Two stage neural network modelling for robust model predictive control. (January 2018)

• Record Type: Journal Article
• Authors: Patan, Krzysztof
• Is Part Of: ISA transactions. Volume 72(2018)
• Page Start: 56
• Page End: 65
• Publication Date: 2018-01
• Subjects: Predictive control -- Robustness -- Neural networks -- Stability; Engineering instruments -- Periodicals; Engineering instruments; Periodicals; Electronic journals; 629.805
• DOI: 10.1016/j.isatra.2017.10.011
• Languages: English
• ISSNs: 0019-0578

Abstract

Abstract: The paper proposes a novel robust model predictive control scheme realized by means of artificial neural networks. The neural networks are used twofold: to design the so-called fundamental model of a plant and to catch uncertainty associated with the plant model. In order to simplify the optimization process carried out within the framework of predictive control an instantaneous linearization is applied which renders it possible to define the optimization problem in the form of constrained quadratic programming. Stability of the proposed control system is also investigated by showing that a cost function is monotonically decreasing with respect to time. Derived robust model predictive control is tested and validated on the example of a pneumatic servomechanism working at different operating regimes. Abstract : Highlights: Robust two-stage identification by means of artificial neural networks is proposed. Robust control using neural network based model error modelling is developed. Stability analysis of robust neural network based model predictive control. Instantaneous linearization of the robust neural network model. Robust control of a pneumatic servomechanism experimental study.