A new approach to predicting mining induced surface subsidence^①

来源期刊：中南大学学报(英文版)2006年第4期

论文作者：丁德馨 张志军 毕忠伟

文章页码：438 - 444

Key words：mining induced surface subsidence; fuzziness and interaction of parameters; artificial neural fuzzy inference system

Abstract: There are many parameters influencing mining induced surface subsidence. These parameters usually interact with one another and some of them have the characteristic of fuzziness. Current approaches to predicting the subsidence cannot take into account of such interactions and fuzziness. In order to overcome this disadvantage, many mining induced surface subsidence cases were accumulated, and an artificial neuro fuzzy inference system(ANFIS) was used to set up 4 ANFIS models to predict the rise angle, dip angle, center angle and the maximum subsidence, respectively. The fitting and generalization prediction capabilities of the models were tested. The test results show that the models have very good fitting and generalization prediction capabilities and the approach can be applied to predict the mining induced surface subsidence.