电子测量与仪器学报

赵迪,王呈.基于改进胶囊网络的运维知识库故障分类方法[J].电子测量与仪器学报,2022,36(5):104-112

基于改进胶囊网络的运维知识库故障分类方法

Fault classification method of operation and maintenance knowledgebase on improved capsule networks

DOI：

英文关键词:fault classification FPN DRSN capsule networks feature extraction

基金项目:近地面探测技术重点实验室预研基金（6142414180104）、轨道交通运行控制系统国家工程技术研究中心开放课题（NERC2019K001）

作者	单位
赵迪	1.江南大学物联网工程学院
王呈	1.江南大学物联网工程学院

Author	Institution
Zhao Di	1.School of Internet of Things Engineering, Jiangnan University
Wang Cheng	1.School of Internet of Things Engineering, Jiangnan University

摘要点击次数: 285

全文下载次数: 754

中文摘要:

针对传统运维知识库不具备图像故障现象识别能力,无法处理非结构化数据的问题,基于深度学习的故障分类网络,提出改进胶囊网络特征提取结构的 Caps-DRFN 算法,实现机电设备运维图像自动分类。首先,针对运维图像存在的多噪声问题, 引入深度残差收缩网络(deep residual shrinkage networks,DRSN)提高模型在含噪声数据上的特征提取效果。然后,针对实际拍摄的运维图像多尺度问题,结合 FPN(feature pyramid networks)算法,实现图像多尺度特征融合提高模型分类准确率。最后,利用胶囊结构构建向量神经元,通过动态路由的特征传递方式,得到分类结构数字胶囊,实现机电设备故障分类。实验结果表明, 相较于传统胶囊网络算法,提出的基于特征融合的 Caps-DRFN 算法准确率提高了 15%且有着更强的鲁棒性。

英文摘要:

Traditional operation and maintenance knowledge base does not have the ability to identify the failure phenomena in the image. Therefore, the knowledge base cannot handle the problem of unstructured data. To tackle this issue, based on fault classification networks in deep learning, an improved capsule network feature extraction structure based Caps-DRFN algorithm is proposed, which can realize automatic classification of operation and maintenance images of electromechanical equipment. Firstly, aiming at the multi-noise problem of operation and maintenance images, the deep residual shrinkage networks (DRSN) are introduced to improve the feature extraction performance of the model on noisy data. Subsequently, for the multi-scale problem of actual shooting operation and maintenance images, through the combination of the feature pyramid networks (FPN) algorithm, the Caps-DRFN realizes image multiscale feature fusion and improves the accuracy of model classification. Finally, the vector neuron is constructed by using the capsule structure, and the digital capsule of the classification structure is obtained through the feature transmission method of dynamic routing. The model realizes the fault classification of electromechanical equipment. The experimental results show that compared with the traditional capsule network algorithm, the accuracy of the proposed Caps-DRFN algorithm based on feature fusion is increased by 15% and it is more robust.

查看全文查看/发表评论下载PDF阅读器