• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.181-189
• /
• 2023

In this paper, we present a case study of developing MVIS (Machine Vision Inspection System) designed for exterior quality inspection of stamping dies used in the production of automotive exterior components in a small to medium-sized factory. While the primary processes within the factory, including machining, transportation, and loading, have been automated using PLCs, CNC machines, and robots, the final quality inspection process still relies on manual labor. We implement the MVIS with general-purpose industrial cameras and Python-based open-source libraries and frameworks for rapid and low-cost development. The MVIS can play a major role on improving throughput and lead time of stamping dies. Furthermore, the processed inspection images can be leveraged for future process monitoring and improvement by applying deep learning techniques.

• The KIPS Transactions:PartD
• /
• v.10D no.4
• /
• pp.727-734
• /
• 2003

Recently various quality assurance activities have been applied in software industry for the purpose of software qualify improvement, and the ultimate target of those activities are focused on removing defects from its developed applications. We declared "ZERO DEFECT 21" movement on March 1999 whose purpose is to deliver defect-free applications to the customer. In this paper we would like to introduce the followings $\circled1$ Approaching Methods, $\circled2$ Achievements of "ZERO DEFECT 21". After accomplishing first you of "ZERO DEFECT 21" movement which consist of Audits and Software inspections, we could get the following improvement . $\circled1$ due to conducting the "Audits," we could prevent 22 cases of customer claims, enhance 11.7% of design quality and improve 23.3% of deliverable reusability : $\circled2$ also, due to conducting the "Periodic Sampling inspection and Final inspection," we could enhance 123% of defect rate compared with early stage of development and 247% of defect rate compared with previous yew. Based on the survey results, we could conclude that "ZERO DEFECT 21 " movement provides confidence to project team members and reliability to our customers.ce to project team members and reliability to our customers.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.18 no.35
• /
• pp.1-8
• /
• 1995

Automatic inspection system software for display image characteristic of CRT is developed. There are two major contributions of this software development. One is that the data from measuring equipments which was usually collected manually is automatically collected through RS-232C port and is saved in computer, then, trend analysis graph and final reports are generated. The other is that evauation of characteristic of electron gun was automatically processed by CCD camera and image processing technique. The system is developed under MS-Windows environment utilizing Borland C++4.0 Compiler and DT 3852-8 image processor board. This system can save the time and man power to measure and to anayze the image characteristics relative to current method.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.40 no.2
• /
• pp.126-131
• /
• 2004

On-machine automatic measuring software from 3-D solid modeler is generally applied to assess the functional performance of a final produce for computer numerical control (CNC) machine. Automatic measuring software may also be performed on individual components of CNC machine in which some functional aspect of the component must be examined and cannot be implicity determined by means of a mechanical inspection. The manufacturing specialist, combined with the appropriate software simulation, can not only create the commands to drive the virtual measuring but also can check for mistakes by viewing the computer graphics simulation of the tool cutting sequence.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.27 no.3
• /
• pp.416-423
• /
• 2003

During the last ten years, the need has been increased for reducing maintenance cost for aged equipments and ensuring safety, efficiency and profitability of petrochemical and refinery plants. RBI (Risk Based Inspection) methodology is one of the most promising technologies satisfying the need in the field of integrity management. In this study, a user-friendly software, realRBl for RBI based on the API 581 code was developed. This software has modules for evaluating qualitative and semi-quantitative risk level, analyzing quantitative risks using the potential consequences of a failure of the pressure boundary, and assessing the likelihood of failure. A quantitative analysis was performed for 16 columns in a domestic NCC (Naphtha Cracking Center) plant whose operating time reaches about 12 years. Each column was considered as two equipment parts by dividing into top and bottom. Generic column failure frequencies were adjusted based on likelihood data. After determining release rate, release duration and release mass for each failure scenario, flammable/explosive and toxic consequences were assessed. Current risks for 32 equipment parts were evaluated and risk based prioritization were determined as a final result.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.11 no.1
• /
• pp.1-9
• /
• 2002

Reverse engineering is an emerging technology to obtain CAD models from existing physical parts in the case that CAD models are not available or paras are changed an(1 modified so that new CAD models for final parts are necessary. Reverse engineering helps designers to quickly generate computer interpretable data from existing Physical objects So it is applying for field of Rapid Prototyping NC Processing CAE, Inspection and so on. The objective of this study is to develop the software that deals with unorganized point data and quickly obtains CAD model. In this paper, several models such as human\`s bone, car, are experimented by the proposed methods.

