STUDY ON A NNT MODEL OF SLOPE DISPLACEMENTS PREDICTION
Song Kezhi1,2 , Wang Mengshu2 ,Song keyong3
（1Yantai JiaoTong College of Normal University , Yantai 264025；2Northern JiaoTong University Research Center of Tunneling and Underground Works，Beijing 100044 China；3Shan Dong Company of Hydraulic Engineering, Jinan 250000）
Abstract：As slope failure is one of widely distributed geological which treads towards to destroy ecological balance and reduces economic profits，the displacement of a slope is basically significant to predict the slope failure．But for the complication, variety, randomicity, nonstablity of factors leading to slope displacement，it is very difficult to develop exact manifest models. However, Neural network posseses strong capacity of nonlinear reflection. This paper adopts BP neural network (NNT) model to forecast the displacements of slope. In the paper, by means of local measurements in northern slope of Cangshang gold mine, Laizhou of Shandong , the BP NNT is trained. Then the net is tested by comparison between existed measurements and calculation. Finally the net can be used to calculate the displacements in the future. The whole progress course is programmed by Matlab languge. Three conclusions can be found: 1) the programs are easily realized by means of Matlab language; 2)there is tiny difference between calculated result and existed measurements and the model possesses high forecasting accuracy; 3)with the criterion of slope failure, we can use the model to predict time of slope failure .
宋克志;王梦恕;宋克勇. 边坡位移预测的神经网络模型研究[J]. 岩石力学与工程学报, 2003, 22(S1): 2382-2385.
Song Kezhi1,2,Wang Mengshu2,Song keyong3. STUDY ON A NNT MODEL OF SLOPE DISPLACEMENTS PREDICTION. , 2003, 22(S1): 2382-2385.
2003, Vol. 22 
