Explainable fault detection and diagnosis based on an IDEOA as applied to an industrial process

• Autorzy: Benbrahim Meriem , Hamaidi Brahim , Haouassi Hichem , Mahdaoui Rafik , Mouss Leila-Hayet

Identyfikatory

DOI

10.29354/diag/203246

• Języki publikacji: EN

Abstrakty

EN

Even with all measures approved by industrial sector specialists to avoid faults leading to major accidents, this field still suffers from some issues. Therefore, the safety and reliability of these industrial systems become necessary, leading to focus more on anticipating fault occurrence by giving fault detection and diagnosis a high priority. To solve this problem, a large set of reliable methods has been developed. Machine learning-based methods have gained significant importance as they have achieved promising results. However, the black-box nature of the generated fault detection models has restricted their investigation by users. Thus, explainable models aim to show features that influence the detection model decision. In this study, an Improved Discrete Equilibrium Optimizer Algorithm (IDEOA), which aims to solve different discrete optimization problems, was proposed to generate a rule-based fault detection model easily explainable by reading its classification rules. To this end, the Opposition-Based Learning (OBL) strategy is adopted in the IDEOA to avoid being stuck in local optima. A key contribution of this study is the novel application of the methodology to the Tennessee Eastman Process. The result of this study is a fault diagnosis model that consists of 16 rules, six of them belong to normal operating conditions and the rest reveal fault occurrence (F4). Then, an accuracy value is calculated to assess the effectiveness of our approach by contrasting it with other algorithms described in the literature. The findings indicate that the proposed approach outperforms other methods.

Słowa kluczowe

EN

fault detection; rule-based classification; Improved Discrete Equilibrium Optimizer Algorithm; interpretable rules

• Wydawca: Polskie Towarzystwo Diagnostyki Technicznej
• Czasopismo: Diagnostyka
• Rocznik: 2025
• Tom: Vol. 26, No. 2
• Strony: art. no. 2025203
• Opis fizyczny: Bibliogr. 37 poz., rys., tab.

Twórcy

autor

Benbrahim Meriem

• LGEM, Electromechanical Engineering Laboratory, Electromechanics Department, Faculty of Technology, Badji Mokhtar-Annaba University, B.P. 12, Annaba, 23000, Algeria

• https://orcid.org/0009-0008-6809-0280

autor

Hamaidi Brahim

• LGEM, Electromechanical Engineering Laboratory, Electromechanics Department, Faculty of Technology, Badji Mokhtar-Annaba University, B.P. 12, Annaba, 23000, Algeria

• https://orcid.org/0009-0006-7238-0438

autor

Haouassi Hichem

• ICOSI Lab, Mathematics and Computer Science Department, Faculty of Science and Technology, Abbas Laghrour University, Khenchela, 40000, Algeria

• https://orcid.org/0000-0001-8465-499X

autor

Mahdaoui Rafik

• ICOSI Lab, Mathematics and Computer Science Department, Faculty of Science and Technology, Abbas Laghrour University, Khenchela, 40000, Algeria

• https://orcid.org/0000-0002-8447-6027

autor

Mouss Leila-Hayet

• Automation and Manufacturing Engineering Laboratory, Industrial Engineering Department, Faculty of Technology, Batna2 University, Batna, 05000, Algeria

