A parameter identification scheme of the visco-hyperelastic constitutive model of rubber-like materials based on general regression neural network

In this research, the hyperelastic strain energy density function based on the exponential-logarithmic invariant is extended to the visco-hyperelastic constitutive model to describe the mechanical characteristics of the rate dependence and large deformations of rubber-like materials. On the basis of the general regression neural network (GRNN) technique, a parameter identification approach for the visco-hyperelastic model is designed. In addition, the proposed research scheme is verified using various uniaxial experimental data of rubber-like materials. The comparison results reveal that the predicted stress responses agree well with the experimental data under different loading conditions. This paper concludes that the present model can describe the mechanical behavior of rubber-like materials and that the GRNN-based approach is practicable for parameter identification of complex visco-hyperelastic constitutive models.

Automated summary

In this research, the hyperelastic strain energy density function based on the exponential-logarithmic invariant is extended to the visco-hyperelastic constitutive model to accurately model the mechanical properties of rubber-like materials. A parameter identification approach using the general regression neural network (GRNN) technique is proposed for evaluating the visco-hyperelastic model. Experimental data of rubber-like materials is used to validate the proposed research scheme, and the results show good agreement between the predicted stress responses and the experimental data. The study concludes that the developed model accurately describes the mechanical behavior of rubber-like materials and the GRNN-based approach is reliable for parameter identification of complex visco-hyperelastic constitutive models.