A CFRP drilling parameter optimization method considering progressive tool wear

In carbon fiber reinforced plastic (CFRP) drilling, hole quality is substantially impacted by tool wear, encompassing various wear types such as abrasive or flank wear. In this paper, the challenge of progressive tool wear in CFRP machining is addressed by proposing an optimization method employing neural networks and genetic algorithm-based adjustment strategies. The analysis of the progressive tool wear is grounded in a wear geometry model reflecting the interaction between the tool and CFRP. Orthogonal machining experiments on CFRP laminated plates are conducted to collect extensive data on hole drilling and damage states under progressive tool wear. Utilizing MATLAB, a back propagation (BP) neural network model is established to fit and predict the obtained data. The optimization objective function, considering tool wear and three specified criteria for hole making evaluation, guides the improvement of drilling parameters using a genetic algorithm.