Detection of Intermittent Oscillation in Process Control Loops with Semi-Supervised Learning

Nova Zidane Ibrahim, Awang Noor Indra Wardana, Agus Arif


Oscillations in the control loops indicate the poor performance of the control loops. The occurrence of oscillations in the process control loop is quite high in the industry, so it needs to be reduced so that the control loop can work properly. The first step for oscillation reduction is oscillation detection. One type of oscillation that is difficult to detect is intermittent oscillation. The smart factory concept encourages the development of the intermittent oscillation detection system using machine learning by being implemented online. Therefore, in this study an online intermittent oscillation detection program is built using K-nearest neighbor (KNN)-based Semi-supervised learning (SSL) method. The SSL method applied is self-training. The training data was obtained by a simulation of the Tennessee Eastman Process. The data is segmented based on window size and extracted time series features. The extracted data is used to build a model to detect oscillations caused by stiction, tuning errors, and external disturbances in the reactor. The model is implemented online with sliding windows and MQTT. The best accuracy and F1-score of the model obtained are 96.15% and 95.15%. In online detection, the model detects the type of oscillation with an average time of 305 seconds.


Intermittent oscillation; Control loops; Semi-supervised learning; K-nearest neighbor

Full Text:



D. Zheng, X. Sun, S. K. Damarla, A. Shah, J. Amalraj, and B. Huang, “Valve Stiction Detection and Quantification Using a K-Means Clustering Based Moving Window Approach,” Ind. Eng. Chem. Res., vol. 60, no. 6, pp. 2563–2577, Feb. 2021, doi: 10.1021/acs.iecr.0c05609.

R. Srinivasan and R. Rengaswamy, “Control Loop Performance Assessment. 1. A Qualitative Approach for Stiction Diagnosis,” Ind. Eng. Chem. Res., vol. 44, no. 17, pp. 6708–6718, Aug. 2005, doi: 10.1021/ie0490280.

W. L. Bialkowski, “Dreams vs. Reality: A View from Both Sides of The Gap,” Pulp Pap, vol. 94, pp. 19–27, 1994.

B. S. Torres, F. B. Carvalho, M. O. Fonseca, and C. S. Filho, “Performance Assessment of Control Loops − Case Studies,” Proc IFAC ADCHEM, pp. 1–6, 2006.

V. Akavalappil and T. K. Radhakrishnan, “Comparison of Current State of Control Valve Stiction Detection and Quantification Techniques,” Trans. Inst. Meas. Control, vol. 44, no. 3, pp. 562–579, Feb. 2022, doi: 10.1177/01423312211038288.

Y. Arbabi Yazdi, H. Toossian Shandiz, and H. Gholizade Narm, “Automatic Oscillations Detection and Classification of Control Loop using Generalized Machine Learning Algorithms,” Trans. Inst. Meas. Control, vol. 45, no. 3, pp. 476–491, Feb. 2023, doi: 10.1177/01423312221118129.

M. Jelali and B. Huang, Eds., Detection and Diagnosis of Stiction in Control Loops. London, UK: Springer London, 2010. doi: 10.1007/978-1-84882-775-2.

Z. Guo, L. Xie, T. Ye, and A. Horch, “Online Detection of Time-Variant Oscillations Based on Improved ITD,” Control Eng. Pract., vol. 32, pp. 64–72, Aug. 2014, doi: 10.1016/j.conengprac.2014.07.002.

Z. Guo, J. Shen, L. Xie, X. Chen, and H. Su, “Automatic Detection of Multiple Oscillations by Wavelet Analysis,” Comput. Electr. Eng., vol. 40, no. 7, pp. 2167–2177, Oct. 2014, doi: 10.1016/j.compeleceng.2014.03.007.

L. Xie, X. Lang, A. Horch, and Y. Yang, “Online Oscillation Detection in The Presence of Signal Intermittency,” Control Eng. Pract., vol. 55, pp. 91–100, Jul. 2016, doi: 10.1016/j.conengprac.2016.06.020.

M. F. Ullah, L. Das, S. Parmar, R. Rengaswamy, and B. Srinivasan, “On Developing a Framework for Detection of Oscillations in Data,” ISA Trans., vol. 89, pp. 96–112, Jun. 2019, doi: 10.1016/j.isatra.2018.12.026.

J. W. V. Dambros, J. O. Trierweiler, and M. Farenzena, “Oscillation Detection in Process Industries – Part I: Review of The Detection Methods,” J. Process Control, vol. 78, pp. 108–123, Jun. 2019, doi: 10.1016/j.jprocont.2019.04.002.

M. Jelali, Control Performance Management in Industrial Automation. London, UK: Springer London, 2013. doi: 10.1007/978-1-4471-4546-2.

