【摘要】 为了预测基坑周围地表道路的沉降,该文结合常州恒生科技园二期建设工程实例,提出了灰色GM(1,1)与神经网络模型组合构成灰色神经网格模型。基于层次分析法,选取建筑物沉降、围护结构顶部水平位移、竖向位移、地下水位作为影响地表道路沉降的主要因素,并将其作为模型的输入因素。研究结果表明,灰色神经网络模型结合三次样条插值建立的组合预测模型,具有较高的预测精度,有利于基坑的预测、预警,有效地保障了基坑施工的安全。更多还原

【Abstract】 In order to predict the settlement of road surface around foundation pit,the grey neural network model combined by GM( 1,1) and neural network model is put forward combined with the engineering practice of the second phase construction project of Changzhou Hengsheng Science Park. Based on the analytic hierarchy process( AHP),the building subsidence,horizontal displacement and vertical displacement at the top of retaining structure and water level are taken as the main factors affecting the surface road settlement and as the input factors of model. The results show that the combination forecasting model based on the grey neural network model and three spline interpolation has higher prediction accuracy,and it is conducively to predict and early warn the foundation pit,and effectively to ensure the safety of the foundation pit construction.更多还原