التفاصيل البيبلوغرافية
| العنوان: |
Back-analysis method of rock mass properties in tunnel engineering using multiple monitoring data based on LS-SVR algorithm. |
| Alternate Title: |
基于LS-SVR算法的多源监测数据 高铁隧道围岩参数反分析方法. (Chinese) |
| المؤلفون: |
Li Zhaozhong, Chang Xiangyu, Wang Hao, Mao Jianxiao |
| المصدر: |
Journal of Southeast University (English Edition); Mar2023, Vol. 39 Issue 1, p1-7, 7p |
| مصطلحات موضوعية: |
BACK propagation, PARAMETER estimation, STOCHASTIC convergence, GAUSSIAN processes, ARTIFICIAL neural networks |
| Abstract (English): |
To accurately estimate the rock mass properties of a high-speed railway tunnel, a back-analysis method using multiple monitoring data based on the least-squares support vector regression (LS-SVR) algorithm is presented. The root mean square error (RMSE) and mean absolute percentage error (MAPE) are used as evaluation indices. The results of the parameter estimation are compared with those of the back propagation neural network (BPNN) and Gaussian process regression (GPR) • The results show that for the single type of monitoring data, the LS-SVR model with vault settlement has the lowest RMSE and MAPE values. Moreover, as the data type increases, the RMSE value of the LS・SVR decreases, especially for the model with the mixed data of vault settlement, convergence, and floor heave. The comparison results show that the presented model has lower RMSE and MAPE values than BPNN and GPR. The LS-SVR model using multiple monitoring data shows better performance than existing back-analysis methods, improving the accuracy of the estimation of rock mass properties. [ABSTRACT FROM AUTHOR] |
| Abstract (Chinese): |
为了准确估计岩体性质, 依托阳山高速铁路隧道, 提出了一种基于最小二乘支持向量回归（LS-SVR） 的多源监测数据高铁隧道围岩参数反分析方法.以均方根误差（RMSE）和绝对百分比误差（MAPE）为评价 指标, 将参数反分析结果与BP神经网络和高斯过程回归模型结果进行比较.结果表明, 对于单一类型的监 测数据, 考虑拱顶沉降的LS-SVR模型的RMSE和MAPE值最低.随着监测数据类型的增加,LS-SVR反分 析模型的RMSE值逐渐减小, 且采用拱顶沉降、收敛和仰拱隆起3种监测数据的反分析模型的RMSE值最 小.相比于BP神经网络和高斯过程回归模型, LS-SVR模型具有较低的RMSE和MAPE值.相较于现有围 岩力学参数反分析方法, 考虑多源监测数据的LS-SVR模型具有更高的参数反分析精度. [ABSTRACT FROM AUTHOR] |
|
Copyright of Journal of Southeast University (English Edition) is the property of Journal of Southeast University Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| قاعدة البيانات: |
Complementary Index |