Recurrent neural networks (RNNs) have been widely used to model nonlinear dynamic systems using time-series data. While the training error of can be rendered sufficiently small in many cases, there is a lack general framework guide construction and determine generalization accuracy RNN models predictive control systems. In this work, we employ statistical machine learning theory develop methodo...

This letter presents the modeling, system identification and nonlinear model predictive control (NMPC) design for longitudinal, full envelope velocity of a small tiltwing hybrid unmanned aerial vehicle (H-UAV). A first-principles based dynamics is derived identified from flight data. It captures important aerodynamic effects including propeller-wing interaction stalled airfoils, but still simpl...

In this paper, a nonlinear model predictive swing-up and stabilizing sliding controller is proposed for an inverted pendulum-cart system. In the swing up phase, the nonlinear model predictive control is formulated as a nonlinear programming problem with energy based objective function. By solving this problem at each sampling instant, a sequence of control inputs that optimize the nonlinear obj...

In the paper, a well-known predictive functional control strategy is extended to nonlinear processes. In our approach the predictive functional control is combined with a fuzzy model of the process and formulated in the state space domain. The prediction is based on a global linear model in the state space domain. The global linear model is obtained by the fuzzy model in Takagi–Sugeno form and ...

In this paper, an Output Feedback Model Predictive Control for nonlinear systems is presented. The proposed output feedback control consists of the well known robust controller NCGPC (Nonlinear Continuous Time Generalized Predictive Control) and an open loop observer (a simulated model in parallel) in order to estimate the output derivatives and a regulation filter used to account for plant/mod...

wind energy today, has attracted widespread interest from among a variety of sources of renewable energy in the world. owing to the increasing demand for production of electrical energy for electricity networks by using wind power, it is essential that wind power plants are actively incorporated in the network’s performance using an appropriate control system. in general, these wind power plant...

a fault-tolerant control (ftc) methodology has been presented for nonlinear processes being imposed by control input constraints. the proposed methodology uses a combination of feedback linearization and model predictive control (flmpc) schemes. the resulting constraints in the transformed process will be dependent on the actual evolving states, making their incorporation in the design context ...

This study discusses vehicle stability control based on explicit nonlinear model predictive (NMPC) and investigates the influence of prediction fidelity controller performance. The solutions are generated through an algorithm using multiparametric quadratic programming (mp-QP) approximations (mp-NLP) problems. Controllers with different models assessed objective indicators in sine-with-dwell te...

In the nonlinear model predictive control (NMPC) field, it is well-known that the multistep control approach is superior to the single-step approach when examining high-order nonlinear systems. In the multistep control approach, however, the online minimization of a 2-norm square objective function over a control horizon of length M always requires solving a set of complex polynomial equations,...

Abstract: This paper deals with the control of the melt index and density of polymers produced. Nonlinear Model predictive control (NLMPC) is used for this purpose. A nonlinear reactor model combined with correlations for predicting polymer melt index and density are used to simulate the process. The simulations revealed the effectiveness of NLMPC to drive the polymer properties to follow a ser...