Korean Chemical Engineering Research

The Korean Institute of Chemical Engineers (한국화학공학회)
권호 표지
DOI QR코드

DOI QR Code

AutoML and Artificial Neural Network Modeling of Process Dynamics of LNG Regasification Using Seawater

해수 이용 LNG 재기화 공정의 딥러닝과 AutoML을 이용한 동적모델링

  • Shin, Yongbeom (Department of Chemical Engineering, Myongji University) ;
  • Yoo, Sangwoo (Department of Disaster and Safety, Myongji University) ;
  • Kwak, Dongho (Department of Chemical Engineering, Myongji University) ;
  • Lee, Nagyeong (Department of Chemical Engineering, Myongji University) ;
  • Shin, Dongil (Department of Chemical Engineering, Myongji University)
  • 신용범 (명지대학교 화학공학과) ;
  • 유상우 (명지대학교 재난안전학과) ;
  • 곽동호 (명지대학교 화학공학과) ;
  • 이나경 (명지대학교 화학공학과) ;
  • 신동일 (명지대학교 화학공학과)
  • Received : 2020.12.29
  • Accepted : 2021.02.23
  • Published : 2021.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

First principle-based modeling studies have been performed to improve the heat exchange efficiency of ORV and optimize operation, but the heat transfer coefficient of ORV is an irregular system according to time and location, and it undergoes a complex modeling process. In this study, FNN, LSTM, and AutoML-based modeling were performed to confirm the effectiveness of data-based modeling for complex systems. The prediction accuracy indicated high performance in the order of LSTM > AutoML > FNN in MSE. The performance of AutoML, an automatic design method for machine learning models, was superior to developed FNN, and the total time required for model development was 1/15 compared to LSTM, showing the possibility of using AutoML. The prediction of NG and seawater discharged temperatures using LSTM and AutoML showed an error of less than 0.5K. Using the predictive model, real-time optimization of the amount of LNG vaporized that can be processed using ORV in winter is performed, confirming that up to 23.5% of LNG can be additionally processed, and an ORV optimal operation guideline based on the developed dynamic prediction model was presented.

ORV의 열교환 효율 향상 및 운전 최적화를 위한, first principle 기반 모델링 연구들이 수행되어왔지만, ORV의 열 전달 계수는 시간, 위치에 따라 불규칙한 시스템으로, 복잡한 모델링 과정을 거친다. 본 연구는 복잡한 시스템에 대한 데이터 기반 모델링의 실효성을 확인하고자, LNG 재기화 공정의 실제 운전데이터를 이용해, ORV의 해수 유량, 해수온도, LNG 유량 변화에 따른 토출 NG 온도 및 토출 해수 온도의 동적 변화 예측이 가능한, FNN, LSTM 및 AutoML 기반 모델링을 진행하였다. 예측 정확도는 MSE 기준 LSTM > AutoML > FNN 순으로 좋은 성능을 보였다. 기계학습 모델의 자동설계 방법인 AutoML의 성능은 개발된 FNN보다 뛰어났으며, 모델 개발 전체소요시간은 복잡한 모델인 LSTM 대비 1/15로 크게 차이를 보여 AutoML의 활용 가능성을 보였다. LSTM과 AutoML을 이용한 토출 NG 및 토출 해수 온도의 예측은 0.5 K 미만의 오차를 보였다. 예측모델을 활용해, 겨울철 ORV를 이용해 처리 가능한 LNG 기화량의 실시간 최적화를 수행하여, 기존 대비 최대 23.5%의 LNG를 추가 처리 가능함을 확인하였고, 개발된 동적 예측모델 기반의 ORV 최적 운전 가이드라인을 제시하였다.