• https://orcid.org/0000-0002-7217-3977

Bibliografia

• 1. Isermann R. Fault-Diagnosis Applications. Springer H. Springer Berlin Heidelberg, Berlin, Heidelberg 2011. https://doi.org/https://doi.org/10.1007/978-3-642-12767-0.
• 2. Isermann R. Supervision FDD Methods - An Introduction. Control Eng Pract [Internet]. 1997;5(5):639-52. Available from: https://doi.org/10.1016/S0967-0661(97)00046-4.
• 3. Venkatasubramanian V, Rengaswamy R, Yin K, Kavuri SN. A review of process fault detection and diagnosis part I: Quantitative model-based methods. Comput Chem Eng. 2003;27(3):293-311. https://doi.org/10.1016/S0098-1354(02)00160-6.
• 4. Katipamula S, Brambley MR, Brambley MR. Methods for Fault Detection , Diagnostics , and Prognostics for Building Systems - A Review , Part I. HVAC R Res. 2005;11(1):3-25. https://doi.org/10.1080/10789669.2005.10391123.
• 5. Venkatasubramanian V, Rengaswamy R, Kavuri SN, Yin K. A review of process fault detection and diagnosis: Part III: Process history based methods. Comput Chem Eng. 2003 Mar 15;27(3):327-46. https://doi.org/10.1016/S0098-1354(02)00162-X.
• 6. Haouassi H, Mahdaoui R, Chouhal O, Bekhouche A. An efficient classification rule generation for coronary artery disease diagnosis using a novel discrete equilibrium optimizer algorithm. J Intell Fuzzy Syst. 2022;43(3):2315-31. https://doi.org/10.3233/JIFS-213257.
• 7. Mahdaoui R, Mouss LH, Mouss MD, Chouhal O. A Temporal Neuro-Fuzzy Monitoring System to Manufacturing Systems. 2011;8(3):237-46. http://arxiv.org/abs/1107.3302.
• 8. Faramarzi A, Heidarinejad M, Stephens B, Mirjalili S. Equilibrium optimizer: A novel optimization algorithm. Knowledge-Based Syst. 2020 Mar 5;191. https://doi.org/10.1016/j.knosys.2019.105190.
• 9. Malik MM, Haouassi H. Efficient sequential covering strategy for classification rules mining using a discrete equilibrium optimization algorithm. J King Saud Univ - Comput Inf Sci [Internet]. 2021; https://doi.org/10.1016/j.jksuci.2021.08.032.
• 10. Zou W, Xia Y, Li H. Fault diagnosis of Tennesseeeastman process using orthogonal incremental extreme learning machine based on driving amount. IEEE Trans Cybern. 2018;48(12):3403-10. https://doi.org/10.1109/TCYB.2018.2830338.
• 11. Onel M, Kieslich CA, Pistikopoulos EN. A nonlinear support vector machine-based feature selection approach for fault detection and diagnosis: Application to the Tennessee Eastman process. AIChE J. 2019;65(3):992-1005. https://doi.org/10.1002/aic.16497.
• 12. Soraya B, Faouzi HM, Abderrazak L. Fault Diagnosis of Tennessee Eastman Process Based on Static PCA. Proc - 2019 1st Int Conf Sustain Renew Energy Syst Appl ICSRESA 2019. 2019;(2). https://doi.org/10.1109/ICSRESA49121.2019.9182366.
• 13. Zhang C, Guo Q, Li Y. Fault detection in the Tennessee eastman benchmark process using principal component difference based on k-nearest neighbors. IEEE Access. 2020;8:49999-50009. https://doi.org/10.1109/ACCESS.2020.2977421.
• 14. Han Y, Ding N, Geng Z, Wang Z, Chu C. An optimized long short-term memory network based fault diagnosis model for chemical processes. J Process Control [Internet]. 2020;92:161-8. https://doi.org/10.1016/j.jprocont.2020.06.005.
• 15. Agarwal P, Tamer M, Budman H. Explainability: Relevance based dynamic deep learning algorithm for fault detection and diagnosis in chemical processes. Comput Chem Eng [Internet]. 2021;154:107467. https://doi.org/10.1016/j.compchemeng.2021.107467.
• 16. Lv F, Wen C, Bao Z, Liu M. Fault diagnosis based on deep learning. In: Proceedings of the American Control Conference. 2016. p. 6851-6. https://doi.org/10.1109/ACC.2016.7526751.
• 17. Lomov I, Lyubimov M, Makarov I, Zhukov LE. Fault detection in Tennessee Eastman process with temporal deep learning models. J Ind Inf Integr [Internet]. 2021;23(September 2020):100216. https://doi.org/10.1016/j.jii.2021.100216.
• 18. Xu H, Ren T, Mo Z, Yang X. A Fault Diagnosis Model for Tennessee Eastman Processes Based on Feature Selection and Probabilistic Neural Network. Appl Sci. 2022;12(17). https://doi.org/10.3390/app12178868.
• 19. Hu M, Hu X, Deng Z, Tu B. Fault Diagnosis of Tennessee Eastman Process with XGB-AVSSAKELM Algorithm. Energies. 2022;15(9):1-25. https://doi.org/10.3390/en15093198.
• 20. De Leon-Aldaco SE, Calleja H, Aguayo Alquicira J. Metaheuristic Optimization Methods Applied to Power Converters: A Review. IEEE Trans Power Electron. 2015;30(12):6791-803. https://doi.org/10.1109/TPEL.2015.2397311.
• 21. Chen J, Patton RJ, Liu GP. An extension to the single bottleneck transportation problem. Int J Syst Sci. 1996;27(6):567-76. https://doi.org/10.1080/00207729608929252.
• 22. Abdel-Basset M, Mohamed R, Mirjalili S. A Binary Equilibrium Optimization Algorithm for 0-1 Knapsack Problems. Comput Ind Eng [Internet]. 2021;151:106946. https://doi.org/10.1016/j.cie.2020.106946.
• 23. Wang J, Yang B, Li D, Zeng C, Chen Y, Guo Z, et al. Photovoltaic cell parameter estimation based on improved equilibrium optimizer algorithm. Energy Convers Manag [Internet]. 2021;236:114051. https://doi.org/10.1016/j.enconman.2021.114051.
• 24. Too J, Mirjalili S. General Learning Equilibrium Optimizer: A New Feature Selection Method for Biological Data Classification. Appl Artif Intell [Internet]. 2021;35(3):247-63. https://doi.org/10.1080/08839514.2020.1861407.
• 25. Guha R, Ghosh KK, Bera SK, Sarkar R MS. Discrete Equilibrium Optimizer Combined with Simulated Annealing for Feature Selection. Res Sq [Internet]. 2022. https://doi.org/10.21203/rs.3.rs-28683/v2.
• 26. Fan Q, Huang H, Yang K, Zhang S, Yao L, Xiong Q. A modified equilibrium optimizer using oppositionbased learning and novel update rules. Expert Syst Appl [Internet]. 2021;170:114575. https://doi.org/10.1016/j.eswa.2021.114575.
• 27. Liu B, Hsu W, Ma Y. KDD98-012.pdf. Kdd [Internet]. 1998;98:80-6. Available from: www.aaai.org.
• 28. Hossain SKM, Ema SA, Sohn H. Rule-Based Classification Based on Ant Colony Optimization: A Comprehensive Review. Appl Comput Intell Soft Comput. 2022;2022. https://doi.org/10.1155/2022/2232000.
• 29. Liu SH, Mernik M, Hrnčič D, Črepinšek M. A parameter control method of evolutionary algorithms using exploration and exploitation measures with a practical application for fitting Sovova’s mass transfer model. Appl Soft Comput J. 2013;13(9):3792-805. https://doi.org/10.1016/j.asoc.2013.05.010.
• 30. Tizhoosh HR. Opposition-based learning: A new scheme for machine intelligence. Proc - Int Conf Comput Intell Model Control Autom CIMCA 2005 Int Conf Intell Agents, Web Technol Internet. 2005;1:695-701. https://doi.org/10.1109/CIMCA.2005.1631345.
• 31. Ul Hassan N, Bangyal WH, Ali Khan MS, Nisar K, Ibrahim AAA, Rawat DB. Improved opposition-based particle swarm optimization algorithm for global optimization. Symmetry (Basel). 2021;13(12):1-23. https://doi.org/10.3390/sym13122280.
• 32. Rahab H, Haouassi H, Souidi MEH, Bakhouche A, Mahdaoui R, Bekhouche M. A Modified Binary Rat Swarm Optimization Algorithm for Feature Selection in Arabic Sentiment Analysis. Arab J Sci Eng [Internet]. 2022; https://doi.org/10.1007/s13369-022-07466-1.
• 33. Downs JJ, Vogel EF. A plant-wide industrial process control problem. Comput Chem Eng. 1993;17(3):245-55. https://doi.org/10.1016/0098-1354(93)80018-I.
• 34. Evan Russell LHC, Braatz and RD. Data-driven Methods for Fault Detection and Diagnosis in Chemical Processes. Springer-Verlag London Berlin Heidelberg; 2000.
• 35. Detroja KP, Gudi RD, Patwardhan SC. Plant-wide detection and diagnosis using correspondence analysis. Control Eng Pract. 2007;15(12):1468-83. https://doi.org/10.1016/j.conengprac.2007.02.007.
• 36. Maran Beena A, Pani AK. Fault Detection of Complex Processes Using nonlinear Mean Function Based Gaussian Process Regression: Application to the Tennessee Eastman Process. Arab J Sci Eng [Internet]. 2021;46(7):6369-90. https://doi.org/10.1007/s13369-020-05052-x.
• 37. Ragab A, El-koujok M, Poulin B, Amazouz M, Yacout S. Fault diagnosis in industrial chemical processes using interpretable patterns based on Logical Analysis of Data. Expert Syst Appl [Internet]. 2018;95:368-83. https://doi.org/10.1016/j.eswa.2017.11.045.