STO-BTCN thermal error prediction model modeling method and transfer learning method thereof

Abstract

The invention discloses an STO-BTCN thermal error prediction model modeling method. The method comprises the following steps: 1) initializing parameters of a swallow gull optimization algorithm (STO); 2) creating a BTCN neural network, and mapping the initial position of the swallow gull into the batch processing size and the number of filters of the BTCN neural network; 3) taking a mean absolute error (MAE) as a fitness function; 4) judging whether the mean absolute error (MAE) is smaller than a set threshold value or not; 5) judging whether the number of iterations reaches the maximum value or not, and if yes, terminating iteration; if not, adding 1 to the number of iterations, mapping the updated swallow gull position into the batch processing size and the number of filters of the BTCN neural network, and circularly executing the step 3); and 6) taking the batch processing size and the number of filters obtained by a swallow gull optimization algorithm (STO) as optimal hyper-parameters of the BTCN neural network, and constructing an STO-BTCN thermal error prediction model. The invention further discloses a transfer learning method of the STO-BTCN thermal error prediction model.

Description

technical field [0001] The invention belongs to the technical field of mechanical error analysis, in particular to a STO-BTCN thermal error prediction model modeling method and a transfer learning method. Background technique [0002] The structural deformation of the tooth grinding machine will affect the geometric accuracy of the workpiece. The higher the geometric accuracy, the better the geometric accuracy of the tooth surface. Geometric and thermal error control is critical to improving part geometric accuracy. For tooth grinding machines, there are many heat sources that affect thermal errors, including motors, bearings, rolling guides, and ball screws. [0003] For thermal error prediction, a variety of mathematical models have been proposed at present, and these models are mainly divided into two categories: (1) numerical simulation models and (2) empirical models. Discrete ideas can be seen everywhere in numerical simulation models. FDM, FEM and FDEM are widely us...

AI Technical Summary

Problems solved by technology

LSTMN has excellent performance in many fields and can be further improved. However, the improvement is not always effective, and its prediction accuracy is difficult to improve

Images