Abstract: The disclosure relates to a method and device for identification of correlations between alarm messages in an alarm system of a technical installation or a technical process and/or correlations between such alarm messages and operator actions, using a data processing device which has access to recorded historical data which relates to alarm messages and operator actions. The data processing device can use market basket analysis methods to deal with and analyze historical data, which occurs at defined intervals, as a market basket. Quality characteristics can be formed from a relationship between respective operator actions before and after an occurrence of a respective alarm message, and/or from correlations between alarm messages and operator actions, via the data processing device, which has access to the recorded historical data which relates to alarm messages and operator actions.

Abstract: The disclosure relates to a method and device for identification of correlations between alarm messages in an alarm system of a technical installation or a technical process and/or correlations between such alarm messages and operator actions, using a data processing device which has access to recorded historical data which relates to alarm messages and operator actions. The data processing device can use market basket analysis methods to deal with and analyze historical data, which occurs at defined intervals, as a market basket. Quality characteristics can be formed from a relationship between respective operator actions before and after an occurrence of a respective alarm message, and/or from correlations between alarm messages and operator actions, via the data processing device, which has access to the recorded historical data which relates to alarm messages and operator actions.

Abstract: The invention relates to a process diagnosis system and a method for the diagnosis of processes and states in a technical process, in particular for the diagnosis of a power station process. The invention is a structured multi-agent system which corresponds to the process and has a plurality of autonomous diagnostic agents. The diagnostic agents in each case contain a neural network, with whose aid a reference behavior of process components that are to be monitored can be learned. In addition, automatic adaptation to a new reference behavior is also possible by the diagnostic agents.