PAPM: A Physics-aware Proxy Model for Process Systems

Pengwei Liu, Zhongkai Hao, Xingyu Ren, Hangjie Yuan, Jiayang Ren, Dong Ni
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:31080-31105, 2024.

Abstract

In the context of proxy modeling for process systems, traditional data-driven deep learning approaches frequently encounter significant challenges, such as substantial training costs induced by large amounts of data, and limited generalization capabilities. As a promising alternative, physics-aware models incorporate partial physics knowledge to ameliorate these challenges. Although demonstrating efficacy, they fall short in terms of exploration depth and universality. To address these shortcomings, we introduce a physics-aware proxy model (PAPM) that fully incorporates partial prior physics of process systems, which includes multiple input conditions and the general form of conservation relations, resulting in better out-of-sample generalization. Additionally, PAPM contains a holistic temporal-spatial stepping module for flexible adaptation across various process systems. Through systematic comparisons with state-of-the-art pure data-driven and physics-aware models across five two-dimensional benchmarks in nine generalization tasks, PAPM notably achieves an average performance improvement of 6.7%, while requiring fewer FLOPs, and just 1% of the parameters compared to the prior leading method.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-liu24v, title = {{PAPM}: A Physics-aware Proxy Model for Process Systems}, author = {Liu, Pengwei and Hao, Zhongkai and Ren, Xingyu and Yuan, Hangjie and Ren, Jiayang and Ni, Dong}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {31080--31105}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/liu24v/liu24v.pdf}, url = {https://proceedings.mlr.press/v235/liu24v.html}, abstract = {In the context of proxy modeling for process systems, traditional data-driven deep learning approaches frequently encounter significant challenges, such as substantial training costs induced by large amounts of data, and limited generalization capabilities. As a promising alternative, physics-aware models incorporate partial physics knowledge to ameliorate these challenges. Although demonstrating efficacy, they fall short in terms of exploration depth and universality. To address these shortcomings, we introduce a physics-aware proxy model (PAPM) that fully incorporates partial prior physics of process systems, which includes multiple input conditions and the general form of conservation relations, resulting in better out-of-sample generalization. Additionally, PAPM contains a holistic temporal-spatial stepping module for flexible adaptation across various process systems. Through systematic comparisons with state-of-the-art pure data-driven and physics-aware models across five two-dimensional benchmarks in nine generalization tasks, PAPM notably achieves an average performance improvement of 6.7%, while requiring fewer FLOPs, and just 1% of the parameters compared to the prior leading method.} }
Endnote
%0 Conference Paper %T PAPM: A Physics-aware Proxy Model for Process Systems %A Pengwei Liu %A Zhongkai Hao %A Xingyu Ren %A Hangjie Yuan %A Jiayang Ren %A Dong Ni %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-liu24v %I PMLR %P 31080--31105 %U https://proceedings.mlr.press/v235/liu24v.html %V 235 %X In the context of proxy modeling for process systems, traditional data-driven deep learning approaches frequently encounter significant challenges, such as substantial training costs induced by large amounts of data, and limited generalization capabilities. As a promising alternative, physics-aware models incorporate partial physics knowledge to ameliorate these challenges. Although demonstrating efficacy, they fall short in terms of exploration depth and universality. To address these shortcomings, we introduce a physics-aware proxy model (PAPM) that fully incorporates partial prior physics of process systems, which includes multiple input conditions and the general form of conservation relations, resulting in better out-of-sample generalization. Additionally, PAPM contains a holistic temporal-spatial stepping module for flexible adaptation across various process systems. Through systematic comparisons with state-of-the-art pure data-driven and physics-aware models across five two-dimensional benchmarks in nine generalization tasks, PAPM notably achieves an average performance improvement of 6.7%, while requiring fewer FLOPs, and just 1% of the parameters compared to the prior leading method.
APA
Liu, P., Hao, Z., Ren, X., Yuan, H., Ren, J. & Ni, D.. (2024). PAPM: A Physics-aware Proxy Model for Process Systems. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:31080-31105 Available from https://proceedings.mlr.press/v235/liu24v.html.

Related Material