电子测量与仪器学报

陈丽,唐圣学,黎霞,姚芳.基于 RLS-SVR 的光伏并网变流器早期故障预测方法研究[J].电子测量与仪器学报,2021,35(4):99-108

基于 RLS-SVR 的光伏并网变流器早期故障预测方法研究

Early fault prediction of connected-grid PV converters based on RLS-SVR

DOI：

英文关键词:photovoltaic cells converters RLS-SVR fault prediction

基金项目:河北省自然科学基金面上项目(E2019202481)、河北省自然科学重点基金(E2017202284)项目资助

作者	单位
陈丽	1. 河北工业大学电气工程学院省部共建电工装备可靠性与智能化国家重点实验室，2. 河北工业大学电气工程学院河北省电磁场与电器可靠性重点实验室
唐圣学	1. 河北工业大学电气工程学院省部共建电工装备可靠性与智能化国家重点实验室，2. 河北工业大学电气工程学院河北省电磁场与电器可靠性重点实验室
黎霞	1. 河北工业大学电气工程学院省部共建电工装备可靠性与智能化国家重点实验室，2. 河北工业大学电气工程学院河北省电磁场与电器可靠性重点实验室
姚芳	1. 河北工业大学电气工程学院省部共建电工装备可靠性与智能化国家重点实验室，2. 河北工业大学电气工程学院河北省电磁场与电器可靠性重点实验室

Author	Institution
Chen Li	1. State Key Laboratory of Reliability and Intelligence of Electrical Equipment, School of Electrical Engineering, Hebei University of Technology, 2. Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province, School of Electrical Engineering, Hebei University of Technology
Tang Shengxue	1. State Key Laboratory of Reliability and Intelligence of Electrical Equipment, School of Electrical Engineering, Hebei University of Technology, 2. Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province, School of Electrical Engineering, Hebei University of Technology
Li Xia	1. State Key Laboratory of Reliability and Intelligence of Electrical Equipment, School of Electrical Engineering, Hebei University of Technology, 2. Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province, School of Electrical Engineering, Hebei University of Technology
Yao Fang	1. State Key Laboratory of Reliability and Intelligence of Electrical Equipment, School of Electrical Engineering, Hebei University of Technology, 2. Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province, School of Electrical Engineering, Hebei University of Technology

摘要点击次数: 335

全文下载次数: 4

中文摘要:

针对光伏并网变流器故障预测问题,提出了基于鲁棒最小二乘-支持向量回归(RLS-SVR)的早期故障预测方法。从系统层面分析了光伏并网变流器脆弱元件退化互相耦合机理及对系统状态特征和早期故障特征选取的影响,进而提出了以特征相对变化量表征变流器状态的电路故障预测方法。为了减小工作条件对特征退化预测的影响,方法首先采用 RLS-SVR 算法, 建立以工作条件为输入、状态特征为输出的无退化拟合 RLS-SVR 计算模型;然后,根据退化过程中工作条件序列、状态特征量序列,结合变流器无退化 RLS-SVR 拟合模型,计算特征相对变化量退化序列;最后,根据特征相对变化量序列,再次采用 RLSSVR 算法构建特征相对变化量预测模型,以实现故障早期预测。预测方法无需额外增加传感器,具有简单、成本低、预测精度高的优点。最后,以光伏发电单相并网变流器为例进行了实验,结果验证了方法的可行性和有效性。

英文摘要:

Aiming at early fault prediction problem of connected-grid PV converters, a fault prediction method is presented based on RLSSVR in this paper. The degradation parameter couplings of vulnerable components and its effects on conditions of converters and selection of features for fault prediction are analyzed in this paper in system level, and then the prediction method using the relative variables of features as converter states is proposed. In order to reduce the degeneration prediction from the working condition, the method firstly builds the feature fitting model without degeneration with work condition as input and state features as output by using robust least squares support vector regression (RLS-SVR). Then, the time series of relative variable features of converters is obtained by combining the online working conditions time series and feature time series with no degeneration fitting model during the degradation procedure. At last, the prediction model of the relative variable time series of features of converters is built based on the degradation time series and using RLS-SVR. The prediction method is simple, low cost, high precision, and without adding other sensors. Experimental results of singlephase PV connected-grid converter show that the proposed method is feasible and effective.

查看全文查看/发表评论下载PDF阅读器