Abstract: In order to establish multi-point sea wall seepage pressure monitoring model to describe its rules considering tidewater etc., radial basis function (RBF) artificial neural network was used together with sea wall seepage pressure effect factors analysis. Former tidewater factor, integral rain factor and time effect factor were put into the network as input units, while multiple suitable seepage pressure survey points were taken as output units together. Furthermore, the method to pre-select RBF center considering sea wall seepage pressure character was studied. Then fuzzy C-means algorithm (FCM) was used to adjust and decide them. The instance of Pudong sea wall shows the process of establishing seepage pressure multi-point RBF monitoring model which has good results. Suggestions of application were presented also.

Key words: sea wall seepage pressure, multi-point monitoring model, radial basis function(RBF), effect factor, fuzzy C-means algorithm(FCM)