【摘要】：多模態(tài)間歇過程測(cè)量數(shù)據(jù)異常直接影響數(shù)據(jù)驅(qū)動(dòng)的多元統(tǒng)計(jì)分析過程建模的準(zhǔn)確性,導(dǎo)致間歇過程的監(jiān)控性能降低。針對(duì)多模態(tài)間歇過程測(cè)量數(shù)據(jù)異常問題,提出了一種基于動(dòng)態(tài)超球結(jié)構(gòu)變化(DHSC)的多模態(tài)間歇過程測(cè)量數(shù)據(jù)異常檢測(cè)方法。該方法通過引入時(shí)序約束的模糊C均值聚類(SCFCM),利用隸屬度變化劃分多模態(tài)間歇過程的模態(tài);針對(duì)不同模態(tài),采用支持向量數(shù)據(jù)描述(SVDD)建立基于訓(xùn)練數(shù)據(jù)的靜態(tài)超球體和基于待檢數(shù)據(jù)的動(dòng)態(tài)超球體,選擇重要的支持向量作為球體結(jié)構(gòu),進(jìn)而通過識(shí)別超球體發(fā)生結(jié)構(gòu)變化實(shí)現(xiàn)過程測(cè)量數(shù)據(jù)異常檢測(cè)。青霉素發(fā)酵過程仿真實(shí)驗(yàn)表明,所提出的方法能夠?qū)崿F(xiàn)多模態(tài)間歇過程的模態(tài)劃分,減少了模態(tài)切換對(duì)過程測(cè)量數(shù)據(jù)異常檢測(cè)精度的影響,并能夠根據(jù)超球體結(jié)構(gòu)變化檢測(cè)過程測(cè)量數(shù)據(jù)異常,具有較高的檢測(cè)精度,降低了誤檢率。
[Abstract]:The outliers of measurement data in multimodal batch processes directly affect the accuracy of data-driven multivariate statistical analysis process modeling and result in the deterioration of monitoring performance of batch processes. In order to solve the problem of outliers in multimodal batch process measurement, a method of detecting outliers in multimodal batch process measurement based on dynamic hypersphere structure (DHSC) is proposed. In this method, the fuzzy C-means clustering (SCFCM), with time series constraints is introduced to divide the multimodal intermittent processes into modes by using the variation of membership degree. For different modes, support vector data is used to describe (SVDD) to establish static hypersphere based on training data and dynamic hypersphere based on data to be checked. The important support vector is chosen as sphere structure. Then the abnormal detection of process measurement data is realized by recognizing the structural changes of hypersphere. The simulation results of penicillin fermentation process show that the proposed method can realize modal partitioning of multimodal batch process and reduce the influence of modal switching on the accuracy of abnormal detection of process measurement data. It can measure the abnormal data according to the change of the hypersphere structure, and has higher detection accuracy and lower false detection rate.
【作者單位】： 北京化工大學(xué)信息科學(xué)與技術(shù)學(xué)院;
【基金】：國家自然科學(xué)基金項(xiàng)目(61240047) 北京市自然科學(xué)基金項(xiàng)目(4152041)~~
【分類號(hào)】：TQ06

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳嘉祺;間歇過程中釜的安排[J];化工設(shè)計(jì);1997年01期

2 李志紅,宋子明,袁志敏;間歇過程能量平衡和，

本文編號(hào)：2354903