Surface roughness prediction of bearing parts based on a new deep learning algorithm

Author : Zhijie Xia, Hui Wang

Abstract :In order to predict the surface quality of bearing part during machining, existing models such as traditional BP neural networks are prone to fall into local optimal solutions and have low convergence efficiency in the training process. A new deep learning algorithm is proposed by combining the genetic algorithm and hippo algorithm to optimize the BP neural network parameters to improve model robustness and prediction accuracy. The genetic algorithm is used to accelerate the global convergence of BP neural network through selection, crossing, mutation and other operations, and the hippopotamus optimization algorithm is used to optimize the population initialization and parameter adjustment of the genetic algorithm to avoid the precocious convergence problem. Experimental results show the effectiveness of the proposed algorithm in improving the accuracy and robustness of the prediction model

Keywords :Roughness prediction, the genetic algorithm, hippopotamus optimization algorithm, neural network.

Conference Name :International Conference on Artificial Intelligence and Neural Networks (ICAINN-25)

Conference Place The Hague, Netherlands

Conference Date 8th Oct 2025