Carbon fiber reinforced polymer (CFRP) is widely used in the aerospace field due to its light weight and high strength. The CFRP milling process is prone to damage such as burrs and tears. The cutting force is closely related to the damage of CFRP and tool wear. In this paper, a back propagation (BP) neural network model of cutting force and edge force coefficients was established. The model considers the effects of instantaneous uncut chip thickness, fiber cutting angle, spindle speed, and axial depth of cut. The unidirectional CFRP laminate instantaneous milling model considering the cutting edge force was further established. The instantaneous milling force prediction model was extended to multi-directional CFRP laminates. And the relationship between the damage mechanism of CFRP and the instantaneous milling force was analyzed. Experiments have proved that the instantaneous milling force prediction model built in this paper has high accuracy.

碳纤维增强聚合物（CFRP）因其重量轻、强度高而被广泛应用于航空航天领域。CFRP铣削过程容易出现毛刺和撕裂等损坏。切削力与CFRP的损伤和刀具磨损密切相关。在本文中，建立了切削力和边缘力系数的反向传播（BP）神经网络模型。该模型考虑了瞬时未切削切屑厚度、纤维切削角度、主轴转速和轴向切削深度的影响。进一步建立了考虑切削刃力的单向CFRP层压板瞬时铣削模型。瞬时铣削力预测模型扩展到多向 CFRP 层压板。并分析了CFRP的损伤机理与瞬时铣削力的关系。