Fault diagnosis of rigid guide based on wavelet transform and improved convolutional neural network
-
摘要: 现有刚性罐道故障诊断方法有的仅适用于小样本数据集，有的虽适用于大样本数据集，但忽略了实际工作环境中的多工况背景。基于卷积神经网络的刚性罐道故障诊断方法存在数据和运算量庞大，易产生过拟合等问题。针对上述问题，提出了一种基于小波变换和改进卷积神经网络的刚性罐道故障诊断方法。首先，在刚性罐道设置错位与间隙2种缺陷，采集多工况下提升容器振动加速度信号。其次，利用小波变换将采集的振动加速度信号转换为二维时频图像，采用试凑法最终确定经Complex Morlet 小波基函数处理后的二维时频图像的时间和频率分辨率最佳。然后，通过改进卷积神经网络模型结构，即保留第1层和第5层池化层，将第2，3，4层池化层替换为小尺度卷积层，以防止过拟合现象。最后，将二维时频图像输入改进后的卷积神经网络模型。实验结果表明: ① 改进模型经过训练后，在训练集上的平均准确率为99%左右，在测试集上的平均准确率为99.5%。② 当数据训练至200步后，改进模型的准确率达99%以上，改进模型的损失函数值趋近于0，说明改进模型收敛性能较好，模型的泛化能力得到了增强，在学习过程中对于过拟合的抑制效果明显。③ 在验证集混淆矩阵上，间隙缺陷和错位缺陷识别准确率为100%，无缺陷识别准确率为92%。④ 与EMD−SVD−SVM、小波包−SVM、EMD−SVD−BP神经网络、小波包−BP神经网络相比，基于小波变换和改进卷积神经网络的刚性罐道故障诊断方法准确率达99%。Abstract: Some of the existing fault diagnosis methods for rigid guide are only suitable for small sample data sets. Although some methods are suitable for large sample data sets, they ignore the multi-condition background in the actual working environment. The method of rigid guide fault diagnosis based on the convolutional neural network has the problems of huge data and computation, and easy to produce over-fitting. In order to solve these problems, a fault diagnosis method of rigid guide based on wavelet transform and improved convolutional neural network is proposed. Firstly, two kinds of defects, dislocation and gap, are set in the rigid cage guide. The vibration acceleration signals of the hoisting container under multiple working conditions are collected. Secondly, the collected vibration acceleration signals are converted into two-dimensional time-frequency images by wavelet transform. The time and frequency resolution of the two-dimensional time-frequency images processed by the Complex Morlet wavelet basis function is determined to be the best by trial and error method. Thirdly, the structure of the convolutional neural network model is adjusted. The first pooling layer and the fifth pooling layer are reserved. The second pool layer, the third pooling layer and the fourth pooling layer are replaced by small-scale convolutional layers to prevent the over-fitting phenomenon. Finally, the two-dimensional time-frequency image is input into the improved convolutional neural network model. The experimental results show the following points. ① After training, the average accuracy of the improved model is about 99% on the training set and 99.5% on the test set. ② When the training data reaches 200 steps, the accuracy of the improved model is more than 99%, and the loss function of the improved model approaches 0. These results show that the improved model has good convergence performance, and the generalization of the model is enhanced. The inhibition effect on over-fitting in the learning process is obvious. ③ On the confusion matrix of the validation set, the identification rate of gap defect and dislocation defects is 100%. The identification rate of no defect is 92%, and 8% of the defect are mistakenly identified as gap defects. ④ Compared with EMD-SVD-SVM, wavelet packet-SVM, EMD-SVD-BP neural network and wavelet packet-BP neural network, the accuracy of rigid guide fault diagnosis method based on wavelet transform and the improved convolutional neural network reaches 99%.
-
-
![]()
图 1 基于小波变换和改进卷积神经网络的刚性罐道缺陷诊断过程
Figure 1. Fault diagnosis process of rigid guide based on wavelet transform and improved convolutional neural network
![]()
图 5 错位缺陷振动加速度信号二维时频图像
Figure 5. Two-dimensional time-frequency image of dislocation defect vibration acceleration signal
![]()
图 6 间隙缺陷时振动加速度信号二维时频图像
Figure 6. Two-dimensional time-frequency image of gap defect vibration acceleration signal
![]()
图 8 改进神经网络模型的准确率
Figure 8. Accuracy rates of improved convolutional neural network model
![]()
图 9 改进神经网络模型准确率与损失函数值变化趋势
Figure 9. Accuracy and loss function values change trend of improved convolutional neural network model
-
[1] 吴波. 立井提升刚性罐道系统健康监测研究[D]. 徐州: 中国矿业大学, 2019. WU Bo. Research on health monitoring of vertical shaft guide rail system[D]. Xuzhou: China University of Mining and Technology, 2019.
[2] 马天兵,王孝东,杜菲,等. 基于小波包和BP神经网络的刚性罐道故障诊断[J]. 工矿自动化,2018,44(8):76-80. MA Tianbing,WANG Xiaodong,DU Fei,et al. Fault diagnosis of rigid cage guide based on wavelet packet and BP neural network[J]. Industry and Mine Automation,2018,44(8):76-80.
[3] 马天兵,王鑫泉,王孝东. 基于EMD−PNN网络的刚性罐道故障诊断方法[J]. 电子测量与仪器学报,2019,33(3):58-64. MA Tianbing,WANG Xinquan,WANG Xiaodong. Fault diagnosis method of rigid cage guide based on EMD-PNN network[J]. Journal of Electronic Measurement and Instrumentation,2019,33(3):58-64.
