Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Engineering consistent machining forces in functionally graded materials

Jin, Xiaoliang ; Kazemi, Farshad ; Lu, Zhenghui ; Clare, Adam T. and M'Saoubi, Rachid LU (2026) In CIRP Annals
Abstract

Additive manufacturing enables multi-material functionally graded materials (FGMs) with expanded functionality, yet post-machining remains challenging because flow stress varies with composition. This paper presents a data-efficient, physics-guided Gaussian process (GP) model for predicting milling forces in SS316/IN718 FGMs without repeated force-coefficient identification. A physics-based milling model with mixture-law baselines is corrected using sparse force measurements, while the GP learns the residual as a smooth function of composition and parameters. The model reduces prediction error from 26.6 to 19.2% for feed force and from 19.8 to 10.6% for normal force, while adaptive feed scheduling lowers peak-force variation from ∼50 to... (More)

Additive manufacturing enables multi-material functionally graded materials (FGMs) with expanded functionality, yet post-machining remains challenging because flow stress varies with composition. This paper presents a data-efficient, physics-guided Gaussian process (GP) model for predicting milling forces in SS316/IN718 FGMs without repeated force-coefficient identification. A physics-based milling model with mixture-law baselines is corrected using sparse force measurements, while the GP learns the residual as a smooth function of composition and parameters. The model reduces prediction error from 26.6 to 19.2% for feed force and from 19.8 to 10.6% for normal force, while adaptive feed scheduling lowers peak-force variation from ∼50 to ∼8%.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; and
organization
publishing date
type
Contribution to journal
publication status
epub
subject
keywords
Force, Functionally graded materials, Milling
in
CIRP Annals
publisher
Elsevier
external identifiers
  • scopus:105037066247
ISSN
0007-8506
DOI
10.1016/j.cirp.2026.04.083
language
English
LU publication?
yes
id
4963a4b1-cf52-4b94-bfc3-a0e4d9b0b241
date added to LUP
2026-06-24 12:21:47
date last changed
2026-06-24 12:22:11
@article{4963a4b1-cf52-4b94-bfc3-a0e4d9b0b241,
  abstract     = {{<p>Additive manufacturing enables multi-material functionally graded materials (FGMs) with expanded functionality, yet post-machining remains challenging because flow stress varies with composition. This paper presents a data-efficient, physics-guided Gaussian process (GP) model for predicting milling forces in SS316/IN718 FGMs without repeated force-coefficient identification. A physics-based milling model with mixture-law baselines is corrected using sparse force measurements, while the GP learns the residual as a smooth function of composition and parameters. The model reduces prediction error from 26.6 to 19.2% for feed force and from 19.8 to 10.6% for normal force, while adaptive feed scheduling lowers peak-force variation from ∼50 to ∼8%.</p>}},
  author       = {{Jin, Xiaoliang and Kazemi, Farshad and Lu, Zhenghui and Clare, Adam T. and M'Saoubi, Rachid}},
  issn         = {{0007-8506}},
  keywords     = {{Force; Functionally graded materials; Milling}},
  language     = {{eng}},
  publisher    = {{Elsevier}},
  series       = {{CIRP Annals}},
  title        = {{Engineering consistent machining forces in functionally graded materials}},
  url          = {{http://dx.doi.org/10.1016/j.cirp.2026.04.083}},
  doi          = {{10.1016/j.cirp.2026.04.083}},
  year         = {{2026}},
}