• The Journal of Bigdata
• /
• v.8 no.2
• /
• pp.83-95
• /
• 2023

Big data analytics and AI play a critical role in the development of smart plants. This study presents a big data platform for plant data and an 'AutoML platform' for AI-based plant O&M(Operation and Maintenance). The big data platform collects, processes and stores large volumes of data generated in plants using Hadoop, Spark, and Kafka. The AutoML platform is a machine learning automation system aimed at constructing predictive models for equipment prognostics and process optimization in plants. The developed platforms configures a data pipeline considering compatibility with existing plant OISs(Operation Information Systems) and employs a web-based GUI to enhance both accessibility and convenience for users. Also, it has functions to load user-customizable modules into data processing and learning algorithms, which increases process flexibility. This paper demonstrates the operation of the platforms for a specific process of an oil company in Korea and presents an example of an effective data utilization platform for smart plants.

• Journal of Convergence for Information Technology
• /
• v.10 no.9
• /
• pp.1-7
• /
• 2020

In order to implement a smart factory for manufacturing innovation, more digital twins will be developed and applied gradually. In particular, simulation and optimization of digital twins makes it possible to support critical decision-making like a predictive maintenance of the equipment for manufacturing. In terms of a user perspective, this study suggests the conceptual framework of Digital Twin Management System (DTMS) for supporting the analytical and managerial activities for Digital Twins. We integrate the methods and structure of the area like Manufacturing Engineering, Decision Support Systems, and Optimization for developing the DTMS. The framework suggested in this study shows a typical DSS which consists of dialog management system, model management system and data management system. It also includes Analytical Digital Twins and simulations & optimization module. The framework is being applied in one of the most competitive and complex industrial sector. Also this study is meaningful to suggest a new direction of research.

• Journal of Convergence for Information Technology
• /
• v.10 no.5
• /
• pp.117-125
• /
• 2020

Our study identifies a cost and a benefit incurred in implementing an investment project to offer new public services by use of food waste disposers and direct input of feces in sewers. This is done with identifying costs of each processing division and benefits of the project by objective statistical data and engineering perspective. In summary, cost items identified are as follows: there are house laterals, removal of septic tanks, etc. for sewer pipes system. As to water quality conservation, cost incurs in storm water outfalls and divert chambers, sewage storage tanks, equipment to treat sewer overflows, and so on. With respect to sewage treatment plants(STPs), there are so many items as increase of contaminant loads in influent of STPs, and other items. There are benefit items in health improvement due to odor mitigation, increase of energy productivity, saving cost of food waste treatment and cleaning septic tanks, etc. These estimates will be used as a basic data for its economic effect.

• Journal of Korea Water Resources Association
• /
• v.54 no.5
• /
• pp.301-309
• /
• 2021

In this study, we tried to improve the performance of the existing U-net-based deep learning rainfall prediction model, which can weaken the meaning of time series order. For this, ConvLSTM2D U-Net structure model considering temporal consistency of data was applied, and we evaluated accuracy of the ConvLSTM2D U-Net model using a RainNet model and an extrapolation-based advection model. In addition, we tried to improve the uncertainty in the model training process by performing learning not only with a single model but also with 10 ensemble models. The trained neural network rainfall prediction model was optimized to generate 10-minute advance prediction data using four consecutive data of the past 30 minutes from the present. The results of deep learning rainfall prediction models are difficult to identify schematically distinct differences, but with ConvLSTM2D U-Net, the magnitude of the prediction error is the smallest and the location of rainfall is relatively accurate. In particular, the ensemble ConvLSTM2D U-Net showed high CSI, low MAE, and a narrow error range, and predicted rainfall more accurately and stable prediction performance than other models. However, the prediction performance for a specific point was very low compared to the prediction performance for the entire area, and the deep learning rainfall prediction model also had limitations. Through this study, it was confirmed that the ConvLSTM2D U-Net neural network structure to account for the change of time could increase the prediction accuracy, but there is still a limitation of the convolution deep neural network model due to spatial smoothing in the strong rainfall region or detailed rainfall prediction.

• Journal of Korea Port Economic Association
• /
• v.40 no.2
• /
• pp.191-204
• /
• 2024

In this study, AHP-based production management job training was developed for MPE companies in the aviation logistics industry. The AHP model was designed with upper and lower classes. Purchase management competency, material management competency, process management competency, and SCM competency were selected as factors of the upper class of production management job training. Lower class evaluation factors were selected for each upper class. As a result of AHP analysis, the relative importance of the upper class evaluation factors was found in the order of SCM competency (0.322), process management competency (0.314), material management competency (0.201), and purchase management competency (0.163). Among the upper classes, it was analyzed that the importance of SCM competency and process management competency was high. The final priority of evaluation factors for the development of the production management curriculum of MPE companies in the aviation logistics industry was analyzed as follows. First, supply chain performance management, which is the lower layer of SCM competency, was analyzed as the top priority factor, and the priorities of evaluation factors were derived such as facility preservation management, which is the lower layer of SCM competency, supply chain production operation, which is the lower layer of SCM competency, process quality management, which is the lower layer of SCM competency, supply chain transportation management, and supply chain supply plan, which are the lower layers of SCM competency

• Korean Journal of Soil Science and Fertilizer
• /
• v.41 no.2
• /
• pp.143-152
• /
• 2008

In order to share the understanding agricultural multifunctionality with people, we carried out quantification and monetary evaluation for controlling flood and fostering water resources function in paddy and upland farming in Korea. The amount of water controlling flood and fostering water resources function in paddy farming was much greater than that in upland. The quantification of flood control function could be estimated by sum of the height of dike and water infiltrated during the flooding periods in paddy farming, and water excepting runoff water from precipitation at flooding time in upland farming. As results of estimation of flood control function, the amounts of water controlling flood have been evaluated as $294mm\;year^{-1}$ in paddy farming and $72.6mm\;year^{-1}$ upland farming, and was calculated 3.71 billion MT on a nation basis in 2006. When it was carried out monetary estimation as the cost of dam construction and the depreciation expense by using replacement cost method, flood control functions in paddy and upland were evaluated as 44,338.9 and 7,221.5 billion won, respectively. Comparing with previous reports, monetary value was analyzed much to increase because of rising price cost recently. Fostering water resource functions were also quantified in paddy and upland farming as the amount of water keeping and infiltrating water during the cultivation. In the basis of estimation model, it was showed that paddy and upland farming had been estimated to have $414.28mm\;year^{-1}$, $18.7mm\;year^{-1}$, respectively. They were also calculated to 4.49 and 0.137 billion MT on a nation basis in 2006, respectively. The economic values of fostering water resources function in paddy and upland farming were also estimated to 1,769.4 and 52.8 billion won, respectively, as replacing the amount of water to the cost of drinking water in 2006. There were differences by much to the amounts of controlling flood function and fostering water resource between paddy and upland farming. It means that paddy farming more play an important role in environment than upland farming in Korea.