基于BO-CNN模型的复合材料疲劳损伤超声导波监测方法

doi:10.3901/JME.2025.24.038

摘要/Abstract

摘要： 监测复合材料疲劳损伤对保障复合材料结构安全具有重要意义。为此，提出基于超声导波与机器学习模型相结合的复合材料疲劳损伤监测方法，旨在提高损伤识别的准确性。该方法首先筛选出受疲劳损伤影响较大的超声导波信号特征，再进行共线性分析降低特征矩阵冗余性，进行预处理后组成样本库；然后以信号特征矩阵为输入，以损伤特征为输出构建出卷积神经网络(Convolutional neural network，CNN)损伤预测模型，结合贝叶斯优化(Bayesian optimization，BO)调整模型超参数，最后将样本库按照8∶1∶1的比例随机分成训练集、验证集和测试集，利用验证集进行超参数选择，测试集进行模型评估。试验结果表明：构建的BO-CNN损伤预测模型相对于CNN损伤预测模型具有更好的损伤诊断能力，量化精度从0.94提高至0.98，且损伤回归预测任务中表现出更高的可靠性。

关键词: 结构健康监测, 疲劳损伤, 机器学习, 卷积神经网络, 贝叶斯优化

Abstract: Monitoring composite fatigue damage is of great significance to ensure the safety of composite structures, for this reason, a composite fatigue damage monitoring method based on the combination of ultrasonic guided wave and machine learning model is proposed, aiming to improve the accuracy of damage identification. The method firstly screens out the ultrasonic guided wave signal features that are greatly affected by fatigue damage, then carries out covariance analysis to reduce the redundancy of the feature matrix, and preprocesses it to form a sample library. Subsequently, the signal feature matrix is used as the input, and the damage features are used as the output to construct a convolutional neural network(CNN) damage prediction model. This model is then combined with the bayesian optimization(BO) to adjust the hyperparameters of the model. Ultimately, the sample library is randomly divided into training set, validation set and test set according to the ratio of 8∶1∶1, using the validation set for hyper-parameter selection and the test set for model evaluation. The experimental results show that the constructed BO-CNN damage prediction model has better damage diagnosis capability relative to the CNN damage prediction model, the quantization accuracy is improved from 0.94 to 0.98, and the damage regression prediction task shows higher reliability.

Key words: structural health monitoring, fatigue damage, machine learning, convolutional neural network, Bayesian optimization

中图分类号:

TB332
TP181

丁梦珂, 高东岳, 顾海洋, 王博睿, 周国泰, 武湛君. 基于BO-CNN模型的复合材料疲劳损伤超声导波监测方法[J]. 机械工程学报, 2025, 61(24): 38-47.

DING Mengke, GAO Dongyue, GU Haiyang, WANG Borui, ZHOU Guotai, WU Zhanjun. Ultrasonic Guided Wave Monitoring of Composite Fatigue Damage Based on BO-CNN model[J]. Journal of Mechanical Engineering, 2025, 61(24): 38-47.

