A versatile software tool making best use of sparse data for closed loop process control. (English) Zbl 1215.92015
Summary: This paper presents the design of a software supported sliding mode controller for a biochemical process. The state of the process is characterized by cell mass and nutrient amount. The controller is designed for tracking of a desired profile in cell mass and it is shown that the nutrient amount in the controlled bioreactor evolves bounded. A smart software tool named Support Vector Machine (SVM), which minimizes the upper bound of an empirical risk function, is proposed to approximate the nonlinear function seen in the control law by using very limited number of numerical data. This removes the necessity of knowing the functional form of the nominal nonlinearity in the control law. It is shown that the controller is robust against noisy measurements, considerable amount of parameter variations, discontinuities in the command signal and large initial errors. The contribution of the present work is the achievement of robustness and tracking performance on a benchmarking process, under the presence of limited prior knowledge.
MSC:
| 92C40 | Biochemistry, molecular biology |
| 92-04 | Software, source code, etc. for problems pertaining to biology |
| 90C90 | Applications of mathematical programming |
| 68T05 | Learning and adaptive systems in artificial intelligence |
Keywords:
bioreactor benchmark problem; sliding mode control; process control; support vector machine; learning with few data; cell mass controlReferences:
| [1] | Anderson, C. W.; Iii, W. T. Miller: Challenging control problems, Neural networks for control, 475-510 (1990) |
| [2] | Bao, Z.; Pi, D.; Sun, Y.: Nonlinear model predictive control based on support vector machine with multi-kernel, Chin J chem eng 15, No. 5, 691-697 (2007) |
| [3] | Baylar, A.; Batan, M.: Usage of artificial intelligence methods in free flowing gated closed conduits for estimation of oxygen transfer efficiency, Adv eng soft 41, No. 5, 729-736 (2010) · Zbl 1307.76069 |
| [4] | Bequette, B. W.: Nonlinear control of chemical processes: a review, Ind eng chem res 30, 1391-1413 (1991) |
| [5] | Brengel, D. D.; Seider, W. D.: Multistep nonlinear predictive controller, Ind eng chem res 28, 1812-1822 (1989) |
| [6] | Camacho, O.; Rojas, R.: A general sliding mode controller for nonlinear chemical processes, Trans ASME: J dynam syst measur control 122, 650-655 (2000) |
| [7] | Chen, C. T.; Peng, S. T.: A sliding mode control scheme for uncertain non-minimum phase cstrs, J chem eng jpn 39, No. 2, 181-196 (2006) |
| [8] | Chuang, C. -C.; Hsu, C. -C.; Tao, C. W.: Embedded support vector regression on cerebellar model articulation controller with Gaussian noise, Appl soft comput 11, No. 1, 1126-1134 (2011) |
| [9] | Colantonio, M. C.; Desages, A. C.; Romagnoli, J. A.; Palazoglu, A.: Nonlinear control of a CSTR: disturbance rejection using sliding mode control, Ind eng chem res 34, 2383-2392 (1995) |
| [10] | Cristianini, N.; Shawe-Taylor, J.: An introduction to support vector machines and other kernel-based learning methods, (2000) · Zbl 0994.68074 |
| [11] | Dochain, D.; Perrier, M.: Bioprocess control. Bioreaction engineering: modeling and control, (2000) |
| [12] | Efe, M. Ö.; Abadoglu, E.; Kaynak, O.: A novel analysis and design of a neural network assisted nonlinear controller for a bioreactor, Int J robust nonlinear control 9, No. 11, 799-815 (1999) · Zbl 0946.93034 · doi:10.1002/(SICI)1099-1239(199909)9:11<799::AID-RNC441>3.0.CO;2-U |
| [13] | Gunn SR. Support vector machines for classification and regression. ISIS Technical Report. United Kingdom: University of Southampton; 1998. |
| [14] | Han, L.; Chen, G.: A fuzzy clustering method of construction of ontology-based user profiles, Adv eng soft 40, No. 7, 535-540 (2009) · Zbl 1164.68003 · doi:10.1016/j.advengsoft.2008.10.006 |
