1. Neural network programming: Integrating first principles into machine learning models.
- Author
-
Carranza-Abaid, Andres and Jakobsen, Jana P.
- Subjects
- *
ARTIFICIAL neural networks , *AUTOMATIC differentiation , *MACHINE learning , *LINEAR equations , *MATHEMATICAL optimization - Abstract
• A new integrated hybrid modelling approach is proposed – Neural Network Programming. • NNP formulates autodifferentiable algorithmically structured neural networks (ASNN). • The performance of NNP-based models is superior to those of black-box models. • ASNNs are transferable between processes with similar structural features. • Hidden layers can be used to solve large sets of linear equations like mass balances. This work introduces Neural Network Programming (NNP) as an integrated hybrid modelling approach. NNP consists in formulating a set of first principles equations that is later decomposed and transcribed into an Algorithmically Structured artificial Neural Network (ASNN). NNP leverages the advantages of the universal approximation theorem and neural network optimization algorithms in order to generate physically coherent machine learning models. Since ASNNs are not mere approximations of physics equations, it is not necessary to modify either the gradient or performance function in order to account for errors with respect to the first principles equations. ASNNs are trained faster and more accurately than typical hybrid models because the gradient is computed through automatic differentiation instead of numeric differentiation. It is shown that the same ASNN architecture is transferable between processes with similar characteristics. In particular, a flash separator, distillation column, and a biogas upgrading process, were modelled using an identical architecture. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF