Community Research and Development Information Service - CORDIS

Abstract

An integrated diagnostics methodology for large scale systems, embodying control engineering and cognitive approaches, is still an open problem in the man-machine interaction (MMI) area. Statistical diagnostics represents a new kind of tool which could play the role either of interlinking several scientific branches, or of interfacing and/or integrating decision support systems. Statistical diagnostics follows the black box philosophy and thus may deal with systems whose complexity makes ordinary control impracticable. It can be applied without prior knowledge of the physical model and deals with the system response as the realisation of a stochastic process. A parameter estimation procedure uses the signals emitted by the system in ordinary working conditions (the reference trajectory) to identify either the model or the transfer function. Then, a hierarchically organised set of statistical tests (diagnostics charts), which respond very sensitively to changes in the trajectories of the system, provides a diagnosis spectrum (diagnostics tree).

Additional information

Authors: LESSI O, University of Padua, Department of Statistics (IT);OLIVI L, University of Padua, Department of Statistics (IT);PARISI P, JRC Ispra (IT)
Bibliographic Reference: Paper presented: IFAC Symposium Safeprocess 94, Helsinki (FI), June 13-15, 1994
Availability: Available from (1) as Paper EN 38063 ORA
Record Number: 199410091 / Last updated on: 1994-11-28
Category: PUBLICATION
Original language: en
Available languages: en