基于集成SAO优化互相关熵极限学习机模型的变压 器故障诊断方法

孙世明; 岑红星; 白建民; 冯雪松; 焦昆; 马文涛

孙世明,岑红星,白建民,冯雪松,焦昆,马文涛.基于集成SAO优化互相关熵极限学习机模型的变压器故障诊断方法[J].电测与仪表,2024,61(9):56-64.
SUN Shiming,CEN Hongxing,FAN Xuesong,Fen Xuesong,JIAO Kun,MA Wentao.Transformer fault diagnosis method based on integrated correntropy extreme learning machine model optimized by SAO[J].Electrical Measurement & Instrumentation,2024,61(9):56-64.

基于集成SAO优化互相关熵极限学习机模型的变压器故障诊断方法

Transformer fault diagnosis method based on integrated correntropy extreme learning machine model optimized by SAO

DOI：10.19753/j.issn1001-1390.2024.09.007

中文关键词: 电力变压器故障诊断集成学习极限学习机互相关熵损失雪消融优化器

英文关键词:power transformer, fault diagnosis, integrated learning, extreme learning machine, correntropy loss, snow ablation optimizer

基金项目:国家自然科学基金资助项目（61976175,U21A20485）

作者中文名	作者英文名	单位
孙世明	SUN Shiming	南瑞集团有限公司（国网电力科学研究院有限公司）；国电南瑞南京控制系统有限公司；国电南瑞科技股份有限公司；电网运行风险防御技术与装备全国重点实验室
岑红星	CEN Hongxing	南瑞集团有限公司（国网电力科学研究院有限公司）；国电南瑞科技股份有限公司
白建民	FAN Xuesong	南瑞集团有限公司（国网电力科学研究院有限公司）；国电南瑞科技股份有限公司
冯雪松	Fen Xuesong	南瑞集团有限公司（国网电力科学研究院有限公司）；国电南瑞科技股份有限公司
焦昆	JIAO Kun	南瑞集团有限公司（国网电力科学研究院有限公司）；国电南瑞科技股份有限公司
马文涛	MA Wentao	西安理工大学电气工程学院

摘要点击次数: 442

中文摘要:

针对基于传统机器学习的变压器故障诊断方法在数据不平衡、训练数据集存在离群值等条件下稳健性弱和泛化能力不强等问题，提出一种稳健集成学习模型用于实现电力变压器的高精度故障诊断。首先针对离群值对模型稳健性的影响，将互相关熵损失(correntropy loss, CL)引入极限学习机(extreme learning machine, ELM)框架并应用梯度法获得最优解，以构建稳健学习模型CLELM，并利用雪消融优化器(snow ablation optimizer, SAO)优化CLELM的隐含层权重和偏差，以进一步改进其性能。其次，为了增强模型的泛化能力，将多个SAO-CLELM进行加权融合以构成稳健集成学习模型。最后，针对变压器故障数据集不平衡问题，采用合成少数类过采样技术对数据进行扩充，并应用平衡化后的数据训练集成SAO-CLELM模型以实现故障诊断。在两种故障测试集下对所提集成SAO-CLELM模型的故障诊断性能进行了验证，实验结果表明所提模型能获得准确的故障分类结果，说明其具有较高的稳健性和泛化性。

英文摘要:

To address the weak robustness and limited generalization capability of traditional machine learning-based transformer fault diagnosis methods under conditions such as data imbalance and the presence of outliers in the training dataset, this paper proposes a robust ensemble learning model for achieving high-accuracy fault diagnosis of power transformers. Firstly, to mitigate the impact of outliers on model robustness, the correntropy loss (CL) is introduced into the traditional extreme learning machine (ELM) framework, and the gradient-based optimization is used to obtain the optimal solution, which results in a novel robust learning model, called CL-enhanced ELM (CLELM). Additionally, the snow ablation optimizer (SAO) is employed to optimize the hidden layer weights and biases of the CLELM, further improving its performance. Secondly, to enhance the generalization capability of the model, multiple SAO-CLELM models are weighted and combined to form a robust ensemble learning model. Finally, to address the data imbalance issue in the transformer fault dataset, the synthetic minority over-sampling technique (SMOTE) is employed to augment the data, and the balanced training data is used to train the ensemble SAO-CLELM model for fault diagnosis classification. The fault diagnostic performance of the proposed integrated SAO-CLELM model is validated under two different fault test sets, and the experimental results demonstrate that the proposed model can achieve accurate fault classification results, indicating its high level of robustness and generalization ability.

查看全文查看/发表评论下载PDF阅读器

关闭