摘要
针对分布式光伏阵列故障频发、传统随机森林 (random forest, RF) 诊断方法准确率与泛化能力不足的问题,提出一种融合多特征优选与袋外 (out-of-bag, OOB) 误差动态优化的 RF 故障诊断方法。首先,基于光伏电池单二极管等效电路,在 MATLAB/Simulink 中构建光伏阵列仿真模型,模拟短路、开路、阴影遮挡、老化及旁路二极管失效等 5 种典型故障,并提取电压、电流、功率等多维故障特征。进而,引入 OOB 误差作为模型训练过程的动态评估指标,实时监控并优化基学习器集成策略,以提升收敛性能与泛化能力;同时,采用“置换重要性初筛+主成分分析二次降维”的两阶段多特征优选方法,从高维特征中筛选出关键故障特征子集,增强模型鲁棒性。实验结果表明,所提 OOB-RF 模型在测试集上的故障诊断准确率达 95.44%,较传统 RF 法提升 8.12 个百分点,过拟合指数显著降低 51.26%,在分类精度与稳定性方面均表现更优,为分布式光伏系统的智能运维提供了有效解决方案。
Abstract
To address the frequent faults in distributed photovoltaic (PV) arrays and the limitations of traditional random forest (RF) methods in diagnostic accuracy and generalization capability, this paper proposes a fault diagnosis method based
on RF that integrates multi-feature optimization and dynamic out-of-bag (OOB) error optimization. First, a PV array simulation model is constructed in MATLAB/Simulink based on the single-diode equivalent circuit of a PV cell. The model simulates five typical fault types, including short circuit, open circuit, partial shading, aging degradation, and bypass diode failure, and extracts multi-dimensional fault features covering voltage, current, and power etc. Furthermore, the OOB error is introduced as a dynamic evaluation metric during model training to monitor and optimize the ensemble strategy of base learners in real time, thereby improving convergence performance and generalization capability. Simultaneously, a twostage multi-feature optimization strategy—“permutation importance preliminary screening + principal component analysis secondary dimensionality reduction”—is adopted to screen the most critical fault feature subset from the original highdimensional features, enhancing model robustness. Experimental results demonstrate that the proposed OOB-RF model achieves a fault diagnosis accuracy of 95.44% on the test set, which is 8.12 percentage points higher than that of the traditional RF model, while the overfitting index is significantly reduced by 51.26%. The proposed method exhibits superior classification accuracy and stability, providing an effective solution for the intelligent operation and maintenance of distributed PV systems.
关键词
光伏阵列 /
故障诊断 /
随机森林 (RF) 算法 /
袋外 (OOB) 误差 /
多特征优选
Key words
photovoltaic  /
array /
fault  /
diagnosis /
random  /
forest  /
(RF)  /
algorithm /
out-of-bag  /
(OOB)  /
error /
multi-feature optimization
骆守康1, 温克欢1, 张昱波1, 孙晓佳1, 李 扬1, 孙文静1, 李天风2.
基于多特征优选机制与OOB优化的随机森林光伏阵列故障诊断方法[J]. 分布式能源, 0 https://doi.org/10.16513/j.2096-2185.DE.26100426.
LUO Shoukang1, WEN Kehuan1, ZHANG Yubo1, SUN Xiaojia1, LI Yang1, SUN Wenjing1, LI Tianfeng2.
A Random Forest Fault Diagnosis Method for Photovoltaic Arrays Based on Multi-feature Optimization Mechanism and OOB Optimization[J]. Distributed Energy, 0 https://doi.org/10.16513/j.2096-2185.DE.26100426.
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
基金
中国南方电网有限责任公司创新项目 (SZKJXM20222146)