本文已被：浏览 953次 下载 562次
投稿时间：2021-03-23
投稿时间：2021-03-23
中文摘要: 为了实现滚动轴承变工况运行下仍能进行有效的故障诊断, 提出了一种基于二维卷积神经网络的滚动轴承变工况故障诊断方法。该方法将原始信号以及运行载荷这一工况变量作为输入信号, 无需人工提取特征向量, 减少特征提取过程中的损失, 实现端到端检测, 并将该方法与传统卷积神经网络模型进行了实验对比。结果表明, 相较于传统卷积神经网络, 该方法在故障的识别准确率和诊断的实时性上都有很大程度的提升。
Abstract:In order to effectively diagnose the rolling bearing under variable operating conditions, a fault diagnosis method based on two-dimensional convolutional neural network for rolling bearing variable operating conditions is proposed.By using the original signal and operating load as the input signal, no manual operation is required.The feature vector is extracted to reduce the loss in the process of feature extraction and realize end-to-end detection, and is compared with the traditional convolutional network model.The results show that compared with the traditional convolutional neural network, this method has greatly improved the accuracy of fault recognition and the real-time performance of the diagnosis.
keywords: two-dimensional convolution neural network variable conditions fault diagnosis end-to-end detection
文章编号：20221005 中图分类号：TP277 文献标志码：
基金项目:国家自然科学基金(51806135)
引用文本：
潘成龙,应雨龙.基于二维卷积神经网络的滚动轴承变工况故障诊断方法[J].上海电力大学学报,2022,38(1):29-34.
PAN Chenglong,YING Yulong.A Fault Diagnosis Method for Rolling Bearings under Variable Condition Based on Two-dimensional Convolutional Neural Network[J].Journal of Shanghai University of Electric Power,2022,38(1):29-34.
潘成龙,应雨龙.基于二维卷积神经网络的滚动轴承变工况故障诊断方法[J].上海电力大学学报,2022,38(1):29-34.
PAN Chenglong,YING Yulong.A Fault Diagnosis Method for Rolling Bearings under Variable Condition Based on Two-dimensional Convolutional Neural Network[J].Journal of Shanghai University of Electric Power,2022,38(1):29-34.