Optimal slip rate identification method based on firefly algorithm to optimize bp neural network

Abstract

The invention provides an optimal slip rate identification method based on a firefly algorithm optimized BP neural network. The method comprises the steps that an initial weight value and an initial threshold value of a firefly algorithm optimized BP neural network model are adopted to obtain an optimal weight value and an optimal threshold value; the optimal weight value and the optimal threshold value are adopted to construct an initial optimal slip rate identification model; training sample data is adopted to perform training on the optimal slip rate identification model to obtain a final IFA-BP optimal slip rate identification model; the final IFA-BP optimal slip rate identification model is adopted to predict the optimal slip rate of an airplane in the braking process. The method has the advantages that the defect that the BP neural network is prone to fall into local minimum is effectively overcome, operational precision is improved, the optimal slip rate can be predicted quickly and accurately in the braking process of the airplane, and therefore the reliability and safety of landing of the airplane are guaranteed.

Description

technical field [0001] The invention belongs to the technical field of aircraft brake control, and in particular relates to an optimal slip rate identification method based on a firefly algorithm to optimize a BP neural network. Background technique [0002] The performance of aircraft braking system plays a vital role in the safety of aircraft operation. How to effectively improve the braking efficiency of the aircraft, shorten the running distance, and improve the adaptability of the aircraft to various load conditions, runway conditions, and weather conditions has become the main goal of aircraft braking system research. [0003] The optimal slip rate identifier is an important part of the aircraft braking system. The optimal slip rate identifier identifies the optimal slip rate s by analyzing the changing combination coefficient μ and slip rate s during the aircraft braking process. p . [0004] In the prior art, the optimal slip rate recognizer mainly adopts the BP ne...

AI Technical Summary

Problems solved by technology

However, using the BP neural network model to predict the optimal slip rate s p However, there are mainly the following shortcomings: the BP neural network model tends to fall into local minimum during the operation process, so that the optimal slip rate s cannot be accurately predicted in a short time p problems, which in turn cause the aircraft to skid and affect the reliability and safety of the aircraft landing

Images