基于物理信息神经网络的同步发电机建模
Modeling of Synchronous Generator Based on Physics-informed Neural Network
杨珂 1王鑫 1凌佳杰 1耿光超 1江全元1
作者信息
- 1. 浙江大学电气工程学院,浙江省 杭州市 310027
- 折叠
摘要
采用物理机理建立的同步发电机模型在表达发电机真实的非线性特性方面存在不足,电力系统正在不断研究和采纳新的同步发电机模型以增强模型的准确性.数据驱动模型具有更强的非线性表达能力,但在同步发电机建模实际应用中面临着模型泛化性不强和所需数据量大等问题.为克服上述问题,该文结合神经元建模原理,以循环神经网络为基本框架,在同步发电机物理机理的引导下,提出基于物理信息神经网络的同步发电机模型.经过算例验证,所提模型可准确表达同步发电机磁饱和特性,并且具有较强的泛化性.该模型可在小规模数据下对同步发电机各阶模型达到更高的拟合准确度,并可应用于现有机电暂态仿真算法.
Abstract
The synchronous generator(SG)models constructed based on physical principles have limitations in accurately capturing the nonlinear characteristics of the SG.Hence,the power system is continuously researching and adopting new SG models to enhance their accuracy.Data-driven models have stronger nonlinear expression capabilities,but they face challenges in practical applications for SG modeling,such as weak model generalization and high data requirements.To overcome these problems,this paper proposes a physics-informed neural network(PINN)model for SG,employing recurrent neural network as the fundamental model architecture.The modelling of the PINN is guided by the physical mechanism of SG and based on the principles of neural network modeling.The PINN can express the magnetic saturation characteristic of SG with high accuracy and has strong generalization ability.It can achieve higher fitting accuracy for SG models of various orders with small-scale data and can be applied to existing electromechanical transient simulation algorithms.
关键词
物理信息神经网络/数据驱动/同步发电机/磁饱和效应Key words
physics-informed neural network/data-driven/synchronous generator/magnetic saturation effect引用本文复制引用
基金项目
国家自然科学基金(52177120)
南方电网数字电网集团有限公司科技项目(670000KK52210032)
出版年
2024
国家科技期刊平台
NSTL
万方数据