Physics-Informed Neural Network Assisted Extraction of Height-Averaged Pulsatile Flow Velocity From Scalar Signal Transport in a Shallow Microfluidic Channel
Journal of Biomechanical Engineering · 01.09.2026 · 148 (9)
DOI: 10.1115/1.4072290 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Biomechanical Engineering, online erschienen am 28.07.2026. Verfasst von Yu-Xing Gong und 5 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Cardio-Cerebrovascular Medicine, Central Hospital of Dalian University of Technology, No. 42 Xuegong Street, Shahekou District, Dalian, …. Hauptthemen laut MEDLINE: Pulsatile Flow, Neural Networks, Computer, Microfluidics. Die Arbeit nennt 46 Literaturangaben. Gefördert von: Dalian University of Technology, National Natural Science Foundation of China.
Abstract (Originalsprache)
Accurate measurement of height-averaged flow velocity from scalar signal transport is important for shallow microfluidic velocimetry. Conventional scalar imaging velocimetry (SIV) is sensitive to scalar-field noise, while deep neural network-assisted-SIV requires extensive labeled velocity data and may exhibit limited generalizability to unseen flow conditions. This study aims to develop an unsupervised physics-informed framework for accurately reconstructing pulsatile flow velocity from concentration signals in a shallow microfluidic channel. Multiscale perturbation-enhanced physics-informed neural network (MPE-PINN) was proposed by decomposing the scalar transport process into steady and pulsatile components and embedding the corresponding perturbation-based governing equations into the loss function. This method was evaluated using numerically generated concentration fields under different scalar transport and flow conditions, and its performance was compared with a conventional PINN using mean absolute percentage error (MAPE), convergence behavior, and noise robustness. Results show that MPE-PINN maintains MAPEs below 1% over a broad operating range with concentration signal frequency fC≤2 Hz and flow frequency fQ≤1.6 Hz. The proposed method also shows improved robustness under noisy concentration fields and better preservation of pulsatile velocity features than the conventional PINN. These results demonstrate that MPE-PINN provides an accurate and robust unsupervised approach for pulsatile velocity extraction in shallow microfluidic channels, offering practical potential for microfluidic flow characterization and biomedical lab-on-a-chip applications.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Cardio-Cerebrovascular Medicine, Central Hospital of Dalian University of Technology, No. 42 Xuegong Street, Shahekou District, Dalian, Liaoning 116033, China; School of Optoelectronic Engineering and Instr…
- School of Biomedical Engineering, Faculty of Medicine, Dalian University of Technology, No. 2 Lingong Road, Ganjingzi District, Dalian, Liaoning 116024, China.
- Institute of Cardio-Cerebrovascular Medicine, Central Hospital of Dalian University of Technology, No. 42 Xuegong Street, Shahekou District, Dalian, Liaoning 116033, China; School of Biomedical Engineering, Faculty of M…
ORCID-Profile: Yu-Xing Gong
Förderung
- Dalian University of Technology
- National Natural Science Foundation of China
Zitieren
APA
Gong, Y. X., Wang, Y. T., Yin, J. G., Hu, X. Q., Li, Y. J., & Qin, K. R. (2026). Physics-Informed Neural Network Assisted Extraction of Height-Averaged Pulsatile Flow Velocity From Scalar Signal Transport in a Shallow Microfluidic Channel. Journal of Biomechanical Engineering, 148(9). https://doi.org/10.1115/1.4072290
Vancouver
Gong YX, Wang YT, Yin JG, Hu XQ, Li YJ, Qin KR. Physics-Informed Neural Network Assisted Extraction of Height-Averaged Pulsatile Flow Velocity From Scalar Signal Transport in a Shallow Microfluidic Channel. Journal of Biomechanical Engineering. 2026;148(9). doi:10.1115/1.4072290
BibTeX
@article{Gong2026,
author = {Gong, Yu-Xing and Wang, Yi-Teng and Yin, Jia-Guo and Hu, Xu-Qu and Li, Yong-Jiang and Qin, Kai-Rong},
title = {Physics-Informed Neural Network Assisted Extraction of Height-Averaged Pulsatile Flow Velocity From Scalar Signal Transport in a Shallow Microfluidic Channel},
journal = {Journal of Biomechanical Engineering},
year = {2026},
volume = {148},
number = {9},
doi = {10.1115/1.4072290}
}
EUVIMED