• 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.

• Journal of Korean Institute of Industrial Engineers
• /
• v.39 no.4
• /
• pp.247-252
• /
• 2013

Korea gas corporation (KOGAS) is responsible for the whole sale of natural gas in the domestic market. It is important to forecast the daily demand of city gas for supply and demand control, and delivery management. Since there is the autoregressive characteristic in the daily gas demand, we introduce a modified autoregressive model as the first step. The daily gas demand also has a close connection with the outdoor temperature. Accordingly, our second proposed model is a temperature-based model. Those two models, however, do not meet the requirement for forecasting performances. To produce acceptable forecasting performances, we develop a weighted average model which compounds the autoregressive model and the temperature model. To examine our proposed methods, the forecasting results are provided. We confirm that our method can forecast the daily city gas demand accurately with reasonable performances.

• Journal of Power Electronics
• /
• v.17 no.3
• /
• pp.695-703
• /
• 2017

In order to satisfy the urgent requirements for the overheating protection of induction motors, an approach that can be used to identify motor temperature has been proposed based on the rotor slots harmonic (RSH) in this paper. One method to accomplish this is to improve the calculation efficiency of the RSH by predicting the stator winding distribution harmonic order by analyzing the harmonics spectrum. Another approach is to increase the identification accuracy of the RSH by suppressing the influence of voltage flashes or current surges during temperature estimation based on model predictive control (MPC). First, an analytical expression of the stator inductance is extracted from a steady-state positive sequence motor equivalent circuit model developed from the rotor flux field orientation. Then a procedure that applies MPC for reducing the identification error of the rotor temperature caused by voltage sag or swell of the power system is given. Due to this work, the efficiency and accuracy of the RSH have been significantly improved and validated our experiments. This work can serves as a reference for the on-line temperature monitoring and overheating protection of an induction motor.

• Proceedings of the KIEE Conference
• /
• 2005.07b
• /
• pp.993-995
• /
• 2005

Recently, the efficiency of power transformer is improved as well as the size is becoming smaller. So, it is very important that temperature characteristics of the transformer should be estimated and predicted precisely. This paper deals with the temperature distribution of power transformer by simplified 2-D hybrid mesh model. The temperature distribution of model transformer was obtained by CFD algorithm considering natural convection. Heat sources are calculated first by magnetic field analysis based on F.E.M. and are usedas the input data for thermal field problem based on computational fluid dynamics(CFD) algorithm. The calculated temperature distribution of the simplified 2-D power transformer model shows good results in accuracy as well as in computing time.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.4
• /
• pp.1232-1245
• /
• 2021

In this study, prediction of product sales as they relate to changes in temperature is proposed. This model uses long short-term memory (LSTM), which has shown excellent performance for time series predictions. For verification of the proposed sales prediction model, the sales of short pants, flip-flop sandals, and winter outerwear are predicted based on changes in temperature and time series sales data for clothing products collected from 2015 to 2019 (a total of 1,865 days). The sales predictions using the proposed model show increases in the sale of shorts and flip-flops as the temperature rises (a pattern similar to actual sales), while the sale of winter outerwear increases as the temperature decreases.

• 한국도로학회:학술대회논문집
• /
• 2010.09a
• /
• pp.99-107
• /
• 2010

A permanent deformation model was developed in this study based on the shear properties of asphalt mixtures such as cohesion and friction angle. Triaxial compressive strength (TCS) and repeated load permanent deformation (RLPD) tests on the three types of asphalt mixtures are performed at various loading and temperature conditions to correlate shear properties of asphalt mixtures to rutting performance. It is observed from the tests results that the ratio of shear stress to strength accurately identifies the mixture rutting performance. It could take care of not only mixture types but also load and temperature conditions dependences. Three different versions of the permanent deformation model based on different input levels are proposed and verified using the tests data. The proposed model based on the ratio of shear stress to strength can successfully predict the permanent deformation of various asphalt mixtures all the way up to the 10% of permanent strain including all three stages of permanent deformation in a wide range of loading and temperature conditions without changing model coefficients.

• KOREAN JOURNAL OF PACKAGING SCIENCE & TECHNOLOGY
• /
• v.21 no.1
• /
• pp.1-10
• /
• 2015

Enzyme kinetics-based respiration model can be effectively used for estimating respiration rate in $O_2$ consumption and $CO_2$ production of fresh produce as a function of $O_2$ and $CO_2$ concentrations. Arrhenius equation can be applied to describe the temperature dependence of the respiration rate. Parameters of enzyme kinetics-based respiration model and activation energy of Arrhenius equation were compiled from analysis of literature data and closed system experiment. They enable to estimate the respiration rate for any modified atmosphere conditions at temperature of interest and thus can be used for design of modified atmosphere packaging of fresh produce.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2009.04a
• /
• pp.97-102
• /
• 2009

In hot strip rolling, sound prediction of the temperature of the strip is vital for achieving the desired finishing mill draft temperature (FDT). In this paper, a precision on-line model for the prediction of temperature distributions along the thickness of the strip in the finishing mill is presented. The model consists of an analytic model for the prediction of temperature distributions in the inter-stand zone, and a semi-analytic model for the prediction of temperature distributions in the bite zone in which thermal boundary conditions as well as heat generation due to deformation are predicted by finite element-based, approximate models. The prediction accuracy of the proposed model is examined through comparison with predictions from a finite element process model.

• KIEAE Journal
• /
• v.8 no.5
• /
• pp.11-16
• /
• 2008

This research has established CFD model on pit's cool-tube system through heat and air movement simulations, of which data was based on experimental and verification. This research work verified the effectiveness of the cool-tube system by analysing temperature, humidity and air current of the actually installed case. Also, we analysed heat transfer through air current simulation and the results are as followings. Firstly, we experiment on temperature, humidity and speed of air currents of the cool tube system with pit space during the month of May (spring). The average exterior temperature was $16.1^{\circ}C$, and $18.2^{\circ}C$ for the pit, $24.7^{\circ}C$ for the compressor room. Secondly, based on measured data of real case, we have analysed heat transfer through air current simulation and verified our proposed model. The actual measurement of average temperature of exhaust air of the pit's area is $19.7^{\circ}C$ with tolerance of $-0.33^{\circ}C{\sim}-0.6^{\circ}C$ compared to above simulations. Thirdly, having verified air current simulation model with formation of 260,000 and 1,000,000 cells, we could get reasonable near values with 260,000 cells. Lastly, the next step of research would be focused on proposing the best possible pit's cool-tube system after analysis of heat transfer of the air current simulation based on verified CFD model.

• Journal of electromagnetic engineering and science
• /
• v.10 no.4
• /
• pp.231-236
• /
• 2010

This study proposes a temperature compensation method of the complex permittivities of biological tissues and organs. The method is based on the temperature dependence of the Debye model of water, which has been thoroughly investigated. This method was applied to measured data at room temperature for whole blood, kidney cortex, bile, liver, and heart muscle. It is shown that our method can compensate for the Cole-Cole model using measured data at 20 $^{\circ}C$, given the Cole-Cole model based on measured data at 35 $^{\circ}C$, with a root-mean-squared deviation of 3~11 % and 2~6 % for the real and imaginary parts of the complex permittivities, respectively, among the measured tissues.