Neural network thermal error compensation of a machining center

A neural network based on Artificial Resonance Theory (ART-map) was used to predict and compensate the tool point errors of a 3-axis machining center using discrete temperature readings from the machine’s structure as inputs. A combination of kinematic error modeling, curve fitting, and the neural network were used to maintain the machine’s three-dimensional (3-D) accuracy within ±7.4 μm, regardless of the thermal state. The network model was evaluated with diagonal measurements and part machining tests. A laser ball bar was used to take the necessary measurements for training the neural network.