Stimulation Initiative for European Neural Applications
Esprit Project 9811
A Neural Network for Optimized Dryer-Regulation
Company background
No information available
The problem
Conventional drying processes of organic compounds, for example
dextrose, involve a great number of intransparent parameters with great
influence on the drying result. In addition to this, deadlines and the
necessity of laboratory analysis of certain parameters make it even more
difficult to meet the requirements for the product's quality.
Neural network application
On the basis of neural network-technology, a simple regulation system
for the drying process of dextrose has been implemented in a dryer.
After being trained by process data the neural network correlates
measurements with product qualities and regulates the drying process.
Benefits
A considerable improvement of product quality has been achieved:
Operators are enabled to act preventively in order to keep the drying
system from reaching an unwelcome condition.
Generalization
Many chemical processes are charcterized by a great amount of complex
parameters with a great influence on the product's quality. Customary
methods for an optimal process control, such as laboratory analysis and
evaluation of data by experts, very often cause stoppages or even
deadlines. Neural network techniques can provide a means for a more
exact analysis of chemical processes in realtime.
Contact person
ATLAN-TEC KG.
Obere Färberstraße 11,
D-41334 Nettetal.
Phone: +49 2153 800 237
Fax: +49 2153 891 32
![[ ]](../logo_small.gif){kind=logo}
SIENA