Document Type : Research Paper


1 Department of Industrial Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran.

2 Department of Industrial Engineering, Iran University of Science and Technology, Tehran, Iran.


One of the most complex and costly systems in the industry is the Gas turbine (GT). Because of the complexity of these assets, various indicators have been used to monitor the health condition of different parts of the gas turbine. Turbine exit temperature (TET) spread is one of the significant indicators that help monitor and detect faults such as overall engine deterioration and burner fault. The goal of this article is to use data-driven approaches to monitor TET data to detect faults early, as fault detection can have a significant impact on gas turbine reliability and availability. In this study, the TET data of v94.2 GT is measured by six temperature transmitters to show a detailed profile. According to the statistical tests, TET data are high dimensional and time-dependent in the real world industry. Hence, three distinctive methods in the field of the gas turbine are proposed in this study for early fault detection. Conventional principal component analysis (PCA), moving window PCA (MWPCA), and incremental PCA (IPCA) were implemented on TET data. According to the results, the conventional PCA model is a non-adaptive method, and the false alarm rate is high due to the incompatibility of this approach and the process. The MWPCA based on V-step-ahead and IPCA approaches overcame the non-stationary problem and reduced the false alarm rate. In fact, these approaches can distinguish between the normal time-varying and slow ramp fault processes. The results showed that IPCA could detect fault situations faster than MWPCA based on V-step-ahead in this study.


