当前位置: X-MOL 学术Eng. Fail. Anal. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Vibration-based damage detection of rail fastener clip using convolutional neural network: Experiment and simulation
Engineering Failure Analysis ( IF 4.4 ) Pub Date : 2020-09-17 , DOI: 10.1016/j.engfailanal.2020.104906
Zhandong Yuan , Shengyang Zhu , Xuancheng Yuan , Wanming Zhai

With the rapid development of rail transportation, health monitoring of railway track structure becomes a challenging problem. In this work, a novel and efficient approach is proposed to carry out damage detection of fastener clips using one dimensional convolutional neural network (CNN). A one dimensional CNN is designed to learn optimal damage-sensitive features from the raw acceleration response and identify the health condition of rail fastener clips automatically. Two case studies are implemented experimentally and numerically to validate its feasibility. First, repeated impact tests are conducted on the track system under different health conditions of fastener clips in laboratory. The time-domain data recorded by accelerometers on the rail are employed for the CNN training and evaluation. Parametric studies are performed on the number of convolution blocks, location of sensor and robustness to noise level. It is found that the CNN achieves a high detecting accuracy and good robustness. Furthermore, in order to collect rail response induced by the passing train under variational clip health condition, a modified vehicle-track coupled dynamics model is established to generate numerical datasets of the rail vertical acceleration under different damage scenarios of the fastener clips. Thereafter, the CNN is trained and evaluated on the numerical datasets, showing a high detection accuracy. Finally, the t-distribution stochastic neighbor embedding (t-SNE) technique is applied to manifest the super feature extraction capability of CNN.



中文翻译:

卷积神经网络基于振动的钢轨扣件损伤检测:实验与仿真

随着铁路运输的快速发展,铁路轨道结构的健康监测成为一个具有挑战性的问题。在这项工作中,提出了一种新颖而有效的方法来使用一维卷积神经网络(CNN)进行紧固件夹的损坏检测。一维CNN旨在从原始加速度响应中学习最佳的损伤敏感特征,并自动识别轨道扣夹的健康状况。实验和数值上进行了两个案例研究,以验证其可行性。首先,在实验室中,在不同的固定夹健康条件下,对轨道系统进行重复的冲击测试。由加速计记录在轨道上的时域数据用于CNN训练和评估。对卷积块的数量,传感器的位置以及对噪声水平的鲁棒性进行参数研究。发现CNN实现了高检测精度和良好的鲁棒性。此外,为了收集在变化的夹子健康状况下由经过的列车引起的轨道响应,建立了改进的车轨耦合动力学模型,以生成在不同的紧固夹子损坏情况下轨道垂直加速度的数值数据集。此后,在数值数据集上对CNN进行训练和评估,显示出很高的检测精度。最后,采用t分布随机邻居嵌入(t-SNE)技术来体现CNN的超特征提取能力。发现CNN实现了高检测精度和良好的鲁棒性。此外,为了收集在变化的夹子健康状况下由经过的列车引起的轨道响应,建立了改进的车轨耦合动力学模型,以生成在不同的紧固夹子损坏情况下轨道垂直加速度的数值数据集。此后,在数值数据集上对CNN进行训练和评估,显示出很高的检测精度。最后,采用t分布随机邻居嵌入(t-SNE)技术来体现CNN的超特征提取能力。发现CNN实现了高检测精度和良好的鲁棒性。此外,为了收集在变化的夹子健康状况下由经过的列车引起的轨道响应,建立了改进的车轨耦合动力学模型,以生成在不同的紧固夹子损坏情况下轨道垂直加速度的数值数据集。此后,在数值数据集上对CNN进行训练和评估,显示出很高的检测精度。最后,采用t分布随机邻居嵌入(t-SNE)技术来体现CNN的超特征提取能力。建立了改进的车轨耦合动力学模型,以生成扣件夹在不同损坏情况下轨道垂直加速度的数值数据集。此后,在数值数据集上对CNN进行训练和评估,显示出很高的检测精度。最后,采用t分布随机邻居嵌入(t-SNE)技术来体现CNN的超特征提取能力。建立了改进的车轨耦合动力学模型,以生成扣件夹在不同损坏情况下轨道垂直加速度的数值数据集。此后,在数值数据集上对CNN进行训练和评估,显示出很高的检测精度。最后,采用t分布随机邻居嵌入(t-SNE)技术来体现CNN的超特征提取能力。

更新日期:2020-10-07
down
wechat
bug