Reference: Manders, E. J.; Mosterman, P. J.; & Biswas, G. Signal to Symbol Transformation Techniques for Robust Diagnosis in TRANSCEND. Knowledge Systems Laboratory, June, 1999.
Abstract: Transcend, our system for monitoring and diagnosis of complex dynamic systems, uses qualitative transient analysis methods to overcome the difficulties that arise in numerical processing, especially for nonlinear systems. Future behavior of hypothesized faults is predicted in the form of signatures, and analyzed by a progressive monitoring scheme. Generating qualitative features from real signals, the signal to symbol transformation problem, is a challenging task. This paper discusses model-driven methods for generating symbolic feature descriptions of magnitude and slope changes in noisy continuous data. Experiments have been successfully conducted on faults introduced into the cooling system of an automobile engine.
Notes: Tenth Intl. Workshop on Principles of Diagnosis, Loch Awe, Scotland, June 1999.