• Journal of Advanced Navigation Technology
• /
• v.26 no.2
• /
• pp.113-118
• /
• 2022

Motivated by people highlighting important phrases while reading or taking notes we propose a neural network training method by highlighting defective pixel areas to classify effectively defect types of images with complex background textures. To verify our proposed method we apply it to the problem of classifying the defect types of tire band fabric images that are too difficult to classify. In addition we propose a backlight highlighting technique which is tailored to the tire band fabric images. Backlight highlighting images can be generated by using both the GradCAM and simple image processing. In our experiment we demonstrated that the proposed highlighting method outperforms the traditional method in the view points of both classification accuracy and training speed. It achieved up to 13.4% accuracy improvement compared to the conventional method. We also showed that the backlight highlighting technique tailored for highlighting tire band fabric images is superior to a contour highlighting technique in terms of accuracy.

• Smart Structures and Systems
• /
• v.19 no.2
• /
• pp.195-202
• /
• 2017

The aim of this paper is to develop a novel method to determine the severity of a damage in a thin plate. This paper presents a novel fault detection and diagnosis approach employing a new electromagnetic acoustic transducer, called EMAT, together with a complex signal processing method. The method consists in the recognition of a fault that exists within the structure, the fault location, i.e. the identification of the geometric position of damage, and the determining the significance of the damage, which indicates the importance or severity of the defect. The main scientific novelties presented in this paper is: to develop of a new type of electromagnetic acoustic transducer; to incorporate wavelet transforms for signal representation enhancements; to investigate multi-parametric analysis for noise identification and defect classification; to study attenuation curves properties for defect localization improvement; flaw sizing and location algorithm development.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.5
• /
• pp.785-796
• /
• 2023

In this study, a methodology for real-time classification and prediction of defects that may appear in PVDF(Polyvinylidene fluoride) sensors, which are widely used for structural integrity monitoring, is proposed. The types of sensor defects appearing according to the sensor attachment environment were classified, and an impact test using an impact hammer was performed to obtain an output signal according to the defect type. In order to cleary identify the difference between the output signal according to the defect types, the time domain statistical features were extracted and a data set was constructed. Among the machine learning based classification algorithms, the learning of the acquired data set and the result were analyzed to select the most suitable algorithm for detecting sensor defect types, and among them, it was confirmed that the highest optimization was performed to show SVM(Support Vector Machine). As a result, sensor defect types were classified with an accuracy of 92.5%, which was up to 13.95% higher than other classification algorithms. It is believed that the sensor defect prediction technique proposed in this study can be used as a base technology to secure the reliability of not only PVDF sensors but also various sensors for real time structural health monitoring.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.4_2
• /
• pp.687-697
• /
• 2022

An automated system is needed for the effectiveness of non-destructive testing. In order to utilize the radiographic testing data accumulated in the film, the types of welding defects were classified into 9 and the shape of defects were analyzed. Data was preprocessed to use deep learning with high performance in image classification, and a combination of one-stage/two-stage method and convolutional neural networks/Transformer backbone was compared to confirm a model suitable for welding defect detection. The combination of two-stage, which can learn step-by-step, and deep-layered CNN backbone, showed the best performance with mean average precision 0.868.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2010.06a
• /
• pp.102-102
• /
• 2010

A purpose of this paper is to recognize partial discharge pattern for cable insulation. The classification of PD sources was widely studied for two decades. this research sought to use the partial discharge detection method, and to diagnose the interface of cable, which is deemed vulnerable of cable systems. A research abalyzed faults that can occur in the interface of cable joint as well as accident mechanisms, manufactured test 22.9kV CNC cable, invented artificial faults and carried out partial discharge detection experiments. As a result, various PD pattern along defect measured and distinguished.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.13-14
• /
• 2020

본 논문에서는 엣지 컴퓨팅 환경에서 머신러닝을 활용해 에스컬레이터 이상 감지 및 결함 분류를 하는 연구를 진행하였다. 엣지 컴퓨팅 기반 머신러닝을 사용해 에스컬레이터의 이상 감지 및 결함 분류를 위한 OneM2M환경을 구축하였으며 에스컬레이터에서 발생하는 소음에서 고장 유형에 따라 나타나는 주파수를 이용한다. Edge TPU를 활용해 엣지 컴퓨팅 시스템의 처리량을 최대화하고, 각 작업의 수행시간을 최소화함으로써 엣지 컴퓨팅 환경에서 이상 감지와 결함 분류를 수행할 수 있다.

• Journal of the Korean Society of Safety
• /
• v.15 no.2
• /
• pp.1-7
• /
• 2000

This paper presents the approach involving fault detection and diagnosis of gears using pattern recognition and Wavelet transform. It describes result of the comparison between KDI (Kullback Discrimination Information) with the nearest neighbor classification rule as one of pattern recognition methods and Wavelet transform to know a way to detect and diagnosis of gear damages experimentally. To model the damages 1) Normal (no defect), 2) one tooth is worn out, 3) All teeth faces are worn out 4) One tooth is broken. The vibration sensor was attached on the bearing housing. This produced the total time history data that is 20 pieces of each condition. We chose the standard data and measure distance between standard and tested data. In Wavelet transform analysis method, the time series data of magnitude in specified frequency (rotary and mesh frequency) were earned. As a result, the monitoring system using Wavelet transform method and KDI with nearest neighbor classification rule successfully detected and classified the damages from the experimental data.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.82-84
• /
• 2021

Through the smart factory construction project, sensor data such as power, vibration, pressure, and temperature are collected from production facilities, and services such as predictive maintenance, defect prediction, and abnormality detection are developed through data analysis. In general, in the case of manufacturing data, because the imbalance between normal and abnormal data is extreme, an anomaly detection service is preferred. In this paper, FFT method is used to extract feature data of manufacturing data as a pre-stage of the anomaly detection service development. Using this method, we classified the produced products and confirmed results. In other words, after FFT of the representative pattern for each product, we verified whether product classification was possible or not, by calculating correlation coefficient.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3608-3626
• /
• 2021

The detection of bolts is an important task in high-speed train inspection systems, and it is frequently performed to ensure the safety of trains. The difficulty of the vision-based bolt inspection system lies in small sample defect detection, which makes the end-to-end network ineffective. In this paper, the problem is resolved in two stages, which includes the detection network and cascaded classification networks. For small bolt detection, all bolts including defective bolts and normal bolts are put together for conducting annotation training, a new loss function and a new boundingbox selection based on the smallest axis-aligned convex set are proposed. These allow YOLOv3 network to obtain the accurate position and bounding box of the various bolts. The average precision has been greatly improved on PASCAL VOC, MS COCO and actual data set. After that, the Siamese network is employed for estimating the status of the bolts. Using the convolutional Siamese network, we are able to get strong results on few-shot classification. Extensive experiments and comparisons on actual data set show that the system outperforms state-of-the-art algorithms in bolt inspection.

• Journal of the Korean Society for Precision Engineering
• /
• v.15 no.7
• /
• 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.