[4] 肖飞. 基于ZYNQ的刚性罐道图像采集处理系统研究[D]. 徐州: 中国矿业大学, 2021. XIAO Fei. Research on image acquisition and processing system of rigid guide based on ZYNQ[D]. Xuzhou: China University of Mining and Technology, 2021.
[5] 黄重谦. 基于多隐层小波卷积极限学习神经网络的滚动轴承故障识别[J]. 工矿自动化,2021,47(5):77-82,100. HUANG Zhongqian. Fault identification of rolling bearing based on multi hidden layers wavelet convolution extreme learning neural network[J]. Industry and Mine Automation,2021,47(5):77-82,100.
[6] 姜洪权,贺帅,高建民,等. 一种改进卷积神经网络模型的焊缝缺陷识别方法[J]. 机械工程学报,2020,56(8):235-242. JIANG Hongquan,HE Shuai,GAO Jianmin,et al. An improved convolutional neural network model for weld defect recognition[J]. Journal of Mechanical Engineering,2020,56(8):235-242.
[7] 杜娟,刘志刚,宋考平,等. 基于卷积神经网络的抽油机故障诊断[J]. 电子科技大学学报,2020,49(5):751-757. DOI: 10.12178/1001-0548.2019205 DU Juan,LIU Zhigang,SONG Kaoping,et al. Fault diagnosis of pumping unit based on convolutional neural network[J]. Journal of University of Electronic Science and Technology of China,2020,49(5):751-757. DOI: 10.12178/1001-0548.2019205
[8] 鄢仁武,林穿,高硕勋,等. 基于小波时频图和卷积神经网络的断路器故障诊断分析[J]. 振动与冲击,2020,39(10):198-205. DOI: 10.13465/j.cnki.jvs.2020.10.027 YAN Renwu,Lin Chuan,GAO Shuoxun,et al. Fault diagnosis analysis of circuit breaker based on wavelet time-frequency representations and cocnvolution neural network[J]. Journal of Vibration and Shock,2020,39(10):198-205. DOI: 10.13465/j.cnki.jvs.2020.10.027
[9] 张西宁,刘书语,余迪,等. 改进深度卷积神经网络及其在变工况滚动轴承故障诊断中的应用[J]. 西安交通大学学报,2021,55(6):1-8. ZHANG Xining,LIU Shuyu,YU Di,et al. Improved deep convolutional neural network with applications to bearing fault diagnosis under variable conditions[J]. Journal of Xi'an Jiaotong University,2021,55(6):1-8.
[10] 马振源. 基于时频分析与CNN的振动信号特征提取方法研究[D]. 哈尔滨: 哈尔滨工业大学, 2020. MA Zhenyuan. Research on vibration signal feature extraction method based on time-frequency analysis and CNN[D]. Harbin: Harbin Institute of Technology, 2020.
[11] 高晓旸. 小波变换理论及其在制造业中的应用[M]. 北京: 机械工业出版社, 2018. GAO Xiaoyang. Wavelets theory and applications for manufacturing[M]. Beijing: China Machine Press, 2018.
[12] 李红岩,杨朝旭,荣相,等. 矿用逆变器功率器件故障预测与健康管理技术现状及展望[J]. 工矿自动化,2022,48(5):15-20. LI Hongyan,YANG Zhaoxu,RONG Xiang,et al. Research status sand prospect of prognostics health management technology for mine inverter power devices[J]. Journal of Mine Automation,2022,48(5):15-20.
[13] 张安安,黄晋英,卫洁洁,等. 基于EMD−SVD与PNN的行星齿轮箱故障诊断研究[J]. 机械传动,2018,42(12):160-165. ZHANG An'an,HUANG Jinying,WEI Jiejie,et al. Research of fault diagnosis of planetary gearbox based on EMD-SVD and PNN[J]. Journal of Mechanical Transmission,2018,42(12):160-165.
[14] 薛小兰. 机械系统故障诊断中BP神经网络的应用研究[J]. 内燃机与配件,2018(24):206-208. DOI: 10.13301/j.cnki.ct.2020.08.055 XUE Xiaolan. The application of BP neural network in the mechanical system fault diagnosis[J]. Internal Combustion Engine & Parts,2018(24):206-208. DOI: 10.13301/j.cnki.ct.2020.08.055
[15] 王孝东. 立井刚性罐道健康监测方法研究[D]. 淮南: 安徽理工大学, 2019. WANG Xiaodong. Research on health monitoring method for steel guide in vertical shaft[D]. Huainan. Anhui University of Science and Technology, 2019.
-
期刊类型引用(5)
1. 陈晓鹏，谢丽君，陈享姿. 基于无线传输的刚性罐道在线监测系统设计. 无线互联科技. 2024(02): 34-37 . 
百度学术
2. 马利芬，王伟，池耀磊，朱宏伟，韩磊. 基于噪声数据驱动CNN和LSTM的罐道故障诊断. 无线电工程. 2024(04): 1043-1052 . 百度学术
3. 李臻. 基于提升小波-SVD差分谱的煤机设备故障诊断. 煤矿机械. 2024(10): 169-173 . 百度学术
4. 李刚，刘世林. 基于EMD与小波变换的微机型继电保护装置干扰信号识别. 电气技术与经济. 2024(10): 308-311 . 百度学术
5. 王鲁娜，杜洪波，朱立军. 基于流形正则的堆叠胶囊自编码器优化算法. 广西师范大学学报(自然科学版). 2023(02): 76-85 . 百度学术
其他类型引用(7)
下载:
计量
- 文章访问数: 271
- HTML全文浏览量: 53
- PDF下载量: 33
- 被引次数: 12
