Keywords
numerical model
status parameters
maintenance factors
Abstract
There are currently around 18,000 commissioned Gas Turbines in use worldwide, with almost 7,500 long-term service agreements[1]. At the same time, orders for new units increase year by year, and after a decrease in production in 2020 from 353 to 328 new units, from 2022 onwards, the level is planned to rise to the previous level of growth. Gas turbines operate worldwide and are exposed to variations in environmental conditions, such as changes in humidity, temperature, and salinity, which can significantly affect the efficiency and faster degradation of individual components. Based on the unit's maintenance report, there are more than 1,940 event alerts annually. A need exists to create a more dynamic analytical and numerical model that determines the impact of environmental variables on gas turbine stability. It is necessary to analyze and improve existing reliability models, which vary due to configurations and the impact of working conditions. The first step should be an analysis of the impact of environmental factors on turbine performance. This paper describes how the maintenance and inspection model developed from an average value over time model to a model tracking the actual degradation of gas turbines. It includes a comparison ofthree models used in the research, considering the developed methodology for selecting input parameters, their correlation, and their appropriateness for use in further analyses.
References
Anping, W. et al. Prognostics of gas turbine: A condition-based maintenance approach based on multi-environmental time similarity. Mechanical Systems, and Signal Processing 109 (2018).
Bazazzadeh, M. & Badihi H.and Shahriari, A. Gas Turbine Engine Control Design Using Fuzzy Logic and Neural Networks. International Journal of Aerospace Engineering 2011.
Gul, M. et al. Multi-objective-optimization of process parameters of industrial-gas-turbine fueled with natural gas by using Grey-Taguchi and ANN methods for better performance. Energy Reports 6 (2020).
Huadong, M., S., G. & Xie., M. Performance-based maintenance of gas turbines for reliable control of degraded power systems. Mechanical Systems and Signal Processing 103 (2018).
Jasnawitz, J., Masso, J. & Childs, C. Heavy-Duty Gas Turbine Operating and Maintenance Considerations, (GE Gas Turbine Reference Library).
Kejian, W. et al. Heavy-duty gas turbine performance state monitoring method based on generalized regression neural network and boxplot analysis. Patent 2019.
Meherwan, P. B. Gas Turbine Engineering Handbook Fourth Edition (Butterworth-Heinemann, 2012).
Mohammadi, R., Naderi, E., Khorasani, K. & Hashtrudi-Zad, S. Fault diagnosis of gas turbine engines by using dynamic neural networks in booktitle IEEE 54th International Midwest Symposium on Circuits and Systems (MWSCAS) (2011), 1–4.
Slade, S. & Palmer, C. Worldwide Gas Turbine Market Report,Turbomachinery Magazine,Handbook (2021).
Tahan, M., Tsoutsanis, E., Muhammad, M. & Karim, A. Performance-based health monitoring, diagnostics and prognostics for condition-based maintenance of gas turbines: A review. Applied Energy 198 (2017).
Xusheng, Y., Mingliang B.and Jinfu, L., L., J. & Daren, Y. Gas path fault diagnosis for gas turbine group based on deep transfer learning. Measurement 181 (2021).
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.