综合岭回归和SARIMA方法在桥梁健康监测数据分析中的应用

桥梁健康监测系统的实测数据普遍存在缺失问题，为了保证桥梁监测数据的完整性，更好地预测桥梁未来的健康状况，提出了一种具有样本内和样本外预测能力的组合模型。样本外预测可以基于现在数据预测未来的桥梁健康状态，样本内回归用于填补传感器数据中的缺失值，确保桥梁监测数据的完整性。由于不同位置处相同类型传感器的相关性较强，首先利用岭回归（Ridge Regression，RR）解决共线性问题，建立各传感器数据之间的关联，并预测缺失数据。接着引入季节性差分自回归滑动平均(Seasonal Autoregressive Integrated Moving Average，SARIMA) 方法，利用其样本外预测能力并结合岭回归方法预测桥梁未来运行数据。然后，通过设立预警值实现健康状况预警，以保证桥梁健康运行。最后，将该方法应用于实桥中，验证了其有效性，为传感器数据填补以及预测桥梁未来状态提供了一个有效的预测模型。

Application of Integrated Ridge Regression and SARIMA Methods in the Analysis of Bridge Health Monitoring Data

To ensure the integrity of bridge monitoring data and to better predict the future health status of bridges, a combined model with in-sample and out-of-sample prediction capability is proposed in order to ensure the integrity of bridge monitoring data, which are commonly missing in the real measurement data of bridge health monitoring systems. The out-of-sample prediction can predict the future bridge health status based on the present data, and the in-sample regression is used to missing data imputation in the sensor data to ensure the integrity of the bridge monitoring data. Due to the strong correlation of the same type of sensors at different locations, Ridge Regression (RR) is first used to solve the covariance problem, establish the correlation between each sensor data, and predict the missing data. Then, the Seasonal Autoregressive Integrated Moving Average (SARIMA) method is introduced to predict the future operation data of the bridge by using its out-of-sample prediction capability and combining with the Ridge Regression method. Then, health condition warning is achieved by establishing early warning values to ensure healthy bridge operation. Finally, the method is applied to a real bridge to verify its effectiveness and provide an effective prediction model for missing sensor data imputation as well as predicting the future state of the bridge.