基于传感器信息融合的轨道交通变形监测

Rail transit deformation monitoring based on sensor information fusion

为提升轨道交通变形监测准确度,文中提出基于传感器信息融合的轨道交通变形的监测方法。该方法构建交通轨道变形监测模型,利用离散Kalman滤波算法对轨道震动信号数据实施滤波处理,通过震动信号轨道表面局部变形的冲击引导方法,引导图像传感器展开图像采集,通过对轨道交通变形图像实施纹理特征提取后,采用学习向量量化神经网络实现变形分类,达到监测轨道交通变形目的。实验结果表明:该方法具有较高数据采集能力,冲击引导能力好、误差低、分类准确度高,可有效实现轨道交通变形监测。

In order to improve the accuracy of rail transit deformation monitoring,a rail transit deformation monitoring method based on sensor information fusion is proposed.In this method,the deformation monitoring model of rail transit is constructed,and the discrete Kalman filtering algorithm is used to filter the track vibration signal data.Through the impact guidance method of the local deformation of the track surface of the vibration signal,the image sensor is guided to carry out the image acquisition.After the texture features of the rail transit deformation image are extracted,the deformation classification is realized by using the learning vector quantization neural network to achieve the purpose of monitoring the deformation of rail transit.The experiment results show that the method has high data acquisition ability,good impact guidance ability,low error,and high classification accuracy,which can effectively realize rail transit deformation monitoring.