Prediction of Dissolved Gas Concentration in Transformer Oil Based on Multistage Feature Extraction and IHHO-KELM

FU Yuchen; CHEN Xing; FU Wenlong; FANG Nian; ZHANG Kai; CAO Zhengjiang

doi:10.13296/j.1001-1609.hva.2026.02.008

您当前的位置：

首页 >

文章列表页 >

Prediction of Dissolved Gas Concentration in Transformer Oil Based on Multistage Feature Extraction and IHHO-KELM

Research & Analysis | 更新时间：2026-03-16

- Prediction of Dissolved Gas Concentration in Transformer Oil Based on Multistage Feature Extraction and IHHO-KELM
- High Voltage Apparatus Vol. 62, Issue 2, Pages: 60-70(2026)
- 作者机构：
  
  三峡大学电气与新能源学院，湖北宜昌 443000
  三峡大学梯级水电站运行与控制湖北省重点实验室，湖北宜昌 443000
  国网浙江省电力有限公司宁波供电公司，浙江宁波 315000
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(51741907)
- DOI：10.13296/j.1001-1609.hva.2026.02.008
  CLC：
- Received：18 July 2025，
  
  Revised：2025-10-01，
  
  Published：16 February 2026
- 稿件说明：
移动端阅览
FU Yuchen, CHEN Xing, FU Wenlong, et al. Prediction of Dissolved Gas Concentration in Transformer Oil Based on Multistage Feature Extraction and IHHO-KELM[J]. High Voltage Apparatus, 2026, 62(2): 60-70.
DOI：

FU Yuchen, CHEN Xing, FU Wenlong, et al. Prediction of Dissolved Gas Concentration in Transformer Oil Based on Multistage Feature Extraction and IHHO-KELM[J]. High Voltage Apparatus, 2026, 62(2): 60-70. DOI： 10.13296/j.1001-1609.hva.2026.02.008.

摘要

油中溶解气体分析是变压器早期故障诊断的主要方法，准确预测未来特征气体体积分数有助于提前获取变压器的运行状态。为此提出了一种基于多级特征提取和IHHO-KELM的变压器油中溶解气体体积分数预测方法。首先，通过自适应白噪声完全集合经验模态分解将气体体积分数序列分解为多个子序列，利用奇异谱分析对子序列做进一步降噪处理，降低其非平稳性；其次，建立核极限学习机预测模型分别对各子序列进行预测，再将各子序列的预测结果叠加得到油中溶解气体体积分数的最终预测结果，并通过改进哈里斯鹰算法优化其超参数；最后，通过算例验证表明，所提模型具有更优的预测性能，可以更好的追踪油中溶解气体体积分数的变化趋势。

Abstract

Dissolved gas analysis in oil is the main method of early fault diagnosis of transformer. Accurate prediction of the future characteristic gas concentration contributes to gain operation status of transformer in advance. Therefore

the prediction model of dissolved gas concentration in transformer oil based on multistage feature extraction andIHHO-KELMis proposed. Firstly

the dissolved gas concentration data is decomposed into multiple subsequences by complete ensemble empirical mode decomposition with adaptive noise

and the subsequences are further denoised by singular spectrum analysis to reduce its non-stationarity. Then

kernel based extreme learning machine is set up to predict each subsequence. After that

the prediction result of each subsequence is superimposed into the final prediction result of oil dissolved gas concentration. Meanwhile

the improved Harris hawk optimization is used to optimize the hyper-parameter of kernel based extreme learning machine. Finally

it is shown by the calculation example that the proposed model has better prediction performance

which can better track the variation trend of dissolved gas concentration in transformer oil.

关键词

Keywords

references

栗磊,王廷涛,殷浩然,等.基于GWO-LSTM与NKDE的变压器油中溶解气体体积分数点—区间联合预测方法[J].高压电器,2022,58(11):88-97.

LI Lei, WANG Tingtao, YIN Haoran, et al. Point-interval joint prediction method of dissolved gas volume fraction in transformer oil based onGWO-LSTMand NKDE[J]. High Voltage Apparatus, 2022, 58(11):88-97.

