Neural-network-based intelligent control for active stressed lap optical polishing process

A neural network based intelligent controller for an optical polishing machine with 60cm diameter active stressed lap has been developed. This paper briefly introduces the shape control strategy of the stressed-lap based optical polishing system. The dynamic change of the surface shape of the stressed lap during the operating process of polishing a large aspheric optical surface is investigated. The principle and structure of neural network based shape control system are discussed. The relationship between the stressed lap driven forces and surface shape is analyzed in detail. The original data from the micro displacement sensor matrix were used to train the neural network model. Simulation results show that the proposed control model can precisely produce the combined driven forces upon given surface shape of the stressed lap and improve the deformation precision.