基于改进深度残差收缩网络的电缆早期故障识别  

Early Fault Identification of Cable Based on Improved Deep Residual Shrinkage Network

作　　者：唐丹 吴浩 蔡源 郑超文 TANG Dan;WU Hao;CAI Yuan;ZHENG Chao-wen(School of Automation and Information Engineering,Sichuan University of Light and Chemical Technology,Yibin 644000,China;Artificial Intelligence Key Laboratory of Sichuan Province,Yibin 644000,China)

机构地区：[1]四川轻化工大学自动化与信息工程学院,宜宾644000 [2]人工智能四川省重点实验室,宜宾644000

出　　处：《科学技术与工程》2024年第28期12159-12168,共10页Science Technology and Engineering

基　　金：四川省科技厅项目(2021YFG0313,2022YFS0518,2022ZHCG0035);人工智能四川省重点实验室项目(2019RYY01);四川轻化工大学人才引进项目(2021RC12);自贡市科技局项目(2019YYJC02,2020YGJC16);四川轻化工大学研究生创新基金(Y2023278)。

摘　　要：电缆早期故障的多次发生易造成电缆出现永久性故障,给电网的稳定运行带来严重的影响。为了在永久性故障发生前准确识别出电缆早期故障,提出一种基于改进深度残差收缩网络的电缆早期故障识别方法。首先通过改进的完全自适应噪声经验模态分解方法(improved complete ensemble empirical mode decomposition with adaptive noise,ICEEMDAN)进行故障信号处理,并利用相关系数筛选本征模态函数(intrinsic mode functions,IMF);然后对IMF分量求其复合多尺度排列熵作为进一步的特征提取,以构建特征数据集;最后利用改进的收缩模块,多尺度卷积层、Self-Attention和SimAM注意力机制对深度残差收缩网络进行改进。使用改进的深度残差收缩网络进行电缆早期故障识别实验。实验结果表明:该算法能准确识别出电缆早期故障,且具有一定的抗干扰能力。The frequent occurrence of early cable faults easily leads to the occurrence of permanent cable faults,causing serious impacts on the stable operation of the power grid.In order to accurately identify early cable faults before permanent failures occur,a method based on an improved deep residual contraction network for early cable fault identification was proposed.Firstly,the improved complete ensemble empirical mode decomposition with adaptive noise(ICEEMDAN)method was employed for fault signal processing,and correlation coefficients were utilized for filtering intrinsic mode functions(IMF)components.Then,the composite multiscale permutation entropy of the IMF component was calculated for further feature extraction,constructing a feature dataset.Finally,the improved deep residual shrinkage network,incorporating an enhanced shrinkage module,multi-scale convolutional layer,Self Attention,and SimAM attention mechanism,was employed for early cable fault identification experiments.The experimental results show that the algorithm can accurately identify early cable faults and exhibit a certain degree of anti-interference capability.

关 键 词：电缆早期故障 改进的完全自适应噪声经验模态分解方法(ICEEMDAN) 复合多尺度排列熵 改进深度残差收缩网络 故障识别 

分 类 号：TM247[一般工业技术—材料科学与工程]