基于核主成分分析的热连轧断带故障诊断

热连轧生产过程中经常出现设备和质量故障,为了快速确定故障原因并排除故障,需要对生产过程开展监控以及对故障进行诊断。基于热连轧生产过程采集的数据,采用核主成分分析法对热连轧轧制过程中精轧机组相关数据进行监控,并对断带故障进行诊断。先使用平方预测误差(SPE)统计量监控生产过程,再基于核主成分分析绘制出各变量贡献率图,最后依据贡献率大小找出造成故障的主要影响变量。与主成分分析法相比,采用核主成分分析法更为高效和准确。基于核主成分分析的热连轧断带故障诊断可节省故障分析时间,为热连轧生产过程调整和故障排除提供依据,具有重要的理论意义和实际应用价值。

Fault diagnosis of strip breaking in hot strip rolling based on kernel principal component analysis

Equipment and quality faults often occur during hot strip rolling process. In order to quickly determine the fault cause and eliminate faults, it is necessary to monitor the production process and diagnose the faults. Based on the data collected in the hot rolling process, the kernel principal component analysis is used to monitor the relevant data of the finishing mill and diagnose the broken strip fault. Using SPE statistics to monitor the production process, based on the kernel principal component analysis, the contribution plot of each variable is drawn, and the main influencing variables causing the fault are found out according to the contribution rate. Compared with principal component analysis, kernel principal component analysis is more efficient and accurate. The fault diagnosis of hot strip breaking based on kernel principal component analysis can save the fault analysis time and provide the basis for the adjustment and troubleshooting of hot rolling production process, which has important theoretical significance and practical application value.