Korean Chemical Engineering Research

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

DOI QR Code

Prediction of Distillation Column Temperature Using Machine Learning and Data Preprocessing

머신 러닝과 데이터 전처리를 활용한 증류탑 온도 예측

  • Lee, Yechan (Green Materials and Processes R&D Group, Korea Institute of Industrial Technology) ;
  • Choi, Yeongryeol (Green Materials and Processes R&D Group, Korea Institute of Industrial Technology) ;
  • Cho, Hyungtae (Green Materials and Processes R&D Group, Korea Institute of Industrial Technology) ;
  • Kim, Junghwan (Green Materials and Processes R&D Group, Korea Institute of Industrial Technology)
  • 이예찬 (한국생산기술연구원 친환경재료공정연구그룹) ;
  • 최영렬 (한국생산기술연구원 친환경재료공정연구그룹) ;
  • 조형태 (한국생산기술연구원 친환경재료공정연구그룹) ;
  • 김정환 (한국생산기술연구원 친환경재료공정연구그룹)
  • Received : 2020.10.14
  • Accepted : 2021.01.04
  • Published : 2021.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

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%.

화학 공정의 주요 설비 중 하나인 증류탑은 물질들의 끓는점 차이를 이용하여 혼합물에서 원하는 생산물을 분리하는 설비이며 증류 공정은 많은 에너지가 소비되기 때문에 최적화 및 운전 예측이 필요하다. 본 연구의 대상 공정은 공급처에 따라 원료의 조성이 일정하지 않아 정상 상태로 운전이 어려워 효율적인 운전이 어렵다. 이를 해결하기 위해 데이터 기반 예측 모델을 이용하여 운전 조건을 예측 할 수 있다. 하지만 미가공 공정 데이터에는 이상치 및 노이즈가 포함되어 있어 예측 성능을 향상시키기 위해 데이터 전처리가 필요하다. 본 연구에서는 인공 신경망 모델인 Long short-term memory (LSTM)과 Random forest (RF)를 사용하여 모델을 최적화한 후, 데이터 전처리 방법으로 Low-pass filter와 One-class support vector machine을 사용하여 데이터 전처리 방법 및 범위에 따른 예측 성능을 비교하였다. 각 모델의 예측 성능과 데이터 전처리의 영향은 R2과 RMSE를 사용하여 비교하였다. 본 연구의 결과, 전처리를 통해 LSTM의 경우 R2은 0.791에서 0.977으로 RMSE는 0.132에서 0.029로 각각 23.5%, 78.0% 향상되었고, RF의 경우 R2은 0.767에서 0.938으로 RMSE는 0.140에서 0.050으로 각각 22.3%, 64.3% 향상되었다.

