【摘要】 青海地区铁路路基的溶陷不均匀沉降病害较为严重,氯盐是引起路基溶陷的最主要因素.为了研究氯盐渍土的溶陷特性,以青海西部氯盐渍土为研究对象,建立基于BP神经网络模型的氯盐渍土溶陷特性的预测方法,研究氯盐含量、含水率及上覆荷载等主要影响因素对氯盐渍土溶陷系数的影响.研究表明,该预测模型的预测结果与实测数据具有较高的拟合度,验证了神经网络模型预测氯盐渍土溶陷特性的可行性.更多还原

【Abstract】 Non-uniform settlement of railway subgrade in Qinghai is serious,among which chlorine salt is the main factor causing the subsidence of railway subgrade.In order to study the subsidence characteristics of chlorine saline soil,a BP neural network model was established to predict the subsidence characteristics of chlorine saline soil in west Qinghai province,and the influences of major factors such as chlorine content,water content and overburden on the subsidence coefficient of chlorine saline soil were studied.The study shows that the prediction results of the model in this paper have a high fitting degree with the measured data,which verifies the feasibility of the neural network model in predicting the subsidence characteristics of the chlorine saline soil.更多还原