A machine methodology for generating qualitative interpretations (QIs) of 2-D sensor patterns is described. The approach enables a computer to interpret multisensor patterns under transient conditions at a level comparable to that of an experienced plant operator. Adaptive Resonance Theory introduced by Grossberg (1976a, b) is utilized with modification to provide human-like memory attributes. The methodology offers a more robust and adaptable means to interface symbolic knowledge-based systems with numeric plant operating systems. Exemplar-based, supervised learning is utilized to construct a high dimensional QI-map. During run-time, qualitative interpretations are generated for input patterns based on their location on this QI-map. Demonstration results for a dynamically simulated chemical process are presented.