A theoretical and deep learning hybrid model for predicting surface roughness of diamond-turned polycrystalline materials

Chunlei He; Jiwang Yan; Shuqi Wang; Shuo Zhang; Guang Chen; Chengzu Ren

doi:10.1088/2631-7990/acdb0a

A theoretical and deep learning hybrid model for predicting surface roughness of diamond-turned polycrystalline materials

Chunlei He
, Jiwang Yan
, Shuqi Wang
, Shuo Zhang
, Guang Chen
, Chengzu Ren

Department of Mechanical Engineering

Research output: Contribution to journal › Article › peer-review

55 Citations (Scopus)

Abstract

Highlight A hybrid surface roughness model combining the theoretical model and deep learning method are suggested. SSGB and GB roughness component reduce due to a decrease of misorientation angle. Transcrystalline/intercrystalline fracture mode of work material is analyzed at different tool sharpness. A flat copper surface finish of Sa 1.314 nm without SSGB is attained.

Original language	English
Article number	035102
Journal	International Journal of Extreme Manufacturing
Volume	5
Issue number	3
DOIs	https://doi.org/10.1088/2631-7990/acdb0a
Publication status	Published - 2023 Sept

Keywords

diamond turning
material-defect roughness component
neural network
polycrystalline copper
simulated annealing algorithm

ASJC Scopus subject areas

Industrial and Manufacturing Engineering

Access to Document

10.1088/2631-7990/acdb0a

Cite this

@article{b977a36114b24b0c821b5b14241907f7,

title = "A theoretical and deep learning hybrid model for predicting surface roughness of diamond-turned polycrystalline materials",

abstract = "Highlight A hybrid surface roughness model combining the theoretical model and deep learning method are suggested. SSGB and GB roughness component reduce due to a decrease of misorientation angle. Transcrystalline/intercrystalline fracture mode of work material is analyzed at different tool sharpness. A flat copper surface finish of Sa 1.314 nm without SSGB is attained.",

keywords = "diamond turning, material-defect roughness component, neural network, polycrystalline copper, simulated annealing algorithm",

author = "Chunlei He and Jiwang Yan and Shuqi Wang and Shuo Zhang and Guang Chen and Chengzu Ren",

note = "Publisher Copyright: {\textcopyright} 2023 The Author(s). Published by IOP Publishing Ltd on behalf of the IMMT.",

year = "2023",

month = sep,

doi = "10.1088/2631-7990/acdb0a",

language = "English",

volume = "5",

journal = "International Journal of Extreme Manufacturing",

issn = "2631-8644",

publisher = "IOP Publishing Ltd.",

number = "3",

}

TY - JOUR

T1 - A theoretical and deep learning hybrid model for predicting surface roughness of diamond-turned polycrystalline materials

AU - He, Chunlei

AU - Yan, Jiwang

AU - Wang, Shuqi

AU - Zhang, Shuo

AU - Chen, Guang

AU - Ren, Chengzu

PY - 2023/9

Y1 - 2023/9

N2 - Highlight A hybrid surface roughness model combining the theoretical model and deep learning method are suggested. SSGB and GB roughness component reduce due to a decrease of misorientation angle. Transcrystalline/intercrystalline fracture mode of work material is analyzed at different tool sharpness. A flat copper surface finish of Sa 1.314 nm without SSGB is attained.

AB - Highlight A hybrid surface roughness model combining the theoretical model and deep learning method are suggested. SSGB and GB roughness component reduce due to a decrease of misorientation angle. Transcrystalline/intercrystalline fracture mode of work material is analyzed at different tool sharpness. A flat copper surface finish of Sa 1.314 nm without SSGB is attained.

KW - diamond turning

KW - material-defect roughness component

KW - neural network

KW - polycrystalline copper

KW - simulated annealing algorithm

UR - https://www.scopus.com/pages/publications/85163437848

UR - https://www.scopus.com/pages/publications/85163437848#tab=citedBy

U2 - 10.1088/2631-7990/acdb0a

DO - 10.1088/2631-7990/acdb0a

M3 - Article

AN - SCOPUS:85163437848

SN - 2631-8644

VL - 5

JO - International Journal of Extreme Manufacturing

JF - International Journal of Extreme Manufacturing

IS - 3

M1 - 035102

ER -

A theoretical and deep learning hybrid model for predicting surface roughness of diamond-turned polycrystalline materials

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this