodology itself, two improved approaches are considered in this paper in addition to the standard k–σ methodology. The two proposed methodologies maintain the same rejection rule of the standard k–σ methodology, but differ in the portions of the time series from which statistical parameters (mean and standard deviation) are inferred. The first approach performs statistical inference by considering all observations prior to the current one, which are assumed reliable, plus a forward window containing a specified number of future observations. The second approach proposed in this paper is based on a moving window scheme. Simulated data are used to tune the parameters of the proposed improved methodologies and to prove their effectiveness in adapting to dynamic time series. The moving window approach is found to be the best on simulated data in terms of true positive rate (TPR), false negative rate (FNR), and false positive rate (FPR). Therefore, the performance of the moving window approach is further assessed toward both different simulated scenarios and field data taken on a GT.

Copyright © 2018 by ASME
Your Session has timed out. Please sign back in to continue.

References

Scheianu, D. , 2014, “ Methods and Results in Remote Monitoring and Diagnosing a Fleet of Industrial Gas Turbines,” ASME Paper No. GT2014-26068.
Jiang, X. , and Foster, C. , 2014, “ Plant Performance Monitoring and Diagnostics–Remote, Real-Time and Automation,” ASME Paper No. GT2014-27314.
Tsoutsanis, E. , Meskin, N. , Benammar, M. , and Khashayar, K. , 2015, “ Transient Gas Turbine Performance Diagnostics Through Nonlinear Adaptation of Compressor and Turbine Maps,” ASME J. Eng. Gas Turbines Power, 137(9), p. 091201. [CrossRef]
Cavarzere, A. , and Venturini, M. , 2011, “ Application of Forecasting Methodologies to Predict Gas Turbine Behavior Over Time,” ASME J. Eng. Gas Turbines Power, 134(1), p. 012401. [CrossRef]
Bettocchi, R. , Pinelli, M. , Spina, P. R. , Venturini, M. , and Sebastianelli, S. , 2001, “ A System for Health State Determination of Natural Gas Compression Gas Turbines,” ASME Paper No. 2001-GT-223.
Pinelli, M. , Spina, P. R. , and Venturini, M. , 2012, “ Gas Turbine Health State Determination: Methodology Approach and Field Application,” Int. J. Rotating Mach., 2012, p. 142173. [CrossRef]
Bettocchi, R. , Pinelli, M. , Spina, P. R. , and Venturini, M. , 2007, “ Artificial Intelligence for the Diagnostics of Gas Turbines—Part I: Neural Network Approach,” ASME J. Eng. Gas Turbines Power, 129(3), pp. 711–719. [CrossRef]
Bettocchi, R. , Pinelli, M. , Spina, P. R. , and Venturini, M. , 2007, “ Artificial Intelligence for the Diagnostics of Gas Turbines—Part II: Neuro-Fuzzy Approach,” ASME J. Eng. Gas Turbines Power, 129(3), pp. 720–729. [CrossRef]
Courdier, A. , and Li, Y. G. , 2016, “ Power Setting Sensor Fault Detection and Accommodation for Gas Turbine Engines Using Artificial Neural Networks,” ASME Paper No. GT2016-56304.
Sarkar, S. , Jin, X. , and Ray, A. , 2011, “ Data-Driven Fault Detection in Aircraft Engines With Noisy Sensor Measurements,” J. Eng. Gas Turbines Power, 133(8), p. 081602. [CrossRef]
Simon, D. , and Litt, J. , 2011, “ A Data Filter for Identifying Steady-State Operating Points in Engine Flight Data for Condition Monitoring Applications,” ASME J. Eng. Gas Turbines Power, 133(7), p. 071603. [CrossRef]
Roumeliotis, I. , Aretakis, N. , and Alexiou, A. , 2016, “ Industrial Gas Turbine Health and Performance Assessment With Field Data,” ASME Paper No. GT2016-57722.
Simon, D. L. , and Rinehart, A. W. , 2016, “ Sensor Selection for Aircraft Engine Performance Estimation and Gas Path Fault Diagnostics,” ASME J. Eng. Gas Turbines Power, 138(7), p. 071201. [CrossRef]
Venturini, M. , and Puggina, N. , 2012, “ Prediction Reliability of a Statistical Methodology for Gas Turbine Prognostics,” ASME J. Eng. Gas Turbines Power, 134(10), p. 101601. [CrossRef]
Venturini, M. , and Therkorn, D. , 2013, “ Application of a Statistical Methodology for Gas Turbine Degradation Prognostics to Alstom Field Data,” ASME J. Eng. Gas Turbines Power, 135(9), p. 091603. [CrossRef]