| [15] | Hanczyc, E. M.; Palazoglu, A.: Sliding mode control of nonlinear distributed parameter chemical processes, Ind eng chem res 34, 557-566 (1995) |
| [16] | Hung, J. Y.; Gao, W.; Hung, J. C.: Variable structure control: a survey, IEEE trans ind electron 40, No. 1, 2-22 (1993) |
| [17] | Iplikci, S.: A support vector machine based control application to the experimental three-tank system, ISA trans 49, No. 3, 376-386 (2010) |
| [18] | Iplikci, S.: Support vector machines based neuro-fuzzy control of nonlinear systems, Neurocomputing 73, No. 10 – 12, 2097-2107 (2010) |
| [19] | Kaya, I.: Sliding-mode control of stable processes, Ind eng chem res 46, No. 2, 571-578 (2007) |
| [20] | Kaynak, O.; Harashima, F.; Hashimoto, H.: Variable structure systems theory, as applied to sub-time optimal position control with an invariant trajectory, Trans inst elect eng jpn E 104, 4752 (1984) |
| [21] | Khalil, H.: Nonlinear systems, (2001) · Zbl 1055.93064 |
| [22] | Lute, V. A.; Upadhyay, K. K. Singh: Support vector machine based aerodynamic analysis of cable stayed bridges, Adv eng soft 40, No. 9, 830-835 (2009) · Zbl 1168.74053 · doi:10.1016/j.advengsoft.2009.01.008 |
| [23] | Li, Z.; Zhang, Y.; Yang, Y.: Support vector machine optimal control for mobile wheeled inverted pendulums with unmodelled dynamics, Neurocomputing 73, No. 13 – 15, 2773-2782 (2010) |
| [24] | Li, J.; Zhang, Y.; Pan, H.: Chattering-free LS-SVM sliding mode control, Lect notes comput sci: adv neural networks 5263, 701-708 (2008) |
| [25] | Puskorius, G. V.; Feldkamp, L. A.: Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks, IEEE trans neural networks 5, No. 2, 279-297 (1990) |
| [26] | Rodil, S. S.; Fuente, M. J.: Fault tolerance in the framework of support vector machines based model predictive control, Eng appl artificial intell 23, No. 7, 1127-1139 (2010) |
| [27] | Shin, J.; Kim, H. J.; Park, S.; Kim, Y.: Model predictive flight control using adaptive support vector regression, Neurocomputing 73, No. 4-6, 1031-1037 (2010) |
| [28] | Slotine, J. -J.E.; Li, W.: Applied nonlinear control, (1991) · Zbl 0753.93036 |
| [29] | Suykens, J. A. K.; Vandewalle, J.; De Moor, B.: Optimal control by least squares support vector machines, Neural networks 14, No. 1, 23-35 (2001) · Zbl 1001.68717 |
| [30] | Tokat, S.: Time-varying sliding surface design with support vector machine based initial condition adaptation, J vibr control 12, No. 8, 901-926 (2006) · Zbl 1182.70076 · doi:10.1177/1077546306067675 |
| [31] | Tokat S, Iplikci S, Ulusoy L., Output feedback sliding mode control with support vector machine based observer gain adaptation. In: Proceedings of the 8th WSEAS international conference on circuits, systems, electronics, control & signal processing, Puerto De La Cruz, Tenerife, Canary Islands, Spain; 2009. pp. 63 – 8. |
| [32] | Ungar, L. H.: A bioreactor benchmark for adaptive-network based process control, Neural networks for control, 387-402 (1990) |
| [33] | Utkin, V. I.: Sliding modes in control optimization, (1992) · Zbl 0748.93044 |
| [34] | Vapnik, V.: The nature of statistical learning theory, (1995) · Zbl 0833.62008 |
| [35] | Wang, H.; Pi, D.; Sun, Y.: Online SVM regression algorithm-based adaptive inverse control, Neurocomputing 70, No. 4-6, 952-959 (2007) |
| [36] | Wang, Y. -N.; Yuan, X. -F.: SVM approximate-based internal model control strategy, Acta automat sinica 34, No. 2, 172-179 (2008) · Zbl 1174.93542 · doi:10.3724/SP.J.1004.2008.00172 |
| [37] | Wang X-D, Ye M-Y. Nonlinear dynamic system identiication using least squares support vector machine regression. In: Proceedings of the 3rd international conference on machine learning and cybernetics, Shanghai, August 26 – 29 2004. p. 941 – 5. |
| [38] | Young KD, Özgüner Utkin VI, Ü. A control engineer’s guide to sliding mode control. IEEE Trans Control Syst Technol 1999;7(3):328 – 42. |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
