Публікація: Intelligent Method of Identifying the Nonlinear Dynamic Model for Helicopter Turboshaft Engines
Вантажиться...
Дата
ORCID
DOI
Назва видання
ISSN
Назва тому
Видання
Sensors. – 2024. – Vol., 24, Issue 19. – Article 6488
Анотація
Дослідження було зосереджено на динамічній моделі турбовального двигуна вертольота, ідентифікації вирішення задач у нестаціонарному та перехідному режимах (запуск двигуна та прискорення) на основі даних датчиків.
This research focused on the helicopter turboshaft engine dynamic model, identifying task solving in unsteady and transient modes (engine starting and acceleration) based on sensor data. It is known that about 85% of helicopter turboshaft engines operate in steady-state modes, while only around 15% operate in unsteady and transient modes. Therefore, developing dynamic multi-mode models that account for engine behavior during these modes is a critical scientific and practical task. The dynamic model for starting and acceleration modes has been further developed using on-board parameters recorded by sensors (gas-generator rotor r.p.m., free turbine rotor speed, gas temperature in front of the compressor turbine, fuel consumption) to achieve a 99.88% accuracy in identifying the dynamics of these parameters. An improved Elman recurrent neural network with dynamic stack memory was introduced, enhancing the robustness and increasing the performance by 2.7 times compared to traditional Elman networks. A theorem was proposed and proven, demonstrating that the total execution time for N Push and Pop operations in the dynamic stack memory does not exceed a certain value O(N). The training algorithm for the Elman network was improved using time delay considerations and Butterworth filter preprocessing, reducing the loss function from 2.5 to 0.12% over 120 epochs. The gradient diagram showed a decrease over time, indicating the model’s approach to the minimum loss function, with optimal settings ensuring the stable training.
В этом исследовании основное внимание уделено динамической модели вертолетного турбовального двигателя, выявлению решения задач в неустановившихся и переходных режимах (запуск двигателя и разгон) на основе данных датчиков.
This research focused on the helicopter turboshaft engine dynamic model, identifying task solving in unsteady and transient modes (engine starting and acceleration) based on sensor data. It is known that about 85% of helicopter turboshaft engines operate in steady-state modes, while only around 15% operate in unsteady and transient modes. Therefore, developing dynamic multi-mode models that account for engine behavior during these modes is a critical scientific and practical task. The dynamic model for starting and acceleration modes has been further developed using on-board parameters recorded by sensors (gas-generator rotor r.p.m., free turbine rotor speed, gas temperature in front of the compressor turbine, fuel consumption) to achieve a 99.88% accuracy in identifying the dynamics of these parameters. An improved Elman recurrent neural network with dynamic stack memory was introduced, enhancing the robustness and increasing the performance by 2.7 times compared to traditional Elman networks. A theorem was proposed and proven, demonstrating that the total execution time for N Push and Pop operations in the dynamic stack memory does not exceed a certain value O(N). The training algorithm for the Elman network was improved using time delay considerations and Butterworth filter preprocessing, reducing the loss function from 2.5 to 0.12% over 120 epochs. The gradient diagram showed a decrease over time, indicating the model’s approach to the minimum loss function, with optimal settings ensuring the stable training.
В этом исследовании основное внимание уделено динамической модели вертолетного турбовального двигателя, выявлению решения задач в неустановившихся и переходных режимах (запуск двигателя и разгон) на основе данных датчиков.
Опис
Ключові слова
Україна, Техніка. Технічні науки. Machinery. Engineering. Техника. Технические науки, publikatsii u WoS, helicopter turboshaft engines, dynamic model, identifying, engine starting and acceleration, Elman recurrent neural network with dynamic stack memory, training, accuracy, sensors, вертолітні турбовальні двигуни, динамічна модель, запуск і розгін двигуна, рекурентна нейронна мережа Елмана з динамічною стековою пам'яттю, навчання, точність, датчики, вертольот, двигун, вертолетные турбовальные двигатели, динамическая модель, запуск и ускорение двигателя
Бібліографічний опис
Intelligent Method of Identifying the Nonlinear Dynamic Model for Helicopter Turboshaft Engines / Serhii Vladov, Arkadiusz Banasik, Anatoliy Sachenko, Wojciech M. Kempa, Valerii Sokurenko, Oleksandr Muzychuk, Piotr Pikiewicz, Agnieszka Molga, Victoria Vysotska // Sensors. – 2024. – Vol., 24, Issue 19. – Article 6488. – DOI : https://doi.org/10.3390/s24196488.
Vladov, S.; Banasik, A.; Sachenko, A.; Kempa, W.M.; Sokurenko, V.; Muzychuk, O.; Pikiewicz, P.; Molga, A.; Vysotska, V. Intelligent Method of Identifying the Nonlinear Dynamic Model for Helicopter Turboshaft Engines. Sensors 2024, 24, 6488. https://doi.org/10.3390/s24196488
Vladov, S.; Banasik, A.; Sachenko, A.; Kempa, W.M.; Sokurenko, V.; Muzychuk, O.; Pikiewicz, P.; Molga, A.; Vysotska, V. Intelligent Method of Identifying the Nonlinear Dynamic Model for Helicopter Turboshaft Engines. Sensors 2024, 24, 6488. https://doi.org/10.3390/s24196488