Deadzone compensation based on constrained RBF neural network (Q705937)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 2134374
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Deadzone compensation based on constrained RBF neural network |
scientific article; zbMATH DE number 2134374 |
Statements
Deadzone compensation based on constrained RBF neural network (English)
0 references
16 February 2005
0 references
Two neural networks are used for the compensation of a deadzone. A radial basis function (RBF) neural network is used for the identification of the parameters. Then the RBF network acts as a single layer neural network and is trained based on the gradient descent technique. The result is used to train the other neural network for the inverse compensation of the deadzone.
0 references
RBF neural network
0 references
inverse deadzone compensation
0 references
back propagation method
0 references
identification
0 references
gradient descent technique
0 references
0.8176066875457764
0 references
0.7916424870491028
0 references
0.7324339747428894
0 references
0.703670859336853
0 references
