Approximate　Entropy　(ApEn)　is　a　newly　introduced　statistic　that　can　be:　used　to　quantify　the　complexity　(or　irregularity)　of　time　series.　Successful　applications　have　been　achieved　in　the　biological　data　analysis,　such　as　heart　rate,　blood　pressure　and　ECG　signals.　The　purpose　of　this　work　is　to　evaluate　the　approximate　entropy　as　a　descriptor　and/or　classifier　of　vibration　signals.　The　results　show　that　the　ApEn　is　able　to　quantify　the　complexity　of　signals,　distinguish　different　running　conditions,　and　provide　an　effective　technology　for　condition　monitoring　and　fault　diagnosis　of　mechanical　equipment.