• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.19 no.7
• /
• pp.7-15
• /
• 2020

Recently, the fourth industrial revolution has been presented as a new paradigm and additive manufacturing (AM) has become one of the most important topics. For this reason, process monitoring for each cross-sectional layer of additive metal manufacturing is important. Particularly, deep learning can train a machine to analyze, optimize, and repair defects. In this paper, image classification is proposed by learning images of defects in the metal cross sections using the convolution neural network (CNN) image labeling algorithm. Defects were classified into three categories: crack, porosity, and hole. To overcome a lack-of-data problem, the amount of learning data was augmented using a data augmentation algorithm. This augmentation algorithm can transform an image to 180 images, increasing the learning accuracy. The number of training and validation images was 25,920 (80 %) and 6,480 (20 %), respectively. An optimized case with a combination of fully connected layers, an optimizer, and a loss function, showed that the model accuracy was 99.7 % and had a success rate of 97.8 % for 180 test images. In conclusion, image labeling was successfully performed and it is expected to be applied to automated AM process inspection and repair systems in the future.

• Structural Engineering and Mechanics
• /
• v.65 no.2
• /
• pp.129-139
• /
• 2018

Post-tensioning (PT) tendons are commonly used for the assembly of modularized concrete members, and tension is applied to the tendons during construction to facilitate the integrated behavior of the members. However, the tension in a PT tendon decreases over time due to steel corrosion and concrete creep, and consequently, the stress on the anchor head that secures the PT tendon also diminishes. This study proposes an automatic detection system to identify tension reduction in a PT tendon using pulsed-eddy-current (PEC) measurement. An eddy-current sensor is installed on the surface of the steel anchor head. The sensor creates a pulsed excitation to the driving coil and measures the resulting PEC response using the pick-up coil. The basic premise is that the tension reduction of a PT tendon results in stress reduction on the anchor head surface and a change in the PEC intensity measured by the pick-up coil. Thus, PEC measurement is used to detect the reduction of the anchor head stress and consequently the reduction of the PT tendon force below a certain threshold value. The advantages of the proposed PEC-based tension-reduction-detection (PTRD) system are (1) a low-cost (< $ 30), low-power (< 2 Watts) sensor, (2) a short inspection time (< 10 seconds), (3) high reliability and (4) the potential for embedded sensing. A 3.3 m long full-scale monostrand PT tendon was used to evaluate the performance of the proposed PTRD system. The PT tendon was tensioned to 180 kN using a custom universal tensile machine, and the tension was decreased to 0 kN at 20 kN intervals. At each tension, the PEC responses were measured, and tension reduction was successfully detected.

• Journal of Biosystems Engineering
• /
• v.39 no.2
• /
• pp.142-149
• /
• 2014

Purpose: A multispectral algorithm for detection and differentiation of defective (defects on apple skin) and normal Red Delicious apples was developed from analysis of a series of hyperspectral line-scan images. Methods: A fast line-scan hyperspectral imaging system mounted on a conventional apple sorting machine was used to capture hyperspectral images of apples moving approximately 4 apples per second on a conveyor belt. The detection algorithm included an apple segmentation method and a threshold function, and was developed using three wavebands at 676 nm, 714 nm and 779 nm. The algorithm was executed on line-by-line image analysis, simulating online real-time line-scan imaging inspection during fruit processing. Results: The rapid multispectral algorithm detected over 95% of defective apples and 91% of normal apples investigated. Conclusions: The multispectral defect detection algorithm can potentially be used in commercial apple processing lines.

• Journal of the Korean Society for Precision Engineering
• /
• v.27 no.2
• /
• pp.70-77
• /
• 2010

This study proposed an auto focusing method for a multi-focus image in assembling lens modules in digital camera phones. A camera module in a camera phone is composed of a lens barrel, an IR glass, a lens mount, a PCB board and aspheric lenses. Alignment among the components is one of the important factors in product quality. Auto-focus is essential to adjust image quality of an IR glass in a lens holder, but there are two focal points in the captured image due to thickness of IR glass. So, sharpness, probability and a scale factor are defined to find desired focus from a multi-focus image. The sharpness is defined as clarity of an image. Probability and a scale factors are calculated using pattern matching with a registered image. The presented algorithm was applied to a lens assembly machine which has 5 axes, two vacuum chucks and an inspection system. The desired focus can be determined on the local maximum of the sharpness, the probability and the scale factor in the experiment.

• Journal of Environmental Science International
• /
• v.19 no.6
• /
• pp.747-753
• /
• 2010

It follows in quality and sewage exclusion method of the investigation objective sector and the Combined Sewer Overflows which is suitable in regional characteristics and the confluence area against the rainfall initially a flow and the medulla and measurement - it analyzes the initial rainfall outflow possibility control plan which is suitable in the domestic actual condition and it proposes the monitor ring plan for the long-term flow and pollution load data accumulation. From the research which it sees the Infiltration water/Influent water and CSOs investigation it passes by the phase of hazard chain and Namwon right time 4 it does not hold reverse under selecting, Measurement it used the hazard automatic flow joint seal Sigma 910 machine and in case 15 minute interval of the I/I, it measured a flow at case 5, 15 minute standing of the CSOs. The water quality investigation for the water leakage investigation of the I/I and the sewage from the point which is identical with flow measurement during on-the-spot inspection duration against 6 items which include the BOD sampling and an analysis, when the rainfall analysis for CSOs fundamental investigation analyzed against 18 items which include the BOD sampling. Consequently, for the optimum interpretation invasion water / inflow water of the this investigation area day average the lowest flow - water quality assessment veterinarian optimum interpretation hazard average per day - lowest flow - it averages a medulla evaluation law department one lowest flow evaluation technique and it selects, it presentation collectively from here it gets, position result with base flow analysis of invasion water / inflow water.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.10a
• /
• pp.363-366
• /
• 2001

