Website under construction...
Data-Driven Computing for Solid Mechanics
A data-driven computational framework coupling physical simulations (by FEM, Meshfree, etc.) and manifold learning based constitutive models.
References: He, X., He, Q. & Chen, J.S., Comput Methods Appl Mech Eng (2021); He, X., He, Q. & Chen, J.S., Data-Centric Engineering (2020); He, Q. et al., Journal of Biomechanics (2020); He, Q. & Chen, J.S., Comput Methods Appl Mech Eng (2019)
Neural-Integrated Meshfree Hybrid Method for Forward and Inverse Modeling of Nonlinear Solids
(a) Schematic of the Neural-Integrated Meshfree (NIM) method; (b) Reference modulus field; (c) Modulus field estimated by inverse NIM using strain data for a heterogeneous hyperelastic material; (d) Setup of an elastoplasticity problem; (e) Comparison of NIM and FEM simulations, illustrating the predictive accuracy and error distribution between the two methods.
Relevant Papers:
- Du, H., & He, Q. (2024). Neural-Integrated Meshfree (NIM) Method: A differentiable programming-based hybrid solver for computational mechanics. Computer Methods in Applied Mechanics and Engineering, 427, 117024.
- Du, H., Guo, B., He, Q. (2024) Differentiable Neural-Integrated Meshfree Method for Forward and Inverse Modeling of Finite Strain Hyperelasticity, Engineering with Computers, 1-21.