Self-organizing map and clustering for wastewater treatment monitoring

The objective of this project is the development of plant supervision techniques based on self-organizing map (SOM) for the implementation in a wastewater treatment plant. SOM is an unsupervised learning algorithm to establish the relationships among process variables. Clustering techniques such as...

Full description

Saved in:
Bibliographic Details
Published in:Engineering applications of artificial intelligence 2004-04, Vol.17 (3), p.215-225
Main Authors: López Garcı́a, Hilario, Machón González, Iván
Format: Article
Language:English
Subjects:
Clustering algorithms
Criterion function
Monitoring
Neural network models
Samples
Self-organizing system
Wastewater treatment
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The objective of this project is the development of plant supervision techniques based on self-organizing map (SOM) for the implementation in a wastewater treatment plant. SOM is an unsupervised learning algorithm to establish the relationships among process variables. Clustering techniques such as K-means algorithm have been used for the system state estimation, monitoring and visualization of process states. The best clustering structure is selected by means of the Davies–Bouldin index for evaluation of the several structures obtained from K-means.
ISSN:0952-1976
1873-6769
DOI:10.1016/j.engappai.2004.03.004