Learning and optimization of machining operations using computing abilities of neural networks

Abstract

The authors present a scheme that uses a feedforward neural network for the learning and synthesis task. Neural networks consist of a collection of interconnected processors that compute in parallel. The parallelism allows the network to examine various constraints simultaneously during the learning phase and enables reductions in computing time that are attractive in real-time applications. The learning abilities of these networks in a tuning operation are discussed. The network learns by observing the effect of the input variables of the operation (such as feed rate, depth of cut, and cutting speed) on the output variables (such as cutting force, power, temperature, and surface finish of the workpiece). The learning phase is followed by a synthesis phase during which the network predicts the input conditions to be used by the machine tool to maximize the metal removal rate subject to appropriate operating constraints.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>