针对煤岩体稳定性预测的声发射分形特征研究  

Fractal Dimension Feature of Acoustic Emissions for Predicting the Stability of Coal Rock

作　　者：李晶 杨勇[2,3] LI Jing;YANG Yong(School of Computer Science,Najing Audit Unversity,Nanjing Jiangsu 211815,China;School of Information Engineering,Xuzhou College of Industrial Technology,Xuzhou Jiangsu 221140,China;Key Laboratory of Underwater Acoustic Signal Processing of Ministry of Education,Southeast University,Nanjing Jiangsu 210096,China)

机构地区：[1]南京审计大学计算机学院,江苏南京211815 [2]徐州工业职业技术学院信息工程学院,江苏徐州221140 [3]东南大学水声信号处理教育部重点实验室,江苏南京210096

出　　处：《电子器件》2025年第1期218-222,共5页Chinese Journal of Electron Devices

基　　金：国家自然科学基金项目(52005267)。

摘　　要：根据煤岩体失稳产生的声发射(AE)信号的混沌特性,提出了一种对信号波形分形(WFD)的分析方法,推导了波形分形维数的计算公式,采用混合蛙跳算法(WFD-SFLA)对公式参数进行优化。结合两种典型破裂模式下声发射实验数据,探讨了波形分形维数与短时释放能量的指数关系,采用支持向量机训练44种特征向量,建立煤岩稳定性评价模型。理论分析和实验结果表明:该声发射信号的分形特征实现了对岩体破裂过程的全面详细描述,明显提高了煤岩稳定性预测的精确度和降低了复杂度。According to the acoustic emission(AE)chaotic features caused by coal rock instability,a new fractal dimension algorithm based on waveform analysis method(WFD)is presented.The WFD computational formula is deduced,and shuffled frog leaping algorithm(WFD-SFLA)to further optimize the formula parameters.Based on this optimal formula,AE data from the two typical coal rock fracture modes in mine are selected to further get the exponent relationship between WFD-SFLA value and short-time energy,and then 44 different features are adopted to train SVM for predicting model of coal rock stability in mine.The theory analysis and experiment show that WFD-SFLA re-flects failure development of coal rock comprehensively and in detail,raises predicting precision and reduces computation complexity obvi-ously,demonstrating that the proposed method is a new effective way to predict and analyze the stability of coal rock.

关 键 词：分形维数 声发射 失稳破裂 岩体稳定性 

分 类 号：P631[天文地球—地质矿产勘探]