Adaptive uncertainty compensation-based nonlinear model predictive control with real-time applications
- 230 Downloads
In this paper, an adaptive model predictive controller (MPC) with a function approximator is proposed to the control of the uncertain nonlinear systems. The proposed adaptive Sigmoid and Chebyshev neural networks-based MPCs (ANN-MPC and ACN-MPC) compensate the system uncertainty and control the system accurately. Using Lyapunov theory, the closed-loop signals of the linearized dynamics and the uncertainty modeling-based model predictive controller have been proved to be bounded. Accuracy of the ANN-MPC and ACN-MPC has been compared with the Runge–Kutta discretization-based nonlinear MPC on an experimental MIMO three-tank liquid-level system where a functional uncertainty is created on its dynamics. Real-time experimental results demonstrate the effectiveness of the proposed controllers. In addition, due to the faster function approximation capability of Chebyshev polynomial networks, ACN-MPC provided better control performance results.
KeywordsModel predictive control Adaptive neural network Chebyshev polynomial network Uncertainty compensation Stability Three-tank liquid-level system Real-time control
Compliance with ethical standards
Conflict of interest
We have received no support or commercial funding for this paper; therefore, we have no conflicts of interest to declare.
- 13.Beyhan S, Alci M (2009) An orthogonal ARX network for identification and control of nonlinear systems. In: XXII international symposium on information, communication and automation technologies. ICAT 2009, IEEE, pp 1–5Google Scholar
- 25.Ławryńczuk M (2014) Computationally efficient model predictive control algorithms. A neural network approach studies in systems, decision and control, vol 3. doi: 10.1007/978-3-319-04229-9
- 37.Amira (2002) DTS 200 laboratory setup three-tank-system. Amira GmbH, DuisburgGoogle Scholar