结合生成对抗网络与支持向量回归提升发电厂励磁系统参数辨识的准确性

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (805 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract The existing methods for parameter identification of the excitation system in power plants usually have problems such as low identification accuracy and poor training stability. These issues lead to insufficient accuracy of parameter identification in the system, which affects the dynamic regulation and stability of the excitation system in power plants. Therefore, this paper combines the generative adversarial network (GAN) and the support vector regression (SVR) model to improve the accuracy of parameter identification in the excitation system of power plants. Firstly, the Wasserstein GAN structure is adopted, and through the adversarial training of the generator and the discriminator, feature data similar to the actual excitation system is generated. Then, the principal component analysis is used to extract and reduce the features of the generated data, mapping the high-dimensional data to a low-dimensional space, providing input for the subsequent SVR model. The SVR model uses the radial basis function kernel function to handle complex nonlinear relationships, thereby accurately predicting the key parameters of the excitation system. Finally, through the dual optimization of combining GAN and SVR, the simulation results show that the mean square error of the GAN+SVR optimization method is generally low, with the highest being 0.000 9 and the lowest being 0.000 1, indicating that the model can effectively capture the dynamic characteristics of the excitation current and maintain high accuracy.

Key words： power plant excitation system generative adversarial network (GAN) support vector regression (SVR) parameter identification

Received: 25 August 2025

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	QIN Ying
	WANG Baoguo
	XIANG Wenya
	JIANG Zongliang
	HUANG Rongfeng

Cite this article:

QIN Ying,WANG Baoguo,XIANG Wenya等. Improving the accuracy of excitation system parameter identification in power plants by combining generative adversarial network and support vector regression[J]. Electrical Engineering, 2026, 27(2): 40-45.

URL:

https://dqjs.cesmedia.cn/EN/Y2026/V27/I2/40

[1] Ibrahim N M A, El-Said E A, Attia H E M, et al. Enhancing power system stability: an innovative approach using coordination of FOPID controller for PSS and SVC FACTS device with MFO algorithm[J]. Electrical Engineering, 2024, 106(3): 2265-2283.
[2] 杨玲, 戴文波. 基于Matlab的励磁系统参数辨识与评价[J]. 电气技术, 2021, 22(12): 22-26, 33.
[3] Ramoji S K, Saikia L C.Maiden application of fuzzy-2DOFTID controller in unified voltage-frequency control of power system[J]. IETE Journal of Research, 2023, 69(7): 4738-4759.
[4] 苏荣强, 施志良, 张高峰, 等. 发电机励磁在线监测系统的研制及应用[J]. 电气技术, 2024, 25(11): 70-75, 80.
[5] Latif A, Suhail Hussain S M, Iqbal A, et al. Concurrent frequency-voltage stabilization for hybrid microgrid with virtual inertia support[J]. IET Renewable Power Generation, 2023, 17(9): 2257-2275.
[6] Ram Babu N, Bhagat S K, Saikia L C, et al.A comprehensive review of recent strategies on auto-matic generation control/load frequency control in power systems[J]. Archives of Computational Methods in Engineering, 2023, 30(1): 543-572.
[7] 刘沐霖, 姜彤, 徐永金, 等. 基于模型-数据混合驱动的同步电机励磁电流在线估计方法[J]. 电工技术学报, 2025, 40(18): 5866-5876.
[8] Raj U, Shankar R.Optimally enhanced fractional-order cascaded integral derivative tilt controller for improved load frequency control incorporating renew-able energy sources and electric vehicle[J]. Soft Computing, 2023, 27(20): 15247-15267.
[9] 康皓宇, 马一鸣, 孙鲁, 等. 基于场路耦合模型的大型交流励磁电机电感参数计算[J]. 电工技术学报, 2025, 40(18): 5805-5817.
[10] 巩超逸. 汽轮发电机组励磁系统参数辨识方法研究[D]. 哈尔滨: 东北农业大学, 2023.
[11] Ding Cheng, Xiao Ran, Do D H, et al.Log-spectral matching GAN: PPG-based atrial fibrillation detection can be enhanced by GAN-based data augmentation with integration of spectral loss[J]. IEEE Journal of Biomedical and Health Informatics, 2023, 27(3): 1331-1341.
[12] 李元, 张昊展, 唐晓初. 基于多模态数据全信息的概率主成分分析故障检测研究[J]. 仪器仪表学报, 2021, 42(2): 75-85.
[13] Ahmed H U, Mostafa R R, Mohammed A, et al.Support vector regression (SVR) and grey wolf optimization (GWO) to predict the compressive strength of GGBFS-based geopolymer concrete[J]. Neural Computing and Applications, 2023, 35(3): 2909-2926.