Korean Chemical Engineering Research

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

DOI QR Code

Fault Detection in LDPE Process using Machine Learning Techniques

머신러닝 기법을 활용한 LDPE 공정의 이상 감지

  • Received : 2020.01.29
  • Accepted : 2020.03.06
  • Published : 2020.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

We propose a machine learning-based method for proactively detecting faults in LDPE processes and predicting equipment lifespan. It is important to detect and prevent unexpected faults in chemical processes in order to maximize safety and productivity. Since LDPE process is a high-pressure process up to 3,000 kg/㎠g or more, once ESD occurs, it can result in productivity loss due to increased maintenance periods. By collecting key variables operation data of the process and using unsupervised machine leaning methods, we developed a fault detection model which detected 4 ESDs 2.4 days prior to the occurrence. In addition, it was confirmed that the life expectancy of a hyper compressor can be predicted by using the physically significant key variables.

머신러닝 기법을 활용하여 LDPE (Low Density Polyethylene) 공정의 이상을 사전 감지하고, 설비의 수명을 예측할 수 있는 기술을 소개한다. 안전성과 생산성 극대화를 위해, 화학 공정의 예상치 못한 이상을 사전에 감지하고 예방하는 것은 매우 중요하다. LDPE 공정은 3,000 kg/㎠g 이상까지 승압되는 고압 공정이기 때문에, ESD (Emergency Shutdown)가 발생하면 예상치 못한 부동이 발생하고, 그에 따른 보수 기간 증가로 인한 생산성 손실이 발생한다. 고압 공정의 주요 변수들의 운전 데이터를 수집하고, 비지도학습 머신러닝 기술을 활용하여, ESD의 사전 감지 모형을 개발하였다. 4회의 ESD를 2.4일 전에 감지하는 결과를 얻을 수 있었다. 더불어, 물리적으로 의미 있는 핵심 변수들을 활용하면, 고압 설비의 수명을 예측할 수 있음을 확인할 수 있었다.

Keywords

References

  1. Venkatasubramanian, V., Rengaswamy, R., Yin, K. and Kavuri, S. N., "A Review of Process Fault Detection and Diagnosis: Part I: Quantitative Model-based Methods," Comput. Chem. Eng., 27, 293-311(2003). https://doi.org/10.1016/S0098-1354(02)00160-6
  2. Venkatasubramanian, V., Rengaswamy, R. and Kavuri, S. N., "A Review of Process Fault Detection and Diagnosis: Part II: Qualitative Models and Search Strategies," Comput. Chem. Eng., 27, 313-326(2003). https://doi.org/10.1016/S0098-1354(02)00161-8
  3. Venkatasubramanian, V., Rengaswamy, R., Kavuri, S. N. and Yin, K., "A Review of Process Fault Detection and Diagnosis: Part III: Process History Based Methods," Comput. Chem. Eng., 27, 327-346(2003). https://doi.org/10.1016/S0098-1354(02)00162-X
  4. Li, H., Wang, H. and Fan, W., "Multimode Process Fault Detection Based on Local Density Ratio-weighted Support Vector Data Description," Ind. Eng. Chem. Res., 56, 2475-2491(2017). https://doi.org/10.1021/acs.iecr.6b03306
  5. Gajjar, S. and Palazoglu, A., "A Data-driven Multidimensional Visualization Technique for Process Fault Detection and Diagnosis," Chemometrics and Intelligent Laboratory Systems, 154, 122-136 (2016). https://doi.org/10.1016/j.chemolab.2016.03.027
  6. Zhang, Z. and Zhao, J., "A Deep Belief Network Based Fault Diagnosis Model for Complex Chemical Processes," Comput. Chem. Eng., 107, 395-407(2017). https://doi.org/10.1016/j.compchemeng.2017.02.041
  7. Liu, K., Fei, Z., Yue, B., Liang, J. and Lin, H., "Adaptive Sparse Principal Component Analysis for Enhanced Process Monitoring and Fault Isolation," Chemometrics and Intelligent Laboratory Systems, 146, 426-436(2015). https://doi.org/10.1016/j.chemolab.2015.06.014
  8. Adedigba, S. A., Khan, F. and Yang, M., "Dynamic Failure Analysis of Process Systems Using Principal Component Analysis and Bayesian Network," Ind. Eng. Chem. Res., 56, 2094-2106(2017). https://doi.org/10.1021/acs.iecr.6b03356
  9. He, Q. P. and Wang, J., "Statistical Process Monitoring as a Big Data Analytics Tool for Smart Manufacturing," Journal of Process Control, 67, 35-43(2018). https://doi.org/10.1016/j.jprocont.2017.06.012