Institute of Computer Science III
University of Bonn
Databases * Information Systems * Software Engineering *
Pattern Recognition * Image Processing * Artificial Intelligence * Robotics
Knowledge-enhanced CO-monitoring in Coal Mines
in Proceedings of the Ninth International Conference on
Industrial & Engineering Applications of
Artificial Intelligence & Expert Systems,
ACROS Fukuoka, June 4-7, 1996
Detection of underground fires is an important security task in
hard-coal mining.Automated fire detection systems are usually
based on the monitoring of carbon monoxide (CO). Systems using
conventional technology based on threshold and tendency
observations, however, generate a large number of false alarms. We
show how CO-concentrations can be forecast by appropriate models
of the physical and chemical processes. We furthermore describe a
rule-based specification system utilizing forecasting for
CO-monitoring. The improvement of this approach over the
conventional is threefold. First, the number of false alarms is
reduced by 50%, at least. Simultaneously, the thresholds for
warnings and alarms can be reduced so that, second, the detection of
real fires becomes both quicker and more reliable. Third, heuristic
rules for fire detection andsuppression of false alarms as well as the
control of the forecasting can be described in a declarative way.
While our system is still in a prototypic stage, the three major
German hard-coal mining companies decided to use our approach in
their CO-monitoring systems.
Click here to obtain the full paper (PS, gzip, 136510 bytes, 10 pages)
webmaster@www.informatik.uni-bonn.de -
16.12.05