Prediction Model of Mining Subsidence Parameters Based on Fuzzy Clustering. (18th February 2022)

• Record Type: Journal Article
• Authors: Cheng, Fei; Yang, Jun; Zhang, Ziwen; Yu, Jingliang; Wang, Xuelian; Wu, Yongdong; Guo, Zhengyi; Li, Hui; Xu, Meng
• Other Names: Jan Naeem Academic Editor.
• Is Part Of: Journal of mathematics. Volume 2022(2022)
• Publication Date: 2022-02-18
• Subjects: Mathematics -- Periodicals; Mathematics; Periodicals; 510
• DOI: 10.1155/2022/7827104
• Languages: English
• ISSNs: 2314-4629

Abstract

Abstract : In view of the inaccuracy of rock movement observation data and the inaccuracy of mining subsidence prediction parameters, a prediction model of mining subsidence parameters based on fuzzy clustering is proposed. Through the analysis of the main geological and mineral characteristics of mining subsidence, the geological and mineral characteristics are simplified according to the third similar theorem. The feature equation is obtained by using the equation analysis method and dimension analysis method. The original fuzzy clustering method is improved, and the IWFCM_CCS algorithm based on competitive merger strategy is obtained. The data of rock movement observation are analyzed by fuzzy clustering. The membership matrix and clustering center of observation station data are obtained, and the regression model based on the weight of membership degree is established. The accuracy and feasibility of the parameter prediction model are verified by analyzing and comparing the actual measurement data and the predicted results of the model. The method reduces the error of the predicted parameters caused by the observation data and provides a method for the future calculation of the predicted parameters.