• Design & Manufacturing
• /
• v.15 no.3
• /
• pp.1-6
• /
• 2021

An artificial neural network model based on a deep learning algorithm is known to be more accurate than humans in image classification, but there is still a limit in the sense that there needs to be a lot of training data that can be called big data. Therefore, various techniques are being studied to build an artificial neural network model with high precision, even with small data. The transfer learning technique is assessed as an excellent alternative. As a result, the purpose of this study is to develop an artificial neural network system that can classify burr images of light guide plate products with 99% accuracy using transfer learning technique. Specifically, for the light guide plate product, 150 images of the normal product and the burr were taken at various angles, heights, positions, etc., respectively. Then, after the preprocessing of images such as thresholding and image augmentation, for a total of 3,300 images were generated. 2,970 images were separated for training, while the remaining 330 images were separated for model accuracy testing. For the transfer learning, a base model was developed using the NASNet-Large model that pre-trained 14 million ImageNet data. According to the final model accuracy test, the 99% accuracy in the image classification for training and test images was confirmed. Consequently, based on the results of this study, it is expected to help develop an integrated AI production management system by training not only the burr but also various defective images.

• Design & Manufacturing
• /
• v.15 no.3
• /
• pp.50-55
• /
• 2021

Solar power generation, which is one of the methods of using solar energy, has a high possibility of practical implementation compared to other renewable energy power generation, and it has the characteristic that it can generate as much power as needed in necessary places. In addition, maintenance is easy, unmanned operation is possible, and power management can be performed more efficiently if operated in a hybrid method with existing electric energy. Therefore, in this study, numerical analysis using a computer program was performed to analyze the efficient operation and performance improvement of solar energy of the rotating condensing type solar LED street lamp. As a result, the two-axis tracking type could obtain 15.23 % more electricity per year than the fixed type, and additional auxiliary power generation was required for the fixed type by 19 % per year than the tracking type. As a result of computational fluid dynamics(CFD) simulation for PV module surface temperature prediction, the The surface temperature of the Photovoltaics(PV) module incident surface was predicted to be about 10℃ higher than that of the fixed type.

• Design & Manufacturing
• /
• v.15 no.1
• /
• pp.8-13
• /
• 2021

Excavators are construction machines used for digging soil, transporting soil, dismantling buildings and clearing the ground at construction sites. There are various attachments attached to the arm end of the excavator and used for various operations. There are the most common types of buckets attached for excavation and other types of attachments used for foresting, road cleaning, snow removal, and waste disposal. When multiple types of work are done at the same time, several attachments must be replaced and a device called a quick coupler is used to reduce replacement time. Although a quick coupler reduces the replacement time of the Attachment, it is necessary to attach safety devices to prevent unintentional detachment of attached attachments during the operation. To prevent the attachment from leaving or falling regardless of the operator's intention, support is installed in the hook of the bucket pin and controlled through a separate hydraulic cylinder to ensure safety. When attaching an attachment, it shall be attached without any action. This study is intended to verify the design validity of safety devices to prevent falls of attachments occurring at construction sites.

• Design & Manufacturing
• /
• v.16 no.3
• /
• pp.16-21
• /
• 2022

In order to reduce the weight of parts and materials for the development of high-efficiency engines in accordance with the strengthening of automobile fuel efficiency regulations, the existing casting material is changed to a iron plate material, and plastic processing and turning operations are performed to lighten the weight and reduce the manufacturing cost. Among the pulley components applied to the damper pulley, the HUB product was manufactured by plastic machining instead of the existing casting process, and the inspection standardized for automating the inner diameter and parallelism measurement of the turning result of the new hub part with improved quality, and the inspection system for this Development of design and operation software to automate the inspection of the inner diameter and parallelism of the hub was described. The representative specifications of the development equipment are a hub inner diameter 22mm inspection system, a three-point inspection system with a parallelism of 0.15mm on the top.

• Journal of the Korean Society for Precision Engineering
• /
• v.12 no.5
• /
• pp.98-107
• /
• 1995

The in-process detection of drill wear and breakage is one of the most importnat technical problems in unmaned machining system. In this paper, the monitoring system is developed to monitor abnormal drilling states such as drill breakage, drill wear and unstable cutting using motor current. Drill breakage is detected by level monitoring. Tool wear is classified by fuzzy pattern recognition. The key feature for classification of tool wear is the estimated flank wear which is calculated by the proposed flank wear model. The characteristic of the model is not sensitive to the variation of cutting conditions but is sensitive to drill wear state. Unstable cutting states due to the unsmooth chip disposal and the overload are monitored by the variance/mean ratio of spindle motor current. Variance/mean ratio also includes the information about the prediction of drill wear and drill breakage. The evaluation experiments have shown that the developed system works very well.

