多变量统计方法监测化工过程的缓变故障

MCUSUM-MSPCA based small shift monitoring in TE process

化工过程中缓变故障的存在,会影响装置长周期稳定的运行,严重的直接造成装置生产能力下降、生产成本增加。针对化工过程中难以监测的缓变故障,提出1种新的多变量统计过程的监测方法。把传统的单变量累计和控制图(CUSUM)扩展为多变量的形式,通过累计作用提取过程的微小变化,并与小波变换在定尺度下提取测量变量决定性特征的特性,以及传统的主元分析(PCA)去除变量间关联的优势相结合,构成新的MCUSUM-MSPCA方法。通过仿真研究TE过程,证明此方法可行和有效,极大地改善了监测过程缓变故障的效果。与PCA方法相比,MCUSUM-MSPCA方法能在不同频率范围内,有效、及时地监测到过程中的缓变故障,提高了过程监测的灵敏性,为操作人员在线排除故障提供了可能,从而可降低操作成本,保证产品质量。

Small shift has been a big problem in process industry, which usually takes a relative long time to develop and is hard to detect in early stage, but can result in facility shutdown. Operation cost and facility capacity will be negatively affected. Principal component analysis （PCA） has been widely used in multivariate process monitoring for its ability to reduce process dimensions. Cumulative sum （CUSUM） uses additional information from the past history of the process for keeping the memory effect of the process behavior trend. Wavelets transform decomposes the signals into approximations and details at different scales. Contributions from each scale are collected in separate matrices, and a PCA model is then constructed to extract correlation at each scale. In order to detect the process deviation initiated by gradual small shifts, we propose a new multivariate statistical method for process monitoring in this paper. The new method extends the conventional cumulative sum （CUSUM） for single variable to multi-variable case （ MCUSUM ） and further combines it with wavelet transform and principal component analysis （PCA） to form MCUSUM-MSPCA. The result shows that the process monitoring performance is significantly improved by proposed method. Compared with conventional PCA, MCUSUM-MSPCA can effectively detect variations at different resolutions and can detect faults in early stage, so as to avoid facility shutdown, reduce the operation cost and stabilize the product quality. So the provided method makes the process monitoring more reliable and prompt.