基于拉曼光谱技术的变压器绝缘油老化研究

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (1743 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract With regard to the measured Raman spectral data of transformer insulating oil, the relevant research is carried out based on Raman spectral data processing, feature extraction and aging diagnosis with Raman spectral technology as a means to accurately identify the aging state of transformer insulation. First of all, combined with the law of change of Raman spectral noise, based on the wavelet transform theory, the global threshold wavelet transform filtering method is proposed, which effectively removes the noise signals in Raman spectra. Further, an improved baseline correction method is proposed based on the adaptive iterative reweighting penalized least squares (airPLS) method, which accurately removes the fluorescence background of Raman spectra. Secondly, the aging feature information in Raman spectra is extracted using successive projections algorithm (SPA), and its relationship with the aging degree of transformer insulating oil is analyzed. Finally, the light gradient boosting machine (LightGBM) classification model is used to realize accurate discrimination of transformer insulation aging state, and the extreme gradient boosting (XGBoost) model is used as a control group to compare the diagnostic accuracy of the two. The experimental results show that the LightGBM model possesses obvious advantages in diagnostic accuracy, and also further verifies the validity of the extracted aging feature information.

Key words： transformer insulating oil Raman spectra noise fluorescence background feature extraction determination of aging

Received: 18 February 2025

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	ZHOU Yuhan
	LIU Qingzhen

Cite this article:

ZHOU Yuhan,LIU Qingzhen. Research on transformer insulating oil aging based on Raman spectra[J]. Electrical Engineering, 2025, 26(6): 8-16.

URL:

https://dqjs.cesmedia.cn/EN/Y2025/V26/I6/8

[1] 邹阳, 林锦茄, 李安娜, 等. 基于灰色关联分析和聚类云模型的变压器油纸绝缘状态评估[J]. 电力系统保护与控制, 2023, 51(21): 35-43.
[2] 苏凯强, 刘庆珍. 基于TLS-ESPRIT算法的变压器油纸绝缘等效电路参数辨识及新特征量提取[J]. 电气技术, 2022, 23(7): 89-96.
[3] 夏源, 杨丽君, 吕晓露, 等. 基于介质响应电流频变特性的油纸绝缘受潮状态评估方法[J]. 电工技术学报, 2024, 39(11): 3444-3456.
[4] 林智勇, 李荣华, 黄国泰, 等. 基于频域介电谱二次微分解谱法的变压器油纸绝缘介电响应等效电路参数辨识[J/OL]. 电工技术学报, 1-10 [2025-02-18]. https://doi.org/10.19595/j.cnki.1000-6753.tces.241347.
[5] 陈新岗, 陈姝婷, 杨定坤, 等. 基于高维拉曼光谱数据的变压器油纸绝缘老化评估方法研究[J]. 光谱学与光谱分析, 2021, 41(5): 1463-1469.
[6] 张振宇, 李永祥, 阎寒冰, 等. SF₆分解特征组分拉曼光谱检测分析系统设计[J]. 光学与光电技术, 2021, 19(6): 11-18.
[7] 宋睿敏, 王建新, 陈伟根, 等. 矿物油中糠醛液芯光纤增强拉曼光谱原位检测方法[J]. 电工技术学报, 2023, 38(24): 6828-6838.
[8] 范元超, 陈孝敬, 黄光造, 等. 基于拉曼光谱的电线绝缘材料老化状态评估[J]. 光谱学与光谱分析, 2022, 42(10): 3161-3167.
[9] 范舟, 陈伟根, 万福, 等. 基于小波包能量熵和Fisher判别的油纸绝缘老化拉曼光谱诊断[J]. 光谱学与光谱分析, 2018, 38(10): 3117-3123.
[10] 邹经鑫, 刘彦琴, 袁明哲, 等. 油纸绝缘老化状态判别的拉曼光谱特征研究[J]. 光谱学与光谱分析, 2021, 41(10): 3159-3165.
[11] 王建新, 陈伟根, 王品一, 等. 变压器故障特征气体空芯反谐振光纤增强拉曼光谱检测[J]. 中国电机工程学报, 2022, 42(16): 6136-6144, 6187.
[12] 陈新岗, 冯煜轩, 李昌鑫, 等. 基于多参量的变压器油中特征气体拉曼光谱分析[J]. 光谱学与光谱分析, 2020, 40(6): 1916-1922.
[13] WANG Ruiqi, QI Ying, ZHANG Qiang, et al.A multi-step water quality prediction model based on the Savitzky-Golay filter and Transformer optimized network[J]. Environmental Science and Pollution Research, 2023, 30(50): 109299-109314.
[14] 胡睿喆, 杨晓峰. 基于小波散射网络-贝叶斯优化门控循环单元的电力变压器声纹识别方法[J]. 电气技术, 2024, 25(8): 35-40, 46.
[15] 方松琼, 邵荣君, 邱丽荣, 等. 基于小波变换的共焦拉曼图像去噪方法[J]. 光学技术, 2019, 45(3): 330-335.
[16] 刘宗溢, 张彩虹, 蒋健康, 等. 基于拉曼光谱结合CNN-LSTM深度学习方法的铁皮石斛总黄酮含量快速检测研究[J]. 光谱学与光谱分析, 2024, 44(4): 1018-1024.
[17] 王忠, 万冬冬, 单闯, 等. 基于反向传播神经网络的拉曼光谱去噪方法[J]. 光谱学与光谱分析, 2022, 42(5): 1553-1560.
[18] 白云飞, 罗海燕, 李志伟, 等. 基于改进的自适应迭代重加权惩罚最小二乘的空间外差拉曼光谱基线校正方法[J]. 光学学报, 2024, 44(7): 251-259.
[19] 刘庆珍, 张溢, 鄢仁武. 基于拉曼光谱数据处理和谱峰识别的变压器油绝缘老化研究[J]. 电力系统保护与控制, 2024, 52(8): 158-166.
[20] ARAÚJO M C U, SALDANHA T C B, GALVÃO R K H, et al. The successive projections algorithm for variable selection in spectroscopic multicomponent analysis[J]. Chemometrics and Intelligent Laboratory Systems, 2001, 57(2): 65-73.
[21] CHEN Yiyang, CHU Bing, FREEMAN C T.Gen- eralized iterative learning control using successive projection: algorithm, convergence, and experimental verification[J]. IEEE Transactions on Control Systems Technology, 2020, 28(6): 2079-2091.
[22] 贾宗潮, 王子鉴, 李雪莹, 等. 主成分分析和连续投影融合的海洋沉积物粒度分类研究[J]. 光谱学与光谱分析, 2023, 43(10): 3075-3080.
[23] 牛芳鹏, 李新国, 白云岗, 等. 遗传算法和连续投影算法结合的土壤有机碳含量高光谱估算模型[J]. 光谱学与光谱分析, 2023, 43(7): 2232-2237.
[24] 钱国超, 彭庆军, 彭惠. 变压器油中气体拉曼光谱光纤增强检测实验研究[J]. 云南电力技术, 2021, 49(6): 21-25.
[25] PUNITHA N, DIVYA BHARATHI K, MANUSKANDAN S R, et al.Analysis of muscle fatigue progression using geometric features of surface electromyography signals and explainable XGBoost classifier[J]. Journal of Medical and Biological Engineering, 2024, 44(2): 191-197.
[26] 韩璟琳, 冯喜春, 胡平, 等. 基于Hyperopt-LightGBM的直流配电网短期负荷抗噪声预测[J]. 高电压技术, 2024, 50(11): 4902-4911.
[27] 王俊杰, 毕利, 张凯, 等. 基于多特征融合和XGBoost-LightGBM-ConvLSTM的短期光伏发电量预测[J]. 太阳能学报, 2023, 44(7): 168-174.
[28] FRIFRA A, MAANAN M, MAANAN M, et al.Harnessing LSTM and XGBoost algorithms for storm prediction[J]. Scientific Reports, 2024, 14(1): 11381.
[29] 赖汶鸿, 刘庆珍, 鄢仁武. 基于关联信息熵和轻量级梯度提升机的油纸绝缘特征优选策略[J]. 电气技术, 2024, 25(1): 34-41, 47.