Oscillation Detection in Process Industries by a Machine Learning-Based Approach
- Jônathan W. V. Dambros*Jônathan W. V. Dambros*E-mail: [email protected]Department of Chemical Engineering, Federal University of Rio Grande do Sul, R. Eng. Luiz Englert, s/n, Campus Central, Porto Alegre, Rio Grande do Sul, BrazilDepartment of Computer Science, University of Kaiserslautern, 67663 Kaiserslautern, GermanyMore by Jônathan W. V. Dambros
- ,
- Jorge O. TrierweilerJorge O. TrierweilerDepartment of Chemical Engineering, Federal University of Rio Grande do Sul, R. Eng. Luiz Englert, s/n, Campus Central, Porto Alegre, Rio Grande do Sul, BrazilMore by Jorge O. Trierweiler
- ,
- Marcelo FarenzenaMarcelo FarenzenaDepartment of Chemical Engineering, Federal University of Rio Grande do Sul, R. Eng. Luiz Englert, s/n, Campus Central, Porto Alegre, Rio Grande do Sul, BrazilMore by Marcelo Farenzena
- , and
- Marius KloftMarius KloftDepartment of Computer Science, University of Kaiserslautern, 67663 Kaiserslautern, GermanyDepartment of Computer Science, University of Southern California, 1002 Childs Way, Los Angeles, California, United StatesMore by Marius Kloft
Abstract
Oscillatory control loop is a frequent problem in process industries. Its incidence highly degrades the plant profitability, which means oscillation detection and removal is fundamental. For detection, many automatic techniques have been proposed. These are usually based on rules compiled into an algorithm. For industrial application, in which the time series have very distinct properties and are subject to interferences such as noise and disturbances, the algorithm must include rules covering all possible time series structures. Since the development of this algorithm is near impractical, it is reasonable to say that current rule-based techniques are subject to incorrect detection. This work presents a machine learning-based approach for automatic oscillation detection in process industries. Rather than being rule-based, the technique learns the features of oscillatory and nonoscillatory loops by examples. A model based on deep feedforward network is trained with artificial data for oscillation detection. Additionally, two other models are trained for the quantification of the number of periods and oscillation amplitude. The evaluation of the technique using industrial data with different features reveals its robustness.
Cited By
This article is cited by 10 publications.
- Wahiba Bounoua, Muhammad Faisal Aftab, Christian Walter Peter Omlin. Controller Performance Monitoring: A Survey of Problems and a Review of Approaches from a Data-Driven Perspective with a Focus on Oscillations Detection and Diagnosis. Industrial & Engineering Chemistry Research 2022, 61
(49)
, 17735-17765. https://doi.org/10.1021/acs.iecr.2c02785
- Xun Lang, Yufeng Zhang, Lei Xie, Xin Jin, Alexander Horch, Hongye Su. Use of Fast Multivariate Empirical Mode Decomposition for Oscillation Monitoring in Noisy Process Plant. Industrial & Engineering Chemistry Research 2020, 59
(25)
, 11537-11551. https://doi.org/10.1021/acs.iecr.9b06351
- Qiming Chen, Qingsong Wen, Xialai Wu, Xun Lang, Yao Shi, Lei Xie, Hongye Su. Detection and time–frequency analysis of multiple plant-wide oscillations using adaptive multivariate intrinsic chirp component decomposition. Control Engineering Practice 2023, 141 , 105715. https://doi.org/10.1016/j.conengprac.2023.105715
- Wahiba Bounoua, Muhammad Faisal Aftab, Christian Walter Peter Omlin. Stiction detection in industrial control valves using Poincaré plot-based convolutional neural networks. IFAC-PapersOnLine 2023, 56
(2)
, 11687-11692. https://doi.org/10.1016/j.ifacol.2023.10.523
- Xun Lang, Qiming Chen, Shan Lu, Alexander Horch, Yufeng Zhang. On demodulation of time-varying oscillations in process plant. Journal of Process Control 2022, 120 , 28-43. https://doi.org/10.1016/j.jprocont.2022.10.004
- Dana Fatadilla Rabba, Awang Noor Indra Wardana, Nazrul Effendy. Intermittent Oscillation Diagnosis in a Control Loop Using Extreme Gradient Boosting. JURNAL NASIONAL TEKNIK ELEKTRO 2022, https://doi.org/10.25077/jnte.v11n3.1040.2022
- M. Aswin Krishna, Ayush Kedawat, Abhishek Bansal, Resmi Suresh. Feature engineering for neural network-based oscillation detection in process industries. 2022, 1153-1158. https://doi.org/10.1016/B978-0-323-95879-0.50193-4
- Jônathan W. V. Dambros, Jorge O. Trierweiler, Marcelo Farenzena. Industrial datasets and a tool for SISO control loops data visualization and analysis. Computers & Chemical Engineering 2021, 146 , 107198. https://doi.org/10.1016/j.compchemeng.2020.107198
- Jie Wang, Chunhui Zhao. Variants of slow feature analysis framework for automatic detection and isolation of multiple oscillations in coupled control loops. Computers & Chemical Engineering 2020, 141 , 107029. https://doi.org/10.1016/j.compchemeng.2020.107029
- Jie Wang, Chunhui Zhao, Haidong Fan, Weijian Zheng. The Automatic Analytics Framework for Multiple Oscillations in the Coupled Control Loops via a New Variant of Slow Feature Analysis. IFAC-PapersOnLine 2020, 53
(2)
, 11632-11637. https://doi.org/10.1016/j.ifacol.2020.12.645