基于MobileNet的电缆局部放电模式识别方法  

Partial discharge pattern recognition method of cable based on MobileNet

作　　者：高鹏 刘嘉良 栾军 沈道义 邹华菁 GAO Peng;LIU Jiaiang;LUAN Jun;SHEN Daoyi;ZOU Huajing(Qingdao Haijian Intelligent Technology Co.,Ltd.,Qingdao 266237,China;Shanghai Gelubu Technology Co.,Ltd.,Shanghai 201210,China;School of Electronics and Information Engineering,Shanghai University of Electric Power,Shanghai 201306,China)

机构地区：[1]青岛海检智能科技有限公司,山东青岛266237 [2]上海格鲁布科技有限公司,上海201210 [3]上海电力大学电子与信息工程学院,上海201306

出　　处：《电子设计工程》2023年第21期93-98,共6页Electronic Design Engineering

摘　　要：针对传统方法判别电缆局部放电类型非常耗时,且准确率较低等问题,提出了一种基于MobileNet的电缆局部放电模式识别方法。对电缆高频局部放电带电检测仪器采集到的各类PRPD图谱进行预处理与数据增强,形成图谱库;将预先训练好的MobileNetV1模型中的权值迁移到局部放电的新任务中,对模型进行网络结构和权值的微调;对迁移后的新模型进行训练,将训练得到的识别率最高的模型作为测试模型,并对测试集中的PRPD图谱进行测试。实验结果表明,该算法的识别准确率可达96.4%,并有效提升了训练的收敛速率。将该算法应用于基于安卓设备的智能局部放电巡检仪,在实际场景下,能够实现局部放电缺陷类型的快速识别,且识别准确率达到95%以上。Aiming at the problem that the traditional methods to recognize the types of partial discharge in cables are time-consuming with low accuracy,a method based on MobileNet is proposed.The various PRPD patterns collected by cable high-frequency partial discharge detection instrument are preprocessed and data enhanced to form PRPD pattern library.The weights in the pre-trained MobileNetV1 model are transferred to the new task of partial discharge,and the network structure and weights of the model are fine-tuned.The new model after migration is trained,the model with the highest recognition rate is used as the test model,and the PRPD patterns in the test set are tested.The experiment shows that the recognition accuracy of the algorithm can reach 96.4%,and the training convergence rate is effectively improved.Applying the algorithm to the intelligent partial discharge detection instrument based on Android devices,in the real scene,it can realize the rapid recognition of partial discharge types,and the recognition accuracy rate can reach more than 95%.

关 键 词：局部放电 深度可分离卷积 迁移学习 模式识别 智能巡检仪 

分 类 号：TN98[电子电信—信息与通信工程]