余文强,付小伟,吕波,等.基于剩磁影响的变压器诊断试验结果治理方法[J].电网与清洁能源,2025,41(11):12-20.

YU Wenqiang, FU Xiaowei, LYU Bo, et al. A management method for transformer diagnostic test results based on remanent flux influence[J].Power System and Clean Energy , 2025 , 41(11):12-20.

邱晟璇,王松,刘子瑞,等.基于FRA法和CNN的变压器绕组故障诊断研究[J].大电机技术,2025(3):108-116.

QIU Shengxuan, WANG Song, LIU Zirui, et al. Research on fault diagnosis of transformer windings based on FRA method and CNN[J].Large Electric Machine and Hydraulic Turbine, 2025(3):108-116.

刘宇鹏,侯文君,周渠,等.基于密度泛函理论的油中特征气体在钯掺杂SnP3单层上吸附及传感性能研究[J].中国电机工程学报,2023,43(5):2040-2049.

LIU Yupeng, HOU Wenjun, ZHOU Qu, et al. Investigation on adsorption and sensing performance of characteristic gas in oil on palladium-doped SnP3 monolayer based on density functional theory[J]. Proceedings of the CSEE, 2023, 43(5):2040-2049.

王子凌,汪科,柴卫健,等.基于PCA和Fast-MCD的油中溶解气体在线监测异常数据识别[J].浙江电力,2025,44(3):100-107.

WANG Ziling, WANG Ke, CHAI Weijian, et al. Identification of abnormal data in online dissolved gas monitoring in oil based on PCA and Fast-MCD[J].Zhejiang Electric Power, 2025, 44(3):100-107.

谢乐,仇炜,李振伟,等.基于变分模态分解和门控循环单元神经网络的变压器油中溶解气体预测模型[J].高电压技术, 2022,48(2):653-660.

XIE Le, QIU Wei, LI Zhenwei, et al. Prediction model of dissolved gas in transformer oil based on variational modal decompo-sition and recurrent neural network with gated recurrent unit[J]. High Voltage Engineering, 2022, 48(2):653-660.

徐惠,罗传仙,张静.基于加性模型的电力变压器油中溶解气体预测方法研究[J].电网与清洁能源,2025,41(7):27-35.

XU Hui, LUO Chuanxian, ZHANG Jing. Research on the prediction method for dissolved gases in transformer oil based on additive models[J].Power System and Clean Energy, 2025, 41(7):27-35.

贾茹宾,高金峰.基于ARIMA模型的变压器油中溶解气体含量时间序列预测方法[J].郑州大学学报（工学版）,2020,41 （2）:67-72.

JIA Rubin, GAO Jinfeng. Time series prediction method of dissolved gas content in transformer oil based on ARIMA model[J].Journal of Zhengzhou University(Engineering Science Edition), 2020, 41(2):67-72.

刘航,王有元,梁玄鸿,等.基于多因素的变压器油中溶解气体体积分数预测方法[J].高电压技术,2018,44(4):1114-1121.

LIU Hang, WANG Youyuan, LIANG Xuanhong, et al. Prediction method of the dissolved gas volume fraction in transformer oil based on multi factors[J]. High Voltage Engineering, 2018, 44(4):1114-1121.

杨廷方,刘沛,李浙,等.应用新型多方法组合预测模型估计变压器油中溶解气体浓度[J].中国电机工程学报,2008,28 (31):108-113.

YANG Tingfang, LIU Pei, LI Zhe, et al. A new combination forecasting model for concentration prediction of dissolved gases in transformer oil[J]. Proceedings of the CSEE, 2008, 28(31):108-113.

连文莉,耿波,周舟,等.基于自适应粒子群优化LSSVM的变压器油中溶解气体浓度预测[J].电工电能新技术,2021,40 (5):42-49.

LIAN Wenli, GENG Bo, ZHOU Zhou, et al. Predicting method for dissolved gas in transformer oil based on improved self-adaptive PSO algorithm and LSSVM[J]. Advanced Technology of Electrical Engineering and Energy, 2021, 40(5):42-49.