• Agricultural and Biosystems Engineering
• /
• v.1 no.2
• /
• pp.106-110
• /
• 2000

An integrated on-line inspection system was constructed with seven cameras, half mirrors to split images. 720 nm and 970 nm band pass filters, illumination chamber having several tungsten-halogen lamps, one main computer, one color frame grabber, two 4-channel multiplexors, and flat plate conveyer, etc. A total of seven images, that is, one color image form the top of an apple and two B/W images from each side (top, right and left) could be captured and displayed on a computer monitor through the multiplexor. One of the two B/W images captured from each side is 720nm filtered image and the other is 970 nm. With this system an on-line grading software was developed to evaluate appearance quality. On-line test results with Fuji apples that were manually fed on the conveyer showed that grading accuracies of the color, defect and shape were 95.3%, 86% and 88.6%, respectively. Grading time was 0.35 second per apple on an average. Therefore, this on-line grading system could be used for inspection of the final products produced from an apple sorting system.

• Transactions of the Korean Society of Pressure Vessels and Piping
• /
• v.7 no.3
• /
• pp.40-47
• /
• 2011

KSNPs(Korea Standard Nuclear Power Plant) have been applied the break exclusion criteria to the high energy lines passing through containment penetration area to ensure that piping failures would not cause the loss of containment isolation function, and to reduce the resulting dynamic effects. Systems with the criteria are the Main Steam system, Feed Water system, Steam Generator Blowdown system, and Chemical & Volume Control system. In accordance with FSAR(Final Safety Analysis Report), a 100% volumetric examination by augmented in-service inspection of all pipe welds appled the break exclusion criteria is required for the break exclusion application piping. However, it is difficult to fully satisfy the requirements of inspection because 12", 8" and 6" weldolet weldments of Main Steam pipe line have complex structural shapes. To resolve the difficulty on the application of conventional UT(Ultrasonic Testing) technique, realistic mock-ups and UT calibration blocks were made. Simulations of conventional UT were performed utilizing CIVA, a commercial NDE(Nondestructive Examination) simulation software. Phased array UT experiments were performed through mock-up including artificial notch type flaws. A phased array UT technique is finally developed to improve the reliability of ultrasonic test at main steam line pipe to 12", 8" and 6" branch connection weld.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2000.11c
• /
• pp.551-559
• /
• 2000

An integrated on-line inspection system was constructed with seven cameras, half mirrors to split images, 720 nm and 970 nm band pass filters, illumination chamber having several tungsten-halogen lamps, one main computer, one color frame grabber, two 4-channel multiplexors, and flat plate conveyer, etc., so that a total of seven images, that is, one color image from the top side of an apple and two B/W images from each side (top, right and left) could be captured and displayed on a computer monitor through the multiplexor. One of the two B/W images captured from each side is 720nm filter image and the other is 970nm. With this system an on-line grading software was developed to evaluate appearance quality. On-line test results to the Fuji apples that were manually fed on the conveyer showed that grading accuracies of the color, defective and shape were 95.3%, 86% and 91%, respectively. Grading time was 0.35 sec per apple on an average. Therefore, this on-line grading system could be used for inspection of the final products produced from an apple sorting system.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.125-140
• /
• 2018

As one of the processes in the manufacturing industry, quality inspection inspects the intermediate products or final products to separate the good-quality goods that meet the quality management standard and the defective goods that do not. The manual inspection of quality in a mass production system may result in low consistency and efficiency. Therefore, the quality inspection of mass-produced products involves automatic checking and classifying by the machines in many processes. Although there are many preceding studies on improving or optimizing the process using the data generated in the production process, there have been many constraints with regard to actual implementation due to the technical limitations of processing a large volume of data in real time. The recent research studies on big data have improved the data processing technology and enabled collecting, processing, and analyzing process data in real time. This paper aims to propose the process and details of applying big data for quality inspection and examine the applicability of the proposed method to the dairy industry. We review the previous studies and propose a big data analysis procedure that is applicable to the manufacturing sector. To assess the feasibility of the proposed method, we applied two methods to one of the quality inspection processes in the dairy industry: convolutional neural network and random forest. We collected, processed, and analyzed the images of caps and straws in real time, and then determined whether the products were defective or not. The result confirmed that there was a drastic increase in classification accuracy compared to the quality inspection performed in the past.