Abstract
Process monitoring helps to estimate the quality of the end products, equipment health parameters, and operational reliability of chemical processes. This is an area in which data-driven approaches are widely used by academic and industrial practitioners. With the ever-increasing complexities in process industries, there is an increased thrust in developing the process monitoring methods of generic nature which are capable of handling the inherent nonlinear characteristics of the chemical process. This demanded the employment of complex data-driven model paradigms in the process monitoring framework. To circumvent the issues related to high-dimensional process data, a large body of these process monitoring algorithms extract only relevant features during the training. Further, model complexity is another important issue that needs to be accounted while employing these methods. In this work, an optimization-based features selection method for process monitoring is proposed, that simultaneously trades-off between the optimal feature selection and the resulting model complexity, by means of solving a multi-objective optimization problem. Particularly, this paper focuses on combining neural network architecture with recursive feature elimination and genetic algorithm to obtain an improved identification accuracy while reducing the number of variables to be measured continuously in the process plant. The efficacy of the proposed approach was validated using a basic numerical case and tested upon the operational data collected from the benchmark Tennessee Eastman plant data, and steel plates manufacturing case studies.
Similar content being viewed by others
References
Qin SJ (2003) Statistical process monitoring: basics and beyond. J Chem J Chemomet Soc 17(8–9):480–502
Qin SJ (2012) Survey on data-driven industrial process monitoring and diagnosis. Ann Rev Control 36(2):220–234
Russell EL, Chiang LH, Braatz RD (2012) Data-driven methods for fault detection and diagnosis in chemical processes. Springer, Berlin
Li G, Qin SJ, Zhou D (2010) Geometric properties of partial least squares for process monitoring. Automatica 46(1):204–210
Chiang LH, Kotanchek ME, Kordon AK (2004) Fault diagnosis based on fisher discriminant analysis and support vector machines. Comput Chem Eng 28(8):1389–1401
Wise BM, Gallagher NB (1996) The process chemometrics approach to process monitoring and fault detection. J Process Control 6(6):329–348
Kodamana H, Raveendran R, Huang B (2017) Mixtures of probabilistic PCA with common structure latent bases for process monitoring. IEEE Trans Control Syst Technol 27(2):838–846
Raveendran R, Kodamana H, Huang B (2018) Process monitoring using a generalized probabilistic linear latent variable model. Automatica 96:73–83
Ghosh K, Ramteke M, Srinivasan R (2014) Optimal variable selection for effective statistical process monitoring. Comput Chem Eng 60:260–276
Ge Z, Yang C, Song Z (2009) Improved kernel PCA-based monitoring approach for nonlinear processes. Chem Eng Sci 64(9):2245–2255
Choi SW, Lee C, Lee JM, Park JH, Lee IB (2005) Fault detection and identification of nonlinear processes based on kernel PCA. Chemometr Intell Lab Syst 75(1):55–67
Jack L, Nandi A (2002) Fault detection using support vector machines and artificial neural networks, augmented by genetic algorithms. Mech Syst Signal Process 16(2–3):373–390
Nashalji MN, Shoorehdeli MA, Teshnehlab M (2010) Fault detection of the Tennessee Eastman process using improved PCA and neural classifier. In: Soft computing in industrial applications. Springer, Berlin, pp 41–50
Zaman B, Riaz M, Ahmad S, Abbasi SA (2015) On artificial neural networking-based process monitoring under bootstrapping using runs rules schemes. Int J Adv Manuf Technol 76(1–4):311–327
Wu D, Gu Y, Luo D, Yang Q (2020) Fault diagnosis of TE process based on incremental learning. In: Fu J, Sun J (eds) 2020 39th Chinese control conference (CCC). IEEE, New York, pp 4227–4232
Han Y, Ding N, Geng Z, Wang Z, Chu C (2020) An optimized long short-term memory network based fault diagnosis model for chemical processes. J Process Control 92:161–168
Wang Y, Pan Z, Yuan X, Yang C, Gui W (2020) A novel deep learning based fault diagnosis approach for chemical process with extended deep belief network. ISA Trans 96:457–467
Chandrashekar G, Sahin F (2014) A survey on feature selection methods. Comput Electr Eng 40(1):16–28
Kira K, Rendell LA (1992) A practical approach to feature selection. In: Edwards P, Sleeman D (eds) Machine learning proceedings. Elsevier, London, pp 249–256
Deb K (2001) Multi-objective optimization using evolutionary algorithms, vol 16. Wiley, London
Guyon I, Weston J, Barnhill S, Vapnik V (2002) Gene selection for cancer classification using support vector machines. Mach Learn 46(1–3):389–422
Tibshirani R (1996) Regression shrinkage and selection via the lasso. J R Stat Soc Ser B (Methodol) 58(1):267–288
