Towards Continuous Process Supervision

This paper provides a contribution to qualitative reasoning for continuous process supervision. Tools for formalizing empirical knowledge of continuous processes and a naive reasoning nat­ urally integrating perception are proposed. A new paradigm emerges : maintenance of a single instantaneous and possibly partial understanding of a physical system during its evolution. This understanding in closed loop includes prediction and truth maintenance of whole histories of evolution at the data sam­ pling rate. This technique relies on both deep and empirical knowledge, using mainly intuitive notions like order of magni­ tude of non-negligible quantity, gain, delay and duration. Our approach is compared to existing work in qualitative physics basically focused on qualitative calculus of classical physics for­ malization.