Neural network model for the condition assessment of hydro turbines
Конференцијски прилог (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
During regular operation, hydro turbine elements have complex operating conditions. In order to prevent major failures, among other common preventive measures, it is necessary to make a useful model of hydro turbine. Development of this model was focused on real elements and data set of real operating history. To solve this, an integral diagnostic approach is used. Based on the real diagnostics data of the condition and data history of the hydro turbine shaft and the designed life expectancy, a multi-layer perceptron (MLP) based artificial neural network (ANN) is built. The idea with this model was to enable to life assessment of the turbine shaft in any particular moment during regular operation.
This paper describes a model for estimating the condition of the shafts of turbines of the current generator in Hydropower plant Derdap 2. The significance of this approach is that real experimental data support development of ML ANN (number of neurons and layers) topology, which is optimal ...for this model, training and testing. Results obtained from this model are used for decision-making about the planning time schedule of maintenance actions, as well as reducing overhaul time and direct losses.
Кључне речи:
Hydroturbines / Shafts / Neural Network model / DiagnosticsИзвор:
1st International Conference on Mathematical Modelling in Mechanics and Engineering Mathematical Institute SANU, 2022, 154-Издавач:
- University of Belgrade - Faculty of Mechanical Engineering, Belgrade, Serbia
Институција/група
Institut za ispitivanje materijalaTY - CONF AU - Ilić, Dragoljub AU - Milošević, Dragan AU - Momčilović, Dejan PY - 2022 UR - http://rims.institutims.rs/handle/123456789/480 AB - During regular operation, hydro turbine elements have complex operating conditions. In order to prevent major failures, among other common preventive measures, it is necessary to make a useful model of hydro turbine. Development of this model was focused on real elements and data set of real operating history. To solve this, an integral diagnostic approach is used. Based on the real diagnostics data of the condition and data history of the hydro turbine shaft and the designed life expectancy, a multi-layer perceptron (MLP) based artificial neural network (ANN) is built. The idea with this model was to enable to life assessment of the turbine shaft in any particular moment during regular operation. This paper describes a model for estimating the condition of the shafts of turbines of the current generator in Hydropower plant Derdap 2. The significance of this approach is that real experimental data support development of ML ANN (number of neurons and layers) topology, which is optimal for this model, training and testing. Results obtained from this model are used for decision-making about the planning time schedule of maintenance actions, as well as reducing overhaul time and direct losses. PB - University of Belgrade - Faculty of Mechanical Engineering, Belgrade, Serbia C3 - 1st International Conference on Mathematical Modelling in Mechanics and Engineering Mathematical Institute SANU T1 - Neural network model for the condition assessment of hydro turbines SP - 154 UR - https://hdl.handle.net/21.15107/rcub_rims_480 ER -
@conference{ author = "Ilić, Dragoljub and Milošević, Dragan and Momčilović, Dejan", year = "2022", abstract = "During regular operation, hydro turbine elements have complex operating conditions. In order to prevent major failures, among other common preventive measures, it is necessary to make a useful model of hydro turbine. Development of this model was focused on real elements and data set of real operating history. To solve this, an integral diagnostic approach is used. Based on the real diagnostics data of the condition and data history of the hydro turbine shaft and the designed life expectancy, a multi-layer perceptron (MLP) based artificial neural network (ANN) is built. The idea with this model was to enable to life assessment of the turbine shaft in any particular moment during regular operation. This paper describes a model for estimating the condition of the shafts of turbines of the current generator in Hydropower plant Derdap 2. The significance of this approach is that real experimental data support development of ML ANN (number of neurons and layers) topology, which is optimal for this model, training and testing. Results obtained from this model are used for decision-making about the planning time schedule of maintenance actions, as well as reducing overhaul time and direct losses.", publisher = "University of Belgrade - Faculty of Mechanical Engineering, Belgrade, Serbia", journal = "1st International Conference on Mathematical Modelling in Mechanics and Engineering Mathematical Institute SANU", title = "Neural network model for the condition assessment of hydro turbines", pages = "154", url = "https://hdl.handle.net/21.15107/rcub_rims_480" }
Ilić, D., Milošević, D.,& Momčilović, D.. (2022). Neural network model for the condition assessment of hydro turbines. in 1st International Conference on Mathematical Modelling in Mechanics and Engineering Mathematical Institute SANU University of Belgrade - Faculty of Mechanical Engineering, Belgrade, Serbia., 154. https://hdl.handle.net/21.15107/rcub_rims_480
Ilić D, Milošević D, Momčilović D. Neural network model for the condition assessment of hydro turbines. in 1st International Conference on Mathematical Modelling in Mechanics and Engineering Mathematical Institute SANU. 2022;:154. https://hdl.handle.net/21.15107/rcub_rims_480 .
Ilić, Dragoljub, Milošević, Dragan, Momčilović, Dejan, "Neural network model for the condition assessment of hydro turbines" in 1st International Conference on Mathematical Modelling in Mechanics and Engineering Mathematical Institute SANU (2022):154, https://hdl.handle.net/21.15107/rcub_rims_480 .