• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.173-180
• /
• 2023

Smart factory companies are installing various sensors in production facilities and collecting field data. However, there are relatively few companies that actively utilize collected data, academic research using field data is actively underway. This study seeks to develop a model that detects anomalies in the process by analyzing spindle power data from a company that processes shafts used in automobile throttle valves. Since the data collected during machining processing is time series data, the model was developed through unsupervised learning by applying the Holt Winters technique and various deep learning algorithms such as RNN, LSTM, GRU, BiRNN, BiLSTM, and BiGRU. To evaluate each model, the difference between predicted and actual values was compared using MSE and RMSE. The BiLSTM model showed the optimal results based on RMSE. In order to diagnose abnormalities in the developed model, the critical point was set using statistical techniques in consultation with experts in the field and verified. By collecting and preprocessing real-world data and developing a model, this study serves as a case study of utilizing time-series data in small and medium-sized enterprises.

• Ocean and Polar Research
• /
• v.41 no.1
• /
• pp.35-46
• /
• 2019

The purpose of this study is to identify factors influencing fish production of shallow-sea aquaculture in South Korea. This study employed the two-way fixed effect and random effect models based on the panel models and also the difference between GMM and system GMM models based on the dynamic panel models using the amount of fish farming production, the number of stocked fry, the number of cultured fish, the amount of inputted feed, the farming area, the number of workers, and the sales price data from 2010 to 2017. First, the two-way fixed effect model of the panel models was selected by panel characteristics, time characteristics and Hausman tests and also the model was statistically significant. As a result of the two-way fixed effect model, the number of stocked fry, the amount of inputted feed, and the number of workers were identified as factors that increase the fish production of shallow-sea aquaculture. However, the number of cultured fish and the sales price were analyzed as factors that reduce the fish production of shallow-sea aquaculture. Second, the system GMM model of the dynamic panel models was selected by Hansen test and Arellano-Bond test in order to identify whether or not the over-discrimination condition is appropriate. Based on the system GMM model, the number of stocked fry, the amount of inputted feed, the number of workers in this year and 1 year ago, the number of cultured fish 2 years ago, and the sale price 3 years ago were analyzed as factors that increase the fish production of shallow-sea aquaculture. However, the amount of fish farming production 1, 2, 3 years ago, the farming area in this year, and the number of cultured fish in this year and 1 year ago were identified as factors that reduce the fish production of shallow-sea aquaculture. In conclusion, this study suggests that it is desirable to control the amount of stocked fry rather than to expand the farming area for fish farming in shallow-sea aquaculture, so as to keep the sale price at a certain level by maintaining the appropriate amount of fish production.

• The Plant Pathology Journal
• /
• v.32 no.6
• /
• pp.537-544
• /
• 2016

We developed a model, termed D-PSA-K, to estimate the accumulated potential damage on kiwifruit canes caused by bacterial canker during the growing and overwintering seasons. The model consisted of three parts including estimation of the amount of necrotic lesion in a non-frozen environment, the rate of necrosis increase in a freezing environment during the overwintering season, and the amount of necrotic lesion on kiwifruit canes caused by bacterial canker during the overwintering and growing seasons. We evaluated the model's accuracy by comparing the observed maximum disease incidence on kiwifruit canes against the damage estimated using weather and disease data collected at Wando during 1994-1997 and at Seogwipo during 2014-2015. For the Hayward cultivar, D-PSA-K estimated the accumulated damage as approximately nine times the observed maximum disease incidence. For the Hort16A cultivar, the accumulated damage estimated by D-PSA-K was high when the observed disease incidence was high. D-PSA-K could assist kiwifruit growers in selecting optimal sites for kiwifruit cultivation and establishing improved production plans by predicting the loss in kiwifruit production due to bacterial canker, using past weather or future climate change data.

• Animal Bioscience
• /
• v.34 no.4
• /
• pp.471-481
• /
• 2021

Objective: A comprehensive study was conducted to study the effects of partition of variance on accuracy of genetic parameters and genetic trends of economic traits in Vanaraja male line/project directorate-1 (PD-1) chicken. Methods: Variance component analysis utilizing restricted maximum likelihood animal model was carried out with five generations data to delineate the population status, direct additive, maternal genetic, permanent environmental effects, besides genetic trends and performance of economic traits in PD-1 chickens. Genetic trend was estimated by regression of the estimated average breeding values (BV) on generations. Results: The body weight (BW) and shank length (SL) varied significantly (p≤0.01) among the generations, hatches and sexes. The least squares mean of SL at six weeks, the primary trait was 77.44±0.05 mm. All the production traits, viz., BWs, age at sexual maturity, egg production (EP) and egg weight were significantly influenced by generation. Model four with additive, maternal permanent environmental and residual effects was the best model for juvenile growth traits, except for zero-day BW. The heritability estimates for BW and SL at six weeks (SL6) were 0.20±0.03 and 0.17±0.03, respectively. The BV of SL6 in the population increased linearly from 0.03 to 3.62 mm due to selection. Genetic trend was significant (p≤0.05) for SL6, BW6, and production traits. The average genetic gain of EP40 for each generation was significant (p≤0.05) with an average increase of 0.38 eggs per generation. The average inbreeding coefficient was 0.02 in PD-1 line. Conclusion: The population was in ideal condition with negligible inbreeding and the selection was quite effective with significant genetic gains in each generation for primary trait of selection. The animal model minimized the over-estimation of genetic parameters and improved the accuracy of the BV, thus enabling the breeder to select the suitable breeding strategy for genetic improvement.

