An　optimal　control　strategy　is　proposed　to　improve　the　fermentation　titer,　which　combines　the　support　vector　machine　(SVM)　with　real　code　genetic　algorithm　(RGA)　A　prediction　model　is　established　with　SVM　for　penicillin　fermentation　processes,　and　it　is　used　in　RGA　for　fitting　function　A　control　pattern　is　proposed　to　overcome　the　coupling　problem　of　fermentation　parameters,　which　describes　the　overall　production　condition　Experimental　results　show　that　the　optimal　control　strategy　improves　the　penicillin　titer　of　the　fermentation　process　by　22.88%,　compared　with　the　routine　operation