Carriage riveting structure performance collaborative optimization model training method and system based on multi-task learning

Abstract

This invention relates to the field of model training technology, and discloses a training method and system for a collaborative optimization model of the performance of a train carriage riveting structure based on multi-task learning. The method includes: Step 1, acquiring sample parameters and generating structured input vectors and performance supervision labels; Step 2, obtaining the riveting coupling state vector based on the structured input vector; Step 3, constructing the riveting coupling state diagram and extracting shared features; Step 4, obtaining task features and performance prediction values; Step 5, constructing the basic loss, coupling consistency loss, and overall training objective function; Step 6, identifying task conflicts and updating model parameters until convergence; Step 7, obtaining the performance collaborative optimization model and determining the collaborative optimization evaluation value. This invention achieves joint prediction and collaborative optimization evaluation of multiple performance aspects of a train carriage riveting structure.

Images