• Design & Manufacturing
• /
• v.17 no.1
• /
• pp.7-12
• /
• 2023

Recently, with the emergence of the 4th industrial revolution, the demand for smart factories and factory automation is increasing. In this study, a tool life prediction program was developed to select optimal machining conditions using CNC milling equipment, which is widely used in flexible production and automation. The equipment used in the experiment was Hwacheon Machine Tool's 5-axis machining equipment, and the tool used was a 17F2R tool. For the machining path, the down-milling cutting method was selected and long-term machining was performed. The analysis standard for side wear on the tool was set at 0.1 to 0.2 mm, and tool life data and wear data were obtained in the cutting experiment. The program was created through the data obtained from the experiment, and a prediction rate of over 90% was secured when comparing the experimental data and the predicted data.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.78-81
• /
• 2021

Through the smart factory construction project, sensors can be installed in manufacturing production facilities and various process data can be collected in real time. Through this, research on real-time facility anomaly detection is being actively conducted to reduce production interruption due to facility abnormality in the manufacturing process. In this paper, to detect abnormalities in production facilities, the manufacturing data was applied to deep learning models Autoencoder(AE), VAE(Variational Autoencoder), and AAE(Adversarial Autoencoder) to derive the results. Manufacturing data was used as input data through a simple moving average technique and preprocessing process, and performance analysis was conducted according to the window size of the simple movement average technique and the feature vector size of the AE model.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.1
• /
• pp.134-138
• /
• 2023

This study focuses on the analysis of the results of computational fluid dynamics simulations of mist-chemical vapor deposition for the growth of an epitaxial wafer in power semiconductor technology using artificial intelligence techniques. The conventional approach of predicting the uniformity of the deposited layer using computational fluid dynamics and design of experimental takes considerable time. To overcome this, artificial intelligence method, which is widely used for optimization, automation, and prediction in various fields, was utilized to analyze the computational fluid dynamics simulation results. The computational fluid dynamics simulation results were analyzed using a supervised deep neural network model for regression analysis. The predicted results were evaluated quantitatively using Euclidean distance calculations. And the Bayesian optimization was used to derive the optimal condition, which results obtained through deep neural network training showed a discrepancy of approximately 4% when compared to the results obtained through computational fluid dynamics analysis. resulted in an increase of 146.2% compared to the previous computational fluid dynamics simulation results. These results are expected to have practical applications in various fields.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.1
• /
• pp.117-126
• /
• 2019

The data generated in the IoT environment is very diverse. Especially, the development of the fourth industrial revolution has made it possible to increase the number of fixed and unstructured data generated in manufacturing facilities such as Smart Factory. With Big Data related solutions, it is possible to collect, store, process, analyze and visualize various large volumes of data quickly and accurately. Therefore, in this paper, we will directly generate data using Raspberry Pi used in IoT environment, and analyze using various Big Data solutions. Collected by using an Sqoop solution collected and stored in the database to the HDFS, and the process is to process the data by using the solutions available Hive parallel processing is associated with Hadoop. Finally, the analysis and visualization of the processed data via the R programming will be used universally to end verification.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.5
• /
• pp.745-750
• /
• 2013

In many recent studies, a variety of environmental control system for practical gardening facilities such as facility house and plant factory have been proposed. However, the plants have been exposed to growth disorder and disease and pest injury because the temperature and humidity have not properly controlled so far. Therefore, a lot of damage of farmers have been reported. The air circulation fan and industrial dehumidifier have been currently utilized as the countermeasures, but they do not meet the expectation. In this study, the growth phase of each plant is recognized by using cycle-by-cycle plants growth recogniztion algorithm to provide optimal environment according to the growth phases of each plant.he productivity can be raised by using cycle-by-cycle plant growth recognition monitoring system because it optimally controls the environment by cycle that is required for plant growth.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.5
• /
• pp.125-133
• /
• 2016

Data processing capacity and speed are rapidly increasing due to the development of hardware and software in recent time. As a result, data usage is geometrically increasing and the amount of data which computers have to process has already exceeded five-thousand transaction per second. That is, the importance of Big Data is due to its 'real-time' and this makes it possible to analyze all the data in order to obtain accurate data at right time under any circumstances. Moreover, there are many researches about this as construction of smart factory with the application of Big Data is expected to have reduction in development, production, and quality management cost. In this paper, system using In-Memory Data Grid for high speed processing is implemented in semiconductor process which numerous data occur and improved performance is proven with experiments. Implemented system is expected to be possible to apply on not only the semiconductor but also any fields using Big Data and further researches will be made for possible application on other fields.

