@Article{cmc.2026.084790,
AUTHOR = {Jianwei Zhang, Ran Shen, Qianqi Zhang, Yuanxin Li, Shengchao Chen, Minghao Zhao, Lubing Shi, Bing Wang},
TITLE = {Characterization of Non-Equibiaxial Residual Stresses via Machine Learning Enhanced Instrumented Indentation Testing},
JOURNAL = {Computers, Materials \& Continua},
VOLUME = {},
YEAR = {},
NUMBER = {},
PAGES = {{pages}},
URL = {http://www.techscience.com/cmc/online/detail/28039},
ISSN = {1546-2226},
ABSTRACT = {Non-equibiaxial residual stresses are prevalent in engineering components such as welding, additive manufacturing, and surface strengthening, making their accurate detection critical for ensuring structural integrity. This paper proposes a novel method capable of simultaneously identifying two principal stress components (<math id="mml-ieqn-1"><mrow><msubsup><mi>σ</mi><mrow><mi mathvariant="normal">x</mi></mrow><mrow><mi mathvariant="normal">R</mi></mrow></msubsup></mrow></math>, <math id="mml-ieqn-2"><mrow><msubsup><mi>σ</mi><mrow><mi mathvariant="normal">z</mi></mrow><mrow><mi mathvariant="normal">R</mi></mrow></msubsup></mrow></math>) using only an individual instrumented indentation. First, the normalized total indentation work variation <i>W</i><sub>norm</sub> and the residual indentation ellipticity <i>λ</i> are extracted as sensitive features from the indentation responses through dimensional analysis. Subsequently, a finite element (FE) simulation database comprising 2400 datasets was established to train three types of neural networks: the single-target approach (ST-MLP), the classical multi-output multi-layer perceptron (MLP), and the parameter sharing-based deep network (DMTR). The outcomes of the training phase indicate that the overall error of the DMTR model is less than 5%, while those of the MLP and ST-MLP models are less than 7%. Furthermore, supplementary FE simulations were conducted on Al 7075, Al 2024, and Ti Grade 5 alloys for validation, showing that the MLP and DMTR prediction errors across all models are controlled within 11%. Finally, experimental validation was conducted on Al 7075 alloy and 18CrNiMo7-6 alloy cruciform specimens. The result is the DMTR model maintains a prediction error within 30 MPa. This study provides a feasible path for the rapid on-site detection of non-equibiaxial residual stress.},
DOI = {10.32604/cmc.2026.084790}
}