System identification using multilayer differential neural networks: a new result
Summary: In previous works, a learning law with a dead zone function was developed for multilayer differential neural networks. This scheme requires strictly a priori knowledge of an upper bound for the unmodeled dynamics. In this paper, the learning law is modified in such a way that this condition is relaxed. By this modification, the tuning process is simpler and the dead-zone function is not required anymore. On the basis of this modification and by using a Lyapunov-like analysis, a stronger result is here demonstrated: the exponential convergence of the identification error to a bounded zone. Besides, a value for upper bound of such zone is provided. The workability of this approach is tested by a simulation example.
- Multilayer dynamic neural networks for non-linear system on-line identification
- Identification of nonlinear dynamical systems using multilayered neural networks
- On ``An improved approach for nonlinear system identification using neural networks.
- Dynamic system identification via recurrent multilayer perceptrons
- scientific article; zbMATH DE number 2012410
- An adaptive nonlinear filter for system identification
- Approximation by superpositions of a sigmoidal function
- Dynamic system identification via recurrent multilayer perceptrons
- scientific article; zbMATH DE number 1573291 (Why is no real title available?)
- scientific article; zbMATH DE number 51537 (Why is no real title available?)
- scientific article; zbMATH DE number 1342053 (Why is no real title available?)
- scientific article; zbMATH DE number 741374 (Why is no real title available?)
- scientific article; zbMATH DE number 2140010 (Why is no real title available?)
- Hysteresis nonlinearity identification using new Preisach model-based artificial neural network approach
- Identification of a Duffing oscillator under different types of excitation
- Multilayer feedforward networks are universal approximators
- Neural networks for control systems - a survey
- Neural networks for modelling and control of dynamic systems. A practitioner's handbook
- Nonlinear black-box modeling in system identification: A unified overview
- Nonlinear system identification using neural networks trained with natural gradient descent
- Passivity analysis for dynamic multilayer neuro identifier
- Robust adaptive control via neural linearization and compensation
- System identification of MEMS vibratory gyroscope sensor
- Wireless Ad hoc and Sensor Networks
- Tracking control based on recurrent neural networks for nonlinear systems with multiple inputs and unknown deadzone
- Robust adaptive neurocontrol of SISO nonlinear systems preceded by unknown deadzone
- On the output-feedback regulation for a second-order system with unknown parameters: an I\&I and MRAC based approach
- Parametric uncertain second-order linear system output-adaptive stabilization: an integral and MRCA based approach
- Application of a multi-layered neural network to system identification
- Identification of nonlinear dynamical systems using multilayered neural networks
- State-input affine approximate modeling based on a differential neural network identifier
- Adaptive output-feedback trajectory tracking for a class of uncertain second-order linear systems
This page was built for publication: System identification using multilayer differential neural networks: a new result
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q442953)