• Design & Manufacturing
• /
• v.17 no.2
• /
• pp.15-21
• /
• 2023

In this study, a diamond turning machine and a laser-assisted machining module were utilized for the complex combined cutting of aspheric shapes and fine patterns on the surface of high-hardness brittle material, silicon. The analysis of material's form accuracy and corrective machining was conducted based on key factors such as laser output, rotational speed, feed rate, and cutting depth to achieve form accuracy below 1 ㎛ and surface roughness below 0.1 ㎛. The cutting condition and corrective machining methods were investigated to achieve the desired form accuracy and surface roughness. The rotational speed of the spindle and the linear feed rate of the diamond turning machine were varied in five stages for the cutting condition test. Surface roughness and form accuracy were measured using both a contact surface profilometer and a non-contact surface profilometer. The experimental results revealed a tendency of improved surface roughness with increased rotational speed of the workpiece, and the best surface roughness and form accuracy were observed at a feed rate of 5 mm/min. Furthermore, based on the cutting condition experiments, corrective machining was performed. The experimental results demonstrated an improvement in form accuracy from 0.94 ㎛ to 0.31 ㎛ and a significant reduction in the average value of the surface roughness curve from 0.234 ㎛ to 0.061 ㎛. This research serves as a foundation for future studies focusing on the machinability in relation to laser output parameters.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.8
• /
• pp.796-805
• /
• 2009

In this paper, a fabrication process for PZT preform of 1-3 type piezo-composite were studied using powder injection molding (PIM). The viscosity and the Pressure-Volume-Temperature (PVT) characteristics of the fabricated PZT feedstock were analyzed. The filling patterns, pressure, temperature distributions, and forming defects of the preform were analyzed with 3D TIMON commercial packages during PIM process. Also the fabrication conditions and the delivery system of the preform were optimized during the entire PIM process. Based on the simulated results, the preform having uniform distributions of the PZT rod was fabricated with the PIM process.

• Design & Manufacturing
• /
• v.18 no.2
• /
• pp.35-40
• /
• 2024

Injection molding is a process widely used across various industries for molding plastics, and it is the most commonly applied process in root industries utilizing molds. Among the different types of injection molding, insert injection molding, where busbars are used as inserts, is increasingly being applied in the electric vehicle industry. However, currently, the insert injection molding process is manually performed, with workers placing insert components by hand before injection molding. This results in issues related to productivity, safety, and quality. Additionally, there is a growing demand for automation of such production lines due to hazardous working conditions, economic difficulties in the manufacturing industry, and the decline in the labor force caused by an aging population. This study focuses on the application of an automated system for the insert injection molding process used in electric vehicles. The development of an automated system for the transport and insertion of insert components, as well as the inspection and stacking processes after injection, has resulted in over a 25% improvement in productivity and more than a 27% reduction in defect rates.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.6
• /
• pp.2458-2464
• /
• 2012

Recently, component materials for display are being developed into higher value-added industries which can strengthen national industrial competitiveness. However, a system for production of component materials for display is nearly depending on import, and its development level is inadequate. For this reason, localization of the embossing treatment system for production of the spacer tape and system improvement for increasing of productivity are needed. Therefore, in this paper, we propose rotary type embossing process system for spacer tape production for localization of system and increasing productivity. The system consists of unwinding, forming, cleaning, winding and testing parts. The mold of forming part is designed to rotary type. And we designed each part and made a prototype to test its performance. We measured embossing shapes, diameter and distance between each embossing and opposite embossing using three coordinate measuring machine. Also, we measured impurity level and the number of impurity particles of sample through the testing and cleaning part. Additionally, the productivity of spacer tape produced by the prototype is measured.

• Composites Research
• /
• v.26 no.6
• /
• pp.363-372
• /
• 2013

Numerical simulation for Resin Transfer Molding manufacturing process is attempted by using the eXtended Finite Element Method (XFEM) combined with the level set method. XFEM allows to obtaining a good numerical precision of the pressure near the resin flow front, where its gradient is discontinuous. The enriched shape functions of XFEM are derived by using the level set values so as to correctly describe the interpolation with the resin flow front. In addition, the level set method is used to transport the resin flow front at each time step during the mold filling. The level set values are calculated by an implicit characteristic Galerkin FEM. The multi-frontal solver of IPSAP is adopted to solve the system. This work is validated by comparing the obtained results with analytic solutions. Moreover, a localization method of XFEM and level set method is proposed to increase the computing efficiency. The computation domain is reduced to the small region near the resin flow front. Therefore, the total computing time is strongly reduced by it. The efficiency test is made with a simple channel flow model. Several application examples are analyzed to demonstrate ability of this method.