基于注意力改进卷积网络的隧道风机预埋基础损伤识别

PDF(1548 KB)

振动与冲击 ›› 2023, Vol. 42 ›› Issue (10) : 307-313.

论文

韩坤林1,2，汤宝平1，刘大洋2，邹小春2

作者信息 +

Damage identification of embedded foundation of tunnel fan based on attention improved convolution network

HAN Kunlin1,2， TANG Baoping1， LIU Dayang2， ZOU Xiaochun2

Author information +

文章历史 +

摘要

针对隧道风机预埋基础损伤信息微弱、特征难以提取等问题，提出一种基于度量-频段注意力卷积神经网络的隧道风机预埋基础损伤识别方法。首先，通过预埋基础冲激试验的激励信号和响应信号，计算预埋基础的频率响应函数并作为损伤识别模型的输入；然后，使用多层卷积将输入的频率响应函数映射到特征空间提取损伤特征信息；再次，采用频段注意力机制对不同频段上的特征进行自适应加权融合，并采用度量损失进一步增强提取特征的可辨识性；最后，将提取的特征输入全连接层以实现预埋基础损伤识别。实测数据验证结果表明，所提方法对比现有的神经网络模型具有更高识别率，能够对隧道风机预埋基础健康状态进行有效地评估。

Abstract

In order to address the issue of tedious feature extraction task caused by the weak damage information when dealing with damage identification of the embedded foundation of tunnel fan, a damage identification method based on attention convolution network is proposed. Firstly, the frequency response function is computed by applying excitation signal and response signal, and is used as the input data of damage identification model; Then, the frequency response function is mapped into the feature space by multiple convolutional layers to extract damage feature information; Thirdly, the frequency band attention mechanism is utilized to adaptively weight the features in different frequency bands, and the metric loss is employed to make the extracted features more distinguishable; Finally, the extracted features are inputted into the fully connected layer to achieve the damage recognition of the embedded foundation. The experimental results of practical measured data show that the proposed method has higher accuracy than the existing neural network models, and can effectively evaluate the health state of the embedded foundation of tunnel fan.

导出引用

韩坤林1,2，汤宝平1，刘大洋2，邹小春2. 基于注意力改进卷积网络的隧道风机预埋基础损伤识别[J]. 振动与冲击, 2023, 42(10): 307-313

HAN Kunlin1,2， TANG Baoping1， LIU Dayang2， ZOU Xiaochun2. Damage identification of embedded foundation of tunnel fan based on attention improved convolution network[J]. Journal of Vibration and Shock, 2023, 42(10): 307-313

