Fault Diagnosis Framework for a CSTR Bioreactor Integrating ANFIS and Zonotopic Estimation

https://doi.org/10.58571/CNCA.AMCA.2025.001

Resumen: This work presents a hybrid fault diagnosis framework for Continuous Stirred Tank Reactor (CSTR) bioreactors by integrating Adaptive Neuro-Fuzzy Inference Systems (ANFIS) and Zonotopic Kalman Filters (ZKF). The proposed method consists of two main stages: (1) modeling the nominal behavior of the CSTR using ANFIS trained on fault-free data to extract a compact set of fuzzy rules, and (2) implementing a ZKF to estimate system states and detect deviations associated with faults. The neuro-fuzzy model captures the system’s dynamics, while the zonotopic filter accounts for bounded uncertainty and measurement noise. Fault detection is achieved by evaluating residuals and comparing them to adaptive thresholds derived from the zonotopic bounds. Simulation results for different actuator and sensor fault scenarios
demonstrate the effectiveness of the proposed approach in identifying deviations from normal operation, highlighting its potential for improving monitoring capabilities in bioprocesses.

¿Cómo citar?

Pérez-Pérez, E., Valencia-Palomo, G., Puig, V., Santos-Ruiz, I. & Guzmán-Rabasa, J. (2025). Fault Diagnosis Framework for a CSTR Bioreactor Integrating ANFIS and Zonotopic Estimation. Memorias del Congreso Nacional de Control Automático 2025, pp. 1-6. https://doi.org/10.58571/CNCA.AMCA.2025.001

Palabras clave

Fault diagnosis, CSTR, ANFIS, Zonotopic Kalman Filter, Bioprocess.

• Alamo, T., Bravo, J.M., and Camacho, E.F. (2005). Guaranteed state estimation by zonotopes. Automatica, 41(6), 1035–1043.
• Azarbani, A., Fakharian, A., and Menhaj, M.B. (2023). On the design of an unknown input observer to fault detection, isolation, and estimation for uncertain multidelay nonlinear systems. Journal of Process Control, 128, 103018.
• Chen, J. and Patton, R.J. (2012). Robust model-based fault diagnosis for dynamic systems, volume 3. Springer Science & Business Media.
• Combastel, C. (2015). Zonotopes and kalman observers: Gain optimality under distinct uncertainty paradigms and robust convergence. Automatica, 55, 265–273.
• Gholizadeh, M., Yazdizadeh, A., and Mohammad-Bagherpour, H. (2017). Fault detection and identification using combination of ekf and neuro-fuzzy network applied to a chemical process (cstr). Pattern Analysis and Applications, 22, 359–373.
• Jagtap, P., Raut, P., Pillai, G.N., Kazi, F., and Singh, N. (2015). Extreme-anfis: A novel learning approach for inverse model control of nonlinear dynamical systems. In 2015 International Conference on Industrial Instrumentation and Control (ICIC), 718–723. IEEE.
• Mitra, S. and Murthy, G.S. (2022). Bioreactor control systems in the biopharmaceutical industry: a critical perspective. Systems Microbiology and Biomanufacturing, 1–22.
• Ostertag, E. (2011). Mono-and multivariable control and estimation: linear, quadratic and LMI methods. Springer Science & Business Media.
• Pan, H., Yu, X., Hu, J., Li, L., She, Y., Zhang, Y., and Zan, H. (2023). A self-healing controller based on sliding-mode control for sensor fault in wastewater treatment processes. Journal of Process Control, 127, 102997.
• Pilario, K.E.S. and Cao, Y. (2018). Canonical variate dissimilarity analysis for process incipient fault detection. IEEE Transactions on Industrial Informatics, 14(12), 5308–5315.
• Sawattanakit, N. and Jaovisidha, V. (1998). Process fault detection and diagnosis in cstr system using on-line approximator. In IEEE. APCCAS 1998. 1998 IEEE Asia-Pacific Conference on Circuits and Systems. Microelectronics and Integrating Systems. Proceedings (Cat. No. 98EX242), 747–750. IEEE.
• Takagi, T. and Sugeno, M. (1985). Fuzzy identification of systems and its applications to modeling and control. IEEE transactions on systems, man, and cybernetics, SMC-15(1), 116–132.
• Venkateswaran, S., Sheriff, M.Z., Wilhite, B., and Kravaris, C. (2021). Design of functional observers for fault detection and isolation in nonlinear systems in the presence of noises. Journal of Process Control, 108, 68–85.