参考文献

[1] 许国琛,陈振华,李承庚,等. CFRP层板低能冲击损伤的非线性兰姆波特征成像[J]. 机械工程学报,2023,59(10):40-47. XU Guochen,CHEN Zhenhua,LI Chenggeng,et al. Nonlinear lamb wave imaging for low energy impact damage of CFRP laminates[J]. Journal of Mechanical Engineering,2023,59(10):40-47.
[2] 余海燕,贺宏伟,邢萍. 考虑不同刚度退化模式的碳纤维增强复合材料失效模型开发[J]. 机械工程学报,2024,60(2):197-208. YU Haiyan,HE Hongwei,XING Ping. Development of carbon fiber reinforced plastic failure models considering different stiffness degradation modes[J]. Journal of Mechanical Engineering,2024,60(2):197-208.
[3] 聂昕,南博. 拼接铺层纤维增强复合材料连接结构设计与离散优化[J]. 机械工程学报,2021,57(7):194-203. NIE Xin,NAN Bo. Ply-overlap fiber reinforced plastic connection structure design and discrete optimization[J]. Journal of Mechanical Engineering,2021,57(7):194-203.
[4] BJORHEIM F,SIRIWARDANE S C,PAVLOU D. A review of fatigue damage detection and measurement techniques[J]. International Journal of Fatigue,2022,154:106556.
[5] ELIASSON S,HULTGREN G,WENNHAGE P,et al. Numerical fatigue assessment of a cross-ply carbon fiber laminate using a probabilistic framework[J]. Composites Part B-Engineering,2024,281:111514.
[6] 李建乐,张佳奇,黄念,等. 基于深度学习的分布式光纤损伤识别方法[J]. 机械工程学报,2022,58(8):88-95. LI Jianle,ZHANG Jiaqi,HUANG Nian,et al. Distributed optical fiber damage identification method based on deep learning[J]. Journal of Mechanical Engineering,2022,58(8):88-95.
[7] GHAREHBAGHI V R,NOROOZINEJAD F,NOORI M,et al. A critical review on structural health monitoring:Definitions,methods,and perspectives[J]. Archives of Computational Methods in Engineering,2022,29(4):2209-2235.
[8] QING Xinlin,LIAO Yuanlai,WANG Yihan,et al. Machine learning based quantitative damage monitoring of composite structure[J]. International Journal of Smart And Nano Materials,2022,13(2):167-202.
[9] GOYAL D,PABLA B S. The Vibration monitoring methods and signal processing techniques for structural health monitoring:A review[J]. Archives of Computational Methods in Engineering,2016,23(4):585-594.
[10] QING Xinlin,LI Wenzhuo,WANG Yishou,et al. Piezoelectric transducer-based structural health monitoring for aircraft applications[J]. Sensors,2019,19(3):545.
[11] JIN Hashen,YAN Jiajia,LIU Xiao,et al. Quantitative defect inspection in the curved composite structure using the modified probabilistic tomography algorithm and fusion of damage index[J]. Ultrasonics,2021,113:106358.
[12] 房芳,郑辉,汪玉,等. 机械结构健康监测综述[J]. 机械工程学报,2021,57(16):269-292. FANG Fang,ZHENG Hui,WANG Yu,et al. Mechanical structural health monitoring:A review[J]. Journal of Mechanical Engineering,2021,57(16):269-292.
[13] KULAKOVSKYI A,MESNIL O,CHAPUIS B,et al. Statistical analysis of guided wave imaging algorithms performance illustrated by a simple structural health monitoring configuration[J]. Journal of Nondestructive Evaluation,Diagnostics and Prognostics of Engineering Systems,2021,4(3):031001.
[14] 高东岳,徐颖珊,郭健,等. 基于超声导波的飞行器密封质量检测方法[J]. 兵器装备工程学报,2021,42(2):229-233. GAO Dongyue,XU Yingshan,GUO Jian,et al. Guided wave-based aircrafts seal quality inspection method[J]. Journal of Ordnance Equipment Engineering,2021,42(2):229-233.
[15] 郑跃滨. 基于超声导波的薄壁结构无基准损伤诊断方法与集成化系统研究[D]. 大连:大连理工大学,2021. ZHENG Yuebin. Research on reference-free damage diagnostic techniques and integrated system for thin-walled structures based on guided waves[D]. Dalian:Dalian University of Technology,2021.
[16] 徐浩,王中枢,马寅魏,等. 基于超声导波和机器学习的蜂窝夹层结构脱黏诊断[J]. 无损检测,2022,44(10):44-47. XU Hao,WANG Zhongshu,MA Yinwei,et al. Debonding diagnosis of honeycomb sandwich structures based on guided waves and machine learning[J]. Nondestructive Testing,2022,44(10):44-47.
