Browse > Article
http://dx.doi.org/10.5762/KAIS.2019.20.9.551

Effect of Different Variable Selection and Estimation Methods on Performance of Fault Diagnosis  

Cho, Hyun-Woo (Department of Materials-Energy Science and Engineering, Daegu University)
Publication Information
Journal of the Korea Academia-Industrial cooperation Society / v.20, no.9, 2019 , pp. 551-557 More about this Journal
Abstract
Diagnosis of abnormal faults is essential for producing high quality products. The role of real-time diagnosis is quite increasing in the batch processes of producing high value-added products such as semiconductors, pharmaceuticals, and so forth. In this study, we evaluate the effect of variable selection and future-value estimation techniques on the performance of the diagnosis system, which is based on nonlinear classification and measurement data. The diagnostic performance can be improved by selecting only the variables that are important and have high contribution for diagnosis. Thus, the diagnostic performance of several variable selection techniques is compared and evaluated. In addition, missing data of a new batch, called future observations, should be estimated because the full data of a new batch is not available before the end of the cycle. In this work the use of different estimation techniques is analyzed. A case study on the polyvinyl chloride batch process was carried out so that optimal variable selection and estimation methods were obtained: maximum 21.9% and 13.3% improvement by variable selection and maximum 25.8% and 15.2% improvement by estimation methods.
Keywords
Fault; Diagnosis; Batch Process; Classification; Variable Selection; Estimation;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Z. Ge, "Process data analytics via probabilistic latent variable models: a tutorial review", Industrial and Engineering Chemistry Research, Vol.57, No.38, pp.12646-12661, 2018. DOI: https://doi.org/10.1021/acs.iecr.8b02913   DOI
2 K. Tidriri, N. Chatti, S. Verron, T. Tiplica, "Bridging data-driven and model-based approaches for process fault diagnosis and health monitoring: A review of researches and future challenges", Annual Reviews in Control, Vol.42, pp.63-81, 2016. DOI: https://doi.org/10.1016/j.arcontrol.2016.09.008   DOI
3 H. Rostami, J. Blue, C. Yugma, "Automatic equipment fault fingerprint extraction for the fault diagnostic on the batch process data", Applied Soft Computing, Vol.68, pp.972-989, 2018. DOI: https://doi.org/10.1016/j.asoc.2017.10.029   DOI
4 S. Bersimis, S. Psarakis, J. Panaretos, "Multivariate Statistical Process Control Charts: An Overview", Quality and Reliability Engineering International, Vol.23, pp.517-543, 2007. DOI: https://doi.org/10.1002/qre.829   DOI
5 H. Cho, K. Kim, "A method for predicting future observations in the monitoring of a batch process", Journal of Quality Technology, Vol.35, pp.59-69, 2003. DOI: https://doi.org/10.1080/00224065.2003.11980191   DOI
6 I. Guyon, J. Weston, S. Barnhill, V. Vapnik, "Gene selection for cancer classification using support vector machines", Machine Learning, Vol.46, pp.389-422, 2002. DOI: https://doi.org/10.1023/A:1012487302797   DOI
7 S. Wold, H. Antti, F. Lindgren, J. Ohman, "Orthogonal signal correction of near-infrared spectra", Chemometrics and Intelligent Laboratory Systems, Vo.44, pp.175-185, 1998. DOI: https://doi.org/10.1016/S0169-7439(98)00109-9   DOI