344 411
Full Length Article
Journal of Cybersecurity and Information Management
Volume 11 , Issue 1, PP: 47-57 , 2023 | Cite this article as | XML | Html |PDF

Title

Data Driven Machine Learning For Fault Detection And Classification In Binary Distillation Column

  Silvester Bennys jakes 1 * ,   M. Mythily 2 ,   D. Vasanthi 3 ,   D. Manamalli 4

1  Department of Instrumentation, MIT Campus, Anna University, Chennai, India
    (jakesbenjamin22@gmail.com )

2  Department of Instrumentation, MIT Campus, Anna University, Chennai, India
    (mythily_eie@yahoo.co.in)

3  Department of Instrumentation, MIT Campus, Anna University, Chennai, India
    (vasanthi_d1@rediffmail.com)

4  Department of Instrumentation, MIT Campus, Anna University, Chennai, India
    ( manamalli_m@yahoo.com)


Doi   :   https://doi.org/10.54216/JCIM.110105

Received: October 27, 2022 Revised: December 20, 2022 Accepted: January 18, 2023

Abstract :

Mathematical programming can express competency concepts in a well-defined mathematical model for a particular Any system that runs is always be expected to experience faults in  different ways. Any change in the physical state of numerous components, control machinery, as well as environmental factors, might result in these problems. In process industries, where prompt detection is crucial in maintaining high product quality, dependability, and safety under various operating situations, finding these flaws is one of the most difficult tasks. The goal of this project is to implement several machine learning techniques for fault identification and classification in a binary distillation column. A pilot binary distillation unit (UOP3CC) is utilized for this purpose. The set up is run under normal operating conditions and the real time data is collected. Three common faults namely reboiler fault, feed pump fault and sensor fault are introduced one at a time and the faulty data is collected. These data are then introduced in to different machine learning algorithms like Logistic Regression, KNN, Naive Bayes, Decision Tree, Gradient Boosting, X Gradient Boosting, SVC and Light Gradient Boosting for model development. 70% of the data samples used for training and 30% of data samples are used for testing. It is found the Decision tree algorithm gives the best accuracy possible with 99.9%. Using decision tree algorithm, fault classification is performed for different datasets and is found that the algorithm was able to classify accurately even for new untrained datasets.

Keywords :

UOP3CC binary distillation column; Normal and faulty data; Machine learning algorithm; Fault classification.

References :

[1] Wang, G.-Y.; Yang, Z.-H.; Zhang, Y.; Wang, H.-H.; Zhang,       Z.-    X.; Gao, B.-J. A Preliminary Fault Detection Methodology for Abnormal Distillation Column Operations Using Acoustic Signals. Appl. Sci. 2022, 12, 12657. https://doi.org/10.3390/app122412657.

 

[2] Taqvi, SAA, Zabiri, H, Uddin, F, et al. Simultaneous fault diagnosis based on multiple kernel support vector machine in nonlinear dynamic distillation column. Energy Sci Eng. 2022; 10: 814– 839. doi:10.1002/ese3.1058

 

[3]      Taqvi, S.A., Tufa, L.D., Zabiri, H. et al. Fault detection in distillation\

          column using NARX neural network. Neural Comput & Applic 32,

          3503–3519 (2020). https://doi.org/10.1007/s00521-018-3658-z.

 

[4] Neema Davis, Gaurav Raina, krishna P.Jagannathan: Aframework for End- to-End Deep Learning-Based Anomaly Detection in Transportation Networks. CoRR abs/1911.08793(2020).

 

[5] E. Lithoxoidou, C. Ziogou, T. Vafeiadis, S. Krinidis, D. Ioannidis, S. Voutetakis, D. Tzovaras, Towards the behavior analysis of chemical reactors utilizing data-driven trend analysis and machine learning techniques, Applied Soft Computing, Volume 94,2020, 106464, ISSN 1568-4946, https://doi.org/10.1016/j.asoc.2020.106464.

 

[6] Souza, Davi & Granzotto, Matheus & De Almeida, Gustavo & Oliveira Lopes, Luis Cláudio. (2014). Fault Detection and Diagnosis Using Support Vector Machines -A SVC and SVR Comparison. Journal of Safety Engineering. 2014. 18-29. 10.5923/j.safety.20140301.03.

 

[7] Goldstein, Markus & Uchida, Seiichi. (2016). A Comparative Evaluation of Unsupervised Anomaly Detection Algorithms for Multivariate Data. PloS one. 11. e0152173. 10.1371/journal.pone.0152173.

 

[8] Alcala, Carlos F., and S. Joe Qin. "Analysis and generalization of fault diagnosis methods for process monitoring." Journal of Process Control 21.3 (2011): 322-330.

 

[9]       Amer, Mennatallah, Markus Goldstein, and Slim Abdennadher. "Enhancing one-class support vector machines for unsupervised anomaly detection." Proceedings of the ACM SIGKDD workshop on outlier detection and description. 2013.

 

[10]     Zhang K, Shardt YAW, Chen Z, Yang X, Ding SX, Peng K. A KPI-based process monitoring and fault detection framework for large-scale processes. ISA Trans. 2017 May;68:276-286. doi: 10.1016/j.isatra.2017.01.029. Epub 2017 Feb 9. PMID: 28190565.

 

[11] Gopal Chaudhary , Puneet Singh Lamba , Deepali Virmani, A Proposed Optimization Model for Water Quality Prediction in Internet of Things Environment, Journal of Intelligent Systems and Internet of Things, Vol. 6 , No. 2 , (2022) : 32-44 (Doi   :  https://doi.org/10.54216/JISIoT.060203)

 

[12] Sweeta Bansal , Karan Kohli , K. K. Vishwakarma , Kush Gupta, Graph Algo Visualizer, Journal of Cognitive Human-Computer Interaction, Vol. 3 , No. 2 , (2022) : 36-41 (Doi   :  https://doi.org/10.54216/JCHCI.030205)

 

[13] RajmohanP , Rishisarvesh. U. S , Ponkumar. G , Naveen. R , Pragathish. R. S , Santhosh. P , Arun. k. D , Syed moinudeen, Transformer Analyzer BOT, Journal of Cognitive Human-Computer Interaction, Vol. 3 , No. 2 , (2022) : 16-20 (Doi   :  https://doi.org/10.54216/JCHCI.030202)

 

[14] Vijay K, Collaborating The Textual Reviews Of The Merchandise and Foretelling The Rating Supported Social Sentiment, Journal of Cognitive Human-Computer Interaction, Vol. 1 , No. 2 , (2021) : 63 - 72 (Doi   :  DOI: https://doi.org/10.54216/JCHCI.010203)


Cite this Article as :
Style #
MLA Silvester Bennys jakes , M. Mythily, D. Vasanthi , D. Manamalli. "Data Driven Machine Learning For Fault Detection And Classification In Binary Distillation Column." Journal of Cybersecurity and Information Management, Vol. 11, No. 1, 2023 ,PP. 47-57 (Doi   :  https://doi.org/10.54216/JCIM.110105)
APA Silvester Bennys jakes , M. Mythily, D. Vasanthi , D. Manamalli. (2023). Data Driven Machine Learning For Fault Detection And Classification In Binary Distillation Column. Journal of Journal of Cybersecurity and Information Management, 11 ( 1 ), 47-57 (Doi   :  https://doi.org/10.54216/JCIM.110105)
Chicago Silvester Bennys jakes , M. Mythily, D. Vasanthi , D. Manamalli. "Data Driven Machine Learning For Fault Detection And Classification In Binary Distillation Column." Journal of Journal of Cybersecurity and Information Management, 11 no. 1 (2023): 47-57 (Doi   :  https://doi.org/10.54216/JCIM.110105)
Harvard Silvester Bennys jakes , M. Mythily, D. Vasanthi , D. Manamalli. (2023). Data Driven Machine Learning For Fault Detection And Classification In Binary Distillation Column. Journal of Journal of Cybersecurity and Information Management, 11 ( 1 ), 47-57 (Doi   :  https://doi.org/10.54216/JCIM.110105)
Vancouver Silvester Bennys jakes , M. Mythily, D. Vasanthi , D. Manamalli. Data Driven Machine Learning For Fault Detection And Classification In Binary Distillation Column. Journal of Journal of Cybersecurity and Information Management, (2023); 11 ( 1 ): 47-57 (Doi   :  https://doi.org/10.54216/JCIM.110105)
IEEE Silvester Bennys jakes, M. Mythily, D. Vasanthi, D. Manamalli, Data Driven Machine Learning For Fault Detection And Classification In Binary Distillation Column, Journal of Journal of Cybersecurity and Information Management, Vol. 11 , No. 1 , (2023) : 47-57 (Doi   :  https://doi.org/10.54216/JCIM.110105)