Dynamic Modeling and Online Updating of Full-Power Converter Wind Turbines Based on Physics-Informed Neural Networks and Bayesian Neural Networks

Xu, Yunyang; Zhou, Bo; Sun, Xinwei; Tian, Yuting; Jiang, Xiaofeng

doi:10.3390/electronics14152985

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Dynamic Modeling and Online Updating of Full-Power Converter Wind Turbines Based on Physics-Informed Neural Networks and Bayesian Neural Networks

by

Yunyang Xu

^1,2,*,

Bo Zhou

^1,2,

Xinwei Sun

^1,2,

Yuting Tian

^1,2 and

Xiaofeng Jiang

^1,2

¹

State Grid Sichuan Electric Power Research Institute, Chengdu 610042, China

²

Power System Security and Operation Key Laboratory of Sichuan, Chengdu 610042, China

^*

Author to whom correspondence should be addressed.

Electronics 2025, 14(15), 2985; https://doi.org/10.3390/electronics14152985 (registering DOI)

Submission received: 26 April 2025 / Revised: 16 June 2025 / Accepted: 24 June 2025 / Published: 26 July 2025

Download Review Reports Versions Notes

Abstract

This paper presents a dynamic model for full-power converter permanent magnet synchronous wind turbines based on Physics-Informed Neural Networks (PINNs). The model integrates the physical dynamics of the wind turbine directly into the loss function, enabling high-accuracy equivalent modeling with limited data and overcoming the typical “black-box” constraints and large data requirements of traditional data-driven approaches. To enhance the model’s real-time adaptability, we introduce an online update mechanism leveraging Bayesian Neural Networks (BNNs) combined with a clustering-guided strategy. This mechanism estimates uncertainty in the neural network weights in real-time, accurately identifies error sources, and performs local fine-tuning on clustered data. This improves the model’s ability to track real-time errors and addresses the challenge of parameter-specific adjustments. Finally, the data-driven model is integrated into the CloudPSS platform, and its multi-scenario modeling accuracy is validated across various typical cases, demonstrating the robustness of the proposed approach.

Keywords: Physics-Informed Neural Networks (PINNs); Bayesian Neural Networks (BNNs); full-power converter permanent magnet synchronous wind turbine generators; online updating mechanism; data-driven modeling

Share and Cite

MDPI and ACS Style

Xu, Y.; Zhou, B.; Sun, X.; Tian, Y.; Jiang, X. Dynamic Modeling and Online Updating of Full-Power Converter Wind Turbines Based on Physics-Informed Neural Networks and Bayesian Neural Networks. Electronics 2025, 14, 2985. https://doi.org/10.3390/electronics14152985

AMA Style

Xu Y, Zhou B, Sun X, Tian Y, Jiang X. Dynamic Modeling and Online Updating of Full-Power Converter Wind Turbines Based on Physics-Informed Neural Networks and Bayesian Neural Networks. Electronics. 2025; 14(15):2985. https://doi.org/10.3390/electronics14152985

Chicago/Turabian Style

Xu, Yunyang, Bo Zhou, Xinwei Sun, Yuting Tian, and Xiaofeng Jiang. 2025. "Dynamic Modeling and Online Updating of Full-Power Converter Wind Turbines Based on Physics-Informed Neural Networks and Bayesian Neural Networks" Electronics 14, no. 15: 2985. https://doi.org/10.3390/electronics14152985

APA Style

Xu, Y., Zhou, B., Sun, X., Tian, Y., & Jiang, X. (2025). Dynamic Modeling and Online Updating of Full-Power Converter Wind Turbines Based on Physics-Informed Neural Networks and Bayesian Neural Networks. Electronics, 14(15), 2985. https://doi.org/10.3390/electronics14152985

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Dynamic Modeling and Online Updating of Full-Power Converter Wind Turbines Based on Physics-Informed Neural Networks and Bayesian Neural Networks

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI