Hybrid machining simulator based on predictive machining theory and neural network modelling

Abstract

A machining simulation system based on a hybrid machining model integrating the predictive machining theory developed by Oxley and neural network models for predicting machining characteristic factors is presented in this paper. The model consists of two components, an analytical component and a neural network component. The analytical component uses Oxley's predictive machining theory, from which the essential machining characteristics such as cutting forces, temperature in the cutting region and chip geometry can be predicted from the input data of the fundamental properties of the workpiece material, tool geometry and cutting conditions, taking into account the effect of strain, strain rate and temperature on chip formation. The neural network component predicts machining characteristics that are difficult to model analytically, such as tool wear, machined workpiece surface roughness and chip breaking ability from the essential machining characteristic factors. The neural network component operates on the essential machining characteristics to make its predictions. The analytical component not only predicts the essential machining characteristics for direct output but also machining characteristic factors for the neural network component which uses these to predict tool wear, machined workpiece surface roughness and chip breaking ability. The tool wear and surface finish are modelled based on their dependence on the analytically predictable machining characteristic factors such as cutting forces and temperature. The chip-breaking ability is defined using a chip packaging density index that is modelled with analytically determined factors: forces, flow stress at the shear plane, chip flow angle, chip thickness and chip width. The accuracy of the hybrid machining simulator has been verified with extensive experimental tests. The simulator, implemented within Microsoft Windows, is capable of predicting results in both numerical and graphical form.