Abstract
Fault detection in the process industries is one of the most challenging tasks. It requires timely detection of anomalies which are present with noisy measurements of a large number of variable, highly correlated data with complex interactions and fault symptoms. This study proposes the robust fault detection method for the distillation column. Fault detection and diagnosis (FDD) for process monitoring and control has been an effective field of research for two decades. This area has been used widely in sophisticated engineering design applications to ensure the proper functionality and performance diagnosis of advanced and complex technologies. Robust fault detection of the realistic faults in distillation column in dynamic condition has been considered in this study. For early detection of faults, the model is based on nonlinear autoregressive with exogenous input (NARX) network. Tapped delays lines (TDLs) have been used for the input and output sequences. A case study was carried out with three different fault scenarios, i.e., valve sticking at reflux and reboiler, and tray upset. These faults would cause the product degradation. The normal data (no fault) is used for the training of neural network in all three cases. It is shown that the proposed algorithm can be used for the detection of both internal and external faults in the distillation column for dynamic system monitoring and to predict the probability of failure.
Similar content being viewed by others
Change history
30 May 2021
A Correction to this paper has been published: https://doi.org/10.1007/s00521-021-05935-6
References
Kresta JV, MacGregor JF, Marlin TE (1991) Multivariate statistical monitoring of process operating performance. Can J Chem Eng 69(1):35–47
Dunia R, Qin SJ (1998) A unified geometric approach to process and sensor fault identification and reconstruction: the unidimensional fault case. Comput Chem Eng 22(7):927–943
Dunia R, Joe Qin S (1998) Subspace approach to multidimensional fault identification and reconstruction. AIChE J 44(8):1813–1831
Singhal A, Seborg DE (2006) Evaluation of a pattern matching method for the tennessee eastman challenge process. J Process Control 16(6):601–613
Zhang H, Qi Y, Wang L, Gao X, Wang X (2017) Fault detection and diagnosis of chemical process using enhanced KECA. Chemometr Intell Lab Syst 161:61–69
Tidriri K, Chatti N, Verron S, Tiplica T (2016) Bridging data-driven and model-based approaches for process fault diagnosis and health monitoring: a review of researches and future challenges. Ann Rev Control 42:63–81
Venkatasubramanian V, Rengaswamy R, Yin K, Kavuri SN (2003) A review of process fault detection and diagnosis: part I: quantitative model-based methods. Comput Chem Eng 27(3):293–311
Ge Z, Song Z, Gao F (2013) Review of recent research on data-based process monitoring. Ind Eng Chem Res 52(10):3543–3562
Benkouider A, Buvat J, Cosmao J, Saboni A (2009) Fault detection in semi-batch reactor using the EKF and statistical method. J Loss Prev Process Ind 22(2):153–161
Botre C, Mansouri M, Karim MN, Nounou H, Nounou M (2017) Multiscale PLS-based GLRT for fault detection of chemical processes. J Loss Prev Process Ind 46:143–153
Isermann R (1982) Process fault detection based on modeling and estimation methods. IFAC Proc Vol 15(4):7–30
Datta S, Sarkar S (2016) A review on different pipeline fault detection methods. J Loss Prev Process Ind 41:97–106
Agudelo C, Anglada FM, Cucarella EQ, Moreno EG (2013) Integration of techniques for early fault detection and diagnosis for improving process safety: application to a fluid catalytic cracking refinery process. J Loss Prev Process Ind 26(4):660–665
Crowl DA, Louvar JF (2001) Chemical process safety: fundamentals with applications. Pearson Education, London
Chang I-C, Yu C-C, Liou C-T (1994) Model-based approach for fault-diagnosis. 1. Principles of deep model algorithm. Ind Eng Chem Res 33(6):1542–1555
Zhan Y, Jiang J (1999) An interacting multiple-model based fault detection, diagnosis and fault-tolerant control approach. In: Proceedings of the 38th IEEE conference on decision and control. IEEE, pp 3593–3598
Amann P, Garcia EA, Koeppen-Seliger B, Frank P (1999) Knowledge-and data-based models for fault diagnosis. Syst Anal Model Simul 35(1):25–44
Dunia R, Qin SJ (1998) Joint diagnosis of process and sensor faults using principal component analysis. Control Eng Pract 6(4):457–469
Dunia R, Qin SJ, Edgar TF, McAvoy TJ (1996) Identification of faulty sensors using principal component analysis. AIChE J 42(10):2797–2812
Kourti T, Nomikos P, MacGregor JF (1995) Analysis, monitoring and fault diagnosis of batch processes using multiblock and multiway PLS. J Process Control 5(4):277–284
Ge Z (2017) Review on data-driven modeling and monitoring for plant-wide industrial processes. Chemom Intell Lab Syst 55:9205–9214
Venkatasubramanian V, Rengaswamy R, Kavuri SN, Yin K (2003) A review of process fault detection and diagnosis: part III: process history based methods. Comput Chem Eng 27(3):327–346
Jain LC, Seera M, Lim CP, Balasubramaniam P (2014) A review of online learning in supervised neural networks. Neural Comput Appl 25(3–4):491–509
Yu J (2012) Local and global principal component analysis for process monitoring. J Process Control 22(7):1358–1373
Kruger U, Wang X, Chen Q, Qin S (2001) An alternative PLS algorithm for the monitoring of industrial process. In: American control conference, 2001. Proceedings of the 2001. IEEE, pp 4455–4459
