Fault detection of batch process based on dynamic MDONPE algorithm

Abstract

Abstract: To solve the problem of poor fault detection effect due to the nonlinear and dynamic characteristics of the data in the batch process, a multiway differential orthogonal neighborhood preserving embedding (MDONPE) algorithm based on the sliding window (SW) is proposed. Firstly, the data of the batch process is preprocessed to find the nearest neighbors of the samples, and the difference operations between the samples and the nearest neighbors is carried out. Then the orthogonal neighborhood preserving embedding algorithm with orthogonal constraints is obtained by orthogonalizing NPE algorithm, and the orthogonal neighborhood preserving embedding algorithm is used to reduce dimensions and extract features. The sliding window strategy is used to combine and achieve the error accumulation by selecting the sampling data within the window width, which can make the features of the fault samples more obvious. Finally, the fault is judged by detection, and the T² and SPE statistics are used to judge if faults have occurred. The data of the Penicillin fermentation simulation process are used and compared with MPCA and KNPE algorithms. The results show that the proposed algorithm has better detection effect than other algorithms in fault detection.

Key words: batch process, fault detection, orthogonal neighborhood preserving embedded, difference strategy, sliding window

CLC Number:

TP277

ZHAO Xiao-qiang, LIU Kai. Fault detection of batch process based on dynamic MDONPE algorithm[J]. Journal of Lanzhou University of Technology, 2022, 48(2): 90-96.

References

[1] JIANG Q C,YAN S F,YAN X F,et al.Data-driven two-dimensional deep correlated representation learning for nonlinear batch process monitoring [J].IEEE Transactions on Industrial Informatics,2020,16(4):2839-2848.
[2] 李春阳,夏丽莎,李军祥.KNPE算法在化工过程故障检测中的应用 [J].控制工程,2020,27(1):92-97.
[3] ZHANG H Y,TIAN X M,DENG X G,et al.Batch process fault detection and identification based on discriminant global preserving kernel slow feature analysis [J].ISA Transactions,2018,79:108-126.
[4] 文成林,吕菲亚.基于深度学习的故障诊断方法综述 [J].电子与信息学报,2020,42(1):234-248.
[5] 郭金玉,刘玉超,李元.一种基于改进局部熵PCA的工业过程故障检测方法 [J].高校化学工程学报,2019,33(4):922-932.
[6] 张成,高宪文,徐涛,等.基于独立元的k近邻故障检测策略 [J].控制理论与应用,2018,35(6):805-812.
[7] 赵帅,宋冰,侍洪波.基于加权互信息主元分析算法的质量相关故障检测 [J].化工学报,2018,69(3):962-973.
[8] 梁春燕,曹伟.基于邻域保持嵌入算法的语种识别 [J].陕西师范大学学报(自然科学版),2020,48(2):38-42.
[9] 王族,闫德勤,何阳,等.基于NPE改进算法的人脸识别 [J].软件导刊,2019,18(2):9-12.
[10] HUI Y Y,ZHAO X Q.Multi-phase batch process monitoring based on multiway weighted global neighborhood preserving embedding method [J].Journal of Process Control,2018,69:44-57.
[11] 杨健,宋冰,谭帅,等.时序约束NPE算法在化工过程故障检测中的应用 [J].化工学报,2016,67(12):5131-5139.
[12] JIANG Q C,YAN X F.Probabilistic weighted NPE-SVDD for chemical process monitoring [J].Control Engineering Practice,2014,28:74-89.
[13] 仝奇,胡双演,李钊,等.基于KPCA的BP神经网络齿轮泵故障诊断方法研究 [J].无线电工程,2015,45(9):72-76.
[14] 常鹏,乔俊飞,王普,等.基于MKECA的非高斯性和非线性共存的间歇过程监测 [J].化工学报,2018,69(3):1200-1206.
[15] 赵小强,王涛.基于SPA间歇过程故障诊断的MKNPE算法 [J].兰州理工大学学报,2016,42(3):82-87.
[16] 张成,郭青秀,冯立伟,等.基于局部近邻标准化和动态主元分析的故障检测策略 [J].计算机应用,2018,38(9):2730-2734.
[17] 张忠祥,程辉,叶贞成,等.用于动态化工过程故障检测的T-TELPP算法 [J].华东理工大学学报(自然科学版),2018,44(4):496-503.
[18] LUO L J,BAO S Y.Knowledge-data-integrated sparse modeling for batch process monitoring [J].Chemical Engineering Science,2018,189:221-232.
[19] 赵化良.基于传递熵的MPCA间歇过程监测方法 [J].计算机系统应用,2016,25(2):146-151.
[20] 郭金玉,齐蕾蕾,李元.基于DMOLPP的间歇过程在线故障检测 [J].仪器仪表学报,2015,36(1):134-142.
[21] 梁秀霞,郑向博,郑晓慧.基于邻域保持嵌入算法的间歇过程故障检测 [J].自动化与仪表,2015,30(10):1-4.
[22] 魏永合,马步芳,刘炜,等.基于VMD与正交局部保持投影的齿轮故障诊断 [J].组合机床与自动化加工技术,2020(3):3-6.
[23] 郭金玉,仲璐璐,李元.基于差分局部保持投影的非线性过程故障检测 [J].信息与控制,2018,47(2):200-205.
[24] 柯亮,熊伟丽,徐保国.基于滑动窗PCA的微小故障检测 [J].小型微型计算机系统,2016,37(6):1360-1364.
[25] 惠永永,赵小强.基于WICA-WGNPE的高斯-非高斯联合指标间歇过程监控 [J].仪器仪表学报,2018,39(1):190-199.
[26] BIROL G,UNDEY C,PARULEKAR S J,et al.A morphologically structured model for penicillin production [J].Biotechnology and Bioengineering,2002,77(5):538-552.