陈铁,陈卫东,李咸善,等.基于油中溶解气体分析的变压器故障预测[J].电子测量技术,2021,44(22):25-31.

CHEN Tie, CHEN Weidong, LI Xianshan, et al. Transformer fault prediction based on analysis of dissolved gas in oil[J]. Electronic Measurement Technology , 2021 , 44(22):25-31.

苏磊,陈璐,徐鹏,等.基于GRNN和KPCA组合模型的变压器油中气体体积分数短期预测[J].高压电器,2021,57(1):82-88.

SU Lei, CHEN Lu, XU Peng, et al. Short-term prediction of gases dissolved in transformer oil based on GRNN and KPCA model[J]. High Voltage Apparatus , 2021 , 57(1):82-88.

江兵,杨春,杨雨亭,等.基于ACO优化BP神经网络的变压器热点温度预测[J].电子测量与仪器学报,2022,36(10):235-242.

JIANG Bing, YANG Chun, YANG Yuting, et al. Temperature prediction of transformer hot spot based on BP neural network optimized byACO[J].Journal of Electronic Measurement and Instrumentation, 2022, 36(10):235-242.

DING Can,DING Qingchang,FENG Lu,et al. Prediction model of dissolved gas in transformer oil based onVMD-SMA-LSSVM[J]. IEEJ Transactions on Electrical and Electronic Engineering,2022, 17(10):1432-1440.

唐勇波,熊印国.基于二次维数约简的油中溶解气体浓度预测[J].电工技术学报,2017,32(21):194-202.

TANG Yongbo, XIONG Yinguo. Prediction model for dissolved gases content in transformer oil based on twice dimensionality reduction[J]. Transactions of China Electrotechnical Society, 2017, 32(21):194-202.

李可军,亓孝武,魏本刚,等.基于核极限学习机误差预测修正的变压器顶层油温预测[J].高电压技术,2017,43(12):40454053.

LI Kejun, QI Xiaowu, WEI Bengang, et al. Prediction of transformer top oil temperature based on kernel extreme learning machine error prediction and correction[J]. High Voltage Engineering, 2017, 43(12):4045-4053.

周锋,孙廷玺,权少静,等.基于集合经验模态分解和极限学习机的变压器油中溶解气体体积分数预测方法[J].高电压技术,2020,46(10):3658-3665.

ZHOU Feng, SUN Tingxi, QUAN Shaojing, et al. Predication of dissolved gases concentration in transformer oil based on ensemble empirical mode decomposition and extreme learning machine[J]. High Voltage Engineering, 2020, 46(10):3658-3665.

王杰,李永鑫,张军亮,等.基于SBOA-TVFEMD的变压器油中溶解气体浓度预测[J].变压器,2025,62 (5):23-31.

WANG Jie, LI Yongxin, ZHANG Junliang, et al. Prediction of dissolved gas concentration in transformer oil based on SBOATVFEMD[J].Transformer, 2025, 62 (5):23-31.

贾东明,韩晓昆,董翔,等.基于Pt-C3N传感器的变压器油中溶解气体的吸附性能研究[J].智慧电力,2024,52(4):40-46.

JIA Dongming, HAN Xiaokun, DONG Xiang, et al. Adsorption performance of dissolved gases in transformer oil based on Pt-C3N sensor[J].Smart Power, 2024, 52(4):40-46.

连鸿松,黄锦,郑东升,等.绝缘油中溶解气体在线监测装置可靠性评测的现场加速试验方法及平台[J].变压器,2025,62 (5):53-58.

LIAN Hongsong, HUANG Jin, ZHENG Dongsheng, et al. Accelerated testing method and platform for reliability of online monitoring device used to gases dissolved in insulation oil[J].Transformer, 2025, 62 (5):53-58.

刘可真,苟家萁,骆钊,等.基于粒子群优化—长短期记忆网络模型的变压器油中溶解气体浓度预测方法[J].电网技术, 2020,44(7):2778-2784.