Granitto PM, Furlanello C, Biasioli F, Gasperi F (2006) Recursive feature elimination with random forest for PTR-MS analysis of agroindustrial products. Chemometr Intell Lab Syst 83(2):83–90
Chen Q, Meng Z, Liu X, Jin Q, Su R (2018) Decision variants for the automatic determination of optimal feature subset in RF-RFE. Genes 9(6):301
Sun L, Yin T, Ding W, Qian Y, Xu J (2020) Multilabel feature selection using ml-Relieff and neighborhood mutual information for multilabel neighborhood decision systems. Inf Sci 537:401–424
Bocca FF, Rodrigues LHA (2016) The effect of tuning, feature engineering, and feature selection in data mining applied to rainfed sugarcane yield modelling. Comput Electron Agric 128:67–76
Zhang X, Zhang Q, Chen M, Sun Y, Qin X, Li H (2018) A two-stage feature selection and intelligent fault diagnosis method for rotating machinery using hybrid filter and wrapper method. Neurocomputing 275:2426–2439
Liu P, Li B, Han C, Wang F (2016) Feature extraction and selection scheme for intelligent engine fault diagnosis based on 2DNMF, mutual information, and NSGA-II. Shock Vib 2016:13
Stief A, Ottewill JR, Baranowski J (2019) Investigation of the diagnostic properties of sensors and features in a multiphase flow facility case study. In: 12th IFAC symposium on dynamics and control of process systems
Reddy TR, Vardhan BV, GopiChand M, Karunakar K (2018) Gender prediction in author profiling using Relieff feature selection algorithm. In: Bhateja V, Coello Coello CA, Satapathy SC, Pattnaik PK (eds) Intelligent engineering informatics. Springer, New York, pp 169–176
Coelho F, Costa M, Verleysen M, Braga AP (2020) Lasso multi-objective learning algorithm for feature selection. Soft Comput 2020:1–9
Arabasadi Z, Alizadehsani R, Roshanzamir M, Moosaei H, Yarifard AA (2017) Computer aided decision making for heart disease detection using hybrid neural network-genetic algorithm. Comput Methods Programs Biomed 141:19–26
Xue Y, Zhang L, Wang B, Zhang Z, Li F (2018) Nonlinear feature selection using gaussian kernel SVM-RFE for fault diagnosis. Appl Intell 48(10):3306–3331
Onel M, Kieslich CA, Pistikopoulos EN (2019) A nonlinear support vector machine-based feature selection approach for fault detection and diagnosis: application to the tennessee eastman process. AIChE J 65(3):992–1005
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
Vahed SH, Mokhtare M, Nozari HA, Shoorehdeli MA, Simani S (2010) Fault detection and isolation of Tennessee Eastman process using improved RBF network by genetic algorithm. In: Simani S (ed) Proceedings of the 8th European workshop on advanced control and diagnosis—ACD2010, no. FrA3, vol 6, pp 362–367
Burges CJ (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Disc 2(2):121–167
Breiman L (2001) Random forests. Mach Learn 45(1):5–32
Yang SL, Weng W, Rong G, Feng YP (2017) Multiple kernel learning based feature selection for process monitoring. In: 2017 IEEE/ACIS 16th international conference on computer and information science (ICIS). IEEE, New York, pp 809–814
Goodfellow I, Bengio Y, Courville A, Bengio Y (2016) Deep learning, vol 1. MIT Press, Cambridge
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. Preprint arXiv:14126980
Deb K, Pratap A, Agarwal S, Meyarivan T (2002) A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans Evol Comput 6(2):182–197
Ricker N, Lee J (1995) Nonlinear modeling and state estimation for the Tennessee Eastman challenge process. Comput Chem Eng 19(9):983–1005
Downs JJ, Vogel EF (1993) A plant-wide industrial process control problem. Comput Chem Eng 17(3):245–255
Bathelt A, Ricker NL, Jelali M (2015) Revision of the Tennessee Eastman process model. IFAC Pap Online 48(8):309–314
Yadav A, Ramteke M, Pant HJ, Roy S (2017) Monte Carlo real coded genetic algorithm (MC-RGA) for radioactive particle tracking (RPT) experimentation. AIChE J 63(7):2850–2863
Buscema M, Tastle W (2010) (2010) A new meta-classifier. In: Fuzzy Information Processing Society (NAFIPS). Annual meeting of the North American. IEEE, New York, pp 1–7
Fakhr M, Elsayad AM (2012) Steel plates faults diagnosis with data mining models. J Comput Sci 8(4):506
Nguyen D, Bagajewicz M (2010) Optimization of preventive maintenance in chemical process plants. Ind Eng Chem Res 49(9):4329–4339
Acknowledgements
Hariprasad Kodamana would like to acknowledge the New Faculty Seed Grant from IIT Delhi. Hariprasad Kodamana and Manojkumar Ramteke would like to acknowledge the SERB CORE RESEARCH GRANT with file number CRG/2018/001555.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Singh, S., Agrawal, A., Kodamana, H. et al. Multi-objective Optimization Based Recursive Feature Elimination for Process Monitoring. Neural Process Lett 53, 1081–1099 (2021). https://doi.org/10.1007/s11063-021-10430-z
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-021-10430-z