基于递归图和预训练迁移学习的电能质量扰动分类OA北大核心
Power Quality Disturbance Classification Based on Recursive Graph and Pre-Trained Transfer Learning
电能质量扰动(power quality disturbances,PQDs)分类任务中深度学习方法的应用越来越广泛.针对实测标签数据不足而仿真数据可以批量生成的特点,提出了一种基于递归图理论和预训练迁移学习的扰动分类方法.首先,使用递归图算法将PQDs信号转换为二维递归图像.接着,使用大量仿真数据对VGG-16深度学习网络进行预训练,并保存模型权重参数.最后,通过迁移学习方法,使用少量实测数据对模型的全连接层进行微调,实现在训练样本数量受限情况…查看全部>>
Applications of deep learning methods in the classification task of power quality disturbances(PQDs)are becoming increas-ingly popular.Aiming at the limited availability of measured label data compared to the ability to generate simulated data in large batches,a disturbance classification method is proposed based on recursive graph theory and pre-trained transfer learning.Firstly,the PQDs signals are transformed into two-dimensional recursive images using th…查看全部>>
王继东;王泽平;张迪
智能电网教育部重点实验室(天津大学),天津 300072智能电网教育部重点实验室(天津大学),天津 300072国网沈阳供电公司,沈阳 110000
动力与电气工程
电能质量扰动分类递归图预训练迁移学习时间序列分类深度学习
classification of power quality disturbancesrecursive graphpre-trainedtransfer learningtime series classificationdeep learning
《南方电网技术》 2025 (2)
48-56,114,10
国家重点研发计划资助项目(2022YFB4200703). Supported by the National Key Research and Development Program of China(2022YFB4200703).
评论