Information access and control operations in multi-agent system based process automation

An approach to combine information access and control operations in a process automation system extended with multi-agent system technology is presented in this paper. According to this approach a multi-agent system supervises an ordinary process automation system by performing higher-level information access and control operations. The information access operations are aimed for actively combining information from different sources depending on the monitoring tasks of the users. The control operations of the multi-agent system are supervisory control tasks performed either in sequential or iterative fashion. The expected benefit of the multi-agent system is enhanced adaptability of the automation system and increased situation awareness of its users. The architecture of the multi-agent system is based on the BDI agent model and utilization of so-called ontologies. An approach for engineering applications for this kind of a multi-agent system is also discussed. The approach is demonstrated with results from experiments performed with industrial test data and a laboratory test process.