This paper presents a novel approach of principal component analysis- (PCA-) assisted back propagation (BP) neural networks for the problem of rotor blade load prediction. 86.5 hours of real flight data were collected from many steady-state and transient flight maneuvers at different altitudes and airspeeds. Prediction of the blade loads was determined by the PCA-BP model from 16 flight parameters measured and monitored by the flight control computer already present in the helicopter. PCA was applied to reduce the dimension of the flight parameters influencing the component load and eliminate the correlation among flight parameters. Thus, obtained principal components were used as input vectors of the BP neural network. The combined PCA-BP neural network model was trained and tested by real flight data. Comparison of this model and to a BP neural network model as well as to a multiple linear regression (MLR) model was also done. The results of comparison demonstrate that the PCA-BP model has higher prediction precision with an average error of 2.46%, while 4.49% for BP and 10.20% for MLR. The results also reveal that the PCA-BP model has a shorter convergence path than the BP model. This method not only is useful in establishing the load spectra of helicopter rotor in-service where installation of strain gauges is impractical but also can reduce the cost of installation and maintenance measured by strain gauges.

In this paper, a load test method of landing gear during take-off and landing of helicopter was proposed and the structure of helicopter landing gear, the modification of strain gauge bridge, the establishment of load calibration equation and the flight test of helicopter were studied. Firstly, according to the structure of helicopter landing gear, the stress analysis of landing gear was carried out, and the load position and force form of landing gear were determined during take-off and landing. Then, the measuring principle of the strain bridge was studied. According to the technical requirements, structural characteristics of the landing gear load test and the properties and principles of the strain bridge, the distribution and load measurement form of the strain bridge of the dangerous structure of the landing gear were designed. Then, studying load calibration test scheme of landing gear and carrying out load calibration test, the load calibration equation of landing gear was obtained, and the accuracy of load calibration equation was verified by comparing the expected load and actual load. Through the flight test, the landing gear load during the take-off and landing of the helicopter was obtained. Finally, the valid analysis of flight load data was carried out. The results show that the proposed method is feasible, and the flight test data of landing gear load are accurate and reliable, which can provide data support for the structure modification, fatigue analysis and the life evaluation of landing gear.

No abstract