An analytical approach on stochastic model for cutting force prediction in milling ceramic matrix composites

Fiber-reinforced ceramic matrix composites are increasingly applied in the aerospace, energy and electronic industries. Nevertheless, the milling process of ceramic matrix composites is considerably difficult owing to the presence of heterogeneous, anisotropic and brittle nature. This paper presents a novel stochastic model of cutting forces in milling process of ceramic matrix composites. The algorithm model of randomly distributed carbon fibers is developed by incorporating the cutting mechanism. The obtained instantaneous relative content of fibers is introduced for dividing the resultant cutting forces into fiber and matrix components in the shear deformed region, the friction deformed region and the ploughing region, respectively. In addition, a probabilistic approach based on the particle filter is used to predict the random tool wear progression, linking online measurement data with the state of tool wear. Then, the empirical uncertain components of cutting forces considering tool wear can be established by using a radial basis function (RBF) neural network. The predicted cutting forces are in good agreement with the measured values. The effects of stochastic fiber distributions, tool wear and machining parameters on cutting forces are investigated by the proposed model.