参考文献

[1] 交通运输部. 2019年交通运输行业发展统计公报[EB/OL]. http://www.gov.cn/xinwen/2020-05/12/content_5510817.htm, 2020.05.12.
[2] JTG/T 6230－2020. 公路隧道运营技术规范[S]. 交通运输部, 2020.
[3] CHEN R, Chen S, YANG L, et al. Looseness diagnosis method for connecting bolt of fan foundation based on sensitive mixed-domain features of excitation - response and manifold learning[J]. Neurocomputing, 2017, 219: 376-388
[4] CHEN Z, Gryllias K, LI W. Intelligent fault diagnosis for rotary machinery using transferable convolutional neural network[J]. IEEE Transactions on Industrial Informatics, 2020, 16: 339-349.
[5] 赵俊锋. 基于卷积神经网络的螺栓松紧状态智能监测方法研究[D]. 西安: 长安大学, 2019.
ZHAO Junfeng. Research on intelligent monitoring method of bolt tension state based on convolutional neural network [D]. Xian: Chang'an University, 2019.
[6] Osama A, Avcı O, Kiranyaz S, et al. Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks[J]. Journal of Sound and Vibration, 2017, 388: 154-170.
[7] 倪伟, 李世立. 基于振动分析的射流风机故障诊断与健康监测方法[J]. 现代信息科技, 2019, 3(17): 140-142+144.
NI Wei, Li Shili. Fault Diagnosis and Health Monitoring Method of Jet Fan Based on Vibration Analysis[J]. Modern Information Technology, 2019, 3(17): 140-142+144.
[8] 余浩帅, 汤宝平, 张楷, 等. 小样本下混合自注意力原型网络的风电齿轮箱故障诊断方法[J].中国机械工程, 2021, 32(20): 2475-2481.
YU Haoshuai, TANG Baoping, ZHANG Kai, et al. Fault Diagnosis Method of Wind Turbine Gearboxes Mixed with Attention Prototype Networks under Small Samples[J]. CHINA MECHANICAL ENGINEERING, 2021, 32(20): 2475-2481.
[9] 朱张莉, 饶元, 吴渊, 等. 注意力机制在深度学习中的研究进展[J]. 中文信息学报, 2019, 33(06): 1-11.
ZHU Zhangli, RAO Yuan, WU Yuan, et al. Research Progress of Attention Mechanism in Deep Learning[J]. JOURNAL OF CHINESE INFORMATION PROCESSING, 2019, 33(06): 1-11.
[10] 郭惠勇, 李正良. 基于不完备频响函数的结构多损伤定性和定量识别[J]. 工程力学, 2007, 24(4): 13-17.
GUO Huiyong, LI Zhenliang. QUALITATIVE AND QUANTITATIVE IDENTIFICATION OF MULTIPLE DAMAGES BASED ON INCOMPLETE FREQUENCY RESPONSE FUNCTIONS[J]. ENGINEERING MECHANICS, 2007, 24(4): 13-17.
[11] 周兴康, 余建波. 基于深度一维残差卷积自编码网络的齿轮箱故障诊断[J]. 机械工程学报, 2020, 56(07): 96-108.
ZHOU Xingkang, YU Jianbo. Gearbox Fault Diagnosis Based on One-dimension Residual Convolutional Auto-encoder[J]. Chinese Journal of Mechanical Engineering, 2020, 56(07): 96-108.
[12] 孔子迁, 邓蕾, 汤宝平, 等. 基于时频融合和注意力机制的深度学习行星齿轮箱故障诊断方法[J]. 仪器仪表学报, 2019, 40(06): 221-227.
KONG Ziqian, DENG Lei, TANG Baoping, et al. Fault diagnosis of planetary gearbox based on deep learning with time-frequency fusion and attention mechanism[J]. Chinese Journal of Scientific Instrument, 2019, 40(06): 221-227.
[13] 周奇才, 刘星辰, 赵炯, 等. 旋转机械一维深度卷积神经网络故障诊断研究[J]. 振动与冲击, 2018, 37(23): 31-37.
ZHOU Qicai, LIU Xingchen, et al. Fault diagnosis for rotating machinery based on 1D depth convolutional neural network [J]. JOURNAL OF VIBRATION AND SHOCK, 2018, 37(23): 31-37.
[14] Lei Y, Zheng J, Zi Y, et al. New clustering algorithm-based fault diagnosis using compensation distance evaluation technique[J]. Mechanical Systems and Signal Processing, 2008, 22: 419-435.
[15] Chauhan V, Kalpana D & Sharma A. Problem formulations and solvers in linear SVM: a review[J]. Artificial Intelligence Review, 2018, 52(2): 1-53.
[16] Woo S, Park J, Lee J, et al. CBAM: Convolutional block attention module[C]. Proceedings of the European Conference on Computer Vision (ECCV). 2018: 104906.
[17] Hou, Qibin, Daquan Zhou & Jiashi Feng. Coordinate attention for efficient mobile network design[J]. ArXiv preprint, ArXiv: 2103.02907, 2021.
[18] 韩坤林. 基于振动分析的公路隧道悬挂风机基础健康性监测方法[J]. 公路隧道, 2016, (1): 45-48, 22.
[19] Lei Y, Zheng J, Zi Y, et al. A new approach to intelligent fault diagnosis of rotating machinery[J]. Expert Systems with Applications, 2008, 35(4): 1593-1600.