Browse > Article
http://dx.doi.org/10.9713/kcer.2022.60.2.223

The Development of a Fault Diagnosis Model Based on Principal Component Analysis and Support Vector Machine for a Polystyrene Reactor  

Jeong, Yeonsu (Department of Safety Engineering, Pukyong National University)
Lee, Chang Jun (Department of Safety Engineering, Pukyong National University)
Publication Information
Korean Chemical Engineering Research / v.60, no.2, 2022 , pp. 223-228 More about this Journal
Abstract
In chemical processes, unintended faults can make serious accidents. To tackle them, proper fault diagnosis models should be designed to identify the root cause of faults. To design a fault diagnosis model, a process and its data should be analyzed. However, most previous researches in the field of fault diagnosis just handle the data set of benchmark processes simulated on commercial programs. It indicates that it is really hard to get fresh data sets on real processes. In this study, real faulty conditions of an industrial polystyrene process are tested. In this process, a runaway reaction occurred and this caused a large loss since operators were late aware of the occurrence of this accident. To design a proper fault diagnosis model, we analyzed this process and a real accident data set. At first, a mode classification model based on support vector machine (SVM) was trained and principal component analysis (PCA) model for each mode was constructed under normal operation conditions. The results show that a proposed model can quickly diagnose the occurrence of a fault and they indicate that this model is able to reduce the potential loss.
Keywords
Fault diagnosis; Principal component analysis; Support vector machine;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 Wold, S., Esbensen, K. and Geladi, P., "Principal Component Analysis," Chemom. Intell. Lab. Syst., 2, 37-52(1987).   DOI
2 Hotelling, H., Multivariate Quality Control-Illustrated by the Air Testing of Sample Bombsights, in Techniques of Statistical Analysis, Eisenhart C, Hastay M.W. and Wallis W.A., (eds) McGrawHill, New York, 111-184(1947).
3 Lee, K. O. and Lee, C. J., "The Development of a Fault Diagnosis Model based on the Parameter Estimations of Partial Least Square Models," J. Korean Soc. Saf., 34, 59-67(2019).
4 Venkatasubramanian, V., Rengaswamy, R., Yin, K. and Kavuri, S. N., "A Review of Process Fault Detection and Diagnosis: Part II: Qualitative Models and Search Strategies," Com. Chem. Eng., 27, 311-326(2003).
5 Venkatasubramanian, V., Rengaswamy, R., Yin, K. and Kavuri, S. N., "A Review of Process Fault Detection and Diagnosis: Part III: Process History Based Methods," Com. Chem. Eng., 27, 327-346(2003).   DOI
6 Lee, C. J., Ko, J. W. and Lee, G., "Operation Modes Classification of Chemical Processes for History Data-Based Fault Diagnosis Methods," Korean Chem. Eng. Res., 46, 383-388(2008).
7 Venkatasubramanian, V., Rengaswamy, R., Yin, K. and Kavuri, S. N., "A Review of Process Fault Detection and Diagnosis: Part I: Quantitative Model-based Methods," Com. Chem. Eng., 27, 293-311(2003).   DOI
8 Lee, C. J., Lee, G. and Lee, J. M., "A Fault Magnitude Based Strategy for Effective Fault Classification," Chem. Eng. Res. Des., 91, 530-541(2013).   DOI
9 Almeida, G. M., Park, S. W., Kim, S. C. and Lee, C. J., "A Smapiling-based Stochastic Optimization for a Boiler Process in a Pulp Industry," Korean J. Chem. Eng., 37, 588-596(2020).   DOI
10 Pyun, H., Lee, C.-J. and Lee, W. B., "Development of Monitoring System for the LNG Plant Fractionation Process based on Multimode Principal Component Analysis," J. Korean Inst. Gas, 23, 32-38(2019).
11 Park, J. Y. and Lee, C. J., "Principal Component Analysis Based Method for Effective Fault Diagnosis," J. Korean Soc. Saf., 29, 73-77(2014).   DOI
12 Vapnik, V. N., The nature of statistical learning theory, Springer Verlag, New York, U.S.A., 17-68(1995).