• Proceedings of the KWS Conference
• /
• 1993.05a
• /
• pp.115-119
• /
• 1993

Many qualitive analyses of sampled process variables have been attempted to predict nugget size in resistance spot welding process. In this paper, dynamic resistance and electrode movement signal which is a good indicative of the nugget size was examined by introducing an artificial neural network estimator. An artificial neural feedforward network with back-propagation of error was applied for the estimation of the nugget size. To assess the advantage of this method. results have been compared with conventional regression method.

• Proceedings of the Korean Society for Bio-Environment Control Conference
• /
• 1994.05a
• /
• pp.92-95
• /
• 1994

과실의 형질을 비파괴적으로 추정하는 방식은 파괴적 추정방식에 비해 연속적으로 측정이 가능하여 생육상태를 상세히 분석할 수 있으며, 같은 과실에 대하여 반복하여 측정할 수 있는 장점을 지닌다는 점에서 생장분석에 유용하게 사용되고 있는 방식이다. 또한 비파괴적 추정은 simulation에 의한 자동화 등에 적용할 수 있어 최적생장조건을 설정하는데 사용되며, 다량의 과실을 자동선별 및 자동수확하는데 이용될 수 있다. (중략)

• Journal of Welding and Joining
• /
• v.16 no.5
• /
• pp.76-85
• /
• 1998

The resistance spot welding process has been used for joining the sheet metal in automotive engineering. In the resistance spot welding, the weld quality is very important, because the quality of weld is one of the most important factors to the automobile quality. The size of he molten nugget has been utilized to estimate the weld quality. However, it is not easy to find the weld defects. For weldability estimation, we have to use the nondestructive method such as X-ray or ultrasonic inspection. But these kinds of approaches are not suitable for detecting the defects in real time. The purpose of this study is to develop the real time monitoring of the weld quality in the resistance spot welding. Obtained data were used to estimate weldability using fuzzy algorithm. It is sound that this monitoring and estimation system can be useful to improve the weld quality in the resistance spot welding process and it is possible to estimate the weldability in real time.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2001.05a
• /
• pp.257-262
• /
• 2001

The objective of this study is to compare compressive strength and rebound number of Schmidt hammer of concrete using basalt aggregate to that using granite aggregate. And is to provide the reference data on the standardization of nondestructive test of concrete. According to test results, compressive strength of concrete using basalt aggregate is highly estimated under the same rebound number compared to that using granite aggregate about 5~15%. It is urgently that newly suggested estimation formula of compressive strength using basalt aggregate must be prescribed because estimation formula of compressive strength of concrete using basalt aggregates overestimates the strength compared to that using granite aggregate.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.6
• /
• pp.37-42
• /
• 2007

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 2-axes inspection robot in order to control of ultrasonic probe on the SWP surface, and programmed to image processing and probabilistic neural network(PNN) classifying code by MATLAB programming. Through this process, we proved efficiency on the system of SWP stability Estimation.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.36 no.5
• /
• pp.384-390
• /
• 2016

It is important to have a pipeline leak-detection system that determines the presence of a leak and quickly identifies its location. Current leak detection methods use a acoustic emission sensors, microphone arrays, and camera images. Recently, many researchers have been focusing on using cameras for detecting leaks. The advantage of this method is that it can survey a wide area and monitor a pipeline over a long distance. However, conventional methods using camera monitoring are unable to target an exact leak location. In this paper, we propose a method of detecting leak locations using leak-detection results combined with multi-frame analysis. The proposed method is verified by experiment.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.22 no.3
• /
• pp.292-303
• /
• 2002

This paper presents experimental results for early-age properties of concrete such as the setting time and strength, evaluated via the ultrasonic pulse velocity (UPV). Developing and using an automatically-recording monitoring system, the UPV's of mortar and concrete with various water to binder ratios (W/B) were measured during the first 24 hours. In addition, probe penetration and compression tests were conducted to measure the setting time and compressive strength, respectively. It was observed that the UPV's of mortar with high W/B remained constant during the first 6.5 hours and then abruptly began to increase at constant rates. On the other hand, the UPV of mortar with low W/B increased relatively slowly and gradually due to the setting retardation caused by the use of high range water reducing agent (HRWR). It was found that setting of concrete occurs when the UPV reaches a certain value. Moreover, it was concluded that the estimation formulas should incorporate the effects of W/B to more accurately estimate the early-age strength of concrete from the UPV.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.30 no.4
• /
• pp.302-310
• /
• 2010

In this paper, we studied Bagging neural network for predicting defect size of steam generator(SG) tube in nuclear power plant. Bagging is a method for creating an ensemble of estimator based on bootstrap sampling. For predicting defect size of SG tube, we first generated eddy current testing signals for 4 defect patterns of SG tube with various widths and depths. Then, we constructed single neural network(SNN) and Bagging neural network(BNN) to estimate width and depth of each defect. The estimation performance of SNN and BNN were measured by means of peak error. According to our experiment result, average peak error of SNN and BNN for estimating defect depth were 0.117 and 0.089mm, respectively. Also, in the case of estimating defect width, average peak error of SNN and BNN were 0.494 and 0.306mm, respectively. This shows that the estimation performance of BNN is superior to that of SNN.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.30 no.4
• /
• pp.359-366
• /
• 2010

For the application of Lamb wave to structural health monitoring(SHM), understanding its physical characteristic and interaction between Lamb wave and defect of the host structure is an important issue. In this study, reflected, transmitted and mode converted Lamb waves at discontinuity of a plate structure were simulated and the amplitude ratios are calculated theoretically using Modal decomposition method. The predicted results were verified comparing with finite element method(FEM) and experimental results simulating attached PZTs. The result shows that the theoretical prediction is close to the FEM and the experimental verification. Moreover, quantitative estimation method was suggested using amplitude ratio of Lamb wave at discontinuity.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.34 no.1
• /
• pp.44-52
• /
• 2014

Leakage is an important factor to be considered for the management of underground water supply pipelines in a smart water grid system, especially if the pipelines are aged and buried under the pavement or various structures of a highly populated city. Because the exact detection of the location of such leaks in pipelines is essential for their efficient operation, a new methodology for leak location detection based on frequency band variation, windowing filters, and probability is proposed in this paper. Because the exact detection of the leak location depends on the precision of estimation of time delay between sensor signals due to leak noise, some window functions that offer weightings at significant frequencies are applied for calculating the improved cross-correlation function. Experimental results obtained by applying this methodology to an actual buried water supply pipeline, ~ 253.9 m long and made of cast iron, revealed that the approach of frequency band variation with those windows and probability offers better performance for leak location detection.