Abstract：The change of landslide displacement is determined by dynamic functioning of inducing factors besides the basic geological conditions. In order to establish the response relation between dynamic changes of landslide displacement and inducing factors，time series decomposable model is used to decompose the displacement into trend term and periodic term by moving average method. Trend term displacement is determined by the potential energy and constraint condition of the slope and is predicted by displacement polynomial function. Periodic term displacement is affected by the periodic dynamic functioning of inducing factors，such as rainfall，reservoir level fluctuation and so on. The rainfall of current month，cumulative rainfall of anterior two months，reservoir level fluctuation of current month and cumulative increment of total displacement in current year are selected as influencing factors，and the multivariable BP neural network is adopted to predict the displacement. The prediction values of trend displacement and periodic displacement are superposed to obtain total displacement prediction. This model is used to deal with the data of displacement，rainfall and reservoir level fluctuation of Baishuihe landslide in the Three Gorges reservoir area. The results indicate that the prediction model based on the inducing factors and the landslide displacement comprehensively can reflect the key role of dynamic change of inducing factors in displacement development and can improve the precision and effectiveness of prediction results.
杜娟，殷坤龙，柴波. 基于诱发因素响应分析的滑坡位移预测模型研究 [J]. 岩石力学与工程学报, 2009, 28(09): 1783-1789.
DU Juan，YIN Kunlong，CHAI Bo. STUDY OF DISPLACEMENT PREDICTION MODEL OF LANDSLIDE BASED ON RESPONSE ANALYSIS OF INDUCING FACTORS . , 2009, 28(09): 1783-1789.