Keywords

References

  1. Kartal, F. and Ozveren, U., "A Deep Learning Approach for Prediction of Syngas Lower Heating Value from CFB Gasifier in Aspen Plus®," Energy, 209, 118457(2020). https://doi.org/10.1016/j.energy.2020.118457
  2. Sneesby, M. G., Tade, M. O., Datta, R. and Smith, T. N., "ETBE Synthesis via Reactive Distillation. 1. Steady-State Simulation and Design Aspects," Ind. Eng. Chem. Res., 36(5), 1855-1869 (1997). https://doi.org/10.1021/ie960283x
  3. Sharma, N. and Singh, K., "Neural Network and Support Vector Machine Predictive Control of Tert-amyl Methyl Ether Reactive Distillation Column," Syst. Sci. Control Eng., 2(1), 512-526(2014). https://doi.org/10.1080/21642583.2014.924082
  4. Lee, D. W. and Lee, S. W., "Hourly Prediction of Particulate Matter (PM2.5) Concentration Using Time Series Data and Random Forest," Trans. Softw. Data Eng., 9(4), 129-136(2020).
  5. Vijaya Raghavan, S. R., Radhakrishnan, T. K. and Srinivasan, K., "Soft Sensor Based Composition Estimation and Controller Design for an Ideal Reactive Distillation Column," ISA Trans., 50(1), 61-70(2011). https://doi.org/10.1016/j.isatra.2010.09.001
  6. Howsalya Devi, R. D., Bai, A. and Nagarajan, N., "A Novel Hybrid Approach for Diagnosing Diabetes Mellitus Using Farthest First and Support Vector Machine Algorithms," Obes. Med., 17, 100152(2020) https://doi.org/10.1016/j.obmed.2019.100152
  7. Erkus, E. C. and Purutcuoglu, V., "Outlier Detection and Quasiperiodicity Optimization Algorithm: Frequency Domain Based Outlier Detection (FOD)," Eur. J. Oper. Res, 291(2), 560-574(2020). https://doi.org/10.1016/j.ejor.2020.01.014
  8. Zhang, R., Zhang, S. and Muthuraman, S, J. J. "One Class Support Vector Machine for Anomaly Detection in the Communication Network Performance Data," 5th WSEAS Int. Conf. Appl. Electromagn. Wirel. Opt. Commun. Tenerife, Spain, December 14-16 (2007).
  9. Kim, J., Park, N. S., Yun, S., Chae, S. H. and Yoon, S., "Application of Isolation Forest Technique for Outlier Detection in Water Quality Data," J. Korean Soc. Environ. Eng., 40(12), 473-480(2018). https://doi.org/10.4491/ksee.2018.40.12.473
  10. Guinon, J. L., Ortega, E., Garcia-Anton, J. and Perez-herranz, V., "Moving Average and Savitzki-Golay Smoothing Filters Using Mathcad," International Conference on Engineering Education, July, Coimbra, 1-4(2007).
  11. Guo, H., Yu, M., Liu, J. and Ning, J., "Butterworth Low-pass Filter for Processing Inertial Navigation System Raw Data," J. Surv. Eng., 130(4), 175-178(2004). https://doi.org/10.1061/(ASCE)0733-9453(2004)130:4(175)
  12. Panigrahi, S., Karali, Y. S. and Behera, H., "Time Series Forecasting Using Evolutionary Neural Network," Int. J. Comput. Appl., 75(10), 13-17(2013). https://doi.org/10.5120/13146-0553
  13. Zhang, Z., Wu, Z., Rincon, D. and Christofides, P. D., "Real-time Optimization and Control of Nonlinear Processes Using Machine Learning," Mathematics, 7(10), 1-25(2019).
  14. Oh, K., Kwon, H., Roh, J., Choi, Y., Park, H., Cho, H. and Kim, J., "Development of Machine Learning-Based Platform for Distillation Column," Korean. Chem. Eng. Res., 23(4), 565-572(2020).
  15. Kwon, H., Oh, K., Chung, Y. G., Cho, H. and Kim, J., "Development of Machine Learning Model for Prediction Distillation Column Temperature," Appl. Chem. Eng., 31(5), 520-525(2020). https://doi.org/10.14478/ACE.2020.1057
  16. Kwon, H., Oh, K., Choi, Y., CHung, Y. G, Kim, J., "Development and Application of Machine Learning-based Prediction Model for Distillation Column, Int. J. Intell. Syst., 36, 1970-1997(2021). https://doi.org/10.1002/int.22368
  17. Kim, T. J. and Hong, J. S., "Classification of Parent Company's Downward Business Clients Using Random Forest: Focused on Value Chain at the Industry of Automobile Parts," J. Soc. E-bus. Stud., 23(1), 1-22(2018). https://doi.org/10.7838/jsebs.2018.23.1.001
  18. Kim, D. W., Lee, S. C., Kim, M. J., Lee, E. J. and Yoo, C. K., "Development of QSAR Model Based on the Key Molecular Descriptors Selection and Computational Toxicology for Prediction of Toxicity of PCBs," Korean Chem. Eng. Res., 54(5), 621-629(2016). https://doi.org/10.9713/kcer.2016.54.5.621
  19. Giap, V., Pineda, I. T., Lee, J. Y., Lee, D. K., Kim, Y. S., Ahn, K. Y. and Lee, Y. D., "Performance Prediction Model of Solid Oxide Fuel Cell Stack Using Deep Neural Network Technique, Trans," Korean Hydrog. Energy Soc., 31(5), 436-443(2020). https://doi.org/10.7316/KHNES.2020.31.5.436