A virtual sample expansion method based on historical data of mechanical products

Abstract

The invention discloses a virtual sample expansion method based on historical data of mechanical products. First, the virtual sample capacity of the virtual sample in the small sample problem is determined according to the measured historical data; then, based on the historical data of mechanical production and prior knowledge related to mechanical production, Constructed a sample pool for generating virtual samples; then sampled samples based on the "roulette" sampling idea, and designed virtual sample generation rules based on the idea of ​​agent model and Jacobian screw theory; finally judged that the conditions were retained and feasible through the rationality of the samples The expansion sample, thus realizing the expansion of the virtual sample training for the small sample regression problem for the prediction of mechanical assembly accuracy. The achievement of the invention can be used to expand the sample capacity of small-capacity sample machine learning training models, which can solve the problem of insufficient number of samples encountered in the prediction of mechanical assembly accuracy, and is of great significance to the use of machine learning regression methods to study the small sample problem of tolerance transfer of customized products .

Description

technical field [0001] The invention relates to a method for expanding the capacity of a virtual sample, in particular to a method for expanding the capacity of a virtual sample based on historical data of mechanical products. Background technique [0002] Machine learning techniques based on large sample data have been widely used in different fields. With the introduction of the concept of intelligent manufacturing, the combination of machine learning technology and the mechanical field is becoming increasingly close. However, with the continuous improvement of mechanical design and manufacturing level, mechanical products have a trend of diversified design requirements, non-standardized and personalized customized production, which leads to some problems in the mechanical field no longer have the conditions to generate large-capacity sample data, thereby limiting application of machine learning techniques. [0003] At present, machine learning in the mechanical field is...

AI Technical Summary

Problems solved by technology

There are few studies on virtual sample generation methods for regression problems

Images