基于一种组合模型的地铁监测数据处理

Subway Monitoring Data Processing Based on a Combined Model

地铁自动监测数据含有较多随机误差成分,可以利用卡尔曼滤波对其进行处理,从而获得真实、稳定的地铁形变信息,然后基于支持向量机法对滤波后的地铁监测数据建立预测模型,并与实际L3水准结果以及BP神经网络预测结果进行比较。结果显示,卡尔曼滤波能够显著降低原始数据中的随机噪声成分。与BP神经网络相比,支持向量机方法预测精度提高了50%。采用不同监测数据量对K-SVM预测精度进行研究,结果表明,在监测数据较少时,增加监测数据能够显著提高预测精度,而当监测数据量大于20时,K-SVM预测模型的已知数据需求达到饱和,能够获得最优预测结果。基于K-SVM的地铁自动监测数据的处理和预测能够更加准确地预测地铁真实形变,为地铁安全监测、预警提供更加可靠的信息。

Based on SVM method,the prediction model of subway monitoring data after Kalman filter processing was established in this paper.And then,the prediction model was compared with the actual L3 level results and BP neural network prediction results.The results show that the Kalman filter can significantly reduce the random noise in the original data.Compared with the BP neural network,the prediction accuracy of SVM method is improved by 50%.The prediction accuracy of K-SVM was studied by using different monitoring data.The results show that when the monitoring data is small,the increase of the monitoring data can improve the prediction accuracy significantly,and when the amount of monitoring data is greater than 20,the known data requirements of the K-SVM prediction model are saturated and the optimal prediction result can be obtained.