The reliability of gas turbine (GT) health state monitoring and forecasting depends on the quality of sensor measurements directly taken from the unit. Outlier detection techniques have acquired a major importance, as they are capable of removing anomalous measurements and improve data quality. To this purpose, statistical parametric methodologies are widely employed thanks to the limited knowledge of the specific unit required to perform the analysis. The backward and forward moving window (BFMW) k–σ methodology proved its effectiveness in a previous study performed by the authors, to also manage dynamic time series, i.e., during a transient. However, the estimators used by the k–σ methodology are usually characterized by low statistical robustness and resistance. This paper aims at evaluating the benefits of implementing robust statistical estimators for the BFMW framework. Three different approaches are considered in this paper. The first methodology, k-MAD, replaces mean and standard deviation (SD) of the k–σ methodology with median and mean absolute deviation (MAD), respectively. The second methodology, σ-MAD, is a novel hybrid scheme combining the k–σ and the k-MAD methodologies for the backward and the forward windows, respectively. Finally, the biweight methodology implements biweight mean and biweight SD as location and dispersion estimators. First, the parameters of these methodologies are tuned and the respective performance is compared by means of simulated data. Different scenarios are considered to evaluate statistical efficiency, robustness, and resistance. Subsequently, the performance of these methodologies is further investigated by injecting outliers in field datasets taken on selected Siemens GTs. Results prove that all the investigated methodologies are suitable for outlier identification. Advantages and drawbacks of each methodology allow the identification of different scenarios in which their application can be most effective.
Skip Nav Destination
Article navigation
Research-Article
Resistant Statistical Methodologies for Anomaly Detection in Gas Turbine Dynamic Time Series: Development and Field Validation
Giuseppe Fabio Ceschini,
Giuseppe Fabio Ceschini
Siemens AG,
Nürnberg 90461, Germany
Nürnberg 90461, Germany
Search for other works by this author on:
Nicolò Gatta,
Nicolò Gatta
Dipartimento di Ingegneria,
Università degli Studi di Ferrara,
Ferrara 44122, Italy
Università degli Studi di Ferrara,
Ferrara 44122, Italy
Search for other works by this author on:
Mauro Venturini,
Mauro Venturini
Dipartimento di Ingegneria,
Università degli Studi di Ferrara,
Ferrara 44122, Italy
Università degli Studi di Ferrara,
Ferrara 44122, Italy
Search for other works by this author on:
Thomas Hubauer,
Thomas Hubauer
Siemens AG,
Nürnberg 90461, Germany
Nürnberg 90461, Germany
Search for other works by this author on:
Alin Murarasu
Alin Murarasu
Siemens AG,
Nürnberg 90461, Germany
Nürnberg 90461, Germany
Search for other works by this author on:
Giuseppe Fabio Ceschini
Siemens AG,
Nürnberg 90461, Germany
Nürnberg 90461, Germany
Nicolò Gatta
Dipartimento di Ingegneria,
Università degli Studi di Ferrara,
Ferrara 44122, Italy
Università degli Studi di Ferrara,
Ferrara 44122, Italy
Mauro Venturini
Dipartimento di Ingegneria,
Università degli Studi di Ferrara,
Ferrara 44122, Italy
Università degli Studi di Ferrara,
Ferrara 44122, Italy
Thomas Hubauer
Siemens AG,
Nürnberg 90461, Germany
Nürnberg 90461, Germany
Alin Murarasu
Siemens AG,
Nürnberg 90461, Germany
Nürnberg 90461, 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 August 10, 2017; published online November 21, 2017. Editor: David Wisler.
J. Eng. Gas Turbines Power. May 2018, 140(5): 052401 (11 pages)
Published Online: November 21, 2017
Article history
Received:
July 14, 2017
Revised:
August 10, 2017
Citation
Fabio Ceschini, G., Gatta, N., Venturini, M., Hubauer, T., and Murarasu, A. (November 21, 2017). "Resistant Statistical Methodologies for Anomaly Detection in Gas Turbine Dynamic Time Series: Development and Field Validation." ASME. J. Eng. Gas Turbines Power. May 2018; 140(5): 052401. https://doi.org/10.1115/1.4038155
Download citation file:
Get Email Alerts
Cited By
Experimental Identification Of Blade Tip Rub Forces At Engine Relevant Temperatures And Speeds
J. Eng. Gas Turbines Power
Study Of Tandem Rotor Dual Wake Interaction With Downstream Stator Under Unsteady Numerical Approach
J. Eng. Gas Turbines Power
Experimental Design Validation of a Swirl-Stabilized Burner With Fluidically Variable Swirl Number
J. Eng. Gas Turbines Power (April 2025)
Experimental Characterization of a Bladeless Air Compressor
J. Eng. Gas Turbines Power (April 2025)
Related Articles
Optimization of Statistical Methodologies for Anomaly Detection in Gas Turbine Dynamic Time Series
J. Eng. Gas Turbines Power (March,2018)
A Comprehensive Approach for Detection, Classification, and Integrated Diagnostics of Gas Turbine Sensors
J. Eng. Gas Turbines Power (March,2018)
Symbolic Time-Series Analysis of Gas Turbine Gas Path Electrostatic Monitoring Data
J. Eng. Gas Turbines Power (October,2017)
Data-Driven Fault Detection in Aircraft Engines With Noisy Sensor Measurements
J. Eng. Gas Turbines Power (August,2011)
Related Proceedings Papers
Related Chapters
Reliability of Electronic Packaging
Essentials of Electronic Packaging: A Multidisciplinary Approach
Artificial Indents as the Root Cause of Rolling Contact Fatigue Damage: Effect of Plastic Properties
Bearing and Transmission Steels Technology
Logarithm Transformation of the Output Response Data for Optimization
Taguchi Methods: Benefits, Impacts, Mathematics, Statistics and Applications