Author Archives: eaydin

Graduation!

Tuse Asrav successfully defended her masters thesis related to physics-informed recurrent neural networks for modeling and control purposes.

She will be joining Denmark Technical University Chemical Engineering department for her PhD studies.

We wish her best of luck for her career!

Publication Alert!

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

Publication Alert!

Our paper “Physics-Informed Recurrent Neural Networks and Hyper-parameter Optimization for Dynamic Process Systems” has been accepted for publication in Computers and Chemical Engineering! Great job Tuse Asrav!

https://www.sciencedirect.com/science/article/pii/S0098135423000649

In this study, two different physics-informed training approaches are investigated. The first approach is using a multi-objective loss function in the training including the discretized form of the differential equation. The second approach is using a hybrid recurrent neural network cell with embedded physics-informed and data-driven nodes performing Euler discretization.

Physics-informed neural networks can improve test performance even though decrease in training performance might be observed. Finally, smaller and more robust architectures are obtained from hyper-parameter optimization when physics-informed training is performed.

Publication Alert!

Our paper entitled “Optimal design and operation of a multi-energy microgrid using mixed-integer nonlinear programming: Impact of carbon cap and trade system and taxing on equipment selections” has been published in the prestigious Applied Energy (Q1, IF: 11.44)!

This work proposes a novel MINLP decision making model to compare the effects of carbon emission taxing and cap and trade system on the optimal equipment selection and scheduling under the regulatory effects of the Paris Agreement for integrated renewable energy based multi-energy microgrids. Congratulations to our doctoral candidate Handan Akulker for the great job!

Special thanks to TÜBİTAK for funding our work under the 2232 International Fellowship for Outstanding Researchers grant.

Thesis defense!

Su Meyra Tatar has successfully defended her master thesis entitled ”Design of Integrated Renewable Energy Systems under uncertainty towards Green Deal in Turkish Energy Market”.

She decided to pursue her doctoral studies on PSE in USA and will be joining Auburn University shortly.

Publication Alert!

How to design and operate renewable-energy assisted microgrids under the sanctions of Green Deal and Paris Agreement?

Our paper on optimal design and operation of integrated microgrids under Green Deal, various demand criteria and Green Hydrogen scenarios has been published in International Journal of Hydrogen Energy (IF: 7.14).

https://www.sciencedirect.com/science/article/pii/S0360319922027628

stay tuned for new updates related to this project…

Publication Alert!

Our collaborative paper between Gebze Technical University and SOCAR R&D deparment, which is related to the optimal design of ANN structures for modeling an industrial etyhlene oxide plant has been published in Computers and Chemical Engineering Journal:

https://www.sciencedirect.com/science/article/pii/S0098135422001880

Thesis defense!

Duygu Kaya successfully defended her masters thesis entitled: Optimization of Energy Density in Supercapacitors by Utilizing a Hybrid Artificial Neural Networks-Genetic Algorithm based Optimization Algorithm. She will continue her studies as a PhD student at Bogazici University!