摘要
本文旨在探讨多技术融合在煤矿掘进机状态监测与维修中的应用,通过集成振动、温度、压力传感器及视觉传感技术,结合机器学习算法,实现了设备健康状态的智能诊断。实验结果显示,多传感器融合诊断方法的故障检出率高达98.2%,平均预警时间提前至5.8天,显著提升了设备的可用率并降低了维修成本。
This article aims to discuss the application of multi-technology integration in the condition monitoring and maintenance of coal mining roadheaders.By integrating vibration,temperature,pressure sensors,and vision sensing technologies,combined with machine learning algorithms,intelligent diagnosis of equipment health status is achieved.Experimental results show that the fault detection rate of the multi-sensor fusion diagnostic method reaches as high as 98.2%,with an average early warning time advanced to 5.8 days,significantly improving the availability of the equipment and reducing maintenance costs.
作者
刘实
陈忠越
付洪磊
赵岩
LIU Shi;CHEN Zhongyue;FU Hongei;ZHAO Yan(Yankuang Energy Group Co.,Ltd.,Xinglongzhuang Coal Mine,Jining Shandong 272000,China)
出处
《信息与电脑》
2024年第16期58-60,65,共4页
Information & Computer
关键词
煤矿掘进机
状态监测
故障诊断
智能维修
coal mine boring machine
status monitoring
fault diagnosis
intelligent maintenance
