Enhanced Autoregressive Integrated Moving Average Model for Anomaly Detection in Power Plant Operations

Document Type : Original Article

Authors

1 Department of Mechanical Engineering, Academy of Engineering, RUDN University, Moscow, Russian Federation

2 Department of Transport Equipment and Technology, Academy of Engineering, RUDN University, Moscow, Russian Federation

Abstract

This study introduces an Enhanced Autoregressive Integrated Moving Average (E-ARIMA) model for anomaly detection in time-series data, using vibrations monitored by CA 202 accelerometers at the Kirkuk Gas Power Plant as a case study. The objective is to overcome the limitations of traditional ARIMA models in analyzing the non-linear and dynamic nature of industrial sensory data. The novel proposed methodology includes data preparation through linear interpolation to address dataset gaps, stationarity confirmation via the Augmented Dickey-Fuller Test, and ARIMA model optimization against the Akaike Information Criterion, with a specialized time-series cross-validation technique. The results show that E-ARIMA model has superior performance in anomaly detection compared to conventional Seasonal ARIMA (SARIMA) and Vector Autoregressive models. In this regard, Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE) criteria were utilized for this evaluation. Finally, the most important achievement of this research is that the results highlight the enhanced predictive accuracy of the E-ARIMA model, making it a potent tool for industrial applications such as machinery health monitoring, where early detection of anomalies is crucial to prevent costly downtimes and facilitate maintenance planning.

Graphical Abstract

Enhanced Autoregressive Integrated Moving Average Model for Anomaly Detection in Power Plant Operations

