An Improved Data-Driven Modeling Method for Aircraft Based on Prediction and Optimization

This paper proposes a data-driven modeling method for aircraft by predicting model errors and optimizing model structures. Based on flight test data from the mechanism model, the aircraft data-driven model is established by several trained basic neural networks for fitting dynamics relationships of aircraft and recurrent neural networks for compensating for model errors. Compared to the traditional data-driven modeling method, this method can more effectively avoid and solve the problem of instability of data-driven models with disturbances at long running times. Finally, the proposed method’s feasibility and the established model’s credibility are verified by simulation experiments with complex disturbance and statistical analysis for model accuracy.