基于聚类分析的磨煤机断煤过渡状态识别

Recognition of Coal-breaking Transitional State of Coal Mill Based on Cluster Analysis

设备故障诊断已进入智能化阶段。提取设备大量的历史运行数据,并对其进行分析,是设备故障诊断的重要手段。该文以发电厂磨煤机为研究对象,根据故障机理分析筛选对磨煤机断煤故障灵敏度高的特征参数作为模型输入参数,基于模糊C均值聚类分析,构建故障识别模型,基于监测数据得到设备在正常、断煤过渡、断煤故障3种不同运行状态下的聚类中心。结果表明,模糊C均值聚类分析可以准确快速地辨识出磨煤机从正常到断煤故障过程中的过渡状态,为避免故障发生提供技术支撑。

Equipment fault diagnosis has entered the intelligent stage.Extracting a large amount of historical operating data of equipment and analyzing it is an important means of equipment fault diagnosis.This paper takes coal mills in power plants as the research object,selects characteristic parameters with high sensitivity to coal-breaking faults of coal mills based on failure mechanism analysis as model input parameters,builds a fault recognition model based on fuzzy C-means cluster analysis,and obtains the clustering center of the equipment in three different operating states,normal,coal cut transition,and coal cut failure based on monitoring data.The results show that the fuzzy C-means clustering analysis can accurately and quickly identify the transition state of the coal mill from normal to failure,and provide technical support for avoiding failures.