Thermal error model construction method, storage medium and computer equipment

By constructing a thermal error model and using whale optimization algorithm to enhance the BP neural network, the problems of universality and applicability of thermal error model parameters in the existing technology are solved, and higher prediction accuracy and stable operation of CNC machine tools are achieved.

CN119689978AActive Publication Date: 2025-03-25SHENYANG UNIVERSITY OF TECHNOLOGY +1
10 Cites 2 Cited by

Patent Information

Application Number
CN202411659167.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-20
Publication Date
2025-03-25
Estimated Expiration
2044-11-20

AI Technical Summary

Technical Problem

Parameters in existing thermal error models are usually determined by empirical or experimental methods, which is difficult to ensure the universality and applicability of parameters, and different parameters have a great impact on the model prediction accuracy.

Method used

By obtaining the working parameters at different speeds of the CNC machine spindle system, a sample set is constructed, and the BP neural network is enhanced by using whale optimization algorithm to adjust the model to improve training effect and generalization performance.

Benefits of technology

It achieves higher thermal error model prediction accuracy, ensures the machining accuracy of CNC machine tools at different speeds, improves the impact of thermal error on machining accuracy, and makes the machine tool operation more stable and reliable.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a construction method of a thermal error model, a storage medium and computer equipment, and the construction method of the thermal error model comprises the steps: obtaining working parameters when a main shaft system in a numerical control machine tool idles at different rotating speeds, the working parameters comprising temperature field data of the main shaft system and thermal deformation data of the main shaft system; constructing a sample set according to the temperature field data of the spindle system and the thermal deformation data of the spindle system; based on a whale optimization algorithm, taking the temperature rise data of the spindle system as input and taking the thermal deformation data of the spindle system as output to adjust the target BP neural network to obtain a first model; training the first model by adopting sample data in the sample set to obtain a thermal error model; wherein the temperature rise data is data determined according to the temperature field data. The whale optimization algorithm is utilized to enhance the global search capability of the BP neural network, so that the training effect and generalization performance of the model are improved, and the influence of thermal errors on the machining precision of the numerical control machine tool is improved.
Need to check novelty before this filing date? Find Prior Art