RBF (Radial Basis Function) neural network optimization method based on improved Harlisia eagle algorithm

Abstract

The invention relates to the technical field of neural network optimization, in particular to an RBF neural network optimization method based on an improved Harlisia eagle algorithm, which optimizes RBF initial parameters through the improved Harlisia eagle algorithm and realizes accurate prediction and suppression of sea clutters. According to the invention, the coefficient r3 in the position updating formula in the exploration stage is correspondingly improved, and the balance between the global search capability and the local search capability of the algorithm is fully considered. A part of individuals with poor fitness is selected to carry out non-uniform variation and greedy selection. Besides, the E is segmented to ensure that global search is executed in the early stage of iteration of the algorithm, the global search capability can be kept under a certain probability in the later stage of iteration, and the possibility that a global optimal solution cannot be found due to search stagnation caused by falling into local optimum is reduced. The global search capability of the improved Harris eagle algorithm is enhanced, and the RBF network optimized by the improved Harris eagle algorithm provides more rising space for the sea clutter prediction precision.

Description

technical field [0001] The invention relates to the technical field of neural network optimization, in particular to an RBF neural network optimization method based on the improved Harris Eagle algorithm. Background technique [0002] High-frequency ground-wave radar utilizes the characteristics of vertically polarized high-frequency electromagnetic waves with small diffraction attenuation along the coastal plane and is not affected by the curvature of the earth to achieve all-weather and beyond-horizon detection of sea and low-altitude targets. However, when using high-frequency ground wave radar to detect targets, sea clutter is often doped in the target echo, which affects the target detection performance. When the target Doppler frequency is close to the sea clutter, the target signal will be submerged in the sea clutter and it is difficult to be detected. Therefore, sea clutter suppression plays a vital role in realizing radar target detection accurately. [0003] At ...

AI Technical Summary

Problems solved by technology

Finally, individuals with poor fitness in HHO may be in the opposite position of the optimal solution or near the optimal solution in the search space, without considering that the positions of these individual variations may converge to the optimal solution faster than ordinary individuals

The result is that the unknown area is not fully searched, and the convergence speed of the algorithm is slow

Images