The invention relates to the technical field of intelligent manufacturing and precision
machining, and discloses a bearing intelligent
machining process recommendation
system based on a
knowledge graph, which comprises a graph construction module, a process recommendation module, a data
perception module, a quality prediction module, a
feedback control module and a self-evolution module. The map construction module fuses multi-
source data by using a
large model and an alignment
algorithm to generate a map, the process recommendation module combines
hybrid retrieval and rule
verification to generate a recommendation scheme and extract a target value, the data sensing module realizes
time sequence alignment of multi-dimensional
sensing data based on a workpiece ID, and the quality prediction module predicts a
processing error in real time by using an LSTM network. The
feedback control module calculates the compensation amount according to the prediction error and drives the
machine tool to execute dynamic deviation correction, and the self-evolution module feeds back measured data to the map based on SPC analysis. According to the method, a
closed loop of beforehand recommendation, in-
process control and after-process iteration is constructed, the problems that
process design depends on experience and lacks real-time correction are solved, and the bearing
machining precision and stability are improved.