Suzhou Electric Appliance Research Institute
期刊號: CN32-1800/TM| ISSN1007-3175

SUBSCRIPTION MANAGEMENT

發(fā)行征訂

首頁 >> 發(fā)行征訂 >> 征訂方式

基于數(shù)據(jù)-特征增強(qiáng)與參數(shù)優(yōu)化的變壓器故障識別方法

來源:電工電氣發(fā)布時(shí)間:2025-12-30 10:30瀏覽次數(shù):12
基于數(shù)據(jù)-特征增強(qiáng)與參數(shù)優(yōu)化的變壓器故障識別方法
 
童宇軒1,李燦2,周佳炎1
(1 國網(wǎng)浙江省電力有限公司慈溪市供電公司,浙江 慈溪 315300; 2 浙江省送變電工程有限公司,浙江 杭州 310020)
 
    摘 要 :針對油浸式電力變壓器故障診斷中存在的樣本不平衡及模型參數(shù)優(yōu)化問題,提出一種基于數(shù)據(jù)-特征增強(qiáng)與自適應(yīng)參數(shù)優(yōu)化的油浸式變壓器機(jī)器學(xué)習(xí)故障識別模型。通過合成少數(shù)類過采樣技術(shù) (SMOTE) 解決數(shù)據(jù)集故障類別不平衡問題,并結(jié)合IEC三比值法構(gòu)建多維故障特征增強(qiáng)數(shù)據(jù)集特征表征能力;采用融合正余弦策略和柯西變異機(jī)制的改進(jìn)麻雀搜索算法 (SCSSA) 實(shí)現(xiàn)對機(jī)器學(xué)習(xí)模型的自適應(yīng)調(diào)參,來有效提升最小二乘支持向量機(jī) (LSSVM) 超參數(shù)尋優(yōu)性能。實(shí)驗(yàn)對比表明,所提模型較傳統(tǒng)模型具有更高的診斷精度和穩(wěn)定性,對提升超期服役變壓器的故障診斷能力具有工程應(yīng)用價(jià)值。
    關(guān)鍵詞 : 變壓器 ;故障診斷;合成少數(shù)類過采樣技術(shù);改進(jìn)麻雀搜索算法;最小二乘支持向量機(jī)
    中圖分類號 :TM407     文獻(xiàn)標(biāo)識碼 :B     文章編號 :1007-3175(2025)12-0042-06
 
Transformer Fault Recognition Method Based on Data-Feature Enhancement and Parameter Optimization
 
TONG Yu-xuan1 , LI Can2 , ZHOU Jia-yan1
(1 Cixi Power Supply Company of State Grid Zhejiang Electric Power Co., Ltd, Cixi 315300, China; 2 Zhejiang Power Transmission and Transformation Engineering Co., Ltd, Hangzhou 310020, China)
 
    Abstract: Aiming at the problems of sample imbalance and model parameter optimization existing in the fault diagnosis of oil-immersed power transformers, a machine learning fault recognition model for oil-immersed transformers based on data-feature enhancement and adaptive parameter optimization is proposed. The synthetic minority over-sampling technique (SMOTE) is employed to solve imbalance problem in datasets fault categories, and the IEC three-ratio method is combined to construct a multidimensional fault feature set, thereby enhancing the feature representation capability of the dataset. Subsequently, an improved sparrow search algorithm (SCSSA) that integrates sine and cosine strategies and Cauchy mutation mechanisms is adopted to achieve adaptive parameter tuning of machine learning models, effectively enhancing the hyperparameter optimization performance of least squares support vector machines (LSSVM).Comparative experiments demonstrate that the proposed model has higher diagnostic accuracy and stability than the traditional model, and has engineering application value for improving the fault diagnosis capability of transformers that have exceeded their service life.
    Key words: transformer; fault diagnosis; synthetic minority over-sampling technique; improved sparrow search algorithm; least squares support vector machines
 
參考文獻(xiàn)
[1] 任志勇,張?zhí)煨?. 一起110 kV 變壓器內(nèi)部放電故障分析 [J]. 電工電氣,2024(1):71-73.
[2] 謝樂,楊浙,潘成南 . 基于分步特征選取和WOA-LSSVM的變壓器故障診斷 [J]. 電工電氣,2024(8):31-36.
[3] 閔永智,令世文,王果 . 基于混合特征選擇和IOMA-CNN的變壓器故障診斷 [J]. 電力系統(tǒng)保護(hù)與控制, 2024,52(23):1-9.
[4] 黨瓏,王琪,董佳寧,等 . 電力變壓器故障診斷方法的比較研究 [J]. 江蘇理工學(xué)院學(xué)報(bào),2023,29(6) :69-80.
[5] 李雷軍,吳超,付華,等 . 基于油中溶解氣體分析的ISSA優(yōu)化LSSVM變壓器故障診斷研究 [J]. 電工電能 新技術(shù),2023,42(10):84-94.
[6] 孔博,趙占軍,郭海波,等 . 基于SSA-CNN的電力變壓器 故障智能診斷方法 [J]. 電工技術(shù),2024(23):190-195.
[7] 黃旭,許冬云 . 基于MF-SAE-SSA-KELM油浸式變壓器 故障診斷方法 [J]. 工業(yè)控制計(jì)算機(jī),2024,37(10): 126-128.
[8] 呂鑫,慕曉冬,張鈞,等 . 混沌麻雀搜索優(yōu)化算法 [J]. 北京航空航天大學(xué)學(xué)報(bào),2021,47(8) :1712-1720.
[9] YUAN J H, ZHAO Z W, LIU Y P, et al.DMPPT control of photovoltaic microgrid based on improved sparrow search algorithm[J].IEEE Access,2021,9: 16623-16629.
[10] LIU G Y, SHU C, LIANG Z G, et al.A modified sparrow search algorithm with application in 3d route planning for UAV[J].Sensors,2021,21(4) :1224.
[11] 王玲芝,李晨陽,李程,等 . 多策略改進(jìn) SSA優(yōu)化LSTM網(wǎng)絡(luò)的短期光伏發(fā)電功率預(yù)測 [J]. 武漢大學(xué)學(xué) 報(bào) ( 工學(xué)版 ),2025,58(8) :1356-1366.
[12] 周萱,吳偉麗 . 基于改進(jìn) SMOTE不均衡樣本處理和 IHPO-DBN的變壓器故障診斷方法研究 [J]. 電力系統(tǒng) 保護(hù)與控制,2024,52(11) :21-30.
[13] 蔡賽男,宋衛(wèi)星,班利明,等 . 基于鯨魚算法優(yōu)化 LSSVM的滾動軸承故障診斷 [J]. 控制與決策,2022, 37(1) :230-236.
[14] 劉澤宇,彭澤源,韓愛國 . 基于SCSSA-CNN-BiLSTM的行駛工況下鋰電池壽命預(yù)測 [J]. 重慶理工大學(xué)學(xué)報(bào) ( 自然科學(xué)版 ),2024,38(1) :308-318.
[15] 柴巖,常曉萌,任生 . 融合多策略改進(jìn)的白鯨優(yōu)化算法 [J]. 計(jì)算機(jī)工程與應(yīng)用,2025,61(5) :76-93.