Keywords

References

  1. Mokhatab, S., Mak, J. Y., Valappil, J. V. and Wood, D. A., "Handbook of Liquefied Natural Gas," Gulf Professional Publishing, 90-93(2014).
  2. Su, H., Yu, S., Fan, J. and Ling, X., "Numerical Simulation of Gasification Process on Rib-tube of Open Rack Vaporizer," J. Comput., 9(2), (2014).
  3. Wang, M., Jin, T., Tang, K. and Chen, G., "Numerical Simulation Analysis of a Heat Transfer Tube in SuperORV," Natural Gas Industry, 33, 102-107(2013).
  4. Jin, T., Wang, M. and Tang, K., "Simulation and Performance Analysis of a Heat Transfer Tube in SuperORV," Cryogenics, 61, 127-132(2014). https://doi.org/10.1016/j.cryogenics.2013.09.008
  5. Deng, Z., Hui, K., Zhang, Y. and Cao, Y., "Numerical Simulation Analysis of the Flow Field and Convective Heat Transfer in New Super Open Rack Vaporizer," Appl. Therm. Eng., 106, 721-730 (2016). https://doi.org/10.1016/j.applthermaleng.2016.03.071
  6. Cheng, H., Ju, Y. and Fu, Y., "Thermal Performance Calculation with Heat Transfer Correlations and Numerical Simulation Analysis for Typical LNG Open Rack Vaporizer," Appl. Therm. Eng., 149, 1069-1079(2018). https://doi.org/10.1016/j.applthermaleng.2018.11.044
  7. Pan, J., Li, R., Lv, T., Wu, G. and Deng, Z., "Thermal Performance Calculation and Analysis of Heat Transfer Tube in Super Open Rack Vaporizer," Appl. Therm. Eng., 93, 27-35(2016). https://doi.org/10.1016/j.applthermaleng.2015.09.047
  8. Qi, C., Yi, C., Wang, B., Wang, W. and Xu, J., "Thermal Performance Analysis and the Operation Method with Low Temperature Seawater of Super Open Rack Vaporizer for Liquefied Natural Gas," Appl. Therm. Eng., 150, 61-69(2019). https://doi.org/10.1016/j.applthermaleng.2018.12.152
  9. Singh, A. K., Tyagi, B. and Kumar, V., "First Principle Modeling and Neural Network-Based Empirical Modeling with Experimental Validation of Binary Distillation Column," Chem. Prod. Process. Model., 8(1) 53-70(2013). https://doi.org/10.1515/cppm-2013-0011
  10. Gupta, A., "Introduction to Deep Learning: Part1," CEP, Jun, 22-29(2018).
  11. Venkatasubramanian, V., "The Promise of Artificial Intelligence in Chemical Engineering: Is It Here, Finally?," AIChE Journal, 65(2), 466-478(2018). https://doi.org/10.1002/aic.16489
  12. Zhang, Z., Wu, Z., Rincon, D. and Christofides, P. D., "Real-Time Optimization and Control of Nonlinear Processes Using Machine Learning," Mathematics, 7(10), 890-914(2019). https://doi.org/10.3390/math7100890
  13. D'Alessandro, A., Izurieta, E. and Tonelli, S., "Decision-making tools for a LNG Regasification Plant Siting," J. Loss. Prev. Process Ind, 43, 255-262(2016). https://doi.org/10.1016/j.jlp.2016.05.012
  14. Houde, S., Shurong, Y., Jianling, F. and Xing, W., "Numerical Analysis on Rib-Tubes of Seawater Open Rack Vaporizer With the Spoiler Lever," Polish Marit. Res., 24(S2), 14-21(2017). https://doi.org/10.1515/pomr-2017-0059
  15. Kim, H., Park, M., Kim, C. W. and Shin, D., "Source Localization for Hazardous Material Release in an Outdoor Chemical Plant via a Combination of LSTM-RNN and CFD Simulation," Comput. Chem. Eng., 125, 476-489(2019). https://doi.org/10.1016/j.compchemeng.2019.03.012
  16. Jin, H., Song, Q. and Hu, X., "Auto-Keras: An Efficient Neural Architecture Search System," KDD'19, Aug, Anchorage, AK, USA(2019).
  17. Sola, J. and Sevilla, J., "Importance of Input Data Normalization for the Application of Neural Networks to Complex Industrial Problems," IEEE Trans Nucl Sci, 44(3), 1464-1468(1997). https://doi.org/10.1109/23.589532
  18. Wainwright, R. and Shenfield, A., "Human Activity Recognition Making Use of Long Short-Term Memory Techniques," Athens J. Sci., 6(1), 19-34(2019). https://doi.org/10.30958/ajs.6-1-2
  19. Kim, N.-K. and Yun, S.-K., "Study on the LNG Vaporization Characteristics of Open Rack Vaporizer(ORV) with Two-way Seawater Supplying System," J. KIGAS, 23(1), 41-46(2019).