Hanachi, H. , Liu, J. , Banerjee, A. , and Chen, Y. , 2016, “ Prediction of Compressor Fouling Rate Under Time Varying Operating Conditions,” ASME Paper No. GT2016-56242.
Dewallef, P. , and Borguet, S. , 2013, “ A Methodology to Improve the Robustness of Gas Turbine Engine Performance Monitoring Against Sensor Faults,” J. Eng. Gas Turbines Power, 135(5), p. 051601. [CrossRef]
van Paridon, A. , Bacic, M. , and Ireland, P. T. , 2016, “ Kalman Filter Development for Real Time Proper Orthogonal Decomposition Disc Temperature Model,” ASME Paper No. GT2016-56330.
Hurst, A. M. , Carter, S. , Firth, D. , Szary, A. , and van De Weert, J. , 2015, “ Real-Time, Advanced Electrical Filtering for Pressure Transducer Frequency Response Correction,” ASME Paper No. GT2015-42895.
Gutierrez, L. A. , Pezzini, P. , Tucker, D. , and Banta, L. , 2014, “ Smoothing Techniques for Real-Time Turbine Speed Sensors,” ASME Paper No. GT2014-25407.
Ben-Gal, I. , 2005, “ Outlier Detection,” Data Mining and Knowledge Discovery Handbook, O. Maimon and L. Rokach , eds., Springer, New York.
Wang, J. , and Xiong, S. , 2014, “ A Hybrid Forecasting Model Based on Outlier Detection and Fuzzy Time Series – A Case Study on Hainan Wind Farm of China,” Energy, 76, pp. 526–541. [CrossRef]
Xu, S. , Baldea, M. , Edgar, T. , Wojsznis, W. , Blevins, T. , and Nixon, M. , 2015, “ An Improved Methodology for Outlier Detection in Dynamic Datasets,” AIChE J., 61(2), pp. 419–433. [CrossRef]
Pinelli, M. , Venturini, M. , and Burgio, M. , 2003, “ Statistical Methodologies for Reliability Assessment of Gas Turbine Measurements,” ASME Paper No. GT2003-38407.
Hampel, F. , 1974, “ The Influence Curve and its Role in Robust Estimation,” J. Am. Stat. Assoc., 69(346), pp. 383–393. [CrossRef]
Gomez, J. , 2011, Kalman Filtering, Nova Science Publishers, Hauppauge, NY. [PubMed] [PubMed]
Martin, R. , and Thomson, D. , 1982, “ Robust-Resistant Spectrum Estimation,” Proc. IEEE, 70(9), pp. 1097–1115. [CrossRef]
Liu, H. , Shah, S. , and Jiang, W. , 2004, “ On-Line Outlier Detection and Data Cleaning,” Comput. Chem. Eng., 28(9), pp. 1635–1647. [CrossRef]
Ganguli, R. , 2002, “ Noise and Outlier Removal From Jet Engine Health Signals Using Weighted FIR Median Hybrid Filters,” Mech. Syst. Signal Process., 16(6), pp. 967–978. [CrossRef]
Takeuchi, J. , and Yamanishi, K. , 2006, “ A Unifying Framework for Detecting Outliers and Change Points From Time Series,” IEEE Trans. Knowl. Data Eng., 18(4), pp. 482–492. [CrossRef]
Takahashi, T. , Tomioka, R. , and Yamanishi, K. , 2014, “ Discovering Emerging Topics in Social Streams via Link-Anomaly Detection,” IEEE Trans. Knowl. Data Eng., 26(1), pp. 120–130. [CrossRef]
Bhattacharya, G. , Ghosh, K. , and Chowdhury, A. , 2015, “ Outlier Detection Using Neighborhood Rank Difference,” Pattern Recognit. Lett., 60–61, pp. 24–31. [CrossRef]
Everitt, B. , and Howell, D. , 2005, Encyclopedia of Statistics in Behavioral Science, Wiley, Chichester, UK. [CrossRef] [PubMed] [PubMed]
Miller, J. , 1991, “ Short Report: Reaction Time Analysis With Outlier Exclusion: Bias Varies With Sample Size,” Q. J. Exp. Psychol. Sect. A, 43(4), pp. 907–912. [CrossRef]
Ceschini, G. , Gatta, N. , Venturini, M. , Hubauer, T. , and Murarasu, A. , 2017, “ Resistant Statistical Methodologies for Anomaly Detection in Gas Turbine Dynamic Time Series: Development and Field Validation,” ASME Paper No. GT2017-63410.
Ceschini, G. F. , Gatta, N. , Venturini, M. , Hubauer, T. , and Murarasu, A. , 2017, “ A Comprehensive Approach for Detection, Classification and Integrated Diagnostics of Gas Turbine Sensors (DCIDS),” ASME Paper No. GT2017-63411.
Young, G. A. , and Smith, R. L. , 2005, Essential of Statistical Inference, Cambridge University Press, Cambridge, UK. [CrossRef]
Sharma, A. B. , Golubchik, L. , and Govindan, R. , 2010, “ Sensor Faults: Detection Methods and Prevalence in Real-World Datasets,” ACM Trans. Sens. Networks, 6(3), p. 23.

