English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The article outlines the methodology of structural and parametric synthesisof neural network controllers for controlling objects with limiters underincomplete information about the controlled object. Artificial neural networksare used to create controllers that are sequentially integrated into a controlsystem with control objects. Reinforcement learning and pre-building a neuralnetwork imitator of the control object are used to synthesize the neuralnetwork controller. This approach is particularly effective when classicalcontrol system synthesis methods are not applicable due to significantnonlinearity and the difficulty in forming a mathematical model of the controlobject with the required accuracy. The proposed methods expand the class oftechnical systems for which direct synthesis of near-optimal control laws ispossible. The robustness, adaptability and technical feasibility of neuralnetwork controllers make them interesting for practical applications. The mainattention in the article is paid to the choice of neural network structure inthe imitator and controller, formation of training samples taking into accountthe limitations of the control object.

Structure and Optimization of Parameters for Neural Network Controllers in Automatic Control Systems