电子测量与仪器学报

伍济钢,文港,杨康.改进一维卷积神经网络的航空发动机故障诊断方法[J].电子测量与仪器学报,2023,37(3):179-186

改进一维卷积神经网络的航空发动机故障诊断方法

Improved one-dimensional convolutional neural network for aero-engine fault diagnosis

DOI：

英文关键词:one-dimensional convolutional neural network multi-scale module aero-engine fault diagnosis

基金项目:国家自然科学基金(51775181)项目资助

作者	单位
伍济钢	1.湖南科技大学机械设备健康维护湖南省重点实验室
文港	1.湖南科技大学机械设备健康维护湖南省重点实验室
杨康	1.湖南科技大学机械设备健康维护湖南省重点实验室

Author	Institution
Wu Jigang	1.one-dimensional convolutional neural network; multi-scale module; aero-engine; fault diagnosis
Wen Gang	1.one-dimensional convolutional neural network; multi-scale module; aero-engine; fault diagnosis
Yang Kang	1.one-dimensional convolutional neural network; multi-scale module; aero-engine; fault diagnosis

摘要点击次数: 805

全文下载次数: 1399

中文摘要:

针对现有航空发动机故障诊断的 1DCNN 方法缺乏故障频率多尺度特征提取能力以及对原始振动信号时域特征提取不足的问题,通过融合内嵌多尺度层到双通道 1DCNN 提出了改进 1DCNN 的航空发动故障诊断方法。提出了幅值变化速率的方法对振动信号进行时域特征增强,在单通道 1DCNN 基础上增加幅值变化通道作为第二通道,构建双通道 1DCNN,加强 1DCNN 的时域特征提取能力,再改进多尺度模块为内嵌多尺度层并应用于 1DCNN 的第一通道,针对航空发动机故障频率域的多尺度特征进行提取。最后将改进 1DCNN 应用于航空发动机转静碰摩、叶片断裂等故障的诊断,通过对比实验证明了改进 1DCNN 检测的优越性、抗噪性、泛化性以及改进点的可行性。

英文摘要:

To address the problems that the existing 1DCNN method for aero-engine fault diagnosis lacks the multi-scale feature extraction capability of fault frequency and the insufficient extraction of time-domain features of the original vibration signal, improved 1DCNN aero-engine fault diagnosis method is proposed by fusing embedded multiscale layers to dual-channel 1DCNN. The method of amplitude change rate is proposed for the time domain feature enhancement of vibration signals, and the amplitude change channel is added as the second channel on the basis of single-channel 1DCNN to build a dual-channel 1DCNN to strengthen the time domain feature extraction capability of 1DCNN, then the multi-scale module is improved to an embedded multi-scale layer and applied to the first channel of 1DCNN to extract multi-scale features of aero-engine fault frequency. Finally, the improved 1DCNN is applied to the diagnosis of aero-engine transient static rubbing, blade fracture and other faults, and the superiority, noise resistance, generalization of the improved 1DCNN detection and the feasibility of the improvement points are proved through comparative experiments.

查看全文查看/发表评论下载PDF阅读器