Abstract
This article introduces fundamentals of self-diagnosis and predictive (or preventive) maintenance technologies for dry vacuum pumps. The state variables of dry pumps are addressed, such as the pump and motor body temperatures, consumption currents of main and booster pumps, mechanical vibration, and exhaust pressure, etc. The adaptive parametric models of the state variables of the dry pump are exploited to provide dramatic reduction of data size and computation time for self-diagnosis. Two indicators, the Hotelling's $T^2$ and the sum of squares residuals (Q), are illustrated to be quite effective and successful in diagnosing dry pumps used in the semiconductor processes.
