Indirect Model for Roughness in Rough Honing Processes Based on Artificial Neural Networks

In the present paper an indirect model based on neural networks is presented for modelling the rough honing process. It allows obtaining values to be set for different process variables (linear speed, tangential speed, pressure of abrasive stones, grain size of abrasive and density of abrasive) as a function of required average roughness Ra. A multilayer perceptron (feedforward) with a backpropagation (BP) training system was used for defining neural networks. Several configurations were tested with different strategies, number of layers, number of neurons and transfer function. Best configuration for the network was searched by means of two different methods, trial and error and Taguchi design of experiments (DOE). In both cases, best configuration corresponds to a single network with two hidden layers. Once best configuration was found, a network was defined for obtaining honing parameters as a function of required roughness parameters related to Abbott-Firestone curve, Rk, Rpk and Rvk.