北京工业大学学报
北京工業大學學報
북경공업대학학보
JOURNAL OF BEIJING POLYTECHNIC UNIVERSITY
2015年
5期
668-673
,共6页
常鹏%王普%高学金%程峥
常鵬%王普%高學金%程崢
상붕%왕보%고학금%정쟁
间歇过程%多向核熵偏最小二乘%高阶统计量%故障监测%故障变量追溯
間歇過程%多嚮覈熵偏最小二乘%高階統計量%故障鑑測%故障變量追溯
간헐과정%다향핵적편최소이승%고계통계량%고장감측%고장변량추소
batch process%multi-way kernel entropy partial least squares ( MKEPLS )%higer order statistics%fault monitoring%fault variable tracing
针对多向核熵偏最小二乘( multi-way kernel entropy partial least squares, MKEPLS)利用的是数据的一阶和二阶统计特性未考虑数据的高阶统计特性,在进行特征提取时会造成有用数据丢失的问题,提出基于高阶统计量的多向核熵偏最小二乘方法( higher order statistics multi-way kernel entropy partial least squares, HOS-MKEPLS)。首先,通过构造样本的高阶统计量将数据从原始的数据空间映射到高阶统计量样本空间。然后,再建立MKEPLS监控模型进行质量相关的故障监控,当监控到有故障发生时进行故障变量的追溯。最后,将该方法应用到工业青霉素发酵过程的监测中并与MKEPLS进行比较。结果表明:该方法具有更好的监控和故障识别性能。
針對多嚮覈熵偏最小二乘( multi-way kernel entropy partial least squares, MKEPLS)利用的是數據的一階和二階統計特性未攷慮數據的高階統計特性,在進行特徵提取時會造成有用數據丟失的問題,提齣基于高階統計量的多嚮覈熵偏最小二乘方法( higher order statistics multi-way kernel entropy partial least squares, HOS-MKEPLS)。首先,通過構造樣本的高階統計量將數據從原始的數據空間映射到高階統計量樣本空間。然後,再建立MKEPLS鑑控模型進行質量相關的故障鑑控,噹鑑控到有故障髮生時進行故障變量的追溯。最後,將該方法應用到工業青黴素髮酵過程的鑑測中併與MKEPLS進行比較。結果錶明:該方法具有更好的鑑控和故障識彆性能。
침대다향핵적편최소이승( multi-way kernel entropy partial least squares, MKEPLS)이용적시수거적일계화이계통계특성미고필수거적고계통계특성,재진행특정제취시회조성유용수거주실적문제,제출기우고계통계량적다향핵적편최소이승방법( higher order statistics multi-way kernel entropy partial least squares, HOS-MKEPLS)。수선,통과구조양본적고계통계량장수거종원시적수거공간영사도고계통계량양본공간。연후,재건립MKEPLS감공모형진행질량상관적고장감공,당감공도유고장발생시진행고장변량적추소。최후,장해방법응용도공업청매소발효과정적감측중병여MKEPLS진행비교。결과표명:해방법구유경호적감공화고장식별성능。
As the multi-way kernel entropy partial least squares ( MKEPLS ) method does not make full use of the higher-order statistics of the process data, which will lose the important information in the feature extraction, and result in degraded fault identification performance. To solve this problem, a novel method based on higher order statistics and multi-way kernel entropy partial least squares ( HOS-MKEPLS) is proposed, in which the raw data space is projected into statistics space by calculating the higher order statistics of the data set, establishing the monitoring MKEPLS model, then adopting the contribution figure method on the trace of the fault variables. Finallay, the method is applied to an industrial penicillin fermentation process, and compared with the MKEPLS model. Results show that the method has a better monitoring performance and can detect and identify the fault.