• Transactions of Materials Processing
• /
• v.13 no.7
• /
• pp.570-579
• /
• 2004

정상상태 압연공정의 오일러리안 공정해석 모델에 관한 연구들을 종합 정리하였다 본 연구의 유한요소해석 모델은 집합조직의 발전에 따른 이방성과 미세기공의 성장에 따른 기계적 성질의 열성화를 평형방정식에 직접 결합하였다 따라서 집합조직의 발전 및 기공률의 변화를 예측하고 동시에 이방성과 기계적성질의 열성화를 해석에 반영할 수 있다. 더불어 오일러리안 해석에서 형상예측을 위하여 자유곡면 수정법과 유선추적법을 유한요소해석 모델에 결합하였다 본 연구의 공정해석 모델을 평판 압연, 클래드압연, 삼차원 사각단면봉의 압연 및 형상압연에 적용하여 집합 조기의 발전, R-값, 항복곡면, 결함성장 등의 기계적성질의 변화 예측과 클래드 압연시에 이중재 접촉면 형상, 배불림, 형상압연 시의 단면변화 등의 형상변화 예측을 보여주었다.

• Journal of Food Hygiene and Safety
• /
• v.13 no.1
• /
• pp.62-67
• /
• 1998

This study was undertaken to find out distribution and contamination sources of microbes on the processing steps and to estimate quality index and shelf life of fried bean curd. It was necessary that the sanitation for water, processing environment and instruments at digestion, formation, cutting and processes after frying must be controlled and microbial growth at digestion and formation must be inhibited, to process efficiently and to improve shelf life of fried bean curd. It was evaluated that quality indexes as to sensory evaluation, especially texture, mold generation and total viable cell counts will be useful to estimate shelf life of fried bean curd and that shelf life of fried bean curd was 6 days.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2001.05a
• /
• pp.20-24
• /
• 2001

공장을 신축할 경우 일반적인 설비계획 절차에 따라 제품설계, 공정 설계, 용량설계를 거쳐 Layout 설계로 이어지게 된다. 이 과정에서 용량설계는 공장에 설치할 기계의 적정 대수를 결정하고, 각 공정 사이의 재공품을 예측하여 저장장소의 적정 면적을 결정한다는 점에서 매우 중요한 단계라 하겠다. 이 논문에서는 볼베어링을 제조하는 D사의 신축공장 설계시 수행했던 용량설계를 위한 시뮬레이션에 대한 사례를 소개하고자 한다. 시뮬레이션의 주요 관심사는 당초 회사측에서 제시했던 설비들의 수량이 회사의 생산목표를 달성할 수 있는 지에 대한 검토와, 이를 해결하기 위한 방향 제시, 공정별 재공품에 대한 예측 등이다.

• Applied Chemistry for Engineering
• /
• v.31 no.5
• /
• pp.520-525
• /
• 2020

In this study, we developed a machine learning-based model for predicting the production stage temperature of distillation process. It is necessary to predict an accurate temperature for control because the control of the distillation process is done through the production stage temperature. The temperature in distillation process has a nonlinear complex relationship with other variables and time series data, so we used the recurrent neural network algorithms to predict temperature. In the model development process, by adjusting three recurrent neural network based algorithms, and batch size, we selected the most appropriate model for predicting the production stage temperature. LSTM₁₂₈ was selected as the most appropriate model for predicting the production stage temperature. The prediction performance of selected model for the actual temperature is RMSE of 0.0791 and R² of 0.924.

• Korean Journal of Food Science and Technology
• /
• v.22 no.3
• /
• pp.325-331
• /
• 1990

The most important factors in the cooking process which is a main process in the sausage manufacture are cooking temperature and relative humidity. In order to design energy efficient processes in cooking, accurate data for the process parameters are necessary. Therefore, texture profiles were analysed and weight losses were measured at different process conditions of the forementioned factors and at different sizes of sausage, The prediction model for the sausage cooking time was then developed by the SPSS computer program The models were developed as a function of cooking temperature, relative humidity and the diameter of sausage by analyszing the scattergram. Then the model obtained could predict the values within 2.5% error. The higher temperature and relative humidity are the less changes of weight during sausage cooking. As the results of measuring physical properties, the values of hardness and cohesiveness at different temperatures and humidities were so much changed, while the values of elasticity and chewiness had little differences.

