Improving Root Cause Analysis by Detecting and Removing Transient Changes in Oscillatory Time Series with Application to a 1,3-Butadiene Process
- Baifan ZhouBaifan ZhouKarlsruhe Institute of Technology, Kaiserstraße 12, Karlsruhe 76131, GermanyMore by Baifan Zhou
- ,
- Moncef Chioua*Moncef Chioua*Email: [email protected] (M.C.).ABB Corporate Research, Wallstadter Straße 59, Ladenburg 68526, GermanyMore by Moncef Chioua
- ,
- Margret BauerMargret BauerDepartment of Electrical, Electronic and Computer Engineering, University of Pretoria, Lynwood Road, Pretoria 0003, South AfricaMore by Margret Bauer
- ,
- Jan Christoph SchlakeJan Christoph SchlakeABB Corporate Research, Wallstadter Straße 59, Ladenburg 68526, GermanyMore by Jan Christoph Schlake
- , and
- Nina F. ThornhillNina F. ThornhillCentre for Process Systems Engineering, Department of Chemical Engineering, Imperial College London, London SW7 2AZ, United KingdomMore by Nina F. Thornhill
Abstract
Oscillations occurring in industrial process plants often reflect the presence of severe disturbances affecting process operations. Accurate detection and root-cause analysis of oscillations is of great interest for the economic viability of the process operation. Standard oscillation detection and root cause analysis methods require a large enough number of data samples. Unrelated transient changes superimposed on the oscillation pattern reduce the number of useful data samples. The present paper proposes simple heuristic methods to effectively detect and remove two types of transient changes from oscillatory signals, namely step changes and spikes. The proposed methods are used to preprocess oscillatory time series. The accuracy gained when using autocorrelation function method for oscillation detection (Thornhill, N. F.; Huang, B.; Zhang, H. J. Process Control2003, 13, 91–100) and transfer entropy method for oscillation propagation (Bauer, M.; Cox, J. W.; Caveness, M. H.; Downs, J. J.; Thornhill, N. F. IEEE Trans. Control Syst. Technol.2007, 15, 12–21) is experimentally evaluated. The methods are carried out on a 1,3-butadiene production process where several measurements showed an established oscillation occurring after a production level change.
Cited By
This article is cited by 15 publications.
- Michael Baron, Sergey V. Malov. Detection and estimation of multiple transient changes. Journal of Applied Statistics 2023, 50
(14)
, 2862-2888. https://doi.org/10.1080/02664763.2023.2174257
- Xun Lang, Yufeng Zhang, Lei Xie, Peng Li, Alexander Horch, Hongye Su. Detrending and Denoising of Industrial Oscillation Data. IEEE Transactions on Industrial Informatics 2023, 19
(4)
, 5809-5820. https://doi.org/10.1109/TII.2022.3188844
- Matthieu Lucke, Moncef Chioua, Nina F. Thornhill. From oscillatory to non-oscillatory disturbances: A comparative review of root cause analysis methods. Journal of Process Control 2022, 113 , 42-67. https://doi.org/10.1016/j.jprocont.2022.03.004
- Baifan Zhou, Tim Pychynski, Markus Reischl, Evgeny Kharlamov, Ralf Mikut. Machine learning with domain knowledge for predictive quality monitoring in resistance spot welding. Journal of Intelligent Manufacturing 2022, 33
(4)
, 1139-1163. https://doi.org/10.1007/s10845-021-01892-y
- Muhammad Yahya, Baifan Zhou, Zhuoxun Zheng, Dongzhuoran Zhou, John G. Breslin, Muhammad Intizar Ali, Evgeny Kharlamov. Towards Generalized Welding Ontology in Line with ISO and Knowledge Graph Construction. 2022, 83-88. https://doi.org/10.1007/978-3-031-11609-4_16
- Dongzhuoran Zhou, Baifan Zhou, Zhuoxun Zheng, Egor V. Kostylev, Gong Cheng, Ernesto Jiménez-Ruiz, Ahmet Soylu, Evgeny Kharlamov. Enhancing Knowledge Graph Generation with Ontology Reshaping – Bosch Case. 2022, 299-302. https://doi.org/10.1007/978-3-031-11609-4_45
- Hao Liu, Dechang Pi, Shuyuan Qiu, Xixuan Wang, Chang Guo. Data-driven identification model for associated fault propagation path. Measurement 2022, 188 , 110628. https://doi.org/10.1016/j.measurement.2021.110628
- Baifan Zhou, Dongzhuoran Zhou, Jieying Chen, Yulia Svetashova, Gong Cheng, Evgeny Kharlamov. Scaling Usability of ML Analytics with Knowledge Graphs: Exemplified with A Bosch Welding Case. 2021, 54-63. https://doi.org/10.1145/3502223.3502230
- Dongzhuoran Zhou, Baifan Zhou, Jieying Chen, Gong Cheng, Egor Kostylev, Evgeny Kharlamov. Towards Ontology Reshaping for KG Generation with User-in-the-Loop: Applied to Bosch Welding. 2021, 145-150. https://doi.org/10.1145/3502223.3502243
- Baifan Zhou, Yulia Svetashova, Andre Gusmao, Ahmet Soylu, Gong Cheng, Ralf Mikut, Arild Waaler, Evgeny Kharlamov. SemML: Facilitating development of ML models for condition monitoring with semantics. Journal of Web Semantics 2021, 71 , 100664. https://doi.org/10.1016/j.websem.2021.100664
- Baifan Zhou, Yulia Svetashova, Andre Gusmao, Ahmet Soylu, Gong Cheng, Ralf Mikut, Arild Waaler, Evgeny Kharlamov. SemML: Facilitating Development of ML Models for Condition Monitoring with Semantics. SSRN Electronic Journal 2021, 7 https://doi.org/10.2139/ssrn.3945440
- Baifan Zhou, Yulia Svetashova, Seongsu Byeon, Tim Pychynski, Ralf Mikut, Evgeny Kharlamov. Predicting Quality of Automated Welding with Machine Learning and Semantics. 2020, 2933-2940. https://doi.org/10.1145/3340531.3412737
- Baifan Zhou, Yulia Svetashova, Tim Pychynski, Ildar Baimuratov, Ahmet Soylu, Evgeny Kharlamov. SemFE. 2020, 3489-3492. https://doi.org/10.1145/3340531.3417436
- Thomas Gamer, Mario Hoernicke, Benjamin Kloepper, Reinhard Bauer, Alf J. Isaksson. The autonomous industrial plant – future of process engineering, operations and maintenance. Journal of Process Control 2020, 88 , 101-110. https://doi.org/10.1016/j.jprocont.2020.01.012
- Yulia Svetashova, Baifan Zhou, Tim Pychynski, Stefan Schmidt, York Sure-Vetter, Ralf Mikut, Evgeny Kharlamov. Ontology-Enhanced Machine Learning: A Bosch Use Case of Welding Quality Monitoring. 2020, 531-550. https://doi.org/10.1007/978-3-030-62466-8_33