R. Rai, M. K. Tiwari, D. Ivanov, and A. Dolgui, “Machine Learning in Manufacturing and Industry 4.0 Applications,” Int. J. Prod. Res., vol. 59, no. 16, pp. 4773–4778, Aug. 2021, doi: 10.1080/00207543.2021.1956675.

Z. Ge, Z. Song, S. X. Ding, and B. Huang, “Data Mining and Analytics in the Process Industry: The Role of Machine Learning,” IEEE Access, vol. 5, pp. 20590–20616, 2017, doi: 10.1109/ACCESS.2017.2756872.

J. W. V. Dambros, J. O. Trierweiler, M. Farenzena, and M. Kloft, “Oscillation Detection in Process Industries by a Machine Learning-Based Approach,” Ind. Eng. Chem. Res., vol. 58, no. 31, pp. 14180–14192, Jul. 2019, doi: 10.1021/acs.iecr.9b01456.

H. Wu and J. Zhao, “Deep Convolutional Neural Network Model Based Chemical Process Fault Diagnosis,” Comput. Chem. Eng., vol. 115, pp. 185–197, Jul. 2018, doi: 10.1016/j.compchemeng.2018.04.009.

S. Sharma, V. Kumar, and K. P. S. Rana, “Machine Learning Application for Oscillation Detection in Control Loops,” in Soft Computing: Theories and Applications, vol. 1053, M. Pant, T. K. Sharma, O. P. Verma, R. Singla, and A. Sikander, Eds. Singapore: Springer Singapore, 2020, pp. 1067–1075. doi: 10.1007/978-981-15-0751-9_98.

Y. Yao, J. Zhang, W. Luo, and Y. Dai, “A Hybrid Intelligent Fault Diagnosis Strategy for Chemical Processes Based on Penalty Iterative Optimization,” Processes, vol. 9, no. 8, p. 1266, Jul. 2021, doi: 10.3390/pr9081266.

D. F. Rabba, A. N. I. Wardana, and N. Effendy, “Intermittent Oscillation Diagnosis in a Control Loop Using Extreme Gradient Boosting,” J. Nas. Tek. Elektro, vol. 11, no. 3, 2022, doi:

N. T. Tsanya, A. N. I. Wardana, and N. Effendy, “Deteksi Osilasi Kontrol pada Proses Industri dengan Menggunakan Jaringan Saraf Tiruan - Review,” J. EECCIS, vol. 16, no. 3, pp. 71–78, Dec. 2022.

W. Xueli, J. Zhiyong, and Y. Dahai, “An Improved KNN Algorithm Based on Kernel Methods and Attribute Reduction,” in 2015 Fifth International Conference on Instrumentation and Measurement, Computer, Communication and Control (IMCCC), Qinhuangdao, China, Sep. 2015, pp. 567–570. doi: 10.1109/IMCCC.2015.125.

Z. Ge, “Semi-Supervised Data Modeling and Analytics in The Process Industry: Current Research Status and Challenges,” IFAC J. Syst. Control, vol. 16, p. 100150, Jun. 2021, doi: 10.1016/j.ifacsc.2021.100150.

N. Z. Ibrahim, “Detection of Intermittent Oscillation in Tennessee Eastman Process Control Loop using KNN-Based Semi-Supervised Learning Method,” Undergraduate Final Project, Universitas Gadjah Mada, Yogyakarta, 2022.

J. J. Downs and E. F. Vogel, “A Plant-wide Industrial Process Control Problem,” Comput. Chem. Eng., vol. 17, no. 3, pp. 245–255, 1993, doi: 10.1016/0098- 1354(93)80018-I.

Y. Y. S. Henry, C. Aldrich, and H. Zabiri, “Detection and severity identification of control valve stiction in industrial loops using integrated partially retrained CNN-PCA frameworks,” Chemom. Intell. Lab. Syst., vol. 206, p. 104143, Nov. 2020, doi: 10.1016/j.chemolab.2020.104143.

M. Barandas et al., “TSFEL: Time Series Feature Extraction Library,” SoftwareX, vol. 11, p. 100456, Jan. 2020, doi: 10.1016/j.softx.2020.100456.

J. Tanha, M. van Someren, and H. Afsarmanesh, “Semi-Supervised Self-Training for Decision Tree Classifiers,” Int. J. Mach. Learn. Cybern., vol. 8, no. 1, pp. 355–370, Feb. 2017, doi: 10.1007/s13042-015-0328-7


Article Metrics

Abstract view : 0 times
PDF - 0 times


  • There are currently no refbacks.

View My Stats


Creative Commons License

Jurnal Rekayasa Elektrika (JRE) is published under license of Creative Commons Attribution-ShareAlike 4.0 International License.