An intelligent reactive monitoring and scheduling system

A system developed for monitoring large-scale distributed processes and modifying the control plan in real time, in response to deviations from the planned production schedule, is reported. The monitoring method is based on behavioral models that represent and manipulate both discrete and continuous process dynamics. Reactive scheduling and control is accomplished by combining real-time problem solving and numeric optimization techniques to generate the lowest-cost recovery plan within the time available. The feasibility of recovery strategies is checked online using the behavioral models in a prognostication mode. A prototype system has been implemented using Concurrent Real Time OPS5 (CROPS5) and C++ and runs on the Mach operating system. The system is being extended as a commercial product for online monitoring and reactive scheduling of continuous-caster steel mills.<
>