CONTROL OF TOLERANCES IN TURNING BY PREDICTIVE CONTROL WITH NEURAL NETWORKS

Stochastic and non-deterministic influences have an effect on cutting processes and lead to an unsteady and dynamic process behaviour. Conce pts for the improvement of process reliability and for the control of tolerances have to be developed in order to fulfil the increasing requ irements on product quality. A concept for the improvement of manufact uring accuracy through artificial neural networks (ANN) will be presen ted as an example for the turning process. This ANN model makes it pos sible to predict the dimensional deviation caused by tool wear. Feedin g this back in an open loop within the: machine controller the deviati on can be compensated by using an adaptive control of the depth of cut .