基于进化算法和长短期记忆网络的光伏阵列多类型复合故障诊断方法

白牧可; 钱志研; 段祥骏; 李佳

doi:doi:10.19912/j.0254-0096.tynxb.2024-1927

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

基于进化算法和长短期记忆网络的光伏阵列多类型复合故障诊断方法

更新时间：2026-04-08

- 基于进化算法和长短期记忆网络的光伏阵列多类型复合故障诊断方法
- Vol. 47, Issue 3, Pages: 625-634(2026)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：doi:10.19912/j.0254-0096.tynxb.2024-1927
  CLC： TM615
- Online First：07 April 2026，
  
  Published：2026
- 稿件说明：
移动端阅览
白牧可, 钱志研, 段祥骏, et al. 基于进化算法和长短期记忆网络的光伏阵列多类型复合故障诊断方法[J]. 2026, 47(3): 625-634.
DOI：

白牧可, 钱志研, 段祥骏, et al. 基于进化算法和长短期记忆网络的光伏阵列多类型复合故障诊断方法[J]. 2026, 47(3): 625-634. DOI： doi:10.19912/j.0254-0096.tynxb.2024-1927.

摘要

为提升光伏阵列故障诊断的准确率

提出利用柯西高斯变异人工兔算法（CGARO）来优化长短期记忆网络（LSTM）的策略

以实现对光伏阵列多类型复合故障的高效诊断。首先

为改善人工兔优化（ARO）算法易陷入局部最优的问题

提出一种柯西高斯变异人工兔算法。将CGARO与ARO、麻雀搜索算法（SSA）、灰狼优化算法（GWO）进行对比分析

验证CGARO算法的有效性。然后

将CGARO算法优化LSTM的参数及学习率

建立CGARO-LSTM光伏阵列故障诊断模型

基于4种单一故障和3种多类型复合故障

通过与LSTM、SSA-LSTM、GWO-LSTM和ARO-LSTM进行对比

表明CGARO-LSTM模型具有更优性能

准确率达到97.75%

显著提高了光伏阵列故障诊断的精度。

Abstract

To improve the accuracy of fault diagnosis in photovoltaic arrays

a strategy is proposed to optimize the Long Short-Term Memory network （LSTM） using the Cauchy Gaussian Mutation Artificial Rabbit Algorithm （CGARO） to achieve efficient diagnosis of multiple types of composite faults in photovoltaic arrays. Firstly

in order to the problem of getting trapped in local optima in the artificial rabbit optimization （ARO）

a Cauchy Gaussian mutation artificial rabbit algorithm is proposed. Comparative analysis was conducted between CGARO and ARO

Sparrow Search Algorithm （SSA）

and Grey Wolf Optimization Algorithm（GWO） to verify the effectiveness of CGARO algorithm. Then

the CGARO algorithm was optimized to optimize the parameters and learning rate of LSTM

and a CGARO-LSTM photovoltaic array fault diagnosis model was established. Based on four types of single faults and three types of composite faults

the CGARO-LSTM model was compared with LSTM

SSA-LSTM

GWO-LSTM

and ARO-LSTM. The results showed that the CGARO-LSTM model had better performance

with an accuracy of 97.75%

significantly improving the accuracy of photovoltaic array fault diagnosis.

关键词

Keywords

references

谢琳琳, 朱武, 崔昊杨. 改进遗传优化神经网络的光伏阵列故障诊断[J]. 电源技术, 2022, 46(7): 802-806.

彭雅兰, 李志刚. 太阳能光伏阵列在线故障诊断方法综述[J]. 电器与能效管理技术, 2019(11): 1-7.

VERGURA S.Correct settings of a joint unmanned aerial vehicle and infrared camera system for the detection of faulty photovoltaic modules[J]. IEEE journal of photovoltaics, 2021, 11(1): 124-130.

蒋琳, 苏建徽, 李欣, 等. 基于可见光和红外热图像融合的光伏阵列热斑检测方法[J]. 太阳能学报, 2022, 43(1): 393-397.

PEI T T, LI L, ZHANG J F, et al.Module block fault locating strategy for large-scale photovoltaic arrays[J]. Energy conversion and management, 2020, 214: 112898.

王欢, 徐小力. 一种新型光伏阵列在线故障检测方法研究[J]. 仪器仪表学报, 2015, 36(12): 2765-2772.

