Composite adaptive radial basis function neural network (RBFNN) control with a lattice distribution of hidden nodes has three inherent demerits: 1) the approximation domain RBFNNs is difficult to be determined a priori ; 2) only partial persistence excitation (PE) condition can guaranteed; 3) i...

Neural networks are applied to the system identification problems using adaptive algorithms for either parameter or functional estimation of dynamic systems. In this paper the neural networks' sensitivity to input values and connections' weights, is studied. The Reduction-Sigmoid-Amplification (RSA) neurons are introduced and four different models of neural network architecture are proposed and...

Combining the adaptive inverted control method based on a compound orthogonal neural network with generic mode control scheme, an adaptive control algorithm based on a compound orthogonal neural network has been proposed, which can embed the process model into the controller by the inverted control method with neural networks. It can guarantee the realizability of the generic model control sche...