Abstract | ||
---|---|---|
A receding-horizon (RH) optimal control scheme for a discrete-time nonlinear dynamic system is presented. A nonquadratic cost function is considered, and constraints are imposed on both the state and control vectors. Two main contributions are reported. The first consists in deriving a stabilizing regulator by adding a proper terminal penalty function to the process cost. The control vector is generated by means of a feedback control law computed off line instead of computing it on line, as is done for existing RH regulators. The off-line computation is performed by approximating the RH regulator by means of a multilayer feedforward neural network (this is the second contribution of the paper). Bounds to this approximation are established. Simulation results show the effectiveness of the proposed approach. |
Year | DOI | Venue |
---|---|---|
1995 | 10.1016/0005-1098(95)00044-W | Automatica |
Keywords | Field | DocType |
nonlinear system,neural approximation,receding-horizon regulator,feedback control,cost function,penalty function,discrete time,neural networks,neural network,nonlinear systems,optimal control | Regulator,Feedforward neural network,Mathematical optimization,Nonlinear system,Optimal control,Control theory,Artificial neural network,Mathematics,Discrete system,Computation,Penalty method | Journal |
Volume | Issue | ISSN |
31 | 10 | 0005-1098 |
Citations | PageRank | References |
76 | 19.86 | 5 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
T Parisini | 1 | 935 | 113.17 |
R. Zoppoli | 2 | 279 | 51.51 |