A filtering agent scheme to remote control of industrial processes using Petri nets

For remote control of industrial processes, certain improper actions may violate desired specifications and result in accidents. For such human-involved systems, this paper has applied a command filtering approach to accept or reject the human-issued commands so that undesirable executions would never be carried out. In the present approach, Petri nets (PNs) are used to model the human behaviors and to synthesize the command filters for further agent implementation. An application to a rapid thermal process in semiconductor manufacturing systems is provided to demonstrate the practicability of the proposed approach.