LIMA N N, DE FREITAS L C, BUIATTI G M, et al. Low complexity system for real-time determination of current-voltage characteristic of PV modules and strings[C]//2013 Twenty-Eighth Annual IEEE Applied Power Electronics Conference and Exposition (APEC). Long Beach, CA, USA, 2013: 2817-2823.

余玲珍, 杨靖, 龙道银, 等. 典型故障条件下光伏阵列建模与仿真[J]. 电网与清洁能源, 2020, 36(10): 103-111, 118.

刘行行, 帕孜来·马合木提, 程志江, 等. 基于XGBoost的光伏阵列故障诊断方法研究[J]. 电子测量技术, 2023, 46(12): 8-14.

JUFRI F H, OH S, JUNG J.Development of photovoltaic abnormal condition detection system using combined regression and support vector machine[J]. Energy, 2019, 176: 457-467.

孙培胜, 陈堂贤, 程陈, 等. 基于SOA-SVM模型的光伏阵列故障诊断研究[J]. 电源学报, 2025, 23(1): 143-150.

MUSTAFA Z, AWAD A S A, AZZOUZ M, et al. Fault identification for photovoltaic systems using a multi-output deep learning approach[J]. Expert systems with applications, 2023, 211: 118551.

贾嵘, 李云桥, 张惠智, 等. 基于改进BP神经网络的光伏阵列多传感器故障检测定位方法[J]. 太阳能学报, 2018, 39(1): 110-116.

ZHAO Y, BALL R, MOSESIAN J, et al.Graph-based semi-supervised learning for fault detection and classification in solar photovoltaic arrays[J]. IEEE transactions on power electronics, 2015, 30(5): 2848-2858.

戴森柏, 陈志聪, 吴丽君, 等. 利用LSTM和稳态时间序列的光伏阵列故障诊断方法[J]. 福州大学学报(自然科学版), 2022, 50(1): 54-60.

张文军, 林永君, 李静, 等. 基于长短期记忆神经网络的光伏阵列故障诊断[J]. 热力发电, 2021, 50(6): 60-68.

WANG L Y, CAO Q J, ZHANG Z X, et al.Artificial rabbits optimization: a new bio-inspired meta-heuristic algorithm for solving engineering optimization problems[J]. Engineering applications of artificial intelligence, 2022, 114: 105082.

彭自然, 许怀顺, 肖伸平, 肖满生. 基于HPO-CatBoost的光伏阵列故障诊断模型[J]. 太阳能学报. 2025, 46(7): 663-673

张子洵, 魏业文, 张轲钦, 等. 基于ICOA-XGBoost的光伏阵列复合故障诊断研究[J]. 太阳能学报. 2025, 46(5): 251-259.

李斌, 高鹏, 郭自强. 改进蜣螂算法优化LSTM的光伏阵列故障诊断[J]. 电力系统及其自动化学报, 2024, 36(8): 70-78.

钱亮, 黄伟, 杨建卫. 基于HHO-ELM的光伏阵列故障诊断方法研究[J]. 电源技术, 2024, 48(2): 345-350.

LYNN N, SUGANTHAN P N.Heterogeneous comprehensive learning particle swarm optimization with enhanced exploration and exploitation[J]. Swarm and evolutionary computation, 2015, 24: 11-24.

XUE J K, SHEN B.A novel swarm intelligence optimization approach: sparrow search algorithm[J]. Systems science & control engineering, 2020, 8(1): 22-34.

MIRJALILI S, MIRJALILI S M, LEWIS A.Grey wolf optimizer[J]. Advances in engineering software, 2014, 69: 46-61.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

基于SV-CBDE模型的光伏阵列故障诊断方法

基于ISSA-RF算法的光伏阵列故障诊断研究

基于ICOA-XGBoost的光伏阵列复合故障诊断研究

基于梯度提升回归树-自训练贝叶斯优化支持向量机的光伏阵列故障诊断方法

FAULT DIAGNOSIS OF PHOTOVOLTAIC ARRAY BASED ON DIGITAL TWIN AND FUSION NEURAL NETWORK

Related Author

李洋

郭春梅

唐俊浩

由玉文

贺中禄

汪磊磊

许桂敏

宋雨航

Related Institution

School of Control and Computer Engineering, North China Electric Power University

Baoding Key Laboratory of State Detection and Optimization of Integrated Energy System

National Energy Group New Energy Technology Research Institute Co.,Ltd.

Department of Mechanical Engineering, North China Electric Power University

School of Information Engineering, Lanzhou City University

AI问答

⁰