基于卷积脉冲神经网络的故障诊断方法研究

doi:10.16088/j.issn.1001-6600.2021070808

广西师范大学学报（自然科学版） ›› 2022, Vol. 40 ›› Issue (3): 112-120.doi: 10.16088/j.issn.1001-6600.2021070808

基于卷积脉冲神经网络的故障诊断方法研究

马新娜^1,2*, 赵猛^1,2, 祁琳^1,2

1.石家庄铁道大学信息科学与技术学院, 河北石家庄 050043;
2.省部共建交通工程结构力学行为与系统安全国家重点实验室(石家庄铁道大学), 河北石家庄 050043

收稿日期:2021-07-08 修回日期:2021-09-09 出版日期:2022-05-25 发布日期:2022-05-27
通讯作者: 马新娜(1978—), 女, 河北石家庄人, 石家庄铁道大学教授, 博士。E-mail: maxinnamxn@163.com
基金资助:
国家自然科学基金(11790282, 11972236); 河北省自然科学基金(A2021210022); 河北省三三三人才项目(A202101018)

Fault Diagnosis Based on Spiking Convolution Neural Network

MA Xinna^1,2*, ZHAO Men^1,2, QI Lin^1,2

1. School of Information Science and Technology, Shijiazhuang Tiedao University, Shijiazhuang Hebei 050043, China;
2. State Key Laboratory of Mechanical Behavior and System Safety of Traffic Engineering Structures (Shijiazhuang Tiedao University), Shijiazhuang Hebei 050043, China

Received:2021-07-08 Revised:2021-09-09 Online:2022-05-25 Published:2022-05-27

摘要/Abstract

摘要： 深度学习为轴承故障诊断的智能化发展提供了新思路。本文从类脑计算角度出发,设计一种对轴承数据敏感的脉冲神经网络来完成故障数据分类任务。首先采用信号分解的方式提高原始信号特征提取效果,然后对故障信号进行脉冲编码,并采用多分量混合输入方式填充时间步作为神经网络的输入,最后采用卷积脉冲神经网络(SCNN)进行故障分类。为了验证该模型的分类效果,采用西储大学轴承数据集进行验证,分类准确率达到了99.78%。结果表明该轴承数据编码方案可以充分发挥脉冲神经网络时空动力学特征,且该脉冲神经网络模型在轴承故障诊断问题上具有高精度、高效率的特性。本研究有利于促进脉冲神经网络在故障诊断领域的研究和应用。

关键词: 脉冲神经网络, 多模态分解, 滚动轴承, 故障诊断, IIR滤波器

Abstract: Deep learning provides ideas for the intelligent development of bearing fault diagnosis. From the perspective of brain-like computing, this paper designs spiking neural network sensitive to bearing data to complete the task of fault data classification. First, signal decomposition is used to improve the feature extraction effect of the original signal, and then the fault signal is spiking-encoded, and the time step is filled with multi-channel chaotic input as the input of the neural network. Finally, the Spiking convolutional neural network (SCNN) is used. In order to verify the classification effect of the model, a classification experiment is done on the CWRU bearing data set, and the classification accuracy rate reaches 99.78%. The results show that the bearing data encoding scheme can give full play to the spatiotemporal dynamic characteristics of the SNN, and the SNN model has the characteristics of high precision and high efficiency in bearing fault diagnosis. This research is helpful to promote the research and application of SNN in the field of fault diagnosis.

Key words: SNN, multimodal decomposition, rolling bearing, fault diagnosis, IIR filter

中图分类号:

TP183

马新娜, 赵猛, 祁琳. 基于卷积脉冲神经网络的故障诊断方法研究[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 112-120.

MA Xinna, ZHAO Men, QI Lin. Fault Diagnosis Based on Spiking Convolution Neural Network[J]. Journal of Guangxi Normal University(Natural Science Edition), 2022, 40(3): 112-120.

