基于多尺度模糊熵和支持向量机的采煤机截割模式识别  

Shearer cutting pattern recognition based on multi-scale fuzzy entropy and support vector machine

作　　者：梁斌[1,2] 刘泽[2] 牛延博[2] LIANG Bin;LIU Ze;NIU Yan-bo(Xuhai College,China University of Mining and Technology,Xuzhou 221008,China;School of Mechatronic Engineering,China University of Mining and Technology,Xuzhou 221116,China)

机构地区：[1]中国矿业大学徐海学院,江苏徐州221008 [2]中国矿业大学机电工程学院,江苏徐州221116

出　　处：《煤炭工程》2021年第5期131-135,共5页Coal Engineering

基　　金：国家自然科学基金项目(51605477);江苏省高等学校自然科学研究面上项目(19KJB510014)。

摘　　要：为解决当前采煤机智能化水平低的问题,提出了一种基于多尺度模糊熵、拉普拉斯分值和支持向量机相融合的采煤机截割模式识别方法。通过提取不同截割模式下摇臂的振动信号的多尺度模糊熵,掌握表征采煤机截割模式的特征向量。同时,利用拉普拉斯分值筛选含有丰富截割模式信息的特征向量,并作为支持向量机的学习样本。搭建了采煤机煤岩截割实验系统,提取了不同截割模式下的摇臂振动信号,并进行实验分析。结果表明:文章所提出的截割模式识别方法具有较高的识别精度。研究成果可为推动综采工作面的智能化快速发展提供技术支撑。Aiming at the low intelligent level of shearer,a method for cutting pattern recognition of shearer is presented which combines multi-scale fuzzy entropy,Laplace score and support vector machine.By extracting the multi-scale fuzzy entropy of the vibration signal under different cutting modes,the feature vector is obtained representing the cutting pattern.At the same time,the feature vectors possessing rich cutting pattern information are selected based on Laplace score,which are used as the learning samples of support vector machine.The experimental system of shearer cutting coal-rock is built,and the vibration signals of rocker arm under different cutting patterns are extracted.The experimental analysis is carried out and the results indicate that the proposed cutting pattern recognition method has high recognition accuracy.The research can provide technical support for the intelligent and rapid development of fully mechanized mining face.

关 键 词：采煤机 截割模式 振动信号 多尺度模糊熵 

分 类 号：TD421.6[矿业工程—矿山机电]