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

Article retrieval

文章檢索

首頁 >> 文章檢索 >> 文章瀏覽排名

基于PRSGMD-XGBoost的光伏直流電能質量擾動識別

來源:電工電氣發(fā)布時間:2024-08-01 14:01 瀏覽次數(shù):149

基于PRSGMD-XGBoost的光伏直流電能質量擾動識別

朱憲宇,熊婕,李慶先,劉良江,左從瑞,劉青
(湖南省計量檢測研究院,湖南 長沙 410018)
 
    摘 要:光伏電網受天氣因素和非線性負載等影響,直流電信號中存在的擾動成分使得電能質量評估的準確性難以保障。利用復合多尺度模糊熵可克服光伏直流電信號初始單分量相似性度量突變的問題,構建了正則化 CMFE 算子評估各初始單分量重構后的復雜度并約束殘余量能量最小,從而實現(xiàn)電信號和噪聲等擾動的準確分離,在此基礎上,提出了基于部分重構辛幾何模態(tài)分解(PRSGMD)的光伏直流電信號自適應去噪方法,結合極限梯度提升機(XGBoost)可有效挖掘特征與暫態(tài)穩(wěn)定性之間關系的優(yōu)勢,實現(xiàn)了光伏直流電信號中復合擾動的分離和識別。
    關鍵詞: 光伏;電能質量擾動識別;部分重構辛幾何模態(tài)分解;極限梯度提升機
    中圖分類號:TM615     文獻標識碼:A     文章編號:1007-3175(2024)07-0061-07
 
Photovoltaic DC Power Quality Disturbance Identification
Based on PRSGMD-XGBoost
 
ZHU Xian-yu, XIONG Jie, LI Qing-xian, LIU Liang-jiang, ZUO Cong-rui, LIU Qing
(Hunan Institute of Metrology and Test, Changsha 410018, China)
 
    Abstract: The photovoltaic (PV) grid is affected by weather factors and nonlinear loads, and the disturbance components in the direct current (DC) signal make it difficult to ensure the accuracy of power quality assessment. Therefore, in this paper the problem that the composite multiscale fuzzy entropy (CMFE) can overcome the sudden change of the initial single component similarity measure of the photovoltai DC signal is utilized, then the regularized CMFE operator is constructed to evaluate the complexity of each initial single component after reconstruction, while constraining the residual energy to be minimized, and finally the separation of electrical signals and noise and other disturbance is realized. On this basis, an adaptive denoising method for photovoltai DC signal based on partial reconstruction of symplectic geometry mode decomposition (PRSGMD) is proposed, and combined with the advantage that extreme gradient boosting (XGBoost) can effectively mine the relationship between features and transient stability, the separation and identification of compound disturbance in photovoltaic DC signals is realized.
    Key words: photovoltaic; power quality disturbance identification; partial reconstruction of symplectic geometry mode decomposition;extreme gradient boosting
 
參考文獻
[1] VINAYAGAM A, OTHMAN M L, VEERASAMY V, et al.A random subspace ensemble classification model for discrimination of power quality events in solar PV microgrid power network[J].Plos One,2022,17(1) :0262570.
[2] 李固. 基于光伏發(fā)電工程的電力系統(tǒng)長期規(guī)劃模型研究[J]. 現(xiàn)代工業(yè)經濟和信息化,2023,13(8) :192-194.
[3] 葛樂,周宇浩,袁曉冬,等. 光伏并網與電能質量治理統(tǒng)一控制 [J]. 太陽能學報,2017,38(9) :2426-2433.
[4] 李家俊,吳建軍,陳武,等. 基于 DWT-PCA-LIBSVM 的電能質量擾動分類方法[J]. 電工電氣,2023(3) :20-24.
[5] 焦晉榮. 直流配電網電能質量問題分析及擾動檢測[D].秦皇島:燕山大學,2017.
[6] 武昭旭,楊岸,祝龍記. 一種新的電能質量擾動識別方法[J] . 重慶工商大學學報(自然科學版),2021,38(5) :49-54.
[7] 奚鑫澤,邢超,覃日升,等. 基于深度卷積去噪網絡的電能質量擾動識別方法[J] . 南方電網技術,2022,16(12) :118-125.
[8] ZHAO Lihua, HONG Guo, WANG Zelong, et al.Research on fault vibration signal features of GIS disconnector based on EEMD and kurtosis criterion[J].IEEJ Transactions on Electrical and Electronic Engineering,2021,16(5) :677-686.
[9] YANG Lin, GUO Linming, ZHANG Wenhai, et al.Classification of multiple power quality disturbances by Tunable-Q wavelet transform with parameter selection[J].Energies,2022,15(9) :3428.
[10] DIVYALAKSHMI D, SUBRAMANIAM N P.Photovoltaic based DVR with power quality detection using wavelet transform[J].Energy Procedia,2017,117 :458-465.
[11] 王新,閆文源. 基于變分模態(tài)分解和 SVM 的滾動軸承故障診斷[J]. 振動與沖擊,2017,36(18) :252-256.
[12] PAN Haiyang, YANG Yu, LI Xin, et al.Symplectic geometry mode decomposition and its application to rotating machinery compound fault diagnosis[J].Mechanical Systems & Signal Processing,2019,114 :189-211.
[13] CHENG Jian, YANG Yu, HU Niaoqing, et al.A noise reduction method based on adaptive weighted symplectic geometry decomposition and its application in early gear fault diagnosis[J].Mechanical Systems and Signal Processing,2020,149(15) :107351.
[14] 鄭直,高崇一,宋金超,等. 基于 SGMD 敏感參數(shù)和 KFCMC 的滾動軸承故障診斷方法[J] . 機床與液壓,2020,48(11) :189-193.
[15] 楊宇,程健,彭曉燕,等. 一種基于改進辛幾何模態(tài)分解的復合故障診斷方法[J]. 湖南大學學報(自然科學版),2020,47(2) :53-59.
[16] 鄭近德,應萬明,潘海洋,等. 基于改進全息希爾伯特譜分析的旋轉機械故障診斷方法[J] . 機械工程學報,2023,59(1) :162-174.
[17] CAI J, CAI Y, CAI H, et al.Feeder Fault Warning of Distribution Network Based on XGBoost[J].Journal of Physics:Conference Series,2020,1639(1) :1-6.
[18] CHAKRABORTY D, ELZARKA H.Early detection of faults in HVAC systems using an XGBoost model with a dynamic threshold[J].Energy and Buildings,2019,185(2) :326-344.
[19] LIU Yinming, LIU Lin, YANG Liu, et al.Measuring distance using ultra-wideband radio technology enhanced by extreme gradient boosting decision tree (XGBoost)[J].Automation in Construction,2021,126(1) :103678.
[20] WANG Zucheng, PENG Yanfeng, LIU Yanfei, et al.Photovoltaic power quality analysis based on the modulation broadband mode decomposition algorithm[J].Energies,2021,14(23) :1423798.
[21] 喻貞楷,王斌,閆墉,等. 多擾動下微電網故障檢測方法[J] . 電力系統(tǒng)及其自動化學報,2023,35(12) :151-158.