Analyse And Study Of Slope Stability Based On Fuzzy Comprehensive Evaluation And Neural Network

Slope engineering is an important branch in geotechnical engineering. Slope engineering is a complicated systematic engineering. A lot of Engineering is related to slope stability, such as mining, road and bridge, water conservancy and structure engineering, etc. Its stabilization directly concerns the safety of engineering. With economical development and large-scale construction cause, it takes up more and more important place.Based on reviews of evaluation methods of slope stability, the main research work conducted in this paper is as follows:(1)Considering the uncertain problems of stability analysis which have the characteristics of random and fuzziness, the author uses the maximum membership degree principle to analyze and evaluate the slope stability. Ridge distribution in effect factor of quantity and trapezium distribution in the effect factor of ration are applied here to construct membership function. The gradation analysis method is used here to determine the proportion of importance of each effect factor. The method of two class synthesis assessment is adopted to analyze the stability of slope.(2)There are eleven effect factors chosen to analyze fuzzily the slope stability. We selected angle of cut slope, state of underwater, angle between surface of cut slope and major structure plane, efflorescence, etc. as major factors effect slop stability. The slop stability is assessed by each factor.(3)Based on one concrete engineering case, the method of fuzzy analysis is examined, and this result demonstrates that eleven membership functions, constructed by the author, are reasonable. So the proportion of importance is reasonable. The membership functions and the distribution of the proportion of importance can also be applied to analyze the stability of similar slopes.(4)Put the judgment of fuzzy comprehensive evaluation as the input of neural network by MATLAB. We transport out the final judgment through the neural network that possess learning ability. We have proved that the neural network can assess slope stability through inputting the model to the trained net.This paper used fuzzy analysis method and artificial neural network to build a model analyzing state of slope. The data of slope stability are adapted to train and test the mode1.And with the example of applicability and validity of the assessment models, we draw a significant and meaningful conclusion.