Aiming　at　the　flexible　job　shop　scheduling　problem　in　machine　tool　manufacturing　plants,　an　improved　genetic　algorithm　based　on　directed　variation　is　proposed.　Based　on　the　real-time　production　situation,　the　algorithm　generates　the　probability　distribution　of　processing　equipment　selection,　and　then　carries　out　directed　variation　operation　according　to　the　probability,　thus　improving　the　optimization　ability　of　the　algorithm.　In　addition,　the　method　of　antibody　self-elimination　is　used　in　species　selection　to　enhance　the　diversity　of　the　population.　©　2023　IEEE.