AI-powered system for predicting tread patterns of abstract lengths

Abstract

Predicting the tire product profile exiting an extruder, as a function of extruder parameters (EXTRD), includes: - obtaining (221) a contextual profile (PL, PT); - decomposing the contextual profile (223) into iterations of a sliding window (FGi) traversing the contextual profile over a set of iterations (FGtot), each iteration of the window (FGi) being centered on a point of interest (Pi) and including at least one point behind (Pi-1) and at least one point in front of the point of interest (Pi+1); - the use of a learning model (225) trained to predict a point of interest (Pi) of a real profile (PR) as a function of a window (FGi) of a contextual profile (PL, PT) centered on the point of interest (Pi), recursively (RCR) over said iteration set so as to obtain a prediction of the entire real profile (226). Figure for the abstract: Fig 2B