Abstract
This paper is mainly aimed at developing an off-line supervision approach geared to complex processes. This approach consists of two parts: the first part is the fault detection and isolation and the second one is the process control. The first part is devoted to the implementation of the multilayer neural PCA which combines the advantage of data reduction provided by the principal component analysis and the power of neural network linearization. The transition to control is conditioned by the absence of faults in the process; if there is a defect, it must be isolated by identifying the defected variables. The second part rests on the combination of two control tools: both the gain scheduling and the feedback linearization yield a new approach called nonlinear gain scheduling. To have our work validated, we applied it to a photovoltaic system and it gave effective results.
Similar content being viewed by others
References
Hwang I et al (2010) A survey of fault detection, isolation, and reconfiguration methods. IEEE Trans Control 18(3):636–653
Chaouch H, Ouni K (2016) Exploiting neural PCA and fisher discriminate analysis for FDI system. Int J Adv Manuf Technol 87:1183–1191
Chaouch H, Ouni K, Nabli L (2016) Multi-variable process data compression and defect isolation using wavelet PCA and genetic algorithm. Int J Adv Manuf Technol. doi:10.1007/s00170-016-9774-y
Alwi H, et al. (2011) Fault detection and fault-tolerant control using sliding modes. In: Advances in industrial control. Springer, chapter 2, pp 7–27
Jiang L (2011) Sensor fault detection and isolation using system dynamics identification techniques. Ph.D. thesis, The University of Michigan
Liu X et al (2011) Application of nonlinear PCA for fault detection in polymer extrusion processes. Sch Electron Electr Eng Comput Sci 6(5):1141–1148
Taouali O et al (2015) New fault detection method based on reduced kernel principal component analysis (RKPCA). Int J Adv Manuf Technol 85:1–6
Wang Y et al (2014) Online fault detection and fault tolerance in electrical energy storage systems. In: IEEE conference publications, pp 1–5
He Z et al (2010) Fault detection and classification in EHV transmission line based on wavelet singular entropy. IEEE Trans Power Deliv 25(4):2156–2163
Tanwani A, Dominguez-Garcia AD, Liberzon D (2011) An inversion based approach to fault detection and isolation in switching electrical networks. IEEE Trans Control Syst Technol 19(5):1059–1074
Salehi R, Vossoughi G, Alasty A (2015) A second-order sliding mode observer for fault detection and isolation of turbocharged SI engines. IEEE Trans Ind Electron 62(12):7795–7803
Alwi H et al (2011) Fault tolerant control and fault detection and isolation. In: Chapter 2, Part of the series advances in industrial control, pp 7–27
Samy I, Gu D-W (2014) Fault detection and isolation (FDI). In: Fault detection and flight data measurement (lecture notes in control and information sciences), pp 5–17
Gonzalez R, Huang B, Lau E (2015) Process monitoring using kernel density estimation and Bayesian networking with an industrial case study. ISA Trans 58:330–347
Zhou J et al (2014) Fault detection and identification spanning multiple processes by integrating PCA with neural network. Sci Dir Appl Soft Comput A 14:4–11
Zhou B et al (2014) Gain scheduled control of linear systems subject to actuator saturation with application to space craft rendezvous. IEEE Trans Control Syst Technol 22(5):2031–2038
White A, Zhu G, Choi J (2011) Hardware-in-the-loop simulation of robust gain-scheduling control of port-fuel-injection processes. IEEE Trans Control Syst Technol 19(6):1433–1443
Ku C-C et al (2015) Gain-scheduled controller design for discrete-time linear parameter varying systems with multiplicative noises. Int J Control Autom Syst 13(6):1382–1390
Kwon H-Y, Choi H-L (2014) Gain scheduling control of nonlinear systems based on approximate input–output linearization. Int J Control Autom Syst 12(5):1131–1137
Yang W et al (2012) Two-state dynamic gain scheduling control applied to an F16 aircraft model. Int J Non Linear Mech 47(10):1116–1123
Veselý V et al (2015) Design of robust gain-scheduled PI controllers. J Frankl Inst 352(4):1476–1494
Arif J, Ray S, Chaudhuri B (2014) Multivariable self-tuning feedback linearization controller for power oscillation damping. IEEE Trans Control Syst Technol 22(4):1519–1526
Angue Mintsa H et al (2012) Feedback linearization-based position control of an electrohydraulic servo system with supply pressure uncertainty. IEEE Trans Control Syst Technol 20(4):1092–1099
Zhang Y, Tao G, Chen M (2015) Relative degrees and adaptive feedback linearization control of T–S Fuzzy systems. IEEE Trans Fuzzy Syst 23(6):2215–2230
Krener AJ (2014) Feedback linearization of nonlinear systems. In: Encyclopedia of systems and control (living reference work entry). Springer, pp 1–14
Venkat V et al (2003) A review of process fault detection and diagnosis, part III: process history based methods. Comput Chem Eng 27:327–346
Luo M (2006) Data-driven fault detection using trending analysis. Ph.D., M.S., Tennessee Tech, Louisiana State University, Baton Rouge
Venkat V, Rengaswamy R, Kavuri SN (2003) A review of process fault detection and diagnosis, part II: qualitative models and search strategies. Comput Chem Eng 27:313–326
Pedro I, Dahunsi O (2011) Neural network based feedback linearization control of a servo-hydraulic vehicle suspension system. Int J Appl Math Comput Sci 21(1):137–147
Tehrani ES, Khorasani K (2009) Fault diagnosis of nonlinear systems using a hybrid approach. Springer, Dordrecht
Funding
This research received no specific grant from any funding agency in the public, commercial, or not-for-profit sectors.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there is no conflict of interest.
Rights and permissions
About this article
Cite this article
Chaouch, H., Charfedine, S., Ouni, K. et al. Intelligent supervision approach based on multilayer neural PCA and nonlinear gain scheduling. Neural Comput & Applic 31, 1153–1163 (2019). https://doi.org/10.1007/s00521-017-3147-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-017-3147-9