基于TWOA-BP的矿井冲击地压分级预测研究  

Study on Classification Prediction of Mine Rock Burst Based on TWOA-BP

作　　者：邵光波 李华强[1] 张涛 SHAO Guangbo;LI Huaqiang;ZHANG Tao(School of Mechanical Engineering,Inner Mongolia University of Technology,Huhhot 010051,China)

机构地区：[1]内蒙古工业大学机械工程学院,呼和浩特010051

出　　处：《煤炭技术》2024年第9期34-37,共4页Coal Technology

基　　金：内蒙古自治区科技计划项目(2021GG0259);内蒙古自治区直属高校基本科研业务费项目(JY20220223)。

摘　　要：为提高煤矿开采工作的安全性,准确预测煤矿冲击地压灾害发生,提出冲击地压分级预测的TWOA-BP模型。先通过灰色关联分析法(GRA)筛选冲击地压的影响因素作为TWOA-BP预测模型的输入层,最终确定8项影响因素后,采用鲸鱼算法(WOA)对BP神经网络的权值和阈值进行优化,随后利用Tent混沌映射初始化鲸鱼种群以增加种群多样性,最终解决了BP模型收敛速度慢和易陷入局部极小的问题。研究结果表明:与其他预测模型相比,TWOA-BP方法具有收敛速度快、预测精度高、操作简便等特点。In order to improve the safety of coal mine mining operations and accurately predict the occurrence of coal mine rock burst disasters,the TWOA-BP model for rock burst classification prediction is proposed.Firstly,the influencing factors of rock burst are selected as the input layer of the TWOA-BP prediction model through the grey relational analysis(GRA)method.After determining 8 influencing factors,the whale optimization algorithm(WOA)is used to optimize the weights and thresholds of the BP neural network.The Tent chaotic mapping is used to initialize the whale population to increase population diversity,which ultimately solves the problems of slow convergence speed and susceptibility to local minima in the BP model.The research results show that compared with other prediction models,the TWOA-BP method has the characteristics of high convergence speed,high prediction accuracy,and simple operation.

关 键 词：灰色关联分析法 Tent混沌映射 鲸鱼算法 BP网络模型 收敛速度 预测精度 

分 类 号：TD324[矿业工程—矿井建设]