• The KIPS Transactions:PartA
• /
• v.17A no.2
• /
• pp.81-92
• /
• 2010

There has been some research in the equipment defect detection based on vibration information. Most research of them is based on vibration monitoring to determine the equipment defect or not. In this paper, we introduce more accurate system for engine defect detection based on vibration information and we focus on detection of engine defect for boat and system control. First, it uses the duplicated-checking method for vibration information to determine the engine defect or not. If there is a defect happened, we use the method using error part of vibration information basis with error range to determine which kind of error is happened. On the other hand, we use the engine trend analysis and standard of safety engine to implement the vibration information database. Our simulation results show that the probability of engine defect determination is 100% and the probability of engine defect classification and detection is 96%.

• IE interfaces
• /
• v.21 no.2
• /
• pp.151-160
• /
• 2008

Defect size distribution is a probability density function for the defects that occur on wafers or glasses during semiconductor/LCD fabrication. It is one of the most important information to estimate manufacturing yield using well-known statistical estimation methods. The defects are detected by automatic optical inspection (AOI) facilities. However, the data that is provided from AOI is not accurate due to resolution of AOI and its defect detection mechanism. It causes distortion of defect size distribution and results in wrong estimation of the manufacturing yield. In this paper, I suggest a size conversion method and a maximum likelihood estimator to overcome the vague defect size information of AOI. The methods are verified by the Monte Carlo simulation that is constructed as similar as real situation.

• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.273-275
• /
• 2005

Active thermography is being used since several years for remote non-destructive testing. It provides thermal images for remote detection and imaging of damages. Also, it is based on propagation and reflection of thermal waves which are launched from the surface into the inspected component by absorption of modulated radiation. For energy deposition, it use external heat sources (e.g., halogen lamp or convective heating) or internal heat generation (e.g., microwaves, eddy current, or elastic wave). Among the external heat sources, the ultrasound is generally used for energy deposition because of defect selective heating up. The heat source generating a thermal wave is provided by the defect itself due to the attenuation of amplitude modulated ultrasound. A defect causes locally enhanced losses and consequently selective heating up. Therefore amplitude modulation of the injected ultrasonic wave turns a defect into a thermal wave transmitter whose signal is detected at the surface by thermal infrared camera. This way ultrasound thermography(UT) allows for selective defect detection which enhances the probability of defect detection in the presence of complicated intact structures. In this paper the applicability of UT for fast defect detection is described. Examples are presented showing the detection of defects in PCB material. Measurements were performed on various kinds of typical defects in PCB materials (both Cu metal and non-metal epoxy). The obtained thermal image reveals area of defect in row of thick epoxy material and PCB.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.4
• /
• pp.577-586
• /
• 2022

Detection and classification of steel surface defects are critical for product quality control in the steel industry. However, due to its low accuracy and slow speed, the traditional approach cannot be effectively used in a production line. The current, widely used algorithm (based on deep learning) has an accuracy problem, and there are still rooms for development. This paper proposes a method of steel surface defect detection combining EfficientNetV2 for image classification and YOLOv5 as an object detector. Shorter training time and high accuracy are advantages of this model. Firstly, the image input into EfficientNetV2 model classifies defect classes and predicts probability of having defects. If the probability of having a defect is less than 0.25, the algorithm directly recognizes that the sample has no defects. Otherwise, the samples are further input into YOLOv5 to accomplish the defect detection process on the metal surface. Experiments show that proposed model has good performance on the NEU dataset with an accuracy of 98.3%. Simultaneously, the average training speed is shorter than other models.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.5
• /
• pp.615-621
• /
• 2009

TFT-LCD image consists of ununiform background, random noises and target defect signal components. Defects in TFT-LCD have some intensity variations compared to background region. It is sometimes difficult for human inspectors to figure out. In this paper, we propose multi-level threshold scheme for detection of the real defect using probability density function with Parzen Window. The experimental results show that the proposed algorithms produce promising results and can be applied to automated inspection systems for finding defects in the TFT-LCD image.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.5
• /
• pp.415-419
• /
• 2008