Keywords

Main Subjects

References

  1. Jahanshahi H, Cevik M, Başar A, editors. Predicting the number of reported bugs in a software repository. Advances in Artificial Intelligence: 33rd Canadian Conference on Artificial Intelligence, Canadian AI 2020, Ottawa, ON, Canada, May 13–15, 2020, Proceedings 33; 2020: Springer.
  2. Ξανθοπούλου ΓΒ. Forecasting power output of photovoltaic systems using machine learning techniques: Αριστοτέλειο Πανεπιστήμιο Θεσσαλονίκης; 2017.
  3. Dorrani Z. Traffic Scene Analysis and Classification using Deep Learning. International Journal of Engineering. 2024;37(3):496-502. https://doi.org/10.5829/ije.2024.37.03c.06
  4. Al Mallah R, Quintero A, Farooq B. Prediction of traffic flow via connected vehicles. IEEE Transactions on Mobile Computing. 2020;21(1):264-77. https://doi.org/10.1109/TMC.2020.3006713
  5. Pan B, Demiryurek U, Shahabi C, editors. Utilizing real-world transportation data for accurate traffic prediction. 2012 ieee 12th international conference on data mining; 2012: IEEE.
  6. Ilu SY, Prasad R. Time series analysis and prediction of COVID-19 patients using discrete wavelet transform and auto-regressive integrated moving average model. Multimedia Tools and Applications. 2024:1-19. https://doi.org/10.1007/s11042-024-18528-x
  7. Pastén D, Czechowski Z, Toledo B. Time series analysis in earthquake complex networks. Chaos: An Interdisciplinary Journal of Nonlinear Science. 2018;28(8). https://doi.org/10.1063/1.5023923
  8. Vogel E, Saravia G, Pastén D, Muñoz V. Time-series analysis of earthquake sequences by means of information recognizer. Tectonophysics. 2017;712:723-8. https://doi.org/10.1016/j.tecto.2017.06.031
  9. Moustra M, Avraamides M, Christodoulou C. Artificial neural networks for earthquake prediction using time series magnitude data or seismic electric signals. Expert systems with applications. 2011;38(12):15032-9. https://doi.org/10.1016/j.eswa.2011.05.043
  10. Fahmi A-TWK, Kashyzadeh KR, Ghorbani S. A comprehensive review on mechanical failures cause vibration in the gas turbine of combined cycle power plants. Engineering Failure Analysis. 2022;134:106094. https://doi.org/10.1016/j.engfailanal.2022.106094
  11. Poullikkas A. An overview of current and future sustainable gas turbine technologies. Renewable and Sustainable Energy Reviews. 2005;9(5):409-43. https://doi.org/10.1016/j.rser.2004.05.009
  12. Tanaka K, Cavalett O, Collins WJ, Cherubini F. Asserting the climate benefits of the coal-to-gas shift across temporal and spatial scales. Nature climate change. 2019;9(5):389-96. https://doi.org/10.1038/s41558-019-0457-1
  13. Meher-Homji CB, Chaker M, Bromley AF, editors. The fouling of axial flow compressors: Causes, effects, susceptibility, and sensitivity. Turbo Expo: Power for Land, Sea, and Air; 2009.
  14. De Michelis C, Rinaldi C, Sampietri C, Vario R. Condition monitoring and assessment of power plant components. Power Plant Life Management and Performance Improvement: Elsevier; 2011. p. 38-109.
  15. Mourad A-HI, Almomani A, Sheikh IA, Elsheikh AH. Failure analysis of gas and wind turbine blades: A review. Engineering Failure Analysis. 2023;146:107107. https://doi.org/10.1016/j.engfailanal.2023.107107
  16. Mevissen F, Meo M. A review of NDT/structural health monitoring techniques for hot gas components in gas turbines. Sensors. 2019;19(3):711. https://doi.org/10.3390/s19030711
  17. Qaiser MT. Data Analysis and Prediction of Turbine Failures Based on Machine Learning and Deep Learning Techniques: NTNU; 2023.
  18. Yan W, Yu L. On accurate and reliable anomaly detection for gas turbine combustors: A deep learning approach. arXiv preprint arXiv:190809238. 2019. https://doi.org/10.48550/arXiv.1908.09238
  19. Zhong S-s, Fu S, Lin L. A novel gas turbine fault diagnosis method based on transfer learning with CNN. Measurement. 2019;137:435-53. https://doi.org/10.1016/j.measurement.2019.01.022
  20. Zhou D, Yao Q, Wu H, Ma S, Zhang H. Fault diagnosis of gas turbine based on partly interpretable convolutional neural networks. Energy. 2020;200:117467. https://doi.org/10.1016/j.energy.2020.117467
  21. Kontopoulou VI, Panagopoulos AD, Kakkos I, Matsopoulos GK. A review of ARIMA vs. machine learning approaches for time series forecasting in data driven networks. Future Internet. 2023;15(8):255. https://doi.org/10.3390/fi15080255
  22. Fahmi A-TWK, Kashyzadeh KR, Ghorbani S. Fault detection in the gas turbine of the Kirkuk power plant: An anomaly detection approach using DLSTM-Autoencoder. Engineering Failure Analysis. 2024;160:108213. https://doi.org/10.1016/j.engfailanal.2024.108213
  23. Paparoditis Efstathios E, Politis DN. The asymptotic size and power of the augmented Dickey–Fuller test for a unit root. 2016. https://doi.org/10.1080/00927872.2016.1178887
  24. Mushtaq R. Augmented dickey fuller test. 2011. https://dx.doi.org/10.2139/ssrn.1911068
  25. Chodakowska E, Nazarko J, Nazarko Ł. Arima models in electrical load forecasting and their robustness to noise. Energies. 2021;14(23):7952. https://doi.org/10.3390/en14237952
  26. Kashyzadeh KR, Ghorbani S. New neural network-based algorithm for predicting fatigue life of aluminum alloys in terms of machining parameters. Engineering Failure Analysis. 2023;146:107128. https://doi.org/10.1016/j.engfailanal.2023.107128
  27. Reza Kashyzadeh K, Amiri N, Ghorbani S, Souri K. Prediction of concrete compressive strength using a back-propagation neural network optimized by a genetic algorithm and response surface analysis considering the appearance of aggregates and curing conditions. Buildings. 2022;12(4):438. https://doi.org/10.3390/buildings12040438
  28. Rezaeian N, Gurina R, Saltykova OA, Hezla L, Nohurov M, Reza Kashyzadeh K. Novel GA-Based DNN Architecture for Identifying the Failure Mode with High Accuracy and Analyzing Its Effects on the System. Applied Sciences. 2024;14(8):3354. https://doi.org/10.3390/app14083354
International Journal of Engineering
Volume 37, Issue 8
TRANSACTIONS B: Applications
August 2024
Pages 1691-1699

Files

Share

How to cite

Statistics