Physics Informed Piecewise Linear Neural Networks for Global Process Optimization!
The paper of our doctoral candidate Ece Serenat Köksal, entitled Physics Informed Piecewise Linear Neural Networks for Process Optimization has been published in Computers and Chemical Engineering!
https://www.sciencedirect.com/science/article/pii/S009813542300114X
Embedding trained machine learning models into the optimization problems has become an effective and state-of-the-art approach for surrogate optimization, whose performance can be improved by physics-informed machine learning.
For all cases, physics-informed trained neural network based optimal results are closer to global optimality. Finally, associated CPU times for the optimization problems are much shorter than the standard optimization results due to convexity.
Here is the preprint: https://arxiv.org/abs/2302.00990