基于多源数据融合的煤矿防治水设备振动信号IMF识别方法  

IMF Recognition Method for Vibration Signals of Coal Mine Water Prevention and Control Equipment Based on Multi-source Data Fusion

作　　者：牛和平 康瑞玲 宋卫文 贺鑫 Niu Heping;Kang Ruiling;Song Weiwen;He Xin(Inner Mongolia Mengtai Buliangou Coal Industry Co.,Ltd.,Ordos 017100,China;School of Resources and Geosciences,China University of Mining and Technology,Xuzhou 221116,China;Anhui Huizhou Geological Safety Research Institute Co.,Ltd.,Hefei 231200,China;Guoyuan Power Co.,Ltd.,CHN Energy Group,Beijing 100033,China)

机构地区：[1]内蒙古蒙泰不连沟煤业有限责任公司,内蒙古鄂尔多斯017100 [2]中国矿业大学资源与地球科学学院,江苏徐州221116 [3]安徽惠洲地质安全研究院股份有限公司,合肥231200 [4]国家能源集团国源电力有限公司,北京100033

出　　处：《煤矿机械》2025年第4期195-198,共4页Coal Mine Machinery

基　　金：华电煤业集团有限公司科技项目(CHDKJ20-02-99)。

摘　　要：由于煤矿防治水设备振动信号具有复杂多变且微弱的特性,在本征模态函数(IMF)识别的过程中难以有效捕捉信号特征,从而导致IMF识别灵敏度较低。为了解决该问题,提出基于多源数据融合的煤矿防治水设备振动信号IMF识别方法。规划传感器部署方案,全面采集多个关键设备的振动信号。结合小波变换与小波包变换的优势,进行多统计特性分析,并应用滑动窗口平均滤波技术,有效融合多源振动信号。利用自适应噪声完备集合经验模态分解(CEEMDAN)算法对融合后的综合振动信号进行深入分解,精准识别IMF分量。实验结果表明,该方法能够高效识别煤矿防治水设备微弱振动信号,显著提升IMF识别灵敏度,为早期故障预警和设备维护提供了可靠依据。Due to the complex and weak vibration signal characteristics of coal mine water prevention and control equipment,it is difficult to effectively capture the signal features in the intrinsic mode functions(IMF)recognition process,resulting in a low IMF recognition sensitivity.To solve this problem,an IMF recognition method for vibration signals of coal mine water prevention and control equipment based on multi-source data fusion was proposed.Planned the deployment scheme of sensors to comprehensively collect vibration signals from multiple key equipment.Combined the advantages of wavelet transform and wavelet packet transform to conduct multi-statistical characteristic analysis,and applied the sliding window average filtering technology to effectively fuse multi-source vibration signals.Used the complete ensemble empirical mode decomposition with adaptive noise(CEEMDAN)algorithm to deeply decompose the integrated vibration signal,and accurately identified the IMF component.Experimental results show that this method can efficiently identify the weak vibration signal of coal mine water prevention and control equipment and significantly improve the IMF recognition sensitivity,which provides reliable basis for early fault warning and equipment maintenance.

关 键 词：多源数据融合 煤矿防治水设备 振动信号 IMF识别 CEEMDAN算法 

分 类 号：TD744[矿业工程—矿井通风与安全]