Fabric hair shearing parameter optimization method based on multi-objective genetic algorithm

Abstract

The present application relates to the technical field of textile strategy optimization, in particular to a fabric hair shearing parameter optimization method based on a multi-objective genetic algorithm. The specific implementation process comprises the following steps: obtaining a hair removal rate and a fabric damage degree, combining a printing pigment solidification distribution map to calculate a local fitness, extracting process parameters to convert into a hair shearing negative pressure matrix, and constructing a virtual evolution space; using a multi-objective genetic algorithm to generate a child parameter population for virtual evaluation to generate a virtual parameter solution set, and inputting the virtual parameter solution set into a deep learning agent network to predict shearing parameters; based on the shearing parameters, generating a virtual Pareto solution set to issue a trial cut, and using real verification feedback to correct the agent network. The present application introduces a deep learning agent network and a virtual evolution space in the evolution operation, uses virtual evaluation to replace frequent real physical trial cutting, realizes local adaptive optimization for different pattern areas of printed fabric, and improves the efficiency of global optimization of shearing parameters.

Images