Composite fault diagnosis method of photovoltaic modules based on feature extraction and machine learning

WANG Qiming; XIA Kun; JIAO Pingyang; HAN Xiang; DONG Jinlong

doi:10.3969/j.issn.1672-3643.2025.04.010

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Composite fault diagnosis method of photovoltaic modules based on feature extraction and machine learning

更新时间：2025-11-08

- Composite fault diagnosis method of photovoltaic modules based on feature extraction and machine learning
- Ningxia Electric Power Issue 4, (2025)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1672-3643.2025.04.010
  CLC：
- Published Online：20 August 2025，
  
  Published：20 August 2025
- 稿件说明：
移动端阅览
WANG Qiming, XIA Kun, JIAO Pingyang, et al. Composite fault diagnosis method of photovoltaic modules based on feature extraction and machine learning[J]. Ningxia electric power, 2025, (4).
DOI：

WANG Qiming, XIA Kun, JIAO Pingyang, et al. Composite fault diagnosis method of photovoltaic modules based on feature extraction and machine learning[J]. Ningxia electric power, 2025, (4). DOI： 10.3969/j.issn.1672-3643.2025.04.010.

摘要

现有光伏故障诊断领域的研究对象多为单一故障，为了达到光伏组件复合故障的精确诊断，提出了基于特征提取的光伏组件复合故障诊断方法。根据光伏阵列串并联结构建立光伏阵列数学模型，在光伏发电仿真系统的基础上搭建光伏故障仿真模型，分析光伏组件单一故障和复合故障伏安输出特性曲线。在表面特征变化的基础上对参数进一步处理，融合新的特征参数获得能够准确表征故障的故障特征，建立特征参数和故障之间的映射关系。构建基于哈里斯鹰（harris hawks optimization

HHO）优化类别提升（categorical boosting

CatBoost）算法的光伏组件故障诊断模型。通过搭建实验平台，验证所提方法对单一故障和复合故障的诊断准确率均达到98%以上。

Abstract

Most existing studies on photovoltaic(PV) fault diagnosis focus on single faults.To accurately identify composite faults in PV modules

this paper proposes a fault diagnosis method based on feature extraction and machine learning.A mathematical model of a PV array is established based on its series-parallel configuration

and a simulation model for PV faults is constructed within a PV generation simulation framework.The voltage-current(V–I) output charac-teristics under both single and composite fault conditions are analyzed.Feature parameters are refined based on observable surface feature variations

and new feature parameters are introduced to form fault descriptors.A mapping relationship between the extracted features and corresponding fault types is then established.A diagnostic model is developed using the CatBoost(categorical boosting) algorithm

optimized by the harris hawks optimization(HHO) method.Experimental results from a custom-built test platform demonstrate that the proposed method achieves diagnostic accuracy exceeding 98% for both single and composite faults.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Fault diagnosis of converter transformers based on time-frequency maps and parallel CNN-LSTM

Research on the development process of partial discharge in GIS due to insulator gap defects

Related Author

CUI Peng

WU Mingkai

LU Hongjian

AN Yanjie

CAO Zhi

FENG Xiaowei

MA Runze

DONG Yulin

Related Institution

Extra High Volgage Company,State Grid Ningxia Electric Power Co[JP10].,Ltd[JP10].

State Grid Ningxia Electric Power Co[JP10].,Ltd[JP10].

Shanghai Institute of Microsystem and Information Technology,Chinese Academy of Sciences

State Grid Changsha Power Supply Company

State Grid Hunan Electric Power Co.,Ltd.

AI问答

⁰