Forecasting Model of the Cultural Heritage Displacements Based on Verhuslt Radial Basis Function Neural Network

Guest Editor Yuantao Teng (Jilin Normal University, Shiping City, China)

Based on the displacement monitoring sequence of cultural heritage, the stability of relics could be judged effectively by forecasting the displacement in the future. Through analyzing advantages and disadvantages of grey forecasting methods and neural network respectively, a new forecasting model of verhuslt radial basis function neural network was proposed. First, in this study, by use of the time series analysis theory, the accumulation of the displacement sequences were generated, then the result sequence were predicated by the model of verhulst radial basis function neural network, at the same time, the ant colony clustering algorithm was used to optimize the parameters of new model. The new model not only developed the advantages of accumulation generation of the grey forecasting method, weakened the effect of stochastic-disturbing factors in original sequence and strengthened the regularity of data, but also used the quickly solving speed and the excellent characteristics of radial basis function neural network for nonlinear relationship and avoided the theoretical defects existing in the grey forecasting model. At last, one example is given to testify the effectiveness of the verhuslt radial basis function neural network method to forecast displacements of Tianlu stone carving of Tangshun tomb in China. The results show that the new model has higher precision.

Journal: International Journal of Simulation: Systems, Science & Technology, IJSSST V17

Published: Jan 7, 2016

DOI: 10.5013/IJSSST.a.17.01.17