Title :
Application of Ultrasonic for Pipeline Flaw Detection
Author :
Runjing, Zhou ; Zhangfei
Author_Institution :
Inner Mongolia Univ., Hohhot
Abstract :
The principle of ultrasonic detection and the detection method of the flaw signal are described. Wavelet neural network is used for signal processing of ultrasonic detection. This method that makes full use of characteristic of self-learning for wavelet neural network reduces wave loss. And convergence speed is improved by modifying error function. It is proved that this method has the good effect and acquires exact location of the flaw and amplitude of the flaw signal. Wavelet neural network is the great significance for signal processing of ultrasonic detection.
Keywords :
echo; flaw detection; neural nets; pipelines; signal processing; ultrasonic materials testing; wavelet transforms; echo signal; error function; flaw signal; pipeline flaw detection; self-learning; signal processing; ultrasonic detection; wave loss; wavelet neural network; Frequency; Integral equations; Neural networks; Petroleum; Pipelines; Scattering; Signal analysis; Signal processing; Wavelet analysis; Wavelet transforms; Echo signal; Noise; Wavelet neural network;
Conference_Titel :
Electronic Measurement and Instruments, 2007. ICEMI '07. 8th International Conference on
Conference_Location :
Xi´an
Print_ISBN :
978-1-4244-1136-8
Electronic_ISBN :
978-1-4244-1136-8
DOI :
10.1109/ICEMI.2007.4351186