Transformer Fault Identification Method Based on Improved LightGBM Hybrid Integration Model
荆澜涛 1张野 1张彬 2姚晔 3许东 4王亮1
扫码查看
点击上方二维码区域，可以放大扫码查看
作者信息
1. 沈阳工程学院电力学院,沈阳 110136
2. 国网辽宁省电力有限公司电力科学研究院,沈阳 110000
3. 国网辽宁省电力有限公司检修分公司,沈阳 110003
4. 国网辽宁省电力有限公司实业分公司,沈阳 110004
折叠
摘要
针对变压器故障识别方法在处理不均衡故障数据时存在较大偏差的问题,构建了一种基于改进轻量级梯度提升机的混合集成模型,用以变压器故障识别.首先,提出一种结合梯度调和损失函数和交叉熵损失函数的改进轻量级梯度提升机(gradient harmonizing mechanism loss and cross entropy loss improved light gradient boosting machine,GCLightGBM),提升模型对数据集中少数样本的关注度.然后,针对GCLightGBM中参数特异性取值影响模型识别能力的问题,提出一种基于GCLightGBM的混合集成模型,进一步提高其准确率的同时,确保模型对现实多变不均衡数据集依然保持良好的准确率.实验结果表明,GCLightGBM可有效解决少数类样本准确率低的问题,整体准确率高达0.911.且针对其他多变不均衡数据集,基于GCLightGBM混合集成模型故障识别方法平均准确率高达0.988.
Abstract
There is a significant bias when imbalanced fault data are dealt with by transformer fault identification methods.To solve this problem,we have built a hybrid ensemble model based on an improved lightweight gradient boosting ma-chine.First,we propose a gradient harmonizing mechanism loss and cross entropy loss improved light gradient boosting machine(GCLightGBM).This approach enhances the model's attention to minority samples in the dataset.Then,to ad-dress the issue of parameter specificity affecting the model's recognition capability in GCLightGBM,we propose a hybrid ensemble model based on GCLightGBM.This model further improves accuracy while ensuring good performance on re-al-world varied and imbalanced datasets.The experimental results show that GCLightGBM can effectively solve the problem of low accuracy of minority samples,and the overall accuracy is as high as 0.911.In addition,for other variable and unbalanced datasets,the fault identification method based on GCLightGBM hybrid ensemble model has an average accuracy of 0.988.
关键词
变压器/不均衡样本/故障识别/梯度调和损失函数/Stacking集成框架
Key words
transformer/unbalanced samples/fault identification/gradient harmonic loss function/Stacking integration framework
维普
万方数据