Thermal Error Prediction and Compensation of YK3610 Hobbing Machine Based on BP Neural Networks
Qianjian Guo*, 1, Rufeng Xu1, Xiaoni Qi2
Identifiers and Pagination:Year: 2015
First Page: 678
Last Page: 681
Publisher Id: TOMEJ-9-678
Article History:Received Date: 3/10/2014
Revision Received Date: 5/1/2015
Acceptance Date: 17/1/2015
Electronic publication date: 17/9/2015
Collection year: 2015
open-access license: This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: (https://creativecommons.org/licenses/by/4.0/legalcode). This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
In this study, error compensation technology was proposed to reduce thermal errors of a gear hobbing machine, and one experiment was carried out to verify the compensation effect. Different thermal sources were used as modeling variables, and a prediction model of thermal errors was presented based on back propagation (BP) neural networks. In order to solve local minimum problem of BP neural networks, ant colony algorithm was used for training its link weights. Finally, one test system was developed based on the presented model, and an experiment was fulfilled. The result shows that prediction performance of the model is very well, and the residual error is less than 5 μm after compensation.