基于SIR多级残差连接密集网络的轴承故障诊断

为了研究旋转机械的滚动轴承在复杂工况下从时变性强、微弱信号中提取特征信息的性能,提出了基于SIR多级残差连接密集网络的轴承故障诊断方法.首先,设计SIR模块,该模块将对输入的数据特征通道赋予不同的权重并拓宽网络的宽度,提取更加重要、更加丰富的特征信息;其次,设计多级残差连接密集网络自适应提取轴承振动信号中的有效特征;最后,构建softmax分类器实现故障分类.通过与多种方法进行对比,实验结果表明,该方法在变噪声、变负荷和变工况下都能够更加准确地检测出故障,对复杂的工况环境更具有鲁棒性和泛化能力.

Bearing fault diagnosis based on SIR multistage residual connection dense network

In order to study the performance of extracting feature information from time-varying and weak signals of rolling bearings in rotating machinery under complex working conditions, a bearing fault diagnosis method based on SIR multi-stage residual connection dense network is proposed. Firstly, the SIR module is designed, which extracts more important and richer feature information by giving different weights to the input data feature channels and broadening the width of the network. Secondly, a multi-stage residual connection dense network is designed to adaptively extract the effective features from the bearing vibration signals. Finally, a softmax classifier is constructed to realize fault classification. Compared with other methods, the experimental results show that the proposed method can detect faults more accurately under variable noise, variable load, and variable working conditions, and has more robustness and generalization ability for complex working conditions.