A hybrid neural network‐first principles approach to process modeling

By Dimitris C. Psichogios, Lyle Ungar. 1992

Subfields: Model Architectures, Numerical Methods & Scientific Computing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Model Architectures

In Numerical Methods & Scientific Computing

Citations in the corpus

Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data (2019, neutral): “[30, 31, 32].”
Adversarial Uncertainty Quantification in Physics-Informed Neural Networks (2018, background): “[6, 7, 8, 9, 10] set foot exactly at this relatively unexplored interface between applied mathematics and contemporary machine learning by revisiting the idea of penalizing the loss function of deep neural networks using diﬀerential equation constraints, as ﬁrst put forth by Psichogios and Ungar [11”
Physics-informed deep generative models (2018, unknown): “[11, 12, 13, 14] explored this new interface between classical scientific computing and machine learning by revisiting the idea of penalizing the loss function of deep neural networks using differential equation constraints, as first put forth by Psichogios and Ungar [15] and Lagaris et.”
Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networks (2019, background): “The philosophy of learning ordinary or partial differential equations through constraint based loss functions is far from a new idea with related works reaching back over two decades ago [10, 11, 12, 13].”
Artificial Neural Network (2020, unknown): “Figures ( 9-12 9-12 ) illustrate the difficulty in controlling this The output responses to all set-point changes are similar with small overshoot and, importantly, the control does not exhibit notable oscillations at any of the set-points.”
A physics-informed variational DeepONet for predicting the crack path in brittle materials (2021, unknown): “Surrogate models [11–19] have received a lot of attention because of their ability to quantitatively capture the fundamental attributes of high-ﬁdelity models while signiﬁcantly improving the computational eﬃciency.”
Pareto Probing: Trading-Off Accuracy and Complexity (2020, background): “However, their inner workings are poorly understood; indeed, for this reason, they are often referred to as black-box systems (Psichogios and Ungar, 1992; Orphanos et al., 1999; Cauer et al., 2000).”
A roadmap for electronic grade 2D materials (2019, methodology): “40 1328–40 [122] Psichogios D 1992 A hybrid neural network-first principles approach to process modeling AIChE J.”
Efficient training of physics‐informed neural networks via importance sampling (2021, background): “The idea of using physics-informed training for neural network solutions of differential equations was first introduced in [1, 5, 6], where neural networks solutions for initial/boundary value problems were developed.”