摘要
【目的】针对滚动轴承微弱故障难以识别的问题,提出了一种基于MR-DCA的滚动轴承故障诊断方法。【方法】利用最大相关峭度解卷积以及共振稀疏分解的方法对输入样本进行预处理,可以有效地滤除原信号中的噪声,突出故障冲击成分。将所获得的故障分量的二维时频图以及原始信号作为网络的训练样本,经两个特征学习模块后,使用注意力机制对输入特征进行筛选,通过权值重分配可以有效地提高模型计算效率和识别精度。为了验证模型性能,使用某大学的滚动轴承微弱故障数据进行故障诊断分析,同时开展消融实验,对诊断模型各个模块的有效性进行验证。【结果】结果表明,所提出的方法识别准确率更高,且具有更快的训练速度和迭代速度。【结论】所提模型在进行滚动轴承微弱故障诊断时可以实现良好的诊断性能。
【Objective】The MR-DCA based rolling bearing fault diagnosis method is proposed for the problem that rolling bearing weak faults are difficult to identify.【Method】The input samples are pre-processed by using the maximun correlated kurtosis deconvolution and resonance-based sparse signal decomposition,which can effectively filter out the noise of original signal and feature the fault impact components.The obtained two-dimensional time-frequency diagrams of the fault components and the original signal are used as the training samples of the network,and after two feature learning modules,the input features are filtered by using the attention mechanism,and the model computational efficiency and recognition accuracy can be effectively improved through weight reassignment.In order to verify the model performance,a rolling bearing weak fault dataset is used for fault diagnosis analysis,while ablation experiments are carried out to verify the effectiveness of each module of the diagnostic model.【Result】The results show that the proposed method has higher recognition accuracy,faster training speed and faster iteration speed.【Conclusion】The proposed model can achieve good diagnostic performance in the diagnosis of rolling bearing weak faults.
作者
肖乾
李楷文
周生通
汪寒俊
宾浩翔
常运清
Xiao Qian;Li Kaiwen;Zhou Shengtong;Wang Hanjun;Bin Haoxiang;Chang Yunqing(Key Laboratory of Conveyance and Equipment of the Ministry of Education of China,East China Jiaotong University,Nanchang 330013,China)
出处
《华东交通大学学报》
2024年第1期113-119,共7页
Journal of East China Jiaotong University
基金
国家自然科学基金项目(51975210,52065022)
江西省自然科学基金项目(20202BABL204036)。
关键词
最大相关峭度解卷积
共振稀疏分解
卷积神经网络
注意力机制
maximun correlated kurtosis deconvolution
resonance-based sparse signal decomposition
convolutional neural networks
attention mechanism
