Enhanced prediction accuracy in high-speed grinding of brittle materials using advanced machine learning techniques

Sangkyoung Lee, Zhuoxiao Chen, Yadan Luo, Xuliang Li, Mingyuan Lu (), Zi Helen Huang and Han Huang ()
Additional contact information
Sangkyoung Lee: University of Queensland
Zhuoxiao Chen: University of Queensland
Yadan Luo: University of Queensland
Xuliang Li: University of Queensland
Mingyuan Lu: University of Queensland
Zi Helen Huang: University of Queensland
Han Huang: University of Queensland

Journal of Intelligent Manufacturing, 2025, vol. 36, issue 8, No 10, 5415-5459

Abstract: Abstract Machine Learning (ML) is transforming manufacturing by adeptly managing large and complex dataset, holding immense potential to improve various machining processes. Application of ML in high-speed precision grinding of brittle solids is critical yet largely unexplored, due to complex deformation and removal mechanisms. The coexistence of ductile and brittle material removals in brittle materials results in intricate surface morphologies that current models struggle to predict accurately. This study addresses this gap by investigating the use of ML to analyse extensive datasets of ground brittle materials and predict grinding outcomes. Incorporating various parameters, including grinding conditions, ground surface images, and workpiece’s mechanical properties, ML algorithms predicted surface roughness and grinding forces accurately. Models were trained and validated using a diverse dataset from the grinding of three different brittle single crystals: GaAs, SiO2, and Si, under various conditions. The results show that both non-deep and image-based deep learning models predicted roughness and grinding forces with high accuracy. Among non-deep algorithms, the Gradient Boosting regressor exhibited exceptional performance, achieving high accuracy in predicting both roughness and grinding force. The novel EfficientNet-based model also achieved outstanding accuracy in such predictions. This study’s main contribution is a predictive model that effectively captures the complex behaviours of brittle materials in grinding, an area previously underexplored. Additionally, the study pioneers the integration of grinding forces into predictive modelling, providing a holistic view of the grinding process. This innovative approach promises significant improvements in adaptive in-process monitoring, control, and optimisation of grinding operations, potentially revolutionising machining practices.

Keywords: Machine learning; Machining; Brittle material; Prediction accuracy; High-speed grinding; Roughness; Grinding force (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10845-024-02532-x 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:36:y:2025:i:8:d:10.1007_s10845-024-02532-x

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

DOI: 10.1007/s10845-024-02532-x

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 ().