Neural Network Control: Theory and ApplicationsThis book provides a systematic treatment of a general and streamlined design procedure for neural network (NN) control schemes. Stability proofs and transient performance guarantees are presented which illustrate the superior efficiency of the NN controllers over other design techniques when the system is unknown. Four main schemes for advanced neural network control are addressed in this book, including NN model-based control, direct adaptive NN control - including state feedback, observer design and decentralized control, adaptive backstopping NN control, adaptive NN control of robot manipulators. |
Contents
Neural Network Fundamentals | 1 |
Mathematical Background | 35 |
Neural Networkbased Learning and Control | 49 |
Copyright | |
7 other sections not shown
Common terms and phrases
2kor accuracy activation function adaptation gain adaptive control adaptive NN control algorithm Amin application approximation error Assumption axis backpropagation backstepping Ĉª chosen closed-loop system compact set Consider constant control law control scheme control structure control system controller design defined denotes derivative desired controller desired trajectory dynamics encoder signals equation estimate follows friction model frictional force fuzzy geometrical error given input vector interpolation k₁ learning rule Lemma linear errors linear motor Lyapunov function machine magnet matrix motion control neuron NN approximation nonlinear function nonlinear systems obtained output perceptron PID controller plant PMLM Proof radial basis function RBF network RBF weights represents robotic system servo shown in Figure sinusoidal smooth function stability subsystem supervised learning Taguchi method Theorem Time(s tion tracking error tracking performance transient performance tuning update law V₁ velocity vi)² W₁ weight adjustments zero Zhang