The authors utilize the harmonic wavelet transform and successfully detect minute signs of small fault in a periodic monitored signal. It is important for the effectual detection of the minute signs to reduce the obstructive noise and edge effect. The edge effect is a peculiar phenomenon to wavelet transform and hampers effective detection. The authors devised useful methods to reduce the obstructive noise and the edge effect. Even if no visible information pertaining to a fault appeared in the monitored waveform, a minute sign of a small fault was successfully captured by the proposed method. In this paper, we extend the proposed technique to an important practical application. A fault generated in a gear tooth is focused on. It is demonstrated that our technique is capable of detecting minute signs arising from a small fault in a gear tooth operated in a constant rotating speed.