The present process of grading leather quality by the rare eyes is not reliable. Because inconsistency of grading due to eyes strain for long time can cause incorrect result of grading. Therefore it is necessary to automate the process of grading quality of leather based on objective standard for it. In this paper, leather automatic classification system consists of the process obtaining the information of leather and the process grading the quality of leather from the information. Leather is graded by its information such as texture density, types and distribution of defects. This paper proposes the algorithm which sorts out leather information like texture density and defects from the gray-level images obtained by digital camera. The density information is sorted out by the distribution value of Fourier spectrum which comes out after original image is converted to the image in frequency domain. And the defect information is obtained by the statistics of pixels which is relevant to Window using searching Window after sort out boundary lines from preprocessed images. The information for entire leather is used as standard of grading leather quality, and the proposed algorithm is practically applied to machine vision system.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2007.11a
• /
• pp.450-454
• /
• 2007

In line with the construction projects, which have been increasingly getting larger and complex, safety accident has been on the rise, particularly those in association with the construction equipment. In a bid to prevent the safety accident, it's needed to analyze the cause of such accidents. The thesis was intended to identify the cause of safety accident by reviewing the cases of construction disaster complied by Korea Occupational Safety and Health Agency. The cases subject to study were limited to the accident by excavator. Summarizing the study is as follows. 1) Among the cause of accidents caused by excavator were, in order of high frequency, being caught in equipment or machine, falling, being crashed or bumped. 2) Among the causes of accident were, in order of high frequency, worker's unauthorized presence within the range of equipment operation. inappropriate use, failure of equipment inspection prior to starting work and inappropriate work method. The study is highly expected to pave the foundation for further study as well as to make commitment to mitigating the safety accident.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.3
• /
• pp.499-505
• /
• 2018

Shipping and logistics safety, security system is strengthening worldwide, the development of shipping and logistics safety security core technology for national security logistics system construction has been carried out. In addition, it is necessary to localize the Array Detection System, which is a core component of the container search machine, to cope with the 100% pre-inspection of the container scheduled for 2018 in the United States. In this research, we propose a test software program developed by using TI-RTOS (Texas Instruments - Real Time Operating System) with a test digital signal processing board which is developed self development. We have developed a program that can test GPIO, SRAM, TCP/IP, and SDcard using M4 MCU. Also we propose a study on a self-developed Digital Signal Processing Board among the array detection systems that replace foreign products. We have developed a test board that can test M4 MCU and developed an X-Ray Detector Digital Signal Processing Board that combines MCU and FPGA.

• Journal of Advanced Navigation Technology
• /
• v.23 no.5
• /
• pp.481-486
• /
• 2019

Smart Factory requires real-time monitoring and analysis of all process processes for optimal production environment. Monitoring system for data collection from various sensors is necessary to make all production processes automatic. By storing and analyzing the collected data, we can check whether there are any signs of abnormalities in any machine or equipment. Thus, in this paper, an integrated monitoring system for smart factory incorporating a working environment monitoring system and an automatic storage system of measurement values was implemented. By using the automatic storage system of measurement values, it is possible to carry out reliable inspection in any place without misentry. Also, through working environment monitoring system using LoRa, production environments such as temperature, humidity and atmospheric pressure can be monitored in real time.

• Smart Structures and Systems
• /
• v.24 no.5
• /
• pp.567-585
• /
• 2019

In the past two decades, structural health monitoring (SHM) systems have been widely installed on various civil infrastructures for the tracking of the state of their structural health and the detection of structural damage or abnormality, through long-term monitoring of environmental conditions as well as structural loadings and responses. In an SHM system, there are plenty of sensors to acquire a huge number of monitoring data, which can factually reflect the in-service condition of the target structure. In order to bridge the gap between SHM and structural maintenance and management (SMM), it is necessary to employ advanced data processing methods to convert the original multi-source heterogeneous field monitoring data into different types of specific physical indicators in order to make effective decisions regarding inspection, maintenance and management. Conventional approaches to data analysis are confronted with challenges from environmental noise, the volume of measurement data, the complexity of computation, etc., and they severely constrain the pervasive application of SHM technology. In recent years, with the rapid progress of computing hardware and image acquisition equipment, the deep learning-based data processing approach offers a new channel for excavating the massive data from an SHM system, towards autonomous, accurate and robust processing of the monitoring data. Many researchers from the SHM community have made efforts to explore the applications of deep learning-based approaches for structural damage detection and structural condition assessment. This paper gives a review on the deep learning-based SHM of civil infrastructures with the main content, including a brief summary of the history of the development of deep learning, the applications of deep learning-based data processing approaches in the SHM of many kinds of civil infrastructures, and the key challenges and future trends of the strategy of deep learning-based SHM.