Machine tool thermal error prediction method and system based on joint distribution self-adaption

The invention relates to the technical field of machine tool application optimization, in particular to a machine tool thermal error prediction method and system based on joint distribution self-adaption. A thermal error regression model under a working condition and equipment is constructed in a source domain, the method can be applied to thermal error prediction tasks under other working conditions and equipment, meanwhile, a traditional joint distribution self-adaptive algorithm kernel function method is modified, the method can be expanded from being only applied to a classification problem scene to be applied to a regression prediction scene, and in addition, the method can be widely applied to the field of thermal error prediction. A classification evaluation index of the joint distribution adaptive algorithm is adapted to a regression problem evaluation index, and a universal prediction scheme can be provided for thermal error data during variable working conditions, cross-equipment, multi-direction an