This　paper　presents　a　novel　method　for　fault　diagnosis　based　on　empirical　mode　decomposition　(EMD),　an　improved　distance　evaluation　technique　and　the　combination　of　multiple　adaptive　neuro-fuzzy　inference　systems　(ANFISs).　The　method　consists　of　three　stages.　First,　prior　to　feature　extraction,　some　preprocessing　techniques,　like　filtration,　demodulation　and　EMD　are　performed　on　vibration　signals　to　acquire　more　fault　characteristic　information.　Then,　six　feature　sets,　including　time-　and　frequency-domain　statistical　features　of　both　the　raw　and　preprocessed　signals,　are　extracted.　Second,　an　improved　distance　evaluation　technique　is　proposed,　and　with　it,　six　salient　feature　sets　are　selected　from　the　six　original　feature　sets,　respectively.　Finally,　the　six　salient　feature　sets　are　input　into　the　multiple　ANFIS　combination　with　genetic　algorithms　(GAs)　to　identify　different　abnormal　cases.　The　proposed　method　is　applied　to　the　fault　diagnosis　of　rolling　element　bearings,　and　testing　results　show　that　the　multiple　ANFIS　combination　can　reliably　recognise　different　fault　categories　and　severities,　which　has　a　better　classification　performance　compared　to　the　individual　classifiers　based　on　ANFIS.　Moreover,　the　effectiveness　of　the　proposed　feature　selection　method　based　on　the　improved　distance　evaluation　technique　is　also　demonstrated　by　the　testing　results.　(c)　2006　Elsevier　Ltd.　All　rights　reserved.