EUVIMEDEUVIMED entdecken
Crossref

Data and physics requirements for reliable physics‐informed neural networks in process modeling

Guoquan Wu, Yuyang Jiang, Yao Shi, Zhe Wu

AIChE Journal · 2026-12 · 72 (12)

DOI: 10.1002/aic.70602 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AIChE Journal, online erschienen am 21.08.2026. Verfasst von Guoquan Wu und 3 weiteren Autor:innen. Die Arbeit nennt 18 Literaturangaben. Gefördert von: National Research Foundation Singapore.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Physics‐informed neural networks (PINNs) have gained increasing attention in chemical process modeling since they can embed first‐principles knowledge into neural network training. However, in practice, the embedded physics is often inaccurate, and experimental data are costly to obtain, raising fundamental questions about the required physics‐model accuracy and data volume required to achieve a target prediction accuracy. This work develops a theoretical framework for analyzing the generalization error of PINNs under model misspecification. We establish both an architecture‐independent error bound and an explicit bound for a specific PINN architecture. The bound is further related to the solution error with respect to the true system, yielding quantitative conditions on admissible model discrepancy, data requirements, and loss‐weight selection. Based on these conditions, two adaptive algorithms are proposed to guide physics‐model refinement and data collection. The theoretical findings are demonstrated using a chemical process network.

Förderung

  • National Research Foundation Singapore

Zitieren

APA

Wu, G., Jiang, Y., Shi, Y., & Wu, Z. (2026). Data and physics requirements for reliable physics‐informed neural networks in process modeling. AIChE Journal, 72(12). https://doi.org/10.1002/aic.70602

Vancouver

Wu G, Jiang Y, Shi Y, Wu Z. Data and physics requirements for reliable physics‐informed neural networks in process modeling. AIChE Journal. 2026;72(12). doi:10.1002/aic.70602

BibTeX
@article{Wu2026,
  author = {Wu, Guoquan and Jiang, Yuyang and Shi, Yao and Wu, Zhe},
  title = {Data and physics requirements for reliable physics‐informed neural networks in process modeling},
  journal = {AIChE Journal},
  year = {2026},
  volume = {72},
  number = {12},
  doi = {10.1002/aic.70602}
}
Kostenlos starten →