Research Article

Application of RBF neural network based on improved Harris eagle algorithm optimization for free-form surface machining error prediction

Guangxi University of Science and Technology, School of Mechanical and Automotive Engineering, Liuzhou, PR China

^* Corresponding author: 2583665275@qq.com

Received: 8 June 2025
Accepted: 1 September 2025

Abstract

With the aim of addressing the problem of low efficiency in free-form surface machining error inspection, an improved Harris hawk optimization-radial basis function (IHHO-RBF) neural network prediction model is proposed in this work. In this model, the dynamic programming learning mechanism is used to avoid the repeated calculation of information and improve the global search capabilities of the Harris hawk optimization (HHO) algorithm. The Nelder-Mead algorithm is used to improve the optimization capabilities of the HHO. The improved Harris hawk optimization (IHHO) algorithm is used to optimize the network parameters of the radial basis function (RBF) neural network. The optimized prediction model is compared with the sparrow search algorithm-radial basis function (SSA-RBF) and fruit fly optimization algorithm-radial basis function (FOA-RBF) models. The results show that IHHO-RBF can effectively improve prediction accuracy in detecting free-form surface machining errors.