Abstract
This paper will postulate the destined progress from classical to neuro-control techniques based upon the structural and functional comparison of fluid powered system with the human body. It will describe the similarities between the feed forward neural network and the proportional-integral-derivative (PID) controller. After establishing the PID controller as a limited form of feed-forward neural net, the paper will discuss the extension of using the neural network back-propagation training technique to the PID controller. Simulated results of a simple system are given to illustrate the training process. (from Authors)
| Original language | English |
|---|---|
| Journal | [No source information available] |
| Publication status | Published - Jan 1 1993 |
| Externally published | Yes |
Fingerprint
ASJC Scopus subject areas
- Engineering(all)
Cite this
Neural network and fluid power control. / Fok, S. C.; Ong, E. K.
In: [No source information available], 01.01.1993.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Neural network and fluid power control
AU - Fok, S. C.
AU - Ong, E. K.
PY - 1993/1/1
Y1 - 1993/1/1
N2 - This paper will postulate the destined progress from classical to neuro-control techniques based upon the structural and functional comparison of fluid powered system with the human body. It will describe the similarities between the feed forward neural network and the proportional-integral-derivative (PID) controller. After establishing the PID controller as a limited form of feed-forward neural net, the paper will discuss the extension of using the neural network back-propagation training technique to the PID controller. Simulated results of a simple system are given to illustrate the training process. (from Authors)
AB - This paper will postulate the destined progress from classical to neuro-control techniques based upon the structural and functional comparison of fluid powered system with the human body. It will describe the similarities between the feed forward neural network and the proportional-integral-derivative (PID) controller. After establishing the PID controller as a limited form of feed-forward neural net, the paper will discuss the extension of using the neural network back-propagation training technique to the PID controller. Simulated results of a simple system are given to illustrate the training process. (from Authors)
UR - http://www.scopus.com/inward/record.url?scp=85041149186&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85041149186&partnerID=8YFLogxK
M3 - Article
JO - [No source information available]
JF - [No source information available]
ER -