Figures

Grahic Jump Location
Fig. 1

Field dataset of nondimensional vibration V1

Grahic Jump Location
Fig. 2

FMW (above) and BFMW (below) methodology applied to the field dataset of nondimensional vibration V1

Grahic Jump Location
Fig. 3

FMW (above) and BFMW (below) applied to the field dataset of nondimensional temperature T1

Grahic Jump Location
Fig. 4

Simulated data with noise 1%, 10% step, 7% outlier magnitude

Grahic Jump Location
Fig. 5

Performance comparison between best and worst tunings of the FMW scheme for different outlier magnitudes

Grahic Jump Location
Fig. 6

Performance comparison between best and worst tunings of the BFMW scheme for different outlier magnitudes

Grahic Jump Location
Fig. 7

Performance comparison between FMW and BFMW methodologies with best performing tuning

Grahic Jump Location
Fig. 8

Influence of backward window size for different outlier magnitudes

Grahic Jump Location
Fig. 9

TPR performance of BFMW methodology as a function of kb and kf values (outlier magnitude at 3% and 7%)

Grahic Jump Location
Fig. 10

FNR performance of BFMW methodology as a function of kb and kf values (outlier magnitude at 3% and 7%)

Grahic Jump Location
Fig. 11

BFMW methodology performance for different outlier magnitudes at 2% noise

Grahic Jump Location
Fig. 12

BFMW methodology TPR (above) and FNR (below) for different outlier magnitudes and different step changes

Grahic Jump Location
Fig. 13

Example of the masking effect for BFMW methodology

Grahic Jump Location
Fig. 14

BFMW methodology performance versus outlier magnitude, with outliers in TSB only (solid line) or SSC only (dashed line)

Grahic Jump Location
Fig. 15

BFMW methodology performance versus step change, with outliers in TSB only (solid line) or SSC only (dashed line)

Grahic Jump Location
Fig. 16

Overview of BFMW methodology TPR and FNR performance for different simulated scenarios

Grahic Jump Location
Fig. 17

Field dataset of nondimensional temperature T2 with injected outliers of 7% magnitude

Grahic Jump Location
Fig. 18

TPR and FNR values as a function of outlier magnitude for the field dataset of nondimensional temperature T2

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In