测试技术学报2025，Vol.39Issue(6)：623-627,5.DOI:10.62756/csjs.1671-7449.2025069
电机故障诊断正则增强图卷积方法研究
Study on Regularized Enhanced Graph Convolution Method for Motor Fault Diagnosis
摘要
Abstract
Vibration signals are important indicators for evaluating the current motor state and are often used to analyze and judge the potential faults of motors.However,due to the sparse distribution of fault signals,the current deep learning-based methods are more likely to predict stable states accurately rather than fault states.To address the above problem,a novel fault diagnosis model for motors based on regu-larized enhanced graph convolutional neural networks was proposed by researching the motor fault diagno-sis task.With the assistance of the encoded motor state correlations and the introduced regularized enhanced structure,the model can improve its prediction ability for various fault types.The experimental results show that compared with traditional deep learning methods,the proposed method has good accu-racy improvement on the motor fault diagnosis dataset,verifying the effectiveness of the proposed model.Graph convolutional neural networks can mine the intrinsic correlations between long-range signals in sig-nal sequences.By combining with the regularized structure,they have broad application prospects in vari-ous industrial time-series tasks.关键词
电机信号/故障诊断/图卷积网络/正则增强/诊断模型Key words
motor signal/fault diagnosis/graph convolutional network/regularized enhancement/diag-nostic model分类
信息技术与安全科学引用本文复制引用
吕栋腾,李俊雨..电机故障诊断正则增强图卷积方法研究[J].测试技术学报,2025,39(6):623-627,5.基金项目
陕西国防学院科研计划资助项目(Gfy25-02) （Gfy25-02）
陕西省教育厅科技处资助项目(21JK0508) （21JK0508）
