In this research, we used nondestructive test based on ultrasonic test as inspection method, and made up inspection robot in order to control of ultrasonic probe on the SWP surface, and programmed to signal processing code and pattern classifying code by user made programming code. For evaluation of flaw signal is reflected on welding flaw, user-made program codes are composed of signal processing and probability neural network (PNN) and backpropagation neural network (BPNN). And then, we actually confirmed to the theoretical advantage of each neural network method compared probability neural network with backpropagation neural network for classification and recognition rate. For the application of classifier to SWP inspection system, BPNN classifier is adequate in the first stage. And then, the application of PNN classifier is adequate as the next stage. Because of PNN application need enough sample data that is due to probabilistic density function.
The NAUT technique allows non-contact ultrasonic testing in air. If the NAUT technique can be applied, not only ultrasonic testing in air with no couplant would be possible, but also the stable transmission and reception of ultrasonic waves, which would thus enable ultrasonic testing of hot or cold materials, or rough surfaces of specimens that could not be tested with conventional-contact ultrasonic testing techniques. By trying NAUT for CFRP (carbon fiber-reinforced plastic) specimens, the applicability of NAUT in these areas was observed, and the results from the waveforms of parts of the specimens were analyzed. To verify the usefulness of NAUT, first, artificially defective specimens were tested to investigate the defect detection ability of NAUT; and second, a test was conducted to select the test conditions, the ultrasonic propagation characteristics, and the mode conversion by the material thickness. Both the spot welding and CFRP specimens showed good applicability of NAUT. For the spot welding specimen, the ultrasonic transmittance was highest at the spot-welded part, regardless of the thickness and location of the specimen. For the CFRP specimen, the waveforms of a defective part and a defect-free part were compared, and the existence of delamination was discovered through the increase and decrease in the amplitude. These findings confirmed the practicality (usefulness) of NAUT.
Importance on the detection of corrosion-related defect is undeniable from the fact that it
can prevent significant economic loss and enhanced safety in mechanical equipments, pipes, ships,
bridges, and other applications. Conventionally researched measurement methods for defect and
thinning from corrosion are acoustic emission, EMAT using ultrasound, laser induced ultrasound, etc.
However, these non-destructive testing methods have the shortcoming of accessibility to on-site. For
instance, EMAT should be close to several millimeters to generate magnetic field in structure. For
laser application, it can be applied to remote non-destructive testing, but some defect might not be
possible to be detected by the surface condition of structure. In this study, infrared thermography
camera is utilized to determine the degree of corrosion on paint-coated metal. In addition,
fundamental researches to develop corrosion detection system for on-site metallic structure are
conducted to provide the applicability of IR camera and possibility of thermal analysis method.
The purpose of this research is stability estimation of plant structure through classification and
recognition about welding flaw in SWP(Spiral Welding Pipe). And, In this research, we used
nondestructive test based on ultrasonic test as inspection method, and made up inspection robot in
order to control of ultrasonic probe on the SWP surface, and programmed to signal processing code
and pattern classifying code by user made programming code. Inspection robot is simply
constructed as 2-axes because of welding bead with fixed pitch. So, inspection of welding part can
be possible as composition of inspection part for tracking on welding line. For evaluation of flaw
signal is reflected on welding flaw, user-made program codes are composed of signal processing
and Bayesian classifier and perceptron neural network and back-propagation neural network. And
then, we confirmed to superiority of neural network method compared with Bayesian classifier for
classification and recognition rate. According to this result, we selected back-propagation neural
network 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, and
constructed on the base of the system of SWP stability Estimation for the application in industrial
fields.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.