Detecting and correcting defects on LCD glasses early in the manufacturing process becomes important for panel makers to reduce the manufacturing costs and to improve productivity. Many attempts have been made and were successfully applied to detect and identify simple defects such as scratches, dents, and foreign objects on glasses. However, it is still difficult to robustly detect low-contrast defect region, called Mura or blemish area on glasses. Typically, these defect areas are roughly defined as relatively large, several millimeters of diameter, and relatively dark and/or bright region of low Signal-to-Noise Ratio (SNR) against background of low-frequency signal. The aim of this article is to present a robust algorithm to segment these blemish defects. Early 90's, a highly robust estimator, known as the Model-Fitting (MF) estimator was developed by X. Zhuang et. al. and have been successfully used in many computer vision application. Compared to the conventional Least-Square (LS) estimator the MF estimator can successfully estimate model parameters from a dataset of contaminated Gaussian mixture. Such a noise model is defined as a regular white Gaussian noise model with probability $1-\varepsilon$ plus an outlier process with probability $varepsilon$. In the sense of robust estimation, the blemish defect in images can be considered as being a group of outliers in the process of estimating image background model parameters. The algorithm developed in this paper uses a modified MF estimator to robustly estimate the background model and as a by-product to segment the blemish defects, the outliers.

• Journal of the Semiconductor & Display Technology
• /
• v.16 no.2
• /
• pp.1-8
• /
• 2017

The visual inspection of electronic parts consists of two steps: automatic visual inspection and verification inspection. In the stage of a verification inspection, the human inspector sequentially inspects all the areas which detected in the automatic inspection. In this study, we propose an algorithm to determine the order of verification inspection by Bayes inference well known in the field of machine learning. This is a method of prioritizing a region estimated to have a high probability of defect using experience data of past inspection. This algorithm was applied to the visual inspection of ultraviolet filters to verify its effectiveness. As a result of the comparison experiment, it was confirmed that the verification inspection can be completed 30% of the conventional method by adapting proposed algorithm.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.946-949
• /
• 2005

This paper deals with the algorithm development that inspects defects such as Bright Defect Dots, Dark Defect Dots, and Line Defect caused by the process of LCD(Liquid Crystal Display). While most of LCD production process is automated, the inspection of LCD panel and its appearance depends on manual process. So, the quality of the inspection is affected by the condition of worker. Especially, the more LCD size increases, the more the worker feels fatigued, which causes the probability of miss judgement. So, the automated inspection is required to manage the consistent quality of the product and reduce the production costs. In this paper, to solve these problems, we developed the imaging processing algorithm to inspect the defects in captured image of LCD. Experimental results reveal that we can recognize various types of defect of LCD with good accuracy and high speed.

• Smart Structures and Systems
• /
• v.11 no.3
• /
• pp.299-314
• /
• 2013

This paper presents a nonlinear time series analysis technique for evaluating machine defect severity, based on the Recurrence Plot (RP) entropy. The RP entropy is calculated from the probability distribution of the diagonal line length in the recurrence plot, which graphically depicts a system's dynamics and provides a global picture of the autocorrelation in a time series over all available time-scales. Results of experimental studies conducted on a spindle-bearing test bed have demonstrated that, as the working condition of the bearing deteriorates due to the initiation and/or progression of structural damages, the frequency information contained in the vibration signal becomes increasingly complex, leading to the increase of the RP entropy. As a result, RP entropy can serve as an effective indicator for defect severity assessment of rolling bearings.

• Bulletin of the Korean Chemical Society
• /
• v.19 no.5
• /
• pp.544-548
• /
• 1998

A Monte Carlo simulation incorporated with the genetic algorithm is presented to describe the defect known as "transition from Y-to X-type deposition" of the cadmium arachidate Langmuir-Blodgett multilayer film. Simulation is performed based on the detachment models of XY-type deposition. The transition is simulated by introducing a probability of surface molecule detachment considering interaction between neighboring molecules. The genetic algorithm is incorporated into Monte Carlo simulation to get the optimum value of the probability factors. The distribution of layers having different thickness predicted by the simulation correlates well with the measured distribution of thickness using the small-angle X-ray reflectivity. The effect of chain length and subphase temperature on the detachment probability are investigated using the simulation. Simulation results show that an increase (or a decrease) of two hydrocarbon chain is roughly equivalent to the detachment probability to a temperature decrease (or increase) of 15 K.