基于神经网络的振动给料机故障诊断算法

doi:10.16265/j.cnki.issn1003-3033.2023.S2.0019

摘要/Abstract

摘要：

为解决振动给料机故障诊断采用传统信号处理方式缺乏自适应性的问题,引入基于自适应一维卷积神经网络(1D-CNN)的故障诊断算法;通过深入分析振动给料机的故障特性,将故障状态的原始振动信号进行预处理,构建训练样本和测试样本;将每个训练样本按照时间划分,作为1D-CNN的输入,在不同时间段内对振动信号的特征进行自适应层级化提取。结果表明:通过引入自适应性,算法能够更灵活地适应振动信号中存在的复杂动态模式。这种自适应性带来了更高的诊断准确度,尤其是在面对振动特性频繁变化或者存在噪声干扰的情况下。通过选取合适的神经网络尺寸,输出针对振动给料机的故障状态的诊断结果,在重叠比例为49%的情况下,准确率高达90.2%。

关键词: 振动给料机, 一维卷积神经网络, 故障诊断, 自适应提取, 重叠比例

Abstract:

To address the lack of adaptability in traditional signal processing methods for vibration feeder fault diagnosis, an adaptive 1D CNN-based fault diagnosis algorithm was introduced. Through an in-depth analysis of the fault characteristics of the vibration feeder, the original vibration signals of fault states were preprocessed to construct training and testing samples. Each training sample was partitioned over time and served as the input for the 1D CNN, enabling adaptive hierarchical extraction of vibration signal features at different time intervals. The results show that by introducing adaptability, the algorithm can adapt more flexibly to complex dynamic patterns in vibration signals. This adaptability results in higher diagnostic accuracy, especially when facing frequent changes in vibration characteristics or the presence of noise interference. After selecting appropriate neural network dimensions, the algorithm outputs diagnostic results for fault states in the vibration feeder. With an overlap ratio of 49%, the accuracy reaches 90.2%.

Key words: vibration feeder, one-dimensional convolutional neural network (1D-CNN), fault diagnosis, adaptive extraction, overlap ratio

中图分类号:

X936

张斌, 张辛忻, 杨海涛. 基于神经网络的振动给料机故障诊断算法[J]. 中国安全科学学报, 2023, 33(S2): 55-59.

ZHANG Bin, ZHANG Xinxin, YANG Haitao. Neural network-based fault diagnosis algorithm for vibration feeder[J]. China Safety Science Journal, 2023, 33(S2): 55-59.

图/表 6

图1

表1

表2

图2

图3

表3

参考文献 15

[1]	王运池. 国内振动给料设备的现状与发展[J]. 煤质技术, 2003(4):29-31.
	WANG Yunchi. Current status and development of vibration feeding equipment in China[J]. Coal Quality Technology, 2003(4): 29-31.
[2]	张洪涛. 电磁振动给料机的故障诊断[J]. 起重运输机械, 1997(5):28-30.
	ZHANG Hongtao. Fault diagnosis of electromagnetic vibration feeder[J]. Lifting and Transportation Machinery, 1997(5): 28-30.
[3]	吴今培. 智能故障诊断技术的发展和展望[J]. 振动·测试与诊断, 1999(5):1-8, 69.
	WU Jinpei. Development and prospects of intelligent fault diagnosis technology[J]. Vibration, Testing and Diagnosis, 1999(5):1-8, 69.
[4]	李红卫, 杨东升, 孙一兰, 等. 智能故障诊断技术研究综述与展望[J]. 计算机工程与设计, 2013, 34(2):632-637.
	LI Hongwei, YANG Dongsheng, SUN Yilan, et al. A review and prospect of intelligent fault diagnosis technology[J]. Computer Engineering and Design, 2013, 34(2): 632-637.
[5]	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. doi: 10.3901/JME.2018.05.094
	LEI Yaguo, JIA Feng, KONG Detong, et al. Opportunities and challenges of mechanical intelligent fault diagnosis under big data[J]. Journal of Mechanical Engineering, 2018, 54(5): 94-104. doi: 10.3901/JME.2018.05.094
[6]	徐红梅. 内燃机振声信号时频特性分析及源信号盲分离技术研究[D]. 杭州: 浙江大学, 2008.
	XU Hongmei. Time-frequency characteristic analysis of vibration and research on source signal blind separation technology of internal combustion engine sound signals[D]. Hangzhou: Zhejiang University, 2008.
[7]	李恒, 张氢, 秦仙蓉, 等. 基于短时傅里叶变换和卷积神经网络的轴承故障诊断方法[J]. 振动与冲击, 2018, 37(19):124-131.
	LI Heng, ZHANG Qing, QIN Xianrong, et al. Bearing fault diagnosis method based on short-time Fourier transform and convolutional neural network[J]. Vibration and Shock, 2018, 37(19): 124-131.
[8]	李舜酩, 郭海东, 李殿荣. 振动信号处理方法综述[J]. 仪器仪表学报, 2013, 34(8):1907-1 915.
	LI Shunming, GUO Haidong, LI Dianrong. A review of vibration signal processing methods[J]. Chinese Journal of Scientific Instrument, 2013, 34(8):1907-1 915.
[9]	DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2013, 62(3): 531-544.
[10]	TANG Zhiguo, ZHANG Fuyao, MA Yan. Adaptive dynamic programming based trajectory tracking control of mobile missile loading manipulator[J]. Control Theory & Applications, 2021, 38(9):1442-1 451.
[11]	HE W, CHEN Y H, ZHAO Y. Adaptive neural network control of an uncertain robot with full-state constraints[J]. IEEE Transactions on Cybernetics, 2016, 46(3): 620-629. doi: 10.1109/TCYB.2015.2411285 pmid: 25850098
[12]	CAO Y, HUANG J. Neural-network-based nonlinear model predictive tracking control of a pneumatic muscle actuator-driven exoskeleton[J]. IEEE/CAA Journal of Automatica Sinica, 2020, 7(6):1478-1 488.
[13]	王照伟, 钟晓勇, 宋向金, 等. 自适应特征选择的多扩张卷积网络轴承故障诊断[J]. 信息与控制, 2023:1-12.
	WANG Zhaowei, ZHONG Xiaoyong, SONG Xiangjin, et al. Fault diagnosis of bearings based on adaptive feature selection in multi-expansion convolutional networks[J]. Information and Control, 2023:1-12.
[14]	范云鹏, 郭小娥. 复合函数求导的方法探析[J]. 现代商贸工业, 2021, 42(19):126-127.
	FAN Yunpeng, GUO Xiao'e. Analysis of methods for derivative calculation of composite functions[J]. Modern Commerce and Trade Industry, 2021, 42(19): 126-127.
[15]	焦瑞强, 赵联文, 刘赪, 等. 基于贝叶斯学习的惩罚因子的选择[J]. 统计与决策, 2017(14):10-14.
	JIAO Ruiqiang, ZHAO Lianwen, LIU Che, et al. Selection of penalty factor based on Bayesian learning[J]. Statistics and Decision, 2017(14): 10-14.

网络结构	核尺寸	步长	核数目	输出尺寸
卷积层1	15	1	32	1 010×32
池化池1	2	1	32	505×32
卷积层2	6	1	64	500×64
池化池2	2	1	32	250×64
扁平化层	—	—	—	16 000×1
全连接层1	—	—	—	128×1
全连接层2	—	—	—	32×1
输出层	—	—	—	5×1

算法	最终选取重叠比例	最大准确率
短时傅里叶	56	85.9
EMD分析	52	88.5
本文算法	49	90.2