[17] YUE N,ALIABADI M H. Hierarchical approach for uncertainty quantification and reliability assessment of guided wave-based structural health monitoring[J]. Structural Health Monitoring,2020,20(5):2274-2299.
[18] 杨斌,胡超杰,轩福贞,等. 基于超声导波的压力容器健康监测III:纤维缠绕压力容器的在线监测[J]. 机械工程学报,2020,56(10):19-26. YANG Bin,HU Chaojie,XUAN Fuzhen,et al. Structural health monitoring of pressure vessel based on guided wave technology. Part III:Online monitoring of filament wound pressure vessel[J]. Journal of Mechanical Engineering,2020,56(10):19-26.
[19] KHELIF R,CHEBEL-MORELLO B,MALINOWSKI S,et al. Direct remaining useful life estimation based on support vector regression[J]. IEEE Transactions On Industrial Electronics,2017,64(3):2276-2285.
[20] 雷亚国,贾峰,周昕,等. 基于深度学习理论的机械装备大数据健康监测方法[J]. 机械工程学报,2015,51(21):49-56. LEI Yaguo,JIA Feng,ZHOU Xin,et al. A deep learning-based method for machinery health monitoring with big data[J]. Journal of Mechanical Engineering,2015,51(21):49-56.
[21] HONG T Y,CHEN C C. Hyperparameter optimization for convolutional neural network by opposite-based particle swarm optimization and an empirical study of photomask defect classification[J]. Applied Soft Computing,2023,148:110904.
[22] WANG Yulong,ZHANG Haoxin,ZHANG Guanwei. cPSO-CNN:An efficient PSO-based algorithm for fine-tuning hyper-parameters of convolutional neural networks[J]. Swarm and Evolutionary Computation,2019,49:114-123.
[23] BERGSTRA J,BENGIO Y. Random search for hyper-parameter optimization[J]. Journal of Machine Learning Research,2012,13(1):281-305.
[24] RERE L M R,FANANY M I,ARYMURTHY A M. Metaheuristic algorithms for convolution neural network[J]. Computational Intelligence and Neuroscience,2016,2016(1):1537325.
[25] ARIAFAR S,COLL-FONT J,BROOKS D,et al. ADMMBO:Bayesian optimization with unknown constraints using ADMM[J]. Journal of Machine Learning Research,2019,20:123.
[26] LI Xiaofei,GUO Hainan,XU Langxing,et al. Bayesian-based hyperparameter optimization of 1D-CNN for structural anomaly detection[J]. Sensors,2023,23(11):5058.
[27] 康永乐,邱雷. 导波结构健康监测中损伤因子的研究和应用[J]. 国外电子测量技术,2021,40(6):113-119. KANG Yongle,QIU Lei. Research and application of damage indexes in guided wave based structural health monitoring[J]. Foreign Electronic Measurement Technology,2021,40(6):113-119.
[28] 宋业栋,马光伟,朱小龙,等. 基于强化层次模糊熵的柴油机故障诊断方法[J]. 振动、测试与诊断,2024,44(4):814-820. SONG Yedong,MA Guangwei,ZHU Xiaolong,et al. Fault diagnosis method of diesel engine based on reinforced hierarchical fuzzy entropy[J]. Journal of Vibration,Measurement & Diagnosis,2024,44(4):814-820.
[29] LIANG Xiao. Image-based post-disaster inspection of reinforced concrete bridge systems using deep learning with Bayesian optimization[J]. Computer-Aided Civil and Infrastructure Engineering,2019,34(5):415-430.
[30] SAXENA A,GOEBEL K,LARROSA C C,et al. Accelerated aging experiments for prognostics of damage growth in composite materials[J]. Structural Health Monitoring,2011,15:1-9.
[31] 肖玉善,吴振,任晓辉. 基于压电信号的复合材料疲劳寿命评估方法[J]. 复合材料学报,2024,41(9):4897-4908. XIAO Yusha,WU Zhen,REN Xiaohui. Fatigue assessment for composites by using piezoelectric signal[J]. Acta Materiae Compositae Sinica,2024,41(9):4897-4908.
[32] 荣雪琴,丁营营,刘勇. 基于数据驱动与相关性的电能误差分析方法研究[J]. 电测与仪表,2025,62(1):101-109. RONG Xueqin,DING Yingying,LIU Yong. Research on data-driven and correlation-based electric energy error analysis method[J]. Electrical Measurement & Instrumentation,2025,62(1):101-109.