• Korean Chemical Engineering Research
• /
• v.43 no.4
• /
• pp.458-466
• /
• 2005

Full-scale utilizations of batch separation process often require knowledge about thermodynamics and correlation techniques of physical properties of complex mixture consisting of a great number of many unknown components. Various empirical correlations have been proposed to predict the physical properties mostly about the pseudocomponent of petroleum. In this study, one parameter correlations are developed for the calculations of the critical physical properties and ideal heat capacity of the pseudo-component of coal tar fractions. Developed model can provide a tool for the design and operations for the batch distillation of coal tar mixture.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.3
• /
• pp.1016-1021
• /
• 2013

While using the hydrogen mixture gas torch, the glass edge sealing and the shape of the edge sealing parts is affected by many parameters such as flow rate of gas, traveling speed of torch, distance between glass and torch. As the glass edge sealing shape have effects on the insulation and airtightness and strength of the glass panel; the sealing shapes are predicted according to the process parameters. The paper highlight the nonlinear regression equations of the cross-sectional shape of the sealing shape according to the parameters, that is experimentally predicted later compared and verified the equation with the experimental result.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.3
• /
• pp.1795-1800
• /
• 2014

The temperature change in the biologically activated sludge wastewater treatment process was predicted using the heat transfer model. All incoming and outgoing heats in wastewater treatment processes were considered. Incoming heats included the solar radiation heat, the heat from impeller mechanical energy, and the biochemical heat in the aeration process. Outgoing heats comprised the radiation heat from the waste itself, the heat of vaporization and surface aeration, the wind convection heat and the conduction heat between the surface and aerator. All heats were used as an input to the existing empirical heat transfer model. The heat transfer model of wastewater treatment processes is presented also. To test the validity of the heat transfer model, the operating conditions of the actual wastewater treatment plant were used. The temperatures were compared with the model temperatures. Model predictions were consistent within the $1.0^{\circ}C$.

• Korean Chemical Engineering Research
• /
• v.59 no.2
• /
• pp.191-199
• /
• 2021

A distillation column, which is a main facility of the chemical process, separates the desired product from a mixture by using the difference of boiling points. The distillation process requires the optimization and the prediction of operation because it consumes much energy. The target process of this study is difficult to operate efficiently because the composition of feed flow is not steady according to the supplier. To deal with this problem, we could develop a data-driven model to predict operating conditions. However, data preprocessing is essential to improve the predictive performance of the model because the raw data contains outlier and noise. In this study, after optimizing the predictive model based long-short term memory (LSTM) and Random forest (RF), we used a low-pass filter and one-class support vector machine for data preprocessing and compared predictive performance according to the method and range of the preprocessing. The performance of the predictive model and the effect of the preprocessing is compared by using R2 and RMSE. In the case of LSTM, R2 increased from 0.791 to 0.977 by 23.5%, and RMSE decreased from 0.132 to 0.029 by 78.0%. In the case of RF, R2 increased from 0.767 to 0.938 by 22.3%, and RMSE decreased from 0.140 to 0.050 by 64.3%.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.362-365
• /
• 2022

최근 노동 집약적인 성격의 섬유 산업에서는 AI를 통해 공정에 들어가는 시간과 비용을 줄이고 품질을 최적화 하려는 시도를 하고 있다. 그러나 섬유 방사 공정은 데이터 수집에 필요한 비용이 크고 체계적인 데이터 처리 시스템이 부족하여 축적된 데이터양이 적다. 또 방사 목적에 따라 특정 변수 위주의 조합에 대한 데이터만을 우선적으로 수집하여 데이터 불균형이 발생하며, 물성 측정환경 차이로 인해 동일 방사조건에서 수집된 샘플 간에도 오차가 존재한다. 이러한 데이터 특성들을 고려하지 않고 AI 모델에 활용할 경우 과적합과 성능 저하 등의 문제가 발생할 수 있다. 따라서 본 논문에서는 물성 단위 및 허용오차를 고려한 이상치 처리 기법과 데이터 불균형 정도 및 물성과의 상관성을 고려한 오버샘플링 기법을 물성 예측 모델에 적용한다. 두 기법들을 모델에 적용한 결과 그렇지 않은 모델에 비해 물성 예측 오차와 방사 공정 데이터에 대한 모델의 적합도가 개선됨을 보인다.