HANNA: Hard-constraint Neural Network for Consistent Activity Coefficient Prediction
This addresses the need for physically consistent and accurate activity coefficient predictions in science and engineering applications, representing a novel method rather than an incremental improvement.
The paper tackled the problem of predicting activity coefficients in thermodynamic mixtures by introducing HANNA, a hard-constraint neural network that strictly adheres to physical laws, achieving significantly higher prediction accuracies than the state-of-the-art UNIFAC model on 317,421 data points from the Dortmund Data Bank.
We present the first hard-constraint neural network for predicting activity coefficients (HANNA), a thermodynamic mixture property that is the basis for many applications in science and engineering. Unlike traditional neural networks, which ignore physical laws and result in inconsistent predictions, our model is designed to strictly adhere to all thermodynamic consistency criteria. By leveraging deep-set neural networks, HANNA maintains symmetry under the permutation of the components. Furthermore, by hard-coding physical constraints in the network architecture, we ensure consistency with the Gibbs-Duhem equation and in modeling the pure components. The model was trained and evaluated on 317,421 data points for activity coefficients in binary mixtures from the Dortmund Data Bank, achieving significantly higher prediction accuracies than the current state-of-the-art model UNIFAC. Moreover, HANNA only requires the SMILES of the components as input, making it applicable to any binary mixture of interest. HANNA is fully open-source and available for free use.