A Meta-Invariant Feature Space Method for Accurate Tool Wear Prediction Under Cross Conditions

Abstract

Cross conditions prediction is a prevalent problem in manufacturing area, where tool wear prediction is a typical one. Existing data-driven methods for tool wear prediction mainly focus on cutting conditions with small variations, which encounters much difficulty under cross conditions with large variations, and the essential is the difference of both marginal distribution and conditional distribution of the data under cross conditions. To address this issue, this article proposes a meta-invariant feature space (MIFS) learning method, where invariant feature space is constructed for paired tasks to close marginal distribution, whose nature law under cross conditions is learned by meta-learning, i.e., MIFS, which can be adapted to achieve accurate tool wear prediction under cross conditions with a small number of new samples. Experimental results provided positive confirmation on the feasibility and accuracy of the proposed method, which can also be readily extended to regression and classification problems in other fields.