基于多元提升核神经网络的机械故障诊断方法及其特征提取可解释性研究

doi:10.3901/JME.2024.12.051

摘要/Abstract

摘要： 以卷积神经网络为代表的深度学习方法为机械故障诊断大数据分析与处理提供有效工具，但其底层逻辑和物理内涵等“黑盒”问题破解是发展可信、安全、可靠人工智能及机械故障智能诊断方法的一个重要研究方向。提升多小波框架是一个天然多通道卷积过程，基于多小波基函数内积匹配思想可有效提取隐藏于背景噪声下多种故障特征。因此，将提升多小波理论引入卷积神经网络，提出基于多元提升核神经网络的机械故障诊断方法并探讨其底层多通道卷积下故障特征提取机理。首先，该网络以提升多小波框架为底层构架设计自适应提升多小波层，并在提升多小波理论数学约束下构造兼备重要信号处理特性的多元提升核，通过单参数训练高效精准完成多故障特征匹配提取。其次，通过仿真试验研究该网络基于内积匹配原理的物理内涵，探讨训练过程中多元提升核波形演化规律并研究其多通道卷积运行机理、网络映射关联含义等特征提取可解释性问题。最后，试验验证表明该方法对同工况类间差异小、多工况类内差异大特性下行星齿轮箱故障识别表现出优异诊断准确性、稳定性和抗噪性，工程应用表明该方法对高精密天线指向机构微弱和复合故障识别也具备精确诊断能力。

关键词: 卷积神经网络, 提升多小波, 可解释性, 特征提取

Abstract: Deep learning method represented by convolutional neural network(CNN) provides an effective tool for big data analysis and processing of mechanical fault diagnosis, but the crack at “black box” issue is one of the important research fields of credible, safe and reliable artificial intelligence and its mechanical fault intelligence diagnosis methods. Lifting multiwavelet framework is a natural multichannel convolution process, and could effectively extract multiple fault features hidden in background noise based on the idea of multiwavelet inner product matching. Therefore, this paper introduces the lifting multiwavelet theory into CNN, proposes the neural network driven by multiple lifting kernels for mechanical fault diagnosis, and discusses the fault feature extraction mechanism for its underlying multichannel convolution. Firstly, the network designs an adaptive lifting multiwavelet layer by lifting multiwavelet framework as the underlying architecture. Multiple lifting kernels are constructed with important signal processing characteristics by the mathematical constraints of lifting multiwavelet theory. Multiple fault feature matching and extraction could be accurately and efficiently achieved by training a single parameter. Secondly, the physical connotation of the network based on the inner product matching principle is studied by simulation experiments. The waveform evolution law of multiple lifting kernels in the training process is discussed. The interpretability problems for feature extraction such as the operation mechanism of multichannel convolution and relationship meaning of network mapping are studied. Finally, the experimental case shows that the method has nice diagnostic accuracy, stability and anti-noise for fault identification of planetary gearboxes with small inter-class differences among the same working conditions and large intra-class differences within multiple working conditions. Meanwhile, the engineering application shows that the method also has accurate diagnosis ability for weak and multiple fault identification of high precision antenna pointing mechanism.

Key words: convolutional neural network, lifting multiwavelets, interpretability, feature extraction

中图分类号:

TH17

袁静, 任港星, 蒋会明, 赵倩, 魏臣隽, 朱骏. 基于多元提升核神经网络的机械故障诊断方法及其特征提取可解释性研究[J]. 机械工程学报, 2024, 60(12): 51-64.

YUAN Jing, REN Gangxing, JIANG Huiming, ZHAO Qian, WEI Chenjun, ZHU Jun. Neural Network Driven by Multiple Lifting Kernels for Mechanical Fault Diagnosis and Its Interpretability Research of Feature Extraction[J]. Journal of Mechanical Engineering, 2024, 60(12): 51-64.

