Neural Network Programming: Integrating First Principles into Machine Learning Models
Doctoral thesis
Permanent lenke
https://hdl.handle.net/11250/3009527Utgivelsesdato
2022Metadata
Vis full innførselSamlinger
Sammendrag
Tired of borrowing the machine learning models proposed by computer scientists? This thesis proposes a new perspective, ideas, and methods to formulate hybrid models through the manipulation of the Artificial Neural Network architectures and parameters. It is shown that the actual transcription of exact physics into a neural network is possible. This allows leveraging all the advantages of neural network modelling, namely, universal approximation feature, autodifferentiation, efficient model evaluation, and advanced optimization schemes. It might be possible to convince even the skeptics that Machine Learning is a feasible tool for the digitalization of chemical engineering processes. No longer we should be constrained by the tyranny of the typical architectures of the Neural Networks!
Består av
Paper 1: Carranza Abaid, Andres; Svendsen, Hallvard Fjøsne; Jakobsen, Jana Poplsteinova. Surrogate modelling of VLE: Integrating machine learning with thermodynamic constraints. Chemical Engineering Science: X 2020 ;Volum 8. s. 1-14 https://doi.org/10.1016/j.cesx.2020.100080 This is an open access article under the CC BY licensePaper 2: Carranza Abaid, Andres; Jakobsen, Jana Poplsteinova. Neural network programming: Integrating first principles into machine learning models. Computers and Chemical Engineering 2022 ;Volum 163. https://doi.org/10.1016/j.compchemeng.2022.107858 This is an open access article under the CC BY license
Paper 3: Carranza-Abaid, Andres; Svendsen, Hallvard F.; Jakobsen, Jana P.; Thermodynamically Consistent Vapor-Liquid Equilibrium Modelling with Artificial Neural Networks.
Paper 4: Carranza-Abaid, Andres; Svendsen, Hallvard F.; Jakobsen, Jana P.; Thermodynamic Modelling using Artificial Neural Networks as Generating Functions: Application to Vapor-Liquid Equilibrium
Paper 5: Carranza-Abaid, Andres; Wanderley Ricardo R.; Knuutila, Hanna K., Jakobsen, Jana P.; Analysis and selection of optimal solventbased technologies for biogas upgrading. Fuel, Vol. 303, 2021. https://doi.org/10.1016/j.fuel.2021.121327 This is an open access article under the CC BY license