Abstract
The instantaneous temperature rise curve of the electromagnetic launch guide rail produced on the launching moment is an important indicator of the health of the launcher. The reliability of the launcher can be improved by predicting the temperature rise curve of the continuous launching guide rail on-line. What's a pity, since the launcher's complex coupling of electrical, magnetic, thermal and force physical fields and system nonlinearity problems, it is difficult to build accurate models to predict the instantaneous temperature rise curve of launcher. In this paper, based on the high sampling rate temperature curve measurement data, a data-driven method is proposed to accurately predict the instantaneous temperature rise curve of the continuously launching guide rail on line. The instantaneous temperature rise time series of continuous emission is an unsteady and nonlinear pulse sequence, and the existing forecasting methods are not applicable. Taking the temperature rise curve of each launch as a unit, the characteristics of the curve are studied, and five characteristic quantities are extracted. The temperature rise time series is divided into five series with the number of launches as the time axis. A multi-variable coupled feature series neural network prediction model is constructed. The parameters of the model are obtained based on the emission data as training sample, and the prediction of feature sequence is performed. Finally, the predicted temperature rise curve is obtained by recovering the curve using the predicted characteristic quantities. After the actual launch data test of a system, the results show that the features' prediction error of the proposed method is less than 1.81%. The predicted temperature rise curve is very close to the measured curve, and the calculation speed is fast enough to be used for on-line prediction, which improves the reliability of rail launching.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
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.