参考文献

[1]余萍,曹洁.深度学习在故障诊断与预测中的应用[J].计算机工程与应用,2020,56(3):1-18.
[2]赵志宏, 赵敬娇, 李晴,等. 基于一维密集连接卷积网络的故障诊断研究[J]. 西南大学学报(自然科学版), 2020,42(12):25-33.
[3]蔺想红,王向文. 脉冲神经网络原理及应用[M]. 北京:科学出版社, 2018:9-10.
[4]胡一凡, 李国齐, 吴郁杰,等. 脉冲神经网络研究进展综述[J]. 控制与决策, 2021,36(1):1-26.
[5]ROY K, JAISWAL A, PANDA P. Towards spike-based machine intelligence with neuromorphic computing[J]. Nature,2019, 575(7784): 607-617.
[6]SHEN J X , SHANG D S , CHAI Y S , et al. Mimicking synaptic plasticity and neural network using memtranstors[J]. Advanced Materials, 2018, 30(12):e1706717.
[7]PRESCOTT S A, SEJNOWSKI T J. Spike-rate coding and spike-time coding are affected oppositely by different adaptation mechanisms[J]. Journal of Neuroscience, 2008, 28(50):13649-13661.
[8]GAUTRAIS J, THORPE S. Rate coding versus temporal order coding: a theoretical approach[J]. Bio Systems, 1998, 48(1/2/3): 57-65.
[9]VAN RULLEN R, THORPE S J. Rate coding versus temporal order coding: what the retinal ganglion cells tell the visual cortex[J]. Neural Computation, 2001, 13(6): 1255-1283.
[10]LU T, LIANG L, WANG X. Temporal and rate representations of time-varying signals in the auditory cortex of awake primates[J]. Nature Neuroscience, 2001,4(11): 1131-1138.
[11]ZUO L, ZHANG L, ZHANG Z H, et al. A spiking neural network-based approach to bearing fault diagnosis[J]. Journal of Manufacturing Systems, 2021,61: 714-724.
[12]尚瑛杰,何虎,杨旭,等.仿生型脉冲神经网络学习算法和网络模型[J].计算机工程与设计,2020,41(5):1390-1397.
[13]MASQUELIER T, THORPE S J. Learning to recognize objects using waves of spikes and spike timing-dependent plasticity[C]// The 2010 International Joint Conference on Neural Networks(IJCNN). Piscataway: IEEE, 2010: 1-8.
[14]SENGUPTA A, YE Y T, WANG R, et al. Going deeper in spiking neural networks: VGG and residual architectures[J]. Frontiers in Neuroscience, 2019, 13: 95.
[15]WU Y J, DENG L, LI G Q, et al. Direct training for spiking neural networks: faster, larger, better[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1):1311-1318.
[16]WU Y J, DENG L, LI G Q, et al. Spatio-temporal backpropagation for training high-performance spiking neural networks[J]. Frontiers in Neuroscience, 2018, 12:331.
[17]GU P J, XIAO R, PAN G, et al. STCA: Spatio-temporal credit assignment with delayed feedback in deep spiking neural networks[C]// Proceedings of 28th International Joint Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2019: 1366-1372.
[18]GÜTIG R, SOMPOLINSKY H. The tempotron: a neuron that learns spike timing-based decisions[J]. Nature Neuroscience,2006, 9(3):420-428.
[19]FANG H W, SHRESTHA A, ZHAO Z Y, et al. Exploiting neuron and synapse filter dynamics in spatial temporal learning of deep spiking neural network[C]// Proceeding of the Twenty-Ninth International Joint Conference on Artificial Intelligence. Yokohama: IJCAI, 2021: 2799-2806.
[20]HAZAN H, SAUNDERS D J, KHAN H, et al. BindsNET: a machine learning-oriented spiking neural networks library in python[J]. Frontiers in Neuroinformatics, 2018, 12: 89.
[21]MOZAFARI M, GANJTABESH M, NOWZARI-DALINI A, et al. SpykeTorch: efficient simulation of convolutional spiking neural networks with at most one spike per neuron[J]. Frontiers in Neuroscience, 2019, 13: 625.
[22]肖雄,王健翔,张勇军,等. 一种用于轴承故障诊断的二维卷积神经网络优化方法[J]. 中国电机工程学报, 2019, 39(15): 4558-4568.
[23]张伟. 基于卷积神经网络的轴承故障诊断算法研究[D]. 哈尔滨:哈尔滨工业大学,2017.
[24]SCHRAUWEN B, VAN CAMPENHOUT J. BSA, a fast and accurate spike train encoding scheme[C]// Proceeding of the International Joint Conference on Neural Networks. Piscataway: IEEE, 2003: 2825-2830.
[25]DELBRUCK T, LICHTSTEINER P. Fast sensory motor control based on event-based hybrid neuromorphic-procedural system[C]// 2007 IEEE International Symposium on Circuits and Systems. Piscataway: IEEE,2007:845-848.
[26]RATHI N, SRINIVASAN G, PANDA P, et al. Enabling deep spiking neural networks with hybrid conversion and spike timing dependent backpropagation[J]. International Conference on Learning Representations. Addis Ababa: ICLR, 2020:1-11.
[27]PETRO B, KASABOV N, KISS R M. Selection and optimization of temporal spike encoding methods for spiking neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 31(2):358-370.
[28]杨琦,陈智才.基于EMD和相关系数法的列车滚动轴承故障诊断方法研究[J].电力机车与城轨车辆,2018,41(3):15-17,23.
[29]李家宁,田永鸿.神经形态视觉传感器的研究进展及应用综述[J].计算机学报,2021,44(6):1258-1286.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于卷积脉冲神经网络的故障诊断方法研究

Fault Diagnosis Based on Spiking Convolution Neural Network

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

Metrics

本文评价

推荐阅读 10

[1]	蒋瑞, 徐娟, 李强. 基于跨域均值逼近的轴承剩余使用寿命预测[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 121-131.
[2]	万雷,罗玉玲,黄星月. 脉冲神经网络硬件系统性能监测平台[J]. 广西师范大学学报（自然科学版）, 2018, 36(1): 9-16.
[3]	林越,刘廷章,陈一凡,金勇,梁立新. 基于AP-HMM混合模型的充电桩故障诊断[J]. 广西师范大学学报（自然科学版）, 2018, 36(1): 25-33.