Fuzzy Self-Adaptable Prediction Method for High-Fill Road Foundation Settlement
Xiangxing Kong, Hongzhe Li · 2014
In the forecasting of road foundation settlement, different methods can often provide valuable information. When different forecasting methods combined properly, comprehensive forecast information are variously utilized. According to the principle of artificial intelligence and method of fuzzy mathematics, the fuzzy combination forecasting method of self-adaptively variable weight is proposed. Based on matching degree of past-recent period and actual value, the weights are automatically adjust, so that forecasting results will be accurate. The fuzzy combination forecasting method of self-adaptively variable weight is applied to the sub grade settlement in Hengzao expressway, which provides the prediction accuracy and reliable applicability. In order to improve the prediction accuracy, the measured sample points should increase, and with the passage of time, the recent settlement results should be set to the set of original sample.