上海交通大学学报

上海交通大学学报 >

2021 , Vol. 55 >Issue 5: 527 - 535

DOI: https://doi.org/10.16183/j.cnki.jsjtu.2020.095

基于长短期记忆神经网络的板裂纹损伤检测方法

展开
  • 高新船舶与深海开发装备协同创新中心, 上海 200240
张松林(1995-),男,山东省济宁市人,硕士生,主要研究方向为船体结构损伤检测.

收稿日期: 2020-04-01

  网络出版日期: 2021-06-01

基金资助

工信部高技术船舶科研项目([2016]548);教育部财政部重大专项(201335)

收起

Method for Plate Crack Damage Detection Based on Long Short-Term Memory Neural Network

Expand
  • Collaborative Innovation Center for Advanced Ship and Deep-Sea Exploration, Shanghai Jiao Tong University, Shanghai 200240, China

Received date: 2020-04-01

  Online published: 2021-06-01

Fold

摘要

针对板不同位置裂纹损伤的智能分类问题,提出了一种基于长短期记忆(LSTM)神经网络的板裂纹损伤检测方法.采用Abaqus二次开发建立板裂纹损伤模型,计算高斯白噪声激励下板的加速度响应,并通过数据扩充方法生成数据集,同时考虑了噪声对损伤检测的影响.建立基于LSTM的板裂纹智能检测模型,直接将板的加速度响应作为输入,不需要额外的损伤特征提取,并以最小预测误差为目标,选择模型的超参数,优化模型配置.与多层感知机模型和基于小波包变换的多层感知机模型进行对比表明,本文提出的LSTM模型在板裂纹损伤检测中具有更高的损伤定位精度和更好的适用性.

关键词： 损伤检测; 长短期记忆神经网络; 板裂纹; 噪声

本文引用格式

张松林, 马栋梁, 王德禹 . 基于长短期记忆神经网络的板裂纹损伤检测方法[J]. 上海交通大学学报, 2021 , 55(5) : 527 -535 . DOI: 10.16183/j.cnki.jsjtu.2020.095

Abstract

Aimed at the problem of intelligent classification of crack damage in different positions of the plate, a method for plate crack damage detection based on long short-term memory (LSTM) neural network is proposed. The Abaqus secondary development is used to build the plate crack damage model and calculate the acceleration response of the plate under Gaussian white noise excitation. The data set is generated by data augmentation, and the influence of noise on damage detection is considered. An intelligent crack detection model based on LSTM is established, which directly takes the acceleration response of the plate as the input and does not require additional damage feature extraction. With the goal of minimizing prediction error, the hyperparameter of the model is selected and the model configuration is optimized. The comparison of the multi-layer perceptron model and the multi-layer perceptron model based on wavelet packet transform shows that the LSTM model proposed in this paper has a higher damage location accuracy and a better applicability in plate crack detection.

Key words： damage detection; long short-term memory (LSTM) neural network; plate crack; noise

参考文献

[1] 张敬芬, 赵德有. 工程结构裂纹损伤振动诊断的发展现状和展望[J]. 振动与冲击, 2002, 21(4):22-26.
[1] ZHANG Jingfen, ZHAO Deyou. Summary review of vibration-based crack diagnosis technique for engingeering structures[J]. Journal of Vibration and Shock, 2002, 21(4):22-26.
[2] 贾连徽, 任慧龙, 孙树政, 等. 船体结构应力监测点的选取方法研究[J]. 船舶力学, 2013, 17(4):389-397.
[2] JIA Lianhui, REN Huilong, SUN Shuzheng, et al. Research on ship structural stress monitoring points selection method[J]. Journal of Ship Mechanics, 2013, 17(4):389-397.
[3] YANG J, HWANG C N, YANG B L. Crack identification in beams and plates by discrete wavelet transform method[J]. Journal of Ship Mechanics, 2008, 12(3):464-472.
[4] MEHRJOO M, KHAJI N, MOHARRAMI H, et al. Damage detection of truss bridge joints using Artificial Neural Networks[J]. Expert Systems with Applications, 2008, 35(3):1122-1131.
[5] GREFF K, SRIVASTAVA R K, KOUTNÍK J, et al. LSTM: A search space odyssey[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(10):2222-2232.
[6] 张建付, 宋雨, 李刚, 等. 基于长短时记忆神经网络的风电机组滚动轴承故障诊断方法[J]. 计算机测量与控制, 2017, 25(1):16-19.
[6] ZHANG Jianfu, SONG Yu, LI Gang, et al. A method of fault diagnosis for rolling bearing of wind turbines based on long short-term memory neural network[J]. Computer Measurement & Control, 2017, 25(1):16-19.
[7] ZOU P, HOU B C, LEI J, et al. Bearing fault diagnosis method based on EEMD and LSTM[J]. International Journal of Computers Communications & Control, 2020, 15(1):1-14.
[8] 陈伟, 陈锦雄, 江永全, 等. 基于RS-LSTM的滚动轴承故障识别[J]. 中国科技论文, 2018, 13(10):1134-1141.
[8] CHEN Wei, CHEN Jinxiong, JIANG Yongquan, et al. Fault identification of rolling bearing based on RS-LSTM[J]. China Sciencepaper, 2018, 13(10):1134-1141.
[9] YU L, QU J L, GAO F, et al. A novel hierarchical algorithm for bearing fault diagnosis based on stacked LSTM[J]. Shock and Vibration, 2019, 2019:1-10.
[10] LUO P, HU Y. Research on rolling bearing fault Identification method based on LSTM neural network[C]//2018 International Conference on Mechanical Engineering, Materials Science and Civil Engineering, Xiamen, China: nstitute of Physics Publishing, 2019, 542:012048.
[11] SRIVASTAVA N, HINTON G E, KRIZHEVSKY A, et al. Dropout: A simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research, 2014, 15(1):1929-1958.
[12] LIN Y Z, NIE Z H, MA H W. Structural damage detection with automatic feature-extraction through deep learning[J]. Computer-Aided Civil and Infrastructure Engineering, 2017, 32(12):1025-1046.
[13] 李世玲, 李治, 李合生. 基于小波包能量特征的滚动轴承故障监测方法[J]. 系统仿真学报, 2003, 15(1):76-80.
[13] LI Shiling, LI Zhi, LI Hesheng. The method of roller bearing fault monitoring based on wavelet packet engergy feature[J]. Journal of System Simulation, 2003, 15(1):76-80.
Options
文章导航

/

〈 〉