Main Subjects

  • Sunadi, S., Purba, H. H., & Saroso, D. S. (2020). Statistical process control (SPC) method to improve the capability process of drop impact resistance: a case study at aluminum cans manufacturing industry in Indonesia. Journal of applied research on industrial engineering7(1), 92-108.
  • Molaei, S., & Cyrus, K. M. (2014). Robust design of maintenance scheduling considering engineering insurance using genetic algorithm. International journal of research in industrial engineering3(1), 39-48.
  • Liu, J., Liu, J., Yu, D., Kang, M., Yan, W., Wang, Z., & Pecht, M. G. (2018). Fault detection for GT hot components based on a convolutional neural network. Energies11(8), 2149.
  • Meher-Homji, C. B., & Bhargava, R. (1992). Condition monitoring and diagnostic aspects of gas turbine transient response. In turbo expo: power for land, sea, and air(78965, V004T11A006). American Society of Mechanical Engineers.
  • Zhang, Y., & Jiang, J. (2008). Bibliographical review on reconfigurable fault-tolerant control systems. Annual reviews in control32(2), 229-252.
  • Chiang, L. H., Russell, E. L., & Braatz, R. D. (2000). Fault detection and diagnosis in industrial systems. Springer Science & Business Media.
  • Chiang, L. H., Russell, E. L., & Braatz, R. D. (2012). Fault detection and diagnosis in industrial systems. Springer London.
  • Fan, C. M., & Lu, Y. P. (2008). A bayesian framework to integrate knowledge-based and data-driven inference tools for reliable yield diagnoses. 2008 winter simulation conference(pp. 2323-2329). IEEE.
  • Alzghoul, A., Backe, B., Löfstrand, M., Byström, A., & Liljedahl, B. (2014). Comparing a knowledge-based and a data-driven method in querying data streams for system fault detection: a hydraulic drive system application. Computers in industry65(8), 1126-1135.
  • Yin, S. (2012). Data-driven design of fault diagnosis systems(Doctoral dissertation, Duisburg, Essen, Universität Duisburg-Essen).
  • Meslameni, W., & Kamoun, T. (2021). Detection of an imbalance fault by vibration monitoring: case of a screw compressor. Journal of applied research on industrial engineering8(1), 27-39.
  • Sankavaram, C., Pattipati, B., Kodali, A., Pattipati, K., Azam, M., Kumar, S., & Pecht, M. (2009). Model-based and data-driven prognosis of automotive and electronic systems. 2009 IEEE international conference on automation science and engineering(pp. 96-101). IEEE.
  • Gol-Ahmadi, N., & Raissi, S. (2018). Residual lifetime prediction for multi-state system using control charts to monitor affecting noise factor on deterioration process. Journal of applied research on industrial engineering5(1), 27-38.
  • Losi, E., Venturini, M., Manservigi, L., Ceschini, G. F., & Bechini, G. (2019). Anomaly detection in gas turbine time series by means of bayesian hierarchical models. Journal of engineering for gas turbines and power141(11).
  • Dundas, R. E., Sullivan, D. A., & Abegg, F. (1992). Performance monitoring of gas turbines for failure prevention. In turbo expo: power for land, sea, and air(78965, V004T10A013). American Society of Mechanical Engineers.
  • Jinfu, L., Jiao, L., Jie, W., Zhongqi, W., & Daren, Y. (2017). Early fault detection of hot components in gas turbines. Journal of engineering for gas turbines and power139(2).
  • Knowles, M. (1994). Gas turbine Temperature spread monitoring detection of combustion system deterioration. In turbo expo: power for land, sea, and air (78873, V005T17A002). American Society of Mechanical Engineers.
  • Korczewski, Z. (2011). Exhaust gas temperature measurements in diagnostic examination of naval gas turbine engines. Polish maritime research, 18(4), 49-53.
  • Medina, P., Saez, D., & Roman, R. (2008). On line fault detection and isolation in gas turbine combustion chambers. In turbo expo: power for land, sea, and air(43123, pp. 315-324).
  • Palmé, T., Liard, F., & Therkorn, D. (2013). Similarity based modeling for turbine exit temperature spread monitoring on gas turbines. In turbo expo: Power for land, sea, and air(55188, p. V004T06A020). American Society of Mechanical Engineers.
  • Tsalavoutas, A., Mathioudakis, K., & Smith, M. K. (1996). Processing of circumferential temperature distributions for the detection of gas turbine burner malfunctions. In turbo expo: power for land, sea, and air(78767, V005T15A010). American Society of Mechanical Engineers.
  • Kenyon, A. D., Catterson, V. M., & McArthur, S. D. J. (2010). Development of an intelligent system for detection of exhaust gas temperature anomalies in gas turbines. Insight-non-destructive testing and condition monitoring52(8), 419-423.
  • Navi, M., Davoodi, M. R., & Meskin, N. (2015). Sensor fault detection and isolation of an industrial gas turbine using partial kernel PCA. IFAC-papers online48(21), 1389-1396.
  • Li, W., Peng, M., Liu, Y., Cheng, S., Jiang, N., & Wang, H. (2018). Condition monitoring of sensors in a NPP using optimized PCA. Science and technology of nuclear installations2018, 1-16.
  • Navi, M., Meskin, N., & Davoodi, M. (2018). Sensor fault detection and isolation of an industrial gas turbine using partial adaptive KPCA. Journal of process control64, 37-48.
  • Jolliffe, I. T. (2002). Principal component analysis for special types of data(pp. 338-372). Springer New York.
  • Halligan, G. R., & Jagannathan, S. (2011). PCA-based fault isolation and prognosis with application to pump. The international journal of advanced manufacturing technology55, 699-707.
  • Jackson, J. E. (2005). A user's guide to principal components. John Wiley & Sons.
  • Valle, S., Li, W., & Qin, S. J. (1999). Selection of the number of principal components: the variance of the reconstruction error criterion with a comparison to other methods. Industrial & engineering chemistry research38(11), 4389-4401.
  • Jaffel, I., Taouali, O., Harkat, M. F., & Messaoud, H. (2015). Online process monitoring using a new PCMD index. The international journal of advanced manufacturing technology80(5-8)), 947-957.
  • Said, M., Fazai, R., Abdellafou, K. B., & Taouali, O. (2018). Decentralized fault detection and isolation using bond graph and PCA methods. The international journal of advanced manufacturing technology99(1-4), 517-529.
  • Li, W., Peng, M., & Wang, Q. (2018). False alarm reducing in PCA method for sensor fault detection in a nuclear power plant. Annals of nuclear energy118, 131-139.
  • Rato, T., Reis, M., Schmitt, E., Hubert, M., & De Ketelaere, B. (2016). A systematic comparison of PCA‐based statistical process monitoring methods for high‐dimensional, time‐dependent processes. AIChE journal62(5), 1478-1493.
  • Gao, Y., Wang, X., Wang, Z., & Zhao, L. (2016). Fault detection in time-varying chemical process through incremental principal component analysis. Chemometrics and intelligent laboratory systems158, 102-116.
  • De Ketelaere, B., Hubert, M., & Schmitt, E. (2015). Overview of PCA-based statistical process-monitoring methods for time-dependent, high-dimensional data. Journal of quality technology47(4), 318-335.
  • Kruger, U., & Xie, L. (2012). Statistical monitoring of complex multivatiate processes: with applications in industrial process control. John Wiley & Sons.
  • De Ketelaere, B., Rato, T., Schmitt, E., & Hubert, M. (2016). Statistical process monitoring of time-dependent data. Quality engineering28(1), 127-142.
  • Wang, X., Kruger, U., & Irwin, G. W. (2005). Process monitoring approach using fast moving window PCA. Industrial & engineering chemistry research44(15), 5691-5702.
  • Ding, S. X. (2014). Data-driven design of fault diagnosis and fault-tolerant control systems. Springer London.
  • Langston, L. S., Opdyke, G., & Dykewood, E. (1997). Introduction to gas turbines for non-engineers. Global gas turbine news37(2), 1-9.
  • Ikpe, A. E., Iluobe, I. C., & Imonitie, D. I. E. (2020). Modelling and simulation of high pressure fogging air intake cooling unit of Omotosho phase II gas turbine power plant. Journal of applied research on industrial engineering7(2), 121-136.
  • International Energy Agency. (2006). Energy technology perspectives.
  • Siemens Energy. (2020). Ingenious design to the core.
  • Ammiche, M., Kouadri, A., & Bensmail, A. (2018). A modified moving window dynamic PCA with fuzzy logic filter and application to fault detection. Chemometrics and intelligent laboratory systems177, 100-113.