Due　to　the　complexity　and　high　non-linearity　of　microbial　fermentation　process,　most　simple　mathematical　models　cannot　describe　the　behavior　of　biochemistry　systems　very　well.　Support　vector　machine　(SVM)　is　a　novel　machine　learning　method,　which　is　powerful　for　the　problem　characterized　by　small　sample,　nonlinearity,　high　dimension　and　local　minima,　and　has　high　generalization.　A　model　for　titer　pre-estimate　in　penicillin　fermentation　process　was　developed　by　SVM　method.　The　model　possesses　the　strong　capability　of　fitting　and　generalization.　The　effects　of　parameter　adjusting　on　model　quality　were　analyzed　by　simulation　experiments.　Some　models　based　on　ANN　methods　were　also　presented.　The　results　show　that　SVM　is　superior　to　ANN　modeling　methods.