Title: Prediction of surface roughness and delamination in spiral milling of CFRP laminates by SAPSO-BP neural network

Authors: Haifeng Ning; Hualin Zheng; Xiufen Ma; Bo Feng; Xinman Yuan

Addresses: School of Mechatronic Engineering, Southwest Petroleum University, Chengdu, China ' School of Mechatronic Engineering, Southwest Petroleum University, Chengdu, China ' City College of Southwest University of Science and Technology, Mianyang, China ' School of Mechatronic Engineering, Southwest Petroleum University, Chengdu, China ' AVIC Chengdu Aircraft Industrial (Group) Co., Ltd., Chengdu, China

Abstract: Due to the anisotropy carbon fibre reinforced polymer (CFRP) materials, problems such as poor surface quality of the hole wall and delamination often occur in the traditional hole-making process. In this study, the Taguchi method was used to design a CFRP spiral-milling experiment using uncoated and diamond-coated carbide cutters. The analysis of variance and signal-to-noise ratio analysis were used to study the influence of process parameters on the surface roughness and delamination factors. Prediction models for surface roughness and delamination factors were established using improved particle-swarm neural network. The results showed that the diamond-coated milling cutters are more suitable for CFRP processing. The order of importance of the process parameters is as follows: axial-feed speed > horizontal-feed speed > spindle speed > revolution radius. The prediction model for the surface roughness and delamination factors developed in this study achieves high accuracy.

Keywords: CFRP; surface roughness; delamination factor; spiral milling; SAPSO-BP neural network.

DOI: 10.1504/IJMMM.2021.121207

International Journal of Machining and Machinability of Materials, 2021 Vol.23 No.5/6, pp.417 - 433

Received: 30 May 2021
Accepted: 10 Sep 2021
Published online: 28 Feb 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article