Condition monitoring of roller bearings using acoustic emission

Abstract. Roller bearing failures in wind turbines' gearboxes lead to long downtimes and high repair costs, which could be reduced by the implementation of a predictive maintenance strategy. In this paper within context, an acoustic-emission-based condition monitoring system is applied roller test rigs with aim identifying critical operating conditions before occurs. Furthermore, comparison regarding detection times carried out traditional vibration-based systems, focus on premature such as white etching cracks. The investigations show sensitivity acoustic-emission towards lubricating conditions. addition, has shown that damaged surface can detected at least ? 4 % (8 h, time failure) earlier than using system. significant deviations from average signal were up 50 (130 h) stop are possibly related sub-surface damage initiation might result future.