Transfer learning of recurrent neural network‐based plasticity models

Abstract

Mechanics‐specific recurrent neural network (RNN) models are known for their ability to describe the complex three‐dimensional stress–strain response of elasto‐plastic solids for arbitrary loading paths. To apply RNN models to real materials, it is crucial to identify a strategy that allows for their training from small datasets that could be obtained from robot‐assisted experiments. It is demonstrated that regular training with datasets comprising random walks (RWs) in strain space yield a significantly higher generalization ability than the same number of sequences for smooth loading paths. Moreover, it is found that transfer learning, that is, initializing the weights and biases with the parameters from an already trained material, improves the convergence rates and reduces the required number of stress–strain sequences for training. When leveraging the experience gained for multiple materials through ensemble transfer learning, even more substantial improvements are obtained. For example, the same model accuracy and generalization ability is obtained from training with 400 smooth stress–strain sequences after ensemble transfer as from training with 10,000 RW sequences after regular training.

Translating strain to stress: a single-layer Bi-LSTM approach to predicting stress-strain curves in alloys during hot deformation

“…Both conventional ML and deep learning algorithms have demonstrated superior performance over constitutive equations, exhibiting exceptional predictive accuracy in modeling stress-stain response across various materials. Notably, RNNs and their variants, LSTM and GRU, have demonstrated remarkable predictive capabilities due to their proficiency in handling sequential data [36][37][38]. However, existing ML models typically predict only specific segments of the stress-strain curves, such as the yield stress, ultimate tensile/compressive stress, and steady-state flow stress, thereby compromising the overall predictive fidelity [39,40].…”