• Journal of Korean Society for Quality Management
• /
• v.50 no.1
• /
• pp.125-138
• /
• 2022

Purpose: Failure Mode and Effect Analysis (FMEA) is a widely utilized technique to measure product reliability by identifying potential failure modes. Even though FMEA techniques have been studied, the form of Risk Priority Number (RPN) used to evaluate risk priority in FMEA is still questionable because of its shortcomings. In this study, we suggest common RPN(cRPN) to resolve shortcomings of the traditional RPN and show the extensibility of cRPN. Methods: We suggest cRPN which is based on Cobb-Douglas production function, and represent the various application on weighting risk factors, weighted RPN in a mathematical way, and show the possibility of statistical approach. We also conduct numerical study to examine the difference of the traditional RPN and cRPN as well as the potential application from the analysis on marginal effects of each risk factor. Results: cRPN successfully integrates previously suggested approaches especially on the relative importance of risk factors and weighting RPN. Moreover, we analyze the effect of corrective actions in terms of econometric analysis using cRPN. Since cRPN is rely on the reliable mathematical model, there would be numerous applications using cRPN such as smart factory based on A.I. techniques. Conclusion: We propose a reliable mathematical model of RPN based on Cobb-Douglas production function. Our suggested model, cRPN, resolves various shortcomings such as consideration of the relative importance, the effect of combinations among risk factors. In addition, by adopting a reliable mathematical model, quantitative approaches are expected to be applied using cRPN. We find that cRPN can be utilized to the field of industry because it is able to be applied without modifying the entire systems or the conventional actions.

• Journal of Bio-Environment Control
• /
• v.29 no.2
• /
• pp.105-109
• /
• 2020

This study was conducted to the improvement of solar light-based artificial light supply system and effect of lettuce cultivation. The artificial light supply system was consisted of units such as light source, power, system measurement and controller. The light source supply was composed of a solar transmitter and an LED lamp. The power supply consisted of an leakage breaker, SMPS, LED controller and relay. The solar transmitter was made of a quartz optical fiber with optimal light transmission. Artificial light used white lamp among LEDs. System measurement and control consisted of touch screen, Zigbee communication module and light quantity sensor. The results of test confirmed that the LED light is automatically activated when the intensity measured by the light intensity sensor is 200 μmolm^-2s^-1 or less. Moreover, the leaf length, root length, chlorophyll content and root fresh weight of optical fiber treatment was hight than LED lamp treatment. Therefore, it can be inferred that the energy-saving solar light collector device can be effective in the indoor lettuce production. However, the use of LED lamp is also recommended to assure the availability of sufficient sunlight in cloudy and rainy days.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.1
• /
• pp.143-150
• /
• 2020

To enhance the effectiveness of the FMS (flexible manufacturing system), it is necessary for the manufacturing control system to be upgraded by integrating the cyber and the physical manufacturing systems. Using the CPPS (Cyber-Physical Production System) concept, this study proposes a 4-stage vertical integration and control framework for an aircraft parts manufacturing plant. In the proposed framework, the process controller prepares the operations schedule for processing work orders generated from the APS (advanced planning & scheduling) system. The scheduled operations and the related control commands are assigned to equipments by the dispatcher of the line controller. The line monitor is responsible for monitoring the overall status of the FMS including work orders and equipments. Finally the process monitor uses the simulation model to check the performance of the production plan using real time plant status data. The W-FMCS (Wing rib-Flexible Manufacturing Control & Simulation) are developed to implement the proposed 4-stage CPPS based FMS control architecture. The effectiveness of the proposed control architecture is examined by the real plant's operational data such as utilization and throughput. The performance improvement examined shows the usefulness of the framework in managing the smart factory's operation by providing a practical approach to integrate cyber and physical production systems.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.5
• /
• pp.153-160
• /
• 2020

Energy Consumption Predictions for Industries has a prominent role to play in the energy management and control system as dynamic and seasonal changes are occurring in energy demand and supply. This paper introduces and explores the steel industry's predictive models of energy consumption. The data used includes lagging and leading reactive power lagging and leading current variable, emission of carbon dioxide (tCO2) and load type. Four statistical models are trained and tested in the test set: (a) Linear Regression (LR), (b) Radial Kernel Support Vector Machine (SVM RBF), (c) Gradient Boosting Machine (GBM), and (d) Random Forest (RF). Root Mean Squared Error (RMSE), Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) are used for calculating regression model predictive performance. When using all the predictors, the best model RF can provide RMSE value 7.33 in the test set.