Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Multilayer discrete-time neural-net controller with guaranteed performance.

S Jagannathan¹, F L Lewis

¹Autom. and Robotics Res. Inst., Texas Univ., Arlington, TX.

IEEE Transactions on Neural Networks

|January 1, 1996

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Microbiologically influenced corrosion dynamics and technological innovations in monitoring and control.

Journal of microbiological methods·2026

Same author

Online lifelong optimal tracking control of uncertain nonlinear continuous-time strict-feedback systems using deep neural networks.

Neural networks : the official journal of the International Neural Network Society·2025

Same author

Status of disinfection byproducts research in India.

Chemosphere·2023

Same author

A deep learning approach to detect blood vessels in basal cell carcinoma.

Skin research and technology : official journal of International Society for Bioengineering and the Skin (ISBS) [and] International Society for Digital Imaging of Skin (ISDIS) [and] International Society for Skin Imaging (ISSI)·2022

Same author

Random lasing from optical fibers with phase separated glass cores.

Optics express·2020

Same author

Direct Error-Driven Learning for Deep Neural Networks With Applications to Big Data.

IEEE transactions on neural networks and learning systems·2019

Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013

Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011

Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011

Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011

Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011

Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011

See all related articles

This study introduces novel neural network controllers for complex systems, offering improved learning and stability without needing extensive data or specific system properties. These controllers ensure reliable performance even in challenging, real-world conditions.

Area of Science:

Control Systems Engineering
Artificial Intelligence
Dynamical Systems Theory

Background:

Standard adaptive control methods face limitations, including requirements for linearity and certainty equivalence.
Existing neural network (NN) control often requires specific conditions like persistency of excitation (PE), limiting practical application.

Purpose of the Study:

To present a novel family of multilayer discrete-time neural-net (NN) controllers for multi-input multi-output (MIMO) dynamical systems.
To develop advanced NN controllers that overcome limitations of traditional adaptive control and function effectively without requiring PE.

Main Methods:

A filtered error/passivity approach is used to derive the NN controller structure.
Novel online tuning algorithms, analogous to sigma/epsilon-modification, are developed for discrete-time systems.

Related Experiment Videos

The concept of persistency of excitation (PE) for multilayer NNs is defined and explored.

Main Results:

The proposed NN controllers exhibit learning-while-functioning capabilities with modified delta rule weight tuning.
New tuning algorithms guarantee system tracking and bounded NN weights, even in non-ideal scenarios, eliminating the need for PE.
The NN controllers are extended to systems with arbitrary hidden layers, introducing concepts of discrete-time passive, dissipative, and robust NNs.

Conclusions:

The novel NN controllers offer a robust and adaptive solution for MIMO systems, surpassing limitations of conventional methods.
The developed tuning algorithms ensure reliable performance and stability, making NN control more applicable to real-world dynamical systems.
The introduction of discrete-time passive, dissipative, and robust NN concepts enhances the theoretical framework for NN-based control.