A hardware/software co-design architecture for ultrasonic flaw detection with Hidden Markov Model and wavelet transform

摘要

This work presents an embedded hardware architecture for real-time ultrasonic NDE applications that incorporate Hidden Markov Model (HMM) based statistical signal methods. HMM has been successfully used in applications like audio segment retrieval, speech/language recognition and image processing applications. Recently, we proposed a new Hidden Markov Model (HMM) based ultrasonic flaw detection algorithm which can not only detect the presence of flaw echoes but also determine the exact location of the flaw within the A-scans. The proposed method is computationally complex and it also involves a supervised training phase for determining the algorithm parameters.