Adaptive-critic based optimal neuro control synthesis for distributed parameter systems (Q5943841): Difference between revisions

From MaRDI portal
Import240304020342 (talk | contribs)
Set profile property.
ReferenceBot (talk | contribs)
Changed an Item
Property / cites work
 
Property / cites work: Adaptive-critic-based neural networks for aircraft optimal control / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q4338950 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Universal approximation bounds for superpositions of a sigmoidal function / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q4848744 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Approximation by superpositions of a sigmoidal function / rank
 
Normal rank
Property / cites work
 
Property / cites work: Direct training method for a continuous-time nonlinear optimal feedback controller / rank
 
Normal rank
Property / cites work
 
Property / cites work: Neural networks for control systems - a survey / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q4395182 / rank
 
Normal rank

Revision as of 19:00, 3 June 2024

scientific article; zbMATH DE number 1648654
Language Label Description Also known as
English
Adaptive-critic based optimal neuro control synthesis for distributed parameter systems
scientific article; zbMATH DE number 1648654

    Statements

    Adaptive-critic based optimal neuro control synthesis for distributed parameter systems (English)
    0 references
    0 references
    0 references
    0 references
    0 references
    16 June 2003
    0 references
    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.
    0 references
    nonlinearity
    0 references
    Riccati-operator solution
    0 references
    neural network
    0 references
    optimal control
    0 references
    partial differential equations
    0 references
    discrete dynamic programming
    0 references
    parabolic equation
    0 references
    linear quadratic regulator
    0 references
    diffusion equation
    0 references

    Identifiers

    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references