Investigation on eXtreme Gradient Boosting for cutting force prediction in milling

Heitz, Thomas; He, Ning; Ait-Mlouk, Addi; Bachrathy, Daniel; Chen, Ni; Zhao, Guolong; Li, Liang

doi:10.1007/s10845-023-02243-9

Cited by 3 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with the "normal network", the transmission network has obvious performance advantages. Heitz1 et al [28] used model training as a new feature of the mechanical force model in the time and frequency domains, and the cutting force was predicted efficiently by the extreme gradient boosting optimization algorithm, which improved the optimization accuracy, efficiency, user-friendliness, and efficiency. Currently, machine learning neural network models are rarely studied for modal parameter predictions.…”

Section: Introductionmentioning

confidence: 99%

Predicting the Dynamic Parameters for Milling Thin-Walled Blades with a Neural Network

Li,

Ding,

Wang

et al. 2024

JMMP

View full text Add to dashboard Cite

Accurately predicting the time-varying dynamic parameters of a workpiece during the milling of thin-walled parts is the foundation of adaptively selecting chatter-free machining parameters. Hence, a method for accurately and quickly predicting the time-varying dynamic parameters for milling thin-walled parts is proposed, which is based on the shell FEM and a three-layer neural network. The time-dependent dynamics of the workpiece can be calculated using the FEM by obtaining the geometrical parameters of the arc-faced junctions within the discrete cells of the initial and machined workpiece. It is unnecessary to re-divide the mesh cells of the thin-walled parts at each cutting position, which enhances the computational efficiency of the workpiece dynamics. Meanwhile, in comparison with the three-dimensional cube elements, the shell elements can reduce the number of degrees of freedom of the FEM model by 74%, which leads to the computation of the characteristic equation that is about nine times faster. The results of the modal test show that the maximum error of the shell FEM in predicting the natural frequency of the workpiece is about 4%. Furthermore, a three-layer neural network is constructed, and the results of the shell FEM are used as samples to train the model. The neural network model has a maximum prediction error of 0.409% when benchmarked against the results of the FEM. Furthermore, the three-layer neural network effectively enhances computational efficiency while guaranteeing accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%

Predicting the Dynamic Parameters for Milling Thin-Walled Blades with a Neural Network

Li,

Ding,

Wang

et al. 2024

JMMP

View full text Add to dashboard Cite

show abstract

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

Lee,

Chen,

Luo

et al. 2024

J Intell Manuf

View full text Add to dashboard Cite

Research on production of microgroove arrays on TiAl intermetallic alloy by micro milling

Xia,

Zhao,

Zhang

et al. 2024

Proceedings of the Institution of Mechanical Engineers, Part B:

View full text Add to dashboard Cite

TiAl intermetallic alloy is a superior lightweight material with excellent performance, and its micro features or components have promising applications in manufacturing fields. In this work, an investigation of micro milling of microgroove arrays on TiAl alloy was studied. The effects of cutting parameters including the feed per tooth (fz) and depth of cut ( ap) on the milling force, surface morphology, surface roughness and burr size of the micro-slots were investigated. The wear types and mechanisms of the micro end mills were also studied. The results showed that the optimal cutting parameters were fz = 3.5 μm/z and ap = 4 μm, which provided the best surface roughness Sa of 152 nm, top-burr heights on up- and down-milling sides of 19 and 19.5 μm respectively. Using the optimized cutting parameters, microgrooves with a width of 500 μm, aspect ratio of 5 and array period of 10 were fabricated successfully. Surface topography, dimensional accuracy and perpendicularity of the microgroove arrays were characterized. Results demonstrated that an increase in the microgroove number, microgroove edge chipping as well as burrs of the entrance and exit increased gradually. The dimensional error between the obtained width and the designed width of the microgroove was less than 2%, and the slope of the sidewalls reached more than 89°. The wear mechanisms of the micro end mills were abrasive wear and adhesive wear, and wear types were coating delamination, cutting edge chipping, and tool nose breakage.

show abstract

Investigation on eXtreme Gradient Boosting for cutting force prediction in milling

Abstract: This paper has been peer-reviewed but does not include the final publisher proof-corrections or journal pagination.

Cited by 3 publications

References 37 publications

Predicting the Dynamic Parameters for Milling Thin-Walled Blades with a Neural Network

Predicting the Dynamic Parameters for Milling Thin-Walled Blades with a Neural Network

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

Research on production of microgroove arrays on TiAl intermetallic alloy by micro milling

Contact Info

Product

Resources

About