The flow rate of aircraft hydraulic system is one of the important parameters to measure the performance of air-craft. The stability of flow rate of hydraulic pipeline is related to the safety of hydraulic system and even aircraft flight. Aiming at the problem that it is difficult to measure the load flow of aircraft hydraulic system, a prediction method based on ensemble learning for the load flow of Engine Driven Pump (EDP) is proposed. According to the different working conditions of EDP, the QPSO-LightGBM intelligent integrated learning algorithm model is established. Through Quantum Particle Swarm Optimization (QPSO) algorithm optimizes the super parameters of Light Gradient Boosting Machine (LightGBM) algorithm, and realizes the regression prediction model of load flow by three factors: system oil pressure, temperature and high pressure oil filtration pressure difference. Finally, by com-paring multiple linear regression, random forest and XGBoost, the Root Mean Square Error(RMSE) of the proposed method is 1.0152 and the goodness of fit R2 has reached to 0.9988. The effectiveness of QPSO-LightGBM method is verified. The method can provide technical support for the fault diagnosis of aeronautical hydraulic system.
Flow Prediction of Aero Engine Driven Pump Based on QPSO-LightGBM
Lect. Notes Electrical Eng.
Proceedings of the 5th China Aeronautical Science and Technology Conference ; Kapitel : 24 ; 240-246
02.11.2021
7 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Flow Prediction of Aero Engine Driven Pump Based on QPSO-LightGBM
British Library Conference Proceedings | 2022
|Modeling method of variable cycle engine based on QPSO hybrid algorithm
British Library Online Contents | 2018
|Flight delay prediction based on LightGBM
IEEE | 2021
|