Skip to content
Accessible Unlicensed Requires Authentication Published by De Gruyter August 3, 2020

Hybrid model for fault detection and diagnosis in an industrial distillation column

Julia Picabea, Mauricio Maestri, Miryan Cassanello and Gabriel Horowitz


The present work describes a method of automatic fault detection and identification based on a hybrid model (HM): First Principles – Neural Network. The FPM can simulate a wide range of situations while the NN corrects the model output using information from the historical data of the process. Operating conditions corresponding to different types of faults were simulated with the HM and saved with their description in a process state library. To detect a fault, the online measured data was compared with that corresponding to the operation under normal conditions. If a significant deviation was detected, the current state was compared with all the states stored in the process state library and it was identified as the one at the shortest distance. The method was tested with real data from a methanol-water industrial distillation column. During the studied period of operation of the plant, two faults were identified and reported. The proposed method was able to identify such failures more effectively than an equivalent model of first principles. The results obtained show that the proposed method has a great potential to be used in the automatic diagnosis of faults in refining and petrochemical processes.

Corresponding author: Gabriel Horowitz, ITAPROQ, Departamento de Industrias, FCEyN, Universidad de Buenos Aires, Int. Güiraldes 2620, C1428BGA, Buenos Aires, Argentina; and Y-TEC, Av. Del Petróleo s/n, 1923, Berisso, Argentina, E-mail:

Funding source: Universidad de Buenos Aires

Award Identifier / Grant number: UBACyT20020130100544BA

Funding source: Agencia Nacional de Promoción Científica y Tecnológica

Award Identifier / Grant number: PICT2014-0704

Funding source: Consejo Nacional de Investigaciones Científicas y Técnicas

Award Identifier / Grant number: PIP1122015-0100902CO


This work was supported by ANPCyT [PICT2014-0704]; Universidad de Buenos Aires [UBACyT 20020130100544BA] and CONICET [PIP1122015-0100902CO]. The authors would also like to acknowledge the operations staff of the methanol plant of YPF (Plaza Huincul).

  1. Author contribution: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.

  2. Research funding: This research was funded by the ANPCyT [PICT2014-0704]; Universidad de Buenos Aires [UBACyT 20020130100544BA] and CONICET [PIP1122015-0100902CO].

  3. Conflict of interest statement: The authors declare no conflicts of interest regarding this article.


1. Nimmo, I. Adequately address abnormal operations. Chem Eng Progress 1995;91(9):36–45.Search in Google Scholar

2. McCoy, JN, Podio, AL, Becker, DJ, Fernandez, G. Wireless simultaneous acquisition and analysis of dynamometer and fluid level data for real-time monitoring of well performance. In: SPE artificial lift conference-Americas, Cartagena: Colombia; 2013.Search in Google Scholar

3. AlGhazzawi, A, Lennox, B. Monitoring a complex refining process using multivariate statistics. Control Eng Pract 2008;16:294–307. in Google Scholar

4. Kourti, T. Abnormal situation detection, three-way data and projection methods; robust data archiving and modeling for industrial applications. Annu Rev Control 2003;27:131–9. in Google Scholar

5. Gao, Z, Cecati, C, Ding, SX. A survey of fault diagnosis and fault-tolerant techniques–part I: fault diagnosis with model-based and signal-based approaches. IEEE Trans Ind Electron 2015;62:3757–67. in Google Scholar

6. Gao, Z, Cecati, C, Ding, SX. A survey of fault diagnosis and fault-tolerant techniques–part II fault diagnosis with knowledge-based and hybrid/active approaches. IEEE Trans Ind Electron 2015;62:3768. in Google Scholar

7. Peres, FAP, Fogliatto, FS. Variable selection methods in multivariate statistical process control: a systematic literature review. Comput Ind Eng 2018;115:603–19. in Google Scholar

8. Xu, S, Adhitya, A, Srinivasan, R. Hybrid model-based framework for alarm anticipation. Ind Eng Chem Res 2014;53:5182–93. in Google Scholar

