Adaptive Neural Networks Command Filtered Control for MIMO Nonlinear Discrete-Time Systems With Input Constraint
Yumeng Xu, Jiapeng Liu, Jinpeng Yu, Qing‐Guo Wang
Abstract
An adaptive neural network command filtered tracking control method is investigated for multiple-input multiple-output (MIMO) discrete-time nonlinear systems with input constraint. Firstly, the noncausal problem in the backstepping is eliminated by using the command filtered control (CFC) technology. Secondly, the error compensation mechanism is brought to solve the filtering error generated by the first-order filter. Thirdly, radial basis function neural networks (RBF NNs) are exploited to deal with unknown nonlinear functions in MIMO discrete-time systems. The effectiveness of the proposed method is tested through a simulation example.
Topics & Concepts
Control theory (sociology)BacksteppingMIMOArtificial neural networkNonlinear systemConstraint (computer-aided design)Computer scienceDiscrete time and continuous timeTracking errorAdaptive controlCompensation (psychology)MathematicsControl (management)Artificial intelligenceChannel (broadcasting)PsychologyGeometryComputer networkQuantum mechanicsPhysicsPsychoanalysisStatisticsAdaptive Control of Nonlinear SystemsIndustrial Technology and Control SystemsAdvanced Algorithms and Applications