
Data Driven Modeling of Interfacial Traction Separation Relations using a Thermodynamically Consistent Neural Network
For multilayer structures, interfacial failure is one of the most import...
read it

Thermodynamicsbased Artificial Neural Networks for constitutive modeling
Machine Learning methods and, in particular, Artificial Neural Networks ...
read it

Datadriven Modeling of the Mechanical Behavior of Anisotropic Soft Biological Tissue
Constitutive models that describe the mechanical behavior of soft tissue...
read it

PhysicsEnforced Modeling for Insertion Loss of Transmission Lines by Deep Neural Networks
In this paper, we investigate datadriven parameterized modeling of inse...
read it

Physical Constraint Embedded Neural Networks for inference and noise regulation
Neural networks often require large amounts of data to generalize and ca...
read it

Learning to Represent Mechanics via Longterm Extrapolation and Interpolation
While the basic laws of Newtonian mechanics are well understood, explain...
read it

Neuralnetwork based general method for statistical mechanics on sparse systems
We propose a general method for solving statistical mechanics problems d...
read it
Thermodynamic Consistent Neural Networks for Learning Material Interfacial Mechanics
For multilayer materials in thin substrate systems, interfacial failure is one of the most challenges. The tractionseparation relations (TSR) quantitatively describe the mechanical behavior of a material interface undergoing openings, which is critical to understand and predict interfacial failures under complex loadings. However, existing theoretical models have limitations on enough complexity and flexibility to well learn the realworld TSR from experimental observations. A neural network can fit well along with the loading paths but often fails to obey the laws of physics, due to a lack of experimental data and understanding of the hidden physical mechanism. In this paper, we propose a thermodynamic consistent neural network (TCNN) approach to build a datadriven model of the TSR with sparse experimental data. The TCNN leverages recent advances in physicsinformed neural networks (PINN) that encode prior physical information into the loss function and efficiently train the neural networks using automatic differentiation. We investigate three thermodynamic consistent principles, i.e., positive energy dissipation, steepest energy dissipation gradient, and energy conservative loading path. All of them are mathematically formulated and embedded into a neural network model with a novel defined loss function. A realworld experiment demonstrates the superior performance of TCNN, and we find that TCNN provides an accurate prediction of the whole TSR surface and significantly reduces the violated prediction against the laws of physics.
READ FULL TEXT
Comments
There are no comments yet.