• Korean Journal of Geomatics
• /
• v.3 no.2
• /
• pp.107-114
• /
• 2004

The National Geographic Information Institute (NGII) in korea, through the National Geographic Information System (NGIS) Program, has prepared to generate and disseminate digital elevation data for Korea. This is a pilot research to propose a policy for production, maintenance, and supply of Korea Digital Elevation Data(KDED). Customer demands for accuracy and resolution of DEM was surveyed through a questionnaire. In order to investigate the quality, the technical efficiency and the production cost, a tentative DEM in a small test site was generated based on digital topographic maps (original paper map scale 1:5,000), analytical plotter, and LIDAR. The Accuracy standard for KDED was derived based on source data generation methods. As a result of this research, a uniformly spaced grid model was recommended for KDED. Its preferable grid space is 5m in urban areas and its vicinity, and 10m in field and mountainous area. LIDAR has been valuated as a proper KDED generation method fulfilling customers' demands for the accuracy.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.447-449
• /
• 2003

Remotely sensed data can be used to estimate biomass production using methodologies relating vegetation indices to light absorption or to leaf photosynthetic capacity. The considerations of both light absorption and photosynthetic capacity in remote sensing-based modeling to estimate biomass production or NPP was introduced based upon Monteith model NPP is one of a evaluation of land degradation. NPP was estimated from annual maximum NDVI by MODIS data. It was known that NPP of the grassland that except the forest and the farming ground was distributed between 50-200g /m2.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.11 no.5
• /
• pp.201-209
• /
• 2003

Virtual human models are widely used to save time and expense in vehicle safety studies. A human model is an essential tool to visualize and simulate a vehicle driver in virtual environments. This research is focused on creation and application of a human model fer virtual reality. The Korean anthropometric data published are selected to determine basic human model dimensions. These data are applied to GEBOD, a human body data generation program, which computes the body segment geometry, mass properties, joints locations and mechanical properties. The human model was constituted using MADYMO based on data from GEBOD. Frontal crash and bump passing test were simulated and the driver's motion data calculated were transmitted into the virtual environment. The human model was organized into scene graphs and its motion was visualized by virtual reality techniques including OpenGL Performer. The human model can be controlled by an arm master to test driver's behavior in the virtual environment.

• Korean Management Science Review
• /
• v.1
• /
• pp.35-45
• /
• 1984

This paper deals with the case study of the establishment of decision supporting system in shipbuilding industory. Facts or information of shipbuilding, sales, finance, production strategic planning in shipbuilding industry are considered. General transportation model for shipyard production schedule is formulated, and shipbuilding demand forecasting scheme is also introduced. This paper shows the several methods of DSS in shipbuilding industry. But production schedule strategic planning system by OR technique is emphasized. For the realization of DSS in shipbuilding industry, another efforts (data gathering and programming etc.) should be given on the basis of these methods.

• Korean Journal of Computational Design and Engineering
• /
• v.11 no.2
• /
• pp.115-127
• /
• 2006

At the initial design stage, the generation process of the production material information of a building block and the simulation process of the block erection, which are required to perform the production planning and scheduling, have been manually performed by using 2D drawings, data of parent ships, and design experiences. To make these processes automatic, the accurate generation method of the production material information and the convenient simulation method of the block erection using the 3D CAD model, which was generated from the initial hull structural design system early developed by us, were proposed in this study. For this, a 3D CAD model for a whole hull structure was generated first, and the block division method for dividing the 3D CAD model into several building blocks was proposed. The generation method of the production material information for calculating the weight, center of gravity, painting area, joint length, etc. of a building block was proposed as well. Moreover, the simulation method of the block erection was proposed. Finally, to evaluate the efficiency of the proposed methods for the generation of the production material information and the simulation of the block erection, these methods were applied to corresponding processes of a deadweight 300,000 ton VLCC (Very Large Crude oil Carrier). As a result, it was shown that the production material information of a building block can be accurately generated and the block erection can be conveniently simulated in the initial design stage.

• Biotechnology and Bioprocess Engineering:BBE
• /
• v.11 no.1
• /
• pp.72-79
• /
• 2006

Kojic acid production by Aspergillus flavus strain S44-1 using sucrose as a carbon source was carried out in a 250-mL shake flask and a 2-L stirred tank fermenter. For comparison, production of kojic acid using glucose, fructose and its mixture was also carried out. Kojic acid production in shake flask fermentation was 25.8 g/L using glucose as the sole carbon source, 23.6 g/L with sucrose, and 6.4 g/L from fructose. Reduced kojic acid production (13.5 g/L) was observed when a combination of glucose and fructose was used as a carbon source. The highest production of kojic acid (40.2 g/L) was obtained from 150 g/L sucrose in a 2 L fermenter, while the lowest kojic acid production (10.3 g/L) was seen in fermentation using fructose as the sole carbon source. The experimental data from batch fermentation and resuspended cell system was analysed in order to form the basis for a kinetic model of the process. An unstructured model based on logistic and Luedeking-Piret equations was found suitable to describe the growth, substrate consumption, and efficiency of kojic acid production by A. flavus in batch fermentation using sucrose. From this model, it was found that kojic acid production by A. flavus was not a growth-associated process. Fermentation without pH control (from an initial culture pH of 3.0) showed higher kojic acid production than single-phase pH-controlled fermentation (pH 2.5, 2.75, and 3.0).