Rock Burst Classification Prediction Method Based on Weight Inverse Analysis Cloud Model

5th International Conference on Environmental Science and Civil Engineering

生态环境科学;土木建筑工程

Yu, Junchao^1 ; Liu, Shangge^2 ; Gao, Ling^3

Hebei Research Institute of Construction and Geotechnical Investigation Co. Ltd., Shijiazhuang, China^1

CCCC Second Highway Consultants Co. Ltd., Wuhan, China^2

Hebei Provincial Communications Planning and Design Institue, Hebei Province, Shijiazhuang, China^3

关键词: Classification prediction;    Comprehensive evaluation;    Evaluation factor;    Hydropower stations;    Independent variables;    Maximum tangential stress;    Objective functions;    Weighting process;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/283/1/012023/pdf
DOI  :  10.1088/1755-1315/283/1/012023

来源: IOP

【 摘 要 】

A cloud model comprehensive evaluation method based on weight inverse analysis is proposed and applied to the prediction of rock burst grade. At first, the objective function with weight as independent variable is derived and established. The objective weight of each evaluation factor is obtained by genetic algorithm. Then the concrete steps of the coupling of weight inverse analysis and cloud model are given. After that, σθ/σc σc/σt and Wet are selected as the evaluation factors. σθ/σc is the ratio of the maximum tangential stress in the cavern to the compressive strength of rock. σc/σt is the ratio of tensile strength to the compressive strength of rock. Wet is the elastic energy index. According to the rock burst engineering example, the inverse analysis and calculation of the factor weights are carried out. Finally, this method is applied to the rock burst grade prediction of Jiangbian Hydropower Station and Maluping Mine. Compared with the cloud model prediction results of other weighting methods, its feasibility and effectiveness has been verified. The research shows that the cloud model for rock burst based on weighted inverse analysis is less subjective in the weighting process and the prediction effect is better.