• 제어로봇시스템학회논문지
• /
• 제2권4호
• /
• pp.337-343
• /
• 1996

In this paper, we investigate the defect detection by making use of pre-made reference image data and classify the defects by using the artificial neural network. The approach is composed of three main parts. The first step consists of a proper generation of two reference image data by using a low level morphological technique. The second step proceeds by performing three times logical bit operations between two ready-made reference images and just captured image to be tested. This results in defects image only. In the third step, by extracting four features from each detected defect, followed by assigning them into the input nodes of an already trained artificial neural network we can obtain a defect class corresponding to the features. All of the image data are formed in a bit level for the reduction of data size as well as time saving. Experimental results show that proposed algorithms are found to be effective for flexible defect detection, robust classification, and high speed process by adopting a simple logic operation.

• Journal of Welding and Joining
• /
• 제16권3호
• /
• pp.64-73
• /
• 1998

This paper is concerned with defects detection and evaluation of heat affected zone (HAZ) in austenitic stainless steel type 304 by ultrasonic wave and neural network. In experiment, the reflected ultrasonic defect signals from artificial defects (side hole, vertical hole, notch) of HAZ appears as beam distance of prove-defect, distance of probe-surface, depth of defect-surface on CRT. For defect classification simulation, neural network system was organized using total results of ultrasonic experiment. The organized neural network system was learned with the accuracy of 99%. Also it could be classified with the accuracy of 80% in side hole, and 100% in vertical hole, 90% in notch about ultrasonic pattern recognition. Simulation results of neural network agree fairly well with results of ultrasonic experiment. Thus were think that the constructed system (ultrasonic wave - neural network) in this work is useful for defects dection and classification such as holes and notches in HAZ of austenitic stainless steel 304.

• 한국생산제조학회지
• /
• 제6권4호
• /
• pp.46-53
• /
• 1997

This paper presents a method of detection localized defects on tapered roller bearing in main spindle of machine tool system. The feature vectors, i.e. statistical parameters, in time-domain analysis technique have been calculated to extract useful features from acoustic emission signals. These feature vectors are used as the input feature of an neural network to classify and detect bearing defects. As a results, the detection of bearing defect conditions could be sucessfully performed by using an neural network with statistical parameters of acoustic emission signals.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.108-111
• /
• 2022

제품의 결함 탐지를 위한 머신 비전 시스템에 딥러닝을 적용하기 위해서는 다양한 결함 사례에 대한 방대한 학습 데이터가 필요하다. 하지만 실제 제조 산업에서는 결함의 종류에 따른 데이터 불균형이 생기기 때문에 결함 사례를 일반화할 수 있을 만큼의 제품 이미지를 수집하기 위해서는 많은 시간이 소요된다. 본 논문에서는 적은 데이터로도 학습이 가능한 샴 신경망을 제품 결함 탐지에 적용하고, 제품 결함 이미지 데이터의 속성을 고려하여 이미지 쌍 구성법과 대조 손실 함수를 수정하였다. AUC-ROC로 샴 신경망의 임베딩 성능을 간접적으로 확인한 결과, 같은 제품끼리만 쌍을 구성하고 결함이 있는 제품 간에는 쌍을 구성하였을 때, 그리고 지수 대조 손실로 학습하였을 때 좋은 임베딩 성능을 보였다.

• 한국정밀공학회지
• /
• 제15권7호
• /
• pp.149-159
• /
• 1998

The importance of soundness and safety evaluation in weld zone using by the ultrasonic wave has been recently increased rapidly because of the collapses of huge structures and safety accidents. Especially, the ultrasonic method that has been often used for a major non-destructive testing(NDT) technique in many engineering fields plays an important role as a volume test method. Hence, the defecting any defects of weld Bone in austenitic stainless steel type 304 using by ultrasonic wave and neural network is explored in this paper. In order to detect defects, a distance amplitude curve on standard scan sensitivity and preliminary scan sensitivity represented of the relation between ultrasonic probe, instrument, and materials was drawn based on a quantitative standard. Also, a total of 93％ of defect types by testing 30 defect patterns after organizing neural network system, which is learned with an accuracy of 99％, based on ultrasonic evaluation is distinguished in order to classify defects such as holes or notches in experimental results. Thus, the proposed ultrasonic wave and neural network is useful for defect detection and Ultrasonic Non-Destructive Evaluation(UNDE) of weld zone in austenitic stainless steel 304.

