Jinghui Deng, Qiyou Cheng and Xing Lu
Helicopter fuselage vibration prediction is important to keep a safety and comfortable flight process. The helicopter vibration mechanism model is difficult to meet of demand for…
Abstract
Purpose
Helicopter fuselage vibration prediction is important to keep a safety and comfortable flight process. The helicopter vibration mechanism model is difficult to meet of demand for accurate vibration prediction. Thus, the purpose of this paper is to develop an intelligent algorithm for accurate helicopter fuselage vibration analysis.
Design/methodology/approach
In this research, a novel weighted variational mode decomposition (VMD)- extreme gradient boosting (xgboost) helicopter fuselage vibration prediction model is proposed. The vibration data is decomposed and reconstructed by the signal clustering results. The vibration response is predicted by xgboost algorithm based on the reconstructed data. The information transfer order between the controllable flight data and flight attitude are analyzed.
Findings
The mean absolute percentage error (MAPE), root mean square error (RMSE) and mean absolute error (MAE) of the proposed weighted VMD-xgboost model are decreased by 6.8%, 31.5% and 32.8% compared with xgboost model. The established weighted VMD-xgboost model has the highest prediction accuracy with the lowest mean MAPE, RMSE and MAE of 4.54%, 0.0162, and 0.0131, respectively. The attitude of horizontal tail and cycle pitch are the key factors to vibration.
Originality/value
A novel weighted VMD-xgboost intelligent prediction methods is proposed. The prediction effect of xgboost model is highly improved by using the signal-weighted reconstruction technique. In addition, the data set used is collected from actual helicopter flight process.
Details
Keywords
Computational fluid dynamics (CFD)/computational structural dynamics (CSD) coupling analysis is an important method in the research of helicopter aeroelasticity due to its high…
Abstract
Purpose
Computational fluid dynamics (CFD)/computational structural dynamics (CSD) coupling analysis is an important method in the research of helicopter aeroelasticity due to its high precision. However, this method still suffers from some problems, such as wake dissipation and large computational cost. In this study, a new coupling method and a new air load correction method that combine the free wake model with the CFD/CSD method are proposed to maintain computational efficiency whilst solving the wake dissipation problem of the prior coupling methods.
Design/methodology/approach
A new coupling method and a new air load correction method that combine the free wake model with the CFD/CSD method are proposed. With the introduction of the free wake model, the CFD solver can adopt two-order accuracy schemes and fewer aerodynamic grids, thus maintaining computational efficiency whilst solving the wake dissipation problem of the prior coupling methods.
Findings
Compared with the predictions of the prior methods and flight test data, those of the proposed method are more accurate and closer to the test data. The difference between the two methods in high-speed forward flight is minimal.
Research limitations/implications
Because of the chosen research approach, the research results may lack generalisability. Therefore, researchers are encouraged to test the proposed method further.
Originality/value
In this paper, a CFD/CSD/free wake coupling method is proposed to improve the computational accuracy of the traditional CFD/CSD coupled method and ensure the computational efficiency.