参考文献

[1] 雷亚国，贾峰，孔德同，等. 大数据下机械智能故障诊断的机遇与挑战[J]. 机械工程学报，2018，54(5)：94-104. LEI Yaguo，JIA Feng，KONG Detong，et al. Opportunities and challenges of machinery intelligent fault diagnosis in big date era[J]. Journal of Mechanical Engineering，2018，54(5)：94-104.
[2] 陈雪峰，訾艳阳. 智能运维与健康管理[M]. 北京：机械工业出版社，2018. CHEN Xuefeng，ZI Yanyang. Intelligent operation and health management[M]. Beijing：China Machine Press，2018.
[3] 姜洪开，邵海东，李兴球. 基于深度学习的飞行器智能故障诊断方法[J]. 机械工程学报，2019，55(7)：27-34. JIANG Hongkai，SHAO Haidong，LI Xingqiu. Deep learning theory with application in intelligent fault diagnosis of aircraft[J]. Journal of Mechanical Engineering，2019，55(7)：27-34.
[4] CHEN Zhuyun，ALEXANDRE M，LI Weihua，et al. A deep learning method for bearing fault diagnosis based on cyclic spectral coherence and convolutional neural networks[J]. Mechanical Systems and Signal Processing，2020，140：106683.
[5] 叶壮，余建波. 基于多通道加权卷积神经网络的齿轮箱振动信号特征提取[J]. 机械工程学报，2021，57(1)：110-120. YE Zhuang，YU Jianbo. Feature extraction of gearbox vibration signals based on multi-channels weighted convolutional neural network[J]. Journal of Mechanical Engineering，2021，57(1)：110-120.
[6] PAN Jun，ZI Yanyang，CHEN Jinglong，et al. LiftingNet：A novel deep learning network with layerwise feature learning from noisy mechanical data for fault classification[J]. IEEE Transactions on Industrial Electronics，2018，65：4973-4982.
[7] LI Tianfu，ZHAO Zhibin，SUN Chuang，et al. WaveletKernelNet：An interpretable deep neural network for industrial intelligent diagnosis[J]. IEEE Transactions on Systems，Man，and Cybernetics：Systems，2022，52：2302-2312.
[8] YUAN Jing，CAO Shuwei，REN Gangxing，et al. LW-Net：An interpretable network with smart lifting wavelet kernel for mechanical feature extraction and fault diagnosis[J]. Neural Computing and Applications，2022，34：15661-15672.
[9] ZHAO Zhibin，LI Tianfu，AN Botao，et al. Model-driven deep unrolling：Towards interpretable deep learning against noise attacks for intelligent fault diagnosis[J]. ISA Transactions，2022，129：644-662.
[10] WANG Dong，CHEN Yikai，SHEN Changqing，et al. Fully interpretable neural network for locating resonance frequency bands for machine condition monitoring[J]. Mechanical Systems and Signal Processing，2022，168：108673.
[11] 何正嘉，袁静，訾艳阳. 机械故障诊断的内积变换原理与应用[M]. 北京：科学出版社，2012. HE Zhengjia，YUAN Jing，ZI Yanyang. Principle and application of inner product transformation in mechanical fault diagnosis[M]. Beijing：Science Press，2012.
[12] AVERBUCH A Z，ZHELUDEV V A，COHEN T. Multiwavelet frames in signal space originated from Hermite splines[J]. IEEE Transactions on Signal Processing，2007，55(3)：797-808.
[13] HONG Lianhuan，LIU Xiaobo，ZUO Hongyan. Compound faults diagnosis based on customized balanced multiwavelets and adaptive maximum correlated kurtosis deconvolution[J]. Measurement，2019，146：87-100.
[14] YUAN Jing，LUO Liangjie，JIANG Huiming，et al. An intelligent index-driven multiwavelet feature extraction method for mechanical fault diagnosis[J]. Mechanical Systems and Signal Processing，2023，188：109992.
[15] JIA Feng，LEI Yaguo，LIN Jing，et al. Deep neural networks：A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data[J]. Mechanical Systems and Signal Processing，2016，72：303-315.
[16] 袁静，何正嘉，訾艳阳. 基于提升多小波的机电设备复合故障分离和提取[J]. 机械工程学报，2010，46(1)：79-85，91. YUAN Jing，HE Zhengjia，ZI Yanyang. Separation and extraction of electromechanical equipment compound faults using lifting multiwavelets[J]. Journal of Mechanical Engineering，2010，46(1)：79-85，91.
[17] YUAN Jing，WANG Yu，PENG Yizhen，et al. Weak fault detection and health degradation monitoring using customized standard multiwavelets[J]. Mechanical Systems and Signal Processing，2017，94：384-399.
[18] SHI Junchuan，PENG Dikang，PENG Zhongxiao，et al. Planetary gearbox fault diagnosis using bidirectional- convolutional LSTM networks[J]. Mechanical Systems and Signal Processing，2022，162：107996.
[19] 赵建华，袁静，周郁，等. 归一化小波能量熵的弹上伺服机构传动链动态可靠性评估[J]. 制导与引信，2016，37(3)：47-51. ZHAO Jianhua，YUAN Jing，ZHOU Yu，et al. Dynamic reliability evaluation of transmission chain of missile servo mechanism based on normalized wavelet energy entropy[J]. Guidance and Fuze，2016，37(3)：47-51.
[20] 王家鑫，周郁，袁静，等. 多小波变换在导引头伺服机构信号降噪与缺陷识别中的应用研究[J]. 制导与引信，2013，34(4)：1-4. WANG Jiaxin，ZHOU Yu，YUAN Jing，et al. Application research on multiwavelet transforms for signal denoising and defect identification of seeker servo mechanism[J]. Guidance and Fuze，2013，34(4)：1-4.
[21] MAATEN L，HINTON G. Visualizing data using t-SNE[J]. Journal of Machine Learning Research，2008，9(11)：2579-2605.