基于BU-DDTW多阶段SPCA-PSD间歇过程故障监测

doi:10.16088/j.issn.1001-6600.2024062302

摘要/Abstract

摘要： 针对间歇过程中复杂的动态特性和多阶段特性导致故障监测精度低的问题,本文提出一种基于自底向上导数动态时间规整(BU-DDTW)的半正定稀疏主成分分析(SPCA-PSD)多阶段间歇过程故障监测方法。首先,利用encoder-decoder模型捕捉批处理后的时间序列动态特征。其次,结合BU-DDTW合并策略,衡量不同子序列之间的动态结构相似度,实现精准阶段划分。然后,通过SPCA-PSD方法引入稀疏性和半正定约束,精准识别表征各阶段特性的关键变量,构建多阶段故障监测模型。在青霉素补料分批发酵过程数据进行实验验证中,本文对6种不同故障类型的平均故障监测率达95.2%,显著优于其他方法,结果证明本文所提方法在间歇过程阶段划分的有效性,同时增强了多阶段故障监测模型的准确性和可解释性。

关键词: 间歇过程, 故障监测, 阶段划分, 非线性, 动态性

Abstract: To address the issue of low fault detection accuracy in intermittent processes due to complex dynamic characteristics and multi-stage features, a fault detection method for multi-stage intermittent processes based on Bottom-Up Derivative Dynamic Time Warping (BU-DDTW) and Semi-Positive Definite Sparse Principal Component Analysis (SPCA-PSD) is proposed. Initially, an encoder-decoder model is utilized to capture the dynamic characteristics of the time series after batching. Subsequently, by integrating the BU-DDTW merging strategy, the dynamic structural similarity between different subsequences is measured, achieving precise phase division. Then, the SPCA-PSD method introduced sparsity and semi-positive definite constraints to accurately identify key variables representing the characteristics of each stage, constructing a multi-stage fault detection model. Experiments are conducted on data from the penicillin supplementation batch fermentation process, and the results demonstrate that the proposed method achieves an average fault detection rate of 95.2% for six different types of faults, significantly outperforming other methods. The results not only prove the effectiveness of the proposed method in phase division of intermittent processes, but also enhance the accuracy and interpretability of the multi-stage fault detection model.

Key words: batch process, fault monitoring, phase division, nonlinearity, dynamic nature

中图分类号: TP277

王震, 高丙朋, 蔡鑫, 祝景亮, 郭思旭. 基于BU-DDTW多阶段SPCA-PSD间歇过程故障监测[J]. 广西师范大学学报（自然科学版）, 2025, 43(5): 91-103.

WANG Zhen, GAO Bingpeng, CAI Xin, ZHU Jingliang, GUO Sixu. Multi-stage SPCA-PSD Intermittent Process Fault Monitoring Based on BU-DDTW[J]. Journal of Guangxi Normal University(Natural Science Edition), 2025, 43(5): 91-103.

参考文献

[1] 赵春晖, 余万科, 高福荣. 非平稳间歇过程数据解析与状态监控: 回顾与展望[J]. 自动化学报, 2020, 46(10): 2072-2091. DOI: 10.16383/j.aas.c190586.
[2] 池荣虎, 侯忠生, 黄彪. 间歇过程最优迭代学习控制的发展: 从基于模型到数据驱动[J]. 自动化学报, 2017, 43(6): 917-932. DOI: 10.16383/j.aas.2017.c170086.
[3] PENG C, KAI W, PU W. Quality relevant over-complete independent component analysis based monitoring for non-linear and non-Gaussian batch process[J]. Chemometrics and Intelligent Laboratory Systems, 2020, 205: 104140. DOI: 10.1016/j.chemolab.2020.104140.
[4] GE Z Q, SONG Z H, GAO F R. Review of recent research on data-based process monitoring[J]. Industrial & Engineering Chemistry Research, 2013, 52(10): 3543-3562. DOI: 10.1021/ie302069q.
[5] 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. DOI: 10.1109/TII.2019.2952931.
[6] 高学金, 孟令军, 王豪, 等. 基于分步时空JITL-MKPLS的间歇过程故障监测[J]. 高校化学工程学报, 2021, 35(1): 127-139. DOI: 10.3969/j.issn.1003-9015.2021.01.015.
[7] JIANG Q C, GAO F R, YAN X F, et al. Multiobjective two-dimensional CCA-based monitoring for successive batch processes with industrial injection molding application[J]. IEEE Transactions on Industrial Electronics, 2019, 66(5): 3825-3834. DOI: 10.1109/TIE.2018.2860571.
[8] LOUWERSE D J, SMILDE A K. Multivariate statistical process control of batch processes based on three