The development of the variational quantum circuits architecture of the quantum long short-term memory model for thermal error compensation in the z-axis of machine tools
Journal
The International Journal of Advanced Manufacturing Technology
ISSN
02683768
Date Issued
2025
Author(s)
Abstract
Effectively controlling thermal errors in machine tools and developing robust thermal error compensation models are crucial research topics in modern manufacturing. A novel Quantum Long Short-Term Memory (QLSTM) model is proposed, featuring an internal variational quantum circuit architecture designed to address challenges in predictive accuracy and reliability for machine tool time-series data. Thirteen temperature sensors are utilized to monitor temperature variations at multiple locations on the machine, while a non-contact optical measurement system is employed to measure the positioning deviations during spindle rotation. The model incorporates optimized design at the quantum encoding layer and introduces a Controlled-RZ gate structure within the variational quantum circuits layer. The proposed compensation model is then compared against traditional QLSTM architectures and alternative variational quantum circuit designs. For performance validation, data from different spindle speed configurations are used to test the model. The proposed model architecture achieves a maximum improvement percentage of 53.4% in model performance. In the thermal error compensation experiments, testing across five spindle speed configurations demonstrates that the proposed compensation model successfully reduces the uncompensated Z-axis error from 52.36 μm to 10.26 μm, achieving a maximum error improvement rate of 80.4%. Additionally, the peak-to-peak error along the spindle's Z-axis is reduced to within 15 μm. In summary, the proposed quantum model significantly enhances the predictive accuracy of the thermal error compensation model and demonstrates substantial improvements in error reduction.
Subjects
Machine tool
Quantum
Thermal error compensation
Variational quantum circuits
SDGs
Publisher
Springer Science and Business Media Deutschland GmbH
Type
journal article