论文部分内容阅读
针对大连地铁香工街车站明挖施工邻接桥桩的问题,构建施工远程信息自动化监测体系,进行静力水准仪、电子测斜仪、电子轴力计等传感器布置,获得施工过程多元信息。基于Visual C#.Net平台自主开发了集成智能分析系统,引入支持向量机和差异进化算法,建立三维力学参数反分析和时间序列预测方法。该软件系统包括数据操作、反馈分析、数据报警和可视化输出的模块。将该方法系统应用于大连地铁香工街车站施工过程,进行多元信息采集,利用实际监测的信息数据,调用系统差异进化算法进行第2层和第3层岩石弹性参数搜索,反馈计算值与监测值的最大相对误差为8.23%,进而简化了倒换撑方案。然后通过对QCJ-13-01桥墩监测数据的DE-SVM非线性时间序列预测和超前报警,及时采取隔离桩措施,有效地控制了桥桩变形。该方法系统集自动化远程监测硬件技术和计算智能分析功能于一体,为类似复杂地下工程信息化施工提供先进有效的途径。
Aiming at the problems of adjacent piles in Mingzhong Street station of Dalian Metro, the automatic monitoring system of construction remote information was constructed and the sensors of static level, electronic inclinometer and electronic axis force meter were arranged to obtain the diversified information of construction process. Based on Visual C # .Net platform, an integrated intelligent analysis system is developed independently. The support vector machine and differential evolution algorithm are introduced to establish the three-dimensional mechanical parameter back analysis and time series prediction. The software system includes data manipulation, feedback analysis, data alarm and visual output module. The method is applied to the construction of station of Xianggong Street in Dalian Subway. Multiple information collection is carried out. The system differential evolution algorithm is used to search the elastic parameters of Layer 2 and Layer 3, and the calculated value and monitoring feedback The value of the maximum relative error of 8.23%, thus simplifying the switching support program. Then by DE-SVM nonlinear time series prediction and advanced alarm of QCJ-13-01 bridge piers monitoring data, the isolation piles measures are taken in time to effectively control the deformation of bridge piles. The method integrates the automatic remote monitoring hardware technology and the computational intelligence analysis function, and provides an advanced and effective way for similar complex underground engineering information construction.