The invention relates to the technical field of precision
machining, discloses a double-shaft DFG
grinding machine Z1-Z2 linkage removal amount control and
grinding wheel loss optimization method and
system, and aims to solve the problems of unreasonable Z1-Z2 removal amount distribution, inaccurate
grinding wheel loss control and poor
wafer surface damage adaptability of existing DFG grinding. According to the method and
system, Z1 rough grinding parameters are determined and adjusted through multi-objective optimization and self-
adaptive control by means of the initial morphology and material characteristics of a
wafer; in combination with a Z1 result, a
deep learning model is utilized to intelligently distribute Z2 accurate grinding removal amount and parameters, and adaptive adjustment and abnormal Air
Cut are realized; and meanwhile, the grinding parameters are continuously optimized by adopting the
grinding wheel loss prediction model. By adopting the technical scheme, the grinding efficiency and precision can be remarkably improved, the service life of the
grinding wheel is prolonged, the cost is reduced, and the problems of removal amount distribution,
grinding wheel loss and
wafer damage are solved.