Method for predicting an operating anomaly of one or several equipment items of an assembly

Abstract

The present invention relates to a method for predicting an operating anomaly of one or several equipment items of an assembly, comprising the steps of taking an assembly, having at least one operating cycle, and comprising one or several series of equipment items comprising at least a first and a second equipment item both operating in parallel and in substantially the same manner, each equipment item comprising a first operating parameter or at least a first, a second and a third operating parameter, each parameter evolving, over time, in a similar manner between the first and the second equipments, recording and storing measurements over time of the first parameters for the first and the second equipment items, for one or several operating cycles, or one or several parts of the cycle(s), collecting the measurements during or after the completion of one or several operating cycles, or one or several parts of the cycle(s), processing the collected measurements, in order to detect a possible malfunction of the first and/or second equipment items, by establishing a first coefficient of determination, between the measurements of the first parameters of the first equipment and the measurements of the first parameters of the second equipment, whether, for one or several operating cycles, or one or several parts of the cycle(s), the first coefficient of determination is below a first determined threshold, emitting a notification indicating the malfunction of the first and second equipment item(s) and/or triggering additional steps of the method according to the invention and, if the first coefficient of determination is greater than or equal to the first threshold, emitting a notification indicating an absence of malfunction of the first and/or second equipment item(s) and/or adjusting the first threshold as a function of the first coefficient of determination.

Dependencies are inferred from the claim text.