This paper introduces a novel technique for condition monitoring of gas tur
bine start up sequences, The vast amount of data and the complex processes
behind on-line fault detection indicate the need for an automated solution.
A multi agent system that views the problem as the interaction of simple i
ndependent software entities, for effective use of the available data, is p
resented. The overall solution is derived from the combination of partial s
olutions provided by the components of the multi-agent system. As a consequ
ence, data interpretation is achieved by converting the data into appropria
te information and combining individual agents' information, resulting in a
n automatic fault diagnosis for the engineers, This multi-agent system can
employ various intelligent system techniques and has been implemented using
the ZEUS Agent Building Toolkit.