INVERSE PROCESS CONTROLLER USING A NEW CLUSTERED NEURAL NETWORK

In this paper a newly developed Clustered Multilayer Perceptron (CMLP) network is applied and compared to the MLP through modeling and simulations of machining processes. Simulation results presented using machining data demonstrate that the CMLP possesses better performance than the standard MLP. During on-line training with machining data about 65% degradation of previously learned information can be observed in the MLP as opposed to only 11% for the CMLP. A feedforward adaptive inverse neuro-controller intended for on-line optimization of the machining processes is also presented. The first results using the CMLP inverse neuro-controller are promising.