Rolling　bearings　are　important　parts　of　rotating　machinery.　When　the　early　failure　occurs,　it　is　difficult　to　effectively　extract　the　weak　fault　features.　Aiming　at　this　problem,　an　early　fault　diagnosis　method　of　Parameter-optimized　Variational　Mode　Decomposition　(VMD)　of　is　proposed.　First,　the　instantaneous　frequency　mean　Judged　method　is　used　to　determine　the　value　of　modal　number　K,　and　then　the　fault　diagnosis　signal　is　processed　by　VMD　method.　By　selecting　the　components　of　the　intrinsic　modal　function　obtained　by　decomposing　the　fault　signal　of　bearing　that　an　envelope　analysis　is　performed　on　the　sensitive　components　to　determine　the　fault　type　and　severity　of　the　bearing.　Finally,　compared　with　the　results　obtained　by　the　empirical　modal　decomposition　algorithm,　it　is　proved　that　VMD　can　successfully　extract　the　early　fault　features　of　rolling　bearing　and　realize　the　diagnosis　of　early　fault　of　bearing.　©　2018　IEEE.