Distinguishing Defective Anchor Bolts with Features Extracted from Ultrasonic Signal

Abstract

Regular inspection on the condition of civil structure is critical to ensure structural integrity, prevent catastrophic failure and minimize downtime for emergency repair. Hitherto, the inspection on the anchor bolts relies on visual observation, which does not provide sufficient information to distinguish between normal and defective bolts. This paper aims to explore the classification of different types of defective anchor bolts based on ultrasonic signal through discrete wavelet transform (DWT). Multiple features are extracted from the ultrasonic signal to identify defective anchor bolts, thus improving the reliability of the inspection process.