arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.01992cs.AIcs.LGeess.SP
收藏

TFN:一种嵌入时频变换的可解释神经网络,用于智能故障诊断

TFN: An Interpretable Neural Network with Time-Frequency Transform Embedded for Intelligent Fault Diagnosis

Shanghai Jiao Tong University(上海交通大学)

Qian Chen, Xingjian Dong, Guowei Tu, Dong Wang, Baoxuan Zhao, Zhike Peng

AI总结:

针对CNN黑箱特性限制高可靠故障诊断应用的问题,提出嵌入物理意义时频变换的可解释时频网络TFN,通过核约束的时频卷积层提取故障时频信息,兼顾诊断性能与频域可解释性,且可推广至不同深度CNN。

摘要:

卷积神经网络(Convolutional Neural Networks, CNNs)凭借强大的特征提取与分类能力,被广泛应用于机械系统的故障诊断中。但CNN是典型的黑箱模型,其决策机制尚不明确,这限制了它在高可靠性要求的故障诊断场景中的应用。为解决这一问题,我们提出了一种名为时频网络(Time-Frequency Network, TFN)的新型可解释神经网络,将具有物理意义的时频变换(time-frequency transform, TFT)方法作为自适应预处理层嵌入传统卷积层中。这个被称为时频卷积(time-frequency convolutional, TFconv)层的预处理层,通过精心设计的核函数进行约束,以提取与故障相关的时频信息。它不仅提升了诊断性能,还从频域层面揭示了CNN预测的逻辑基础。不同的TFT方法对应TFconv层不同的核函数。本研究考虑了四种典型的TFT方法来构建TFN,并通过三个机械故障诊断实验证明了它们的有效性和可解释性。实验结果还表明,所提出的TFconv层可以轻松推广到其他不同深度的CNN中。TFN的代码可在https://github.com/ChenQian0618/TFN 获取。

英文摘要:

Convolutional Neural Networks (CNNs) are widely used in fault diagnosis of mechanical systems due to their powerful feature extraction and classification capabilities. However, the CNN is a typical black-box model, and the mechanism of CNN's decision-making are not clear, which limits its application in high-reliability-required fault diagnosis scenarios. To tackle this issue, we propose a novel interpretable neural network termed as Time-Frequency Network (TFN), where the physically meaningful time-frequency transform (TFT) method is embedded into the traditional convolutional layer as an adaptive preprocessing layer. This preprocessing layer named as time-frequency convolutional (TFconv) layer, is constrained by a well-designed kernel function to extract fault-related time-frequency information. It not only improves the diagnostic performance but also reveals the logical foundation of the CNN prediction in the frequency domain. Different TFT methods correspond to different kernel functions of the TFconv layer. In this study, four typical TFT methods are considered to formulate the TFNs and their effectiveness and interpretability are proved through three mechanical fault diagnosis experiments. Experimental results also show that the proposed TFconv layer can be easily generalized to other CNNs with different depths. The code of TFN is available on https://github.com/ChenQian0618/TFN.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