A back propagation neural network with improved sine cosine algorithm approach for multi-response drilling optimization of carbon fiber reinforced polymer (CFRP)
Year: 2026
Type: preprint
Abstract: In this study, the integration of Back Propagation Neural Network (BPNN) with an Improved Sine-Cosine Algorithm (ISCA) is proposed to predict and optimize the drilling process of carbon fiber reinforced polymer (CFRP). The BPNN is firstly performed to model and predict the optimal values of the drilling responses, in which multiple characteristics of drilling performances have been taken into account, namely thrust force (\(\:{\text{F}}_{\text{T}\text{h}}\)), torque (\(\:\text{M}\)), hole entry delamination (\(\:{\text{F}\text{D}}_{\text{e}\text{n}}\)), and hole exit delamination (\(\:{\text{F}\text{D}}_{\text{e}\text{x}}\)). The model is then being optimized by the ISCA to obtain the best drilling parameters level combination. Two mechanisms are presented to improve the general framework of Sine Cosine Algorithm (SCA): 1) adaptive selection of operators, and 2) population management technique. The results have clearly shown that the proposed approach is able to improve the performance of the standard BPNN-SCA.
Source: Research Square
Language: English
Subfield: Mechanical Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7214915484