ISSN:
1013-9826
Source:
Scientific.Net: Materials Science & Technology / Trans Tech Publications Archiv 1984-2008
Topics:
Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
Notes:
The purpose of this research is stability estimation of plant structure through classification andrecognition about welding flaw in SWP(Spiral Welding Pipe). And, In this research, we usednondestructive test based on ultrasonic test as inspection method, and made up inspection robot inorder to control of ultrasonic probe on the SWP surface, and programmed to signal processing codeand pattern classifying code by user made programming code. Inspection robot is simplyconstructed as 2-axes because of welding bead with fixed pitch. So, inspection of welding part canbe possible as composition of inspection part for tracking on welding line. For evaluation of flawsignal is reflected on welding flaw, user-made program codes are composed of signal processingand Bayesian classifier and perceptron neural network and back-propagation neural network. Andthen, we confirmed to superiority of neural network method compared with Bayesian classifier forclassification and recognition rate. According to this result, we selected back-propagation neuralnetwork as classification and recognition method about the system of SWP stability Estimation[2].Through this process, we proved efficiency on the system of SWP stability Estimation, andconstructed on the base of the system of SWP stability Estimation for the application in industrialfields
Type of Medium:
Electronic Resource
URL:
http://www.tib-hannover.de/fulltexts/2011/0528/01/47/transtech_doi~10.4028%252Fwww.scientific.net%252FKEM.261-263.1385.pdf
Permalink