基于改进多尺度主元分析的故障监测  

Fault monitoring based on improved multiscale principal component analysis

作　　者：李立[1] 齐咏生[1] 王林[1] 高学金[2] 王普[2] 

机构地区：[1]内蒙古工业大学电力学院,内蒙古自治区呼和浩特010080 [2]北京工业大学电子信息与控制工程学院,北京100124

出　　处：《计算机与应用化学》2014年第8期998-1002,共5页Computers and Applied Chemistry

基　　金：国家自然科学基金资助项目(61174109;61364009);内蒙古工业大学科学研究资助项目(ZD201234)

摘　　要：针对工业过程数据的非平稳性、含噪声以及随机性等特点,提出一种改进多尺度主元分析方法用于过程故障监测。首先利用小波阈值去噪的方法,消除原始过程数据中的大部分高频随机噪声,使得数据不受噪声的影响,然后利用小波分解将去噪后的数据分解成逼近系数和细节系数,分别在各个尺度上建立主元分析模型,对各个尺度小波系数消噪并重构得到综合尺度的故障监测模型。将该算法应用于田纳西伊士曼(Tennessee Eastman)过程中进行验证,仿真结果表明,与传统PCA以及MSPCA方法相比,改进的算法减少了误报率和漏报率,提高了过程监测的准确性。In order to handle the problem of nonstationary and random nature of data in the process industry, an improved multiscale principal component analysis is proposed, which contains different noises inevitably. Firstly, an improved wavelet threshold denoising method which combines multiple wavelet transform with a new threshold function based on the characteristics of wavelet analysis is proposed. The data collected from the industry condition are processed by means of the improved wavelet threshold danoising method. Using wavelets, the individual variable is decomposed 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. According to the simulation of Tennessee Eastman, and comparing the improved MSPCA with traditional MSPCA, it shows that the improved MSPCA has enhanced the accuracy of process monitoring.

关 键 词：小波变换 阈值去噪 多尺度主元分析 过程监测 

分 类 号：TQ015.9[化学工程] TP391.9[自动化与计算机技术—计算机应用技术]