Abstract:

In order to accurately predict the development height of water-conducting fracture zone in

16 coal mining of Binhu Coal Mine，the measured data of 31 lower coal mining faces in North China Coal⁃

field were collected，and five factors including mining height，mining depth，coal seam dip angle，tendency

length and hard rock ratio coefficient were selected for comprehensive analysis.The Harris Hawk algorithm

(HHO) is used to optimize the ELM neural network，and the HHO-ELM water-conducting fracture zone

height prediction model is constructed.The model is applied to the prediction of the height of the water-con⁃

ducting fracture zone in Binhu Coal Mine，and the prediction results are compared with the calculation re⁃

sults of the standard formula and the measured results.The results show that the HHO-ELM model predicts

that the development height of the water-conducting fracture zone in the 21603 working face of Binhu Coal

Mine is 24.17 m，the calculation result of the standard formula is 18.58~29.78 m，and the measured result

is 21.45~22.98 m.It can be seen that the model is used to predict the height of the water-conducting fracture

zone，which is simple in calculation，strong in pertinence，and reliable in prediction accuracy. It provides a

basis for the decision-making of roof water damage control in the lower group of coal mining in Binhu Coal

Mine and similar geological conditions in North China Coalfield.

Key words:

North China coalfiled, height of water-conducting fracture zone, HHO-ELM model, in?jection water leakage measuring metod