Federal transfer learning enhanced multi-agent workshop dynamic regulation and control method

The invention discloses a federal transfer learning enhanced multi-agent workshop dynamic regulation and control method. The method comprises the following steps: establishing a distributed flexible flow workshop dynamic scheduling model based on a multi-agent system; utilizing federal learning to obtain a feature extraction network with characterization capability; establishing a multi-agent deep reinforcement learning model based on cross sampling based on the feature extraction network in combination with the work data subjected to feature processing according to actual task requirements and equipment features of a workshop; training the multi-agent deep reinforcement learning model by using a deep Q learning algorithm; collecting data of other workshops or factories and local similar tasks by adopting a federal transfer learning technology, and training a Q network according to the data; then, effective migration of knowledge is realized through an adaptive weight fusion technology; and dynamic regulation