• 전자공학회논문지 IE
• /
• 제48권2호
• /
• pp.26-31
• /
• 2011

본 논문에서는 LCD 제조공정 상에서 발생할 수 있는 결함을 검사하고 분류할 수 있는 적응적인 LCD 표면 결함 검사 시스템을 제안하였다. 즉, 반복되는 LCD 패턴의 주기를 확정한 후에 결함 패턴을 검출하고 검출된 결함 패턴의 특징을 계산하여 결함을 분류하였다. 그리고 결함을 검출하는 과정에서 발생하는 잡음은 모폴로지 연산자를 이용하여 제거하였다. 또한, 검출된 결함 패턴에서 기하학적인 특징과 통계적 특징을 계산한 후 신경회로망 알고리즘을 이용하여 여러 종류의 결함 패턴을 적응적으로 분류하였으며, 실험 결과 92.3%의 결함 검출율 및 94.5%의 결함 분류 및 인식율을 획득함으로써, LCD 결함 검사 시스템의 실질적인 구현 가능성을 제시하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권1호
• /
• pp.245-265
• /
• 2022

In response to problems such as insufficient extraction information, low detection accuracy, and frequent misdetection in the field of Thangka image defects, this paper proposes a YOLOv5 prediction algorithm fused with the attention mechanism. Firstly, the Backbone network is used for feature extraction, and the attention mechanism is fused to represent different features, so that the network can fully extract the texture and semantic features of the defect area. The extracted features are then weighted and fused, so as to reduce the loss of information. Next, the weighted fused features are transferred to the Neck network, the semantic features and texture features of different layers are fused by FPN, and the defect target is located more accurately by PAN. In the detection network, the CIOU loss function is used to replace the GIOU loss function to locate the image defect area quickly and accurately, generate the bounding box, and predict the defect category. The results show that compared with the original network, YOLOv5-SE and YOLOv5-CBAM achieve an improvement of 8.95% and 12.87% in detection accuracy respectively. The improved networks can identify the location and category of defects more accurately, and greatly improve the accuracy of defect detection of Thangka images.

• 반도체디스플레이기술학회지
• /
• 제20권3호
• /
• pp.125-130
• /
• 2021

Scaffold is used to produce bio sensor. Scaffold is required high dimensional accuracy. 3D printer is used to manufacture scaffold. 3D printer can't detect defect during printing. Defect detection is very important in scaffold printing. Real-time defect detection is very necessary on industry. In this paper, we proposed the method for real-time scaffold defect detection. Real-time defect detection model is produced using CNN(Convolution Neural Network) algorithm. Performance of the proposed model has been verified through evaluation. Real-time defect detection system are manufactured on hardware. Experiments were conducted to detect scaffold defects in real-time. As result of verification, the defect detection system detected scaffold defect well in real-time.

• 한국정밀공학회지
• /
• 제12권5호
• /
• pp.33-39
• /
• 1995

This paper presents a method of detecting localized defects on tapered roller bearing in main spindle of machine tool system. The statistical parameters in time-domain processing technique have been calculated to extract useful features from bearing vibration signals. These features are used by the input feature of an artificial neural network to detect and diagnose bearing defects. As a results, the detection of bearing defect conditions could be successfully performed by using an artificial neural network with statistical parameters of acceleration signals.

• 반도체디스플레이기술학회지
• /
• 제15권3호
• /
• pp.18-23
• /
• 2016

QFN (Quad Flat No-leads Package) is one of the SMD (Surface Mount Device). Since there is no lead in QFN, there are many defects on solder. Therefore, we propose an efficient mechanism for QFN solder defect detection at this paper. For this, we employ Convolutional Neural Network (CNN) of the Machine Learning algorithm. QFN solder's color multi-layer images are used to train CNN. Since these images are 3-channel color images, they have a problem with applying to CNN. To solve this problem, we used each 1-channel grayscale image (Red, Green, Blue) that was separated from 3-channel color images. We were able to detect QFN solder defects by using this CNN. In this paper, it is shown that the CNN is superior to the conventional multi-layer neural networks in detecting QFN solder defects. Later, further research is needed to detect other QFN.