Comparison and review of classical and machine learning-based constitutive models for polymers used in aeronautical thermoplastic composites

Abstract: Most of the stress–strain relationships of thermoplastic polymers for aeronautical composites tend to be nonlinear and sensitive to strain rate and temperature, so accurate constitutive models are urgently required. Classical and machine learning-based constitutive models for thermoplastic polymers are compared and discussed. In addition, some typical models have been recovered and compared by authors to evaluate the performance of classical and machine learning-based constitutive models, so that the advantages and shortcomings of these models can be demonstrated. By reviewing constitutive models, it was found that the equations of physical constitutive models are derived according to thermodynamical principles, so the physical constitutive models can describe the deformation mechanism at the microscopic level. The phenomenological constitutive models may combine the macroscopic phenomena and theories of physical models, and good performance and wide range of applications can be realized. In addition, phenomenological constitutive models combined with machine learning algorithms have attracted attentions of investigators, and these models perform well in predicting the stress–strain relationships. In the future, the constitutive models combining the theories of physical constitutive models, phenomenological constitutive models, and machine learning algorithms will be increasingly attractive as some challenging issues are effectively addressed.

Object Details

• Location: Deutsche Nationalbibliothek Frankfurt am Main
• Extent: Online-Ressource
• Language: Englisch

References and Relationships

• Bibliographic citation: Comparison and review of classical and machine learning-based constitutive models for polymers used in aeronautical thermoplastic composites ; volume:62 ; number:1 ; year:2023 ; extent:23 ; Reviews on advanced materials science ; 62, Heft 1 (2023) (gesamt 23)

Contributors, Places and Time

• Creator: Ling, Shengbo ; Wu, Zhen ; Mei, Jie

Further information

• DOI: 10.1515/rams-2023-0107
• URN: urn:nbn:de:101:1-2023081914030124941603
• Rights: Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
• Last update: 14.08.2025, 10:58 AM CEST