9. Isermann, R. Model-based fault-detection and diagnosis – status and applications. Annu Rev Control 2005;29:71–85. in Google Scholar

10. Venkatasubramanian, V. The promise of artificial intelligence in chemical engineering: is it here, finally?. AIChE J 2019;65:466–78. in Google Scholar

11. Rathod, N, La Bella, A, Puleo, G, Scattolini, R, Rossetti, A, Sandroni, C. Modelling and predictive control of a solar cooling plant with flexible configuration. J Process Control 2019;76:74–86. in Google Scholar

12. Mahalec, V, Sanchez, Y. Inferential monitoring and optimization of crude separation units via hybrid models. Comput Chem Eng 2012;45:15–26. in Google Scholar

13. von Stosch, M, Oliveira, R, Peres, J, Feyo de Azevedo, S. A general hybrid semi-parametric process control framework. J Process Control 2012;22:1171–81. in Google Scholar

14. Salahuddin, NF, Shamiri, A, Hussain, MA, Mostoufi, N. Hybrid model-based control of propylene copolymerization in fluidized bed reactor. Comput Aided Chem Eng 2018;44:751–56. in Google Scholar

15. Ibrehem, AS. Hybrid modeling for modified mathematical model for gas phase olefine in fluidized bed catalyst reactors using artificial neural networks. Chem Prod Process Modeling 2009;4:46. in Google Scholar

16. Bollas, GM, Papadokonstadakis, S, Michalopoulos, J, Arampatzis, G, Lappas, AA, Vasalos, IA, et al.. Using hybrid neural networks in scaling up an FCC model from a pilot plant to an industrial unit. Chem Eng Process 2003;42:697–713. in Google Scholar

17. Lahiri, SK, Ghanta, KC. Development of a hybrid artificial neural network and genetic algorithm model for regime identification of slurry transport in pipelines. Chem Prod Process Modeling 2009;4:22. in Google Scholar

18. Sheibat-Othman, N, Laouti, N, Valour, JP, Othman, S. Support vector machines combined to observers for fault diagnosis in chemical reactors. Can J Chem Eng 2014;92:685–95. in Google Scholar

19. von Stosch, M, Oliveira, R, Peres, J, Feyo de Azevedo, S. Hybrid semi-parametric modelling in process systems engineering: past, present and future. Comput Chem Eng 2014;60:86–101. in Google Scholar

20. Zendehboudia, S, Rezaeia, N, Lohib, A. Applications of hybrid models in chemical, petroleum, and energy systems: a systematic review. Appl Energy 2018;228:2539–66. in Google Scholar

21. Psichogios, DC, Ungar, LH. A hybrid neural network-first principles approach to process modeling. AIChE J 1992;38:1499–511. in Google Scholar

22. Eikens, B, Karim, MN, Simon, L. Combining neural networks and first principle models for bioprocess modeling. In: Mujtaba, IM, Hussain, MA, editors. Application of neural networks and other learning technologies in Process Engineering, Imperial College Press: Chp 6, pp. 121–48; 2001.Search in Google Scholar

23. Venkatasubramanian, V, Rengaswamy, R, Kavuri, SN, Yin, K. A review of process fault detection and diagnosis: Part I, Part II and Part III. Comput Chem Eng 2003;27:293–346. in Google Scholar

24. Cedeño, M, Rodríguez Aguilar, LPF, Sánchez, M. Bioprocess statistical control: identification stage based on hierarchical clustering. Process Biochem 2016;51:1919–29. in Google Scholar

25. Yang, NS, Chuang, KT, Afacan, A, Resetarits, MR, Blinkley, MJ. Improving the efficiency and capacity of methanol-water distillation trays. Ind Eng Chem Res 2003;42:6601–6. in Google Scholar

Received: 2020-01-19
Accepted: 2020-05-01
Published Online: 2020-08-03

© 2020 Walter de Gruyter GmbH, Berlin/Boston