论文部分内容阅读
基坑工程施工中,需要根据现场实际情况、周围环境、建筑安全等级等对变形进行严格控制。通过对基坑实测变形数据进行整理和分析,对未来变形量作出预测,保证基坑安全。结合BP神经网络的高度非线性映射能力,提出了一种基于BP神经网络的基坑变形时间序列预测方法。在基坑开挖过程中,采取滚动预测的方法,不断利用前期已有实测数据建模预测后期变形量,以实现信息化施工和动态控制。实例分析表明,BP神经网络模型具有较高的预测精度,并能获得满意的预测结果。
During the construction of foundation pit, it is necessary to strictly control the deformation according to the actual conditions of the site, the surrounding environment and the level of building safety. According to the actual measured deformation data of foundation pit, the deformation of the foundation pit is predicted and predicted to ensure the safety of foundation pit. Combined with the highly nonlinear mapping ability of BP neural network, a prediction method of foundation pit deformation time series based on BP neural network is proposed. In the excavation process of the foundation pit, the method of rolling prediction is adopted to continuously forecast the late deformation by using the existing measured data to predict and realize the information construction and dynamic control. The case study shows that the BP neural network model has high prediction accuracy and can obtain satisfactory prediction results.