1989 American Control Conference 1989
DOI: 10.23919/acc.1989.4790321
|View full text |Cite
|
Sign up to set email alerts
|

Neural Networks for System Identification

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
9
0

Year Published

1992
1992
2006
2006

Publication Types

Select...
3
2
1

Relationship

0
6

Authors

Journals

citations
Cited by 25 publications
(9 citation statements)
references
References 6 publications
0
9
0
Order By: Relevance
“…What these approaches provide in real-time identification of modal parameters comes with significant computational cost and complexity. Other real-time capable approaches include model predictive and neural network based identification methods that fit parameters to generic or non-physical models [9,24,26,27].…”
Section: Introductionmentioning
confidence: 99%
“…What these approaches provide in real-time identification of modal parameters comes with significant computational cost and complexity. Other real-time capable approaches include model predictive and neural network based identification methods that fit parameters to generic or non-physical models [9,24,26,27].…”
Section: Introductionmentioning
confidence: 99%
“…( 3 ) The neural network may implement the LSE well, but may not give the correct results because of local minimum [ 2 ] . As noted by a reviewer , this problem has not been adequately addressed, and requires more study.…”
Section: Discussionmentioning
confidence: 99%
“…implementation of LSE using neural networks [ 2 ] . Specifically, they show that a system described by a state space description such as equation (2) can be precisely identified with a Hopfield network using state measurements.…”
Section: Cb Dmentioning
confidence: 99%
See 2 more Smart Citations