Zhang GP (2000) Neural networks for classification: a survey. IEEE Trans Syst Man Cybern C (Appl Rev) 30(4):451–462
Taqvi SA, Tufa LD, Zabiri H, Mahadzir S, Maulud AS, Uddin F (2017) Artificial neural network for anomalies detection in distillation column. In: Asian simulation conference. Springer, pp 302–311
Rusinov L, Rudakova I, Remizova O, Kurkina V (2009) Fault diagnosis in chemical processes with application of hierarchical neural networks. Chemometr Intell Lab Syst 97(1):98–103
Sheikh MA, Nor NM, Ibrahim T, Irfan M (2017) Unsupervised on-line method to diagnose unbalanced voltage in three-phase induction motor. Neural Comput Appl 13:1–16
Mishra DP, Ray P (2017) Fault detection, location and classification of a transmission line. Neural Comput Appl. https://doi.org/10.1007/s00521-017-3295-y
Pearl J (2014) Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan Kaufmann, Burlington
Zhang Z, Dong F (2014) Fault detection and diagnosis for missing data systems with a three time-slice dynamic Bayesian network approach. Chemometr Intell Lab Syst 138:30–40
Tong C, Lan T, Shi X (2017) Fault detection and diagnosis of dynamic processes using weighted dynamic decentralized PCA approach. Chemometr Intell Lab Syst 161:34–42
Deng X, Tian X, Chen S, Harris CJ (2017) Fault discriminant enhanced kernel principal component analysis incorporating prior fault information for monitoring nonlinear processes. Chemometr Intell Lab Syst 162:21–34
Hori Y, Yamamoto H, Suzuki T, Okitsu J, Nakamura T, Maeda T, Matsuo T, Zabiri HB, Tufa LD, Marappagounder R (2017) Online anomaly detection of distillation tower system using adaptive resonance theory. J Chem Eng Jpn 50(6):430–438
Kano M, Tanaka S, Hasebe S, Hashimoto I, Ohno H (2003) Monitoring independent components for fault detection. AIChE J 49(4):969–976
Lee J-M, Yoo C, Lee I-B (2004) Statistical process monitoring with independent component analysis. J Process Control 14(5):467–485
Rad MAA, Yazdanpanah MJ (2015) Designing supervised local neural network classifiers based on EM clustering for fault diagnosis of Tennessee Eastman process. Chemometr Intell Lab Syst 146:149–157
Nozari HA, Shoorehdeli MA, Simani S, Banadaki HD (2012) Model-based robust fault detection and isolation of an industrial gas turbine prototype using soft computing techniques. Neurocomputing 91:29–47
Ertunc HM, Ocak H, Aliustaoglu C (2013) ANN-and ANFIS-based multi-staged decision algorithm for the detection and diagnosis of bearing faults. Neural Comput Appl 22(1):435–446
Taqvi SA, Tufa LD, Muhadizir S (2016) Optimization and dynamics of distillation column using Aspen plus®. Proc Eng 148:978–984
Taqvi SA, Tufa LD, Zabiri H, Mahadzir S, Maulud AS, Uddin F (2017) Rigorous dynamic modelling and identification of distillation column using Aspen plus. In: Control and system graduate research colloquium (ICSGRC), 2017 IEEE 8th. IEEE, pp 262–267
Chen S, Billings S, Grant P (1990) Non-linear system identification using neural networks. Int J Control 51(6):1191–1214
Narendra KS, Parthasarathy K (1990) Identification and control of dynamical systems using neural networks. IEEE Trans Neural Netw 1(1):4–27
Menezes JMP, Barreto GA (2008) Long-term time series prediction with the NARX network: an empirical evaluation. Neurocomputing 71(16):3335–3343
Ljung L, Söderström T (1983) Theory and practice of recursive identification, vol 5. JSTOR, New York
Lin T-N, Giles CL, Horne BG, Kung S-Y (1997) A delay damage model selection algorithm for NARX neural networks. IEEE Trans Signal Process 45(11):2719–2730
Chiang LH, Russell EL, Braatz RD (2000) Fault detection and diagnosis in industrial systems. Springer Science & Business Media, Berlin
Lau C, Ghosh K, Hussain M, Hassan CC (2013) Fault diagnosis of Tennessee Eastman process with multi-scale PCA and ANFIS. Chemometr Intell Lab Syst 120:1–14
Luyben WL (1989) Process modeling, simulation and control for chemical engineers. McGraw-Hill Higher Education, New York
Acknowledgements
The author acknowledges the valuable assistance and support of Chemical Engineering Department, Universiti Teknologi PETRONAS.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
All authors declare that they have no conflict of interest.
Appendix: Dynamic model of distillation column
Appendix: Dynamic model of distillation column
A binary mixture with constant relative volatility at 100% tray efficiency has been assumed. This means the simple vapor–liquid equilibrium relationship can be used [41, 50];
N number of trays, F feed flow rate, Z molar composition, M liquid holdup in condenser (mol), xD top composition, xB bottom composition, R reflux flow rate, D distillate flow rate, B bottom flow rate, MB liquid holdup in reboiler (mol).
The fundamental relation for component continuity for condenser and reflux drum is given as:
The fundamental relation for component continuity for reboiler and column base is given as:
The component continuity is given as:
The state operation of each module comprises the following equation referred as MESH equations.
[MESH = material balance equations, efficiency relations, summation equation, and heat (enthalpy) balance equations].
Material balance equation:
Stage efficiency relations:
where \(y_{i} = \frac{{v_{i} }}{{V_{i} }}\) and \(x_{i} = \frac{{l_{i} }}{{L_{i} }}\).
Summation equation:
Enthalpy balance equation:
Rights and permissions
About this article
Cite this article
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
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-018-3658-z