Abstract

Abstract A wind tunnel balance is an important device for force measurement experiments in vehicle wind tunnel experiments and is used to measure the aerodynamic loads acting on the model. The static calibration of the balance is a critical step to ensure measurement accuracy. The traditional calibration method uses a fitting method based on the least squares method, which could be better for dealing with the nonlinear errors of the balance. In order to further improve the calibration performance of wind tunnel balance, this paper proposes a fitting method based on the Convolutional Neural Network (CNN). The mapping relationship between input and output is established for a six-component balance. The optimal parameters of the network model are explored. Through the analysis of the prediction results of the network model, it is found that the CNN balance calibration method is generally better than the traditional least squares fitting method in suppressing the error caused by system nonlinearity. The prediction accuracy of its components reaches the advanced index of the national military standard, which improves the fitting accuracy of the balance formula.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.