LIU Kezhen, GOU Jiaqi, LUO Zhao, et al. Prediction of dissolved gas concentration in transformer oil based onPSO-LSTMmodel[J]. Power System Technology, 2020, 44(7):2778-2784.

刘云鹏,许自强,董王英,等.基于经验模态分解和长短期记忆神经网络的变压器油中溶解气体浓度预测方法[J].中国电机工程学报,2019,39(13):3998-4007.

LIU Yunpeng, XU Ziqiang, DONG Wangying, et al. Concentration prediction of dissolved gases in transformer oil based on empirical mode decomposition and long short-term memory neural networks[J]. Proceedings of the CSEE, 2019, 39(13):3998-4007.

舒畅,金潇,李自品,等.基于CEEMDAN的配电变压器放电故障噪声诊断方法[J].高电压技术,2018,44(8):2603-2611.

SHU Chang, JIN Xiao, LI Zipin, et al. Noise diagnosis method of distribution transformer discharge fault based onCEEMDAN[J]. High Voltage Engineering, 2018, 44(8):2603-2611.

唐竹,肖宇航,郭淳,等.基于CEEMDAN模态分解和TCNBiGRU的短期电力负荷预测[J].智慧电力,2024,52(12):59-64.

TANG Zhu, XIAO Yuhang, GUO Chun, et al. Short-term electricity load forecasting based on CEEMDAN decomposition and TCN-BIGRU model[J].Smart Power, 2024, 52(12):59-64.

李佳,邓科,侯玉莲,等.基于GRA-CEEMDAN-BiLSTM的变压器油中溶解气体浓度预测[J].变压器,2022,59(6):42-47.

LI Jia, DENG Ke, HOU Yulian, et al. Prediction of dissolved gas concentration in transformer oil based onGRA-CEEMDANBiLSTM[J]. Transformer, 2022, 59(6):42-47.

马秉伟,陈晓国,郑宇,等.电力变压器环保绝缘油研究进展与趋势[J].南方电网技术,2024,18(5):12-21.

MA Bingwei, CHEN Xiaoguo, ZHENG Yu, et al.Research progress and trends of eco-friendly insulating oil for power transformers[J]. Southern Power System Technology, 2024, 18(5):12-21.

TORRES M E,COLOMINAS M A,SCHLOTTHAUER G,et al. A complete ensemble empirical mode decomposition with adaptive noise[C]//2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). CZ:IEEE,2011:4144-4147.

陈铁,陈一夫,李咸善,等.基于SDS-SSA-LSTM的变压器油中溶解气体浓度预测[J].电子测量技术,2022,45(12):6-11.

CHEN Tie, CHEN Yifu, LI Xianshan, et al. Prediction of dissolved gas concentration in transformer oil based on SDS-SSA-LSTM[J]. Electronic Measurement Technology , 2022 , 45(12) :6-11.

王延年,王栋,廉继红,等.局部遮荫下基于IP & O-SSA的MPPT控制研究[J].西安工程大学学报,2023,37(4):110-117.

WANG Yannian, WANG Dong, LIAN Jihong, et al. Research on MPPT control based on IP & O-SSA under partial shading[J].Journal of Xi’an Polytechnic University, 2023, 37(4):110-117.

HEIDARI A A,MIRJALILI S,FARIS H,et al. Harris hawks optimization:Algorithm and applications[J]. Future Generation Computer Systems,2019(97):849-872.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Prediction of Dissolved Gas Concentration in Transformer Oil Based on Multistage Feature Extraction and IHHO-KELM

Research on Vibration Defect Detection Method of GIS Based on Singular Spectrum Analysis and Decision Tree

Related Author

FU Yuchen

CHEN Xing

FU Wenlong

FANG Nian

TENG Yun

LI Hongtao

LI Yujie

XIAO Hanyan

Related Institution

State Grid Zhejiang Electric Power Co., Ltd., Ningbo Power Supply Company

State Grid Laboratory of GIS Operation and Maintenance Technology, State Grid Jiangsu Electric Power Co., Ltd. Research Institute

Shanghai Rhythm Electronics Technology Co., Ltd.

⁰