Adaptive-critic based optimal neuro control synthesis for distributed parameter systems

DOI10.1016/S0005-1098(01)00093-0MaRDI QIDQ5943841zbMATH OpenOpenAlexFDO

Authors Radhakant Padhi, S. N. Balakrishnan, Timothy W. Randolph

Publication date 16 June 2003

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/s0005-1098(01)00093-0

zbMATH Keywords

diffusion equationdiscrete dynamic programminglinear quadratic regulatorneural networknonlinearityoptimal controlparabolic equationpartial differential equationsRiccati-operator solution

Mathematics Subject Classification ID

Dynamic programming in optimal control and differential games (49L20) Linear-quadratic optimal control problems (49N10) Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) Synthesis problems (93B50) Nonlinear systems in control theory (93C10) Control/observation systems governed by partial differential equations (93C20)

Review text

A neural network based optimal control synthesis approach is presented for systems modeled by partial differential equations. The problem is formulated via discrete dynamic programming, and necessary conditions for optimality are derived. For the synthesis of the controller, the authors propose two sets of neural networks: the set of action networks captures the mapping between the state and control, while the set of critic networks captures the mapping between the state and costate. They illustrate the solution process with a parabolic equation involving a nonlinear term. For comparison, they consider the linear quadratic regulator problem for the diffusion equation, for which the Riccati-operator based solution is known. The results show that this adaptive-critic based systematic approach holds promise for obtaining the optimal control design of both linear and nonlinear distributed parameter systems.

Recommendations

• Adaptive neural network-based optimal control of nonlinear continuous-time systems in strict-feedback form
• Optimal and robust control of a class of nonlinear systems using dynamically re-optimised single network adaptive critic design
• Neural-network-based robust optimal control design for a class of uncertain nonlinear systems via adaptive dynamic programming
• Adaptive control of nonlinear dynamic systems using -adaptive neural networks
• Neural networks solving free final time optimal control problem

Cites work

• Adaptive-critic-based neural networks for aircraft optimal control
• Approximation by superpositions of a sigmoidal function
• Direct training method for a continuous-time nonlinear optimal feedback controller
• scientific article; zbMATH DE number 1016634 (Why is no real title available?)
• scientific article; zbMATH DE number 1163608 (Why is no real title available?)
• scientific article; zbMATH DE number 798179 (Why is no real title available?)
• Neural networks for control systems - a survey
• Universal approximation bounds for superpositions of a sigmoidal function

Cited in

(6)

• Optimal neurocontroller synthesis for impulse-driven systems
• Neural networks solving free and fixed final time optimal control problems
• scientific article; zbMATH DE number 786545 (Why is no real title available?)
• Bezier Curve Parameterization Methods for Solving Optimal Control Problems of SIR Model
• Radial basis function networks simulation of age-structure population
• A single network adaptive critic (SNAC) architecture for optimal control synthesis for a class of nonlinear systems

This page was built for publication: Adaptive-critic based optimal neuro control synthesis for distributed parameter systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5943841)