Industrial-oriented machine learning big data framework for temporal-spatial error prediction and control with DTSMGCN model

Hongquan Gui (), Jialan Liu (), Chi Ma () and Mengyuan Li ()
Additional contact information
Hongquan Gui: Chongqing University
Jialan Liu: Chongqing University
Chi Ma: Chongqing University
Mengyuan Li: Chongqing University

Journal of Intelligent Manufacturing, 2024, vol. 35, issue 3, No 12, 1173-1196

Abstract: Abstract The thermal error reduces the machining accuracy of machine tools, and should be effectively controlled. But the accurate prediction of the thermal error is challenging because of the complex and dynamic running conditions. In previous studies, the temporal feature of the thermal error is considered, and the spatial feature of the thermal error is not considered. However, the thermal error has temporal-spatial (TS) behaviors, and then it is not sufficient to consider the temporal feature only, leading to a low prediction accuracy and poor robustness. Furthermore, most studies on the TS modeling ignore the complexity of the spatial feature, resulting in the spatial feature of the thermal error not being comprehensively captured. When building a TS model, many studies simply connect the spatial model with the temporal model in series. However, the spatial feature changes with the running time, and the series model cannot truly reflect the TS features. To address these challenges, a new dynamic TS memory graph convolutional network (DTSMGCN) model is proposed to learn the dynamic TS features of the thermal error in this study. The generation mechanism of the thermal error is demonstrated by solving the heat conduction equation, and the dynamic TS behaviors are revealed by the Laplace transform. The designed DTSMGCN cell consists of the marginal unit, joint unit, and hybrid adjacency matrix, and can capture the temporal feature of each variable and the TS features among variables. Moreover, to expedite the training process and improve the executing efficiency, an industrial-oriented machine learning big data framework (IOMLBDF) is designed. The proposed DTSMGCN model is embedded into the designed IOMLBDF. The results show that the DTSMGCN model outperforms other machine learning models, and the designed IOMLBDF can improve the training efficiency when increasing the number of virtual machine nodes and achieve the real-time control of the thermal error.

Keywords: Temporal-spatial modeling; Big data framework; Machine learning; Virtual machine node (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10845-023-02095-3 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joinma:v:35:y:2024:i:3:d:10.1007_s10845-023-02095-3

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10845

DOI: 10.1007/s10845-023-02095-3

Access Statistics for this article

Journal of Intelligent Manufacturing is currently edited by Andrew Kusiak

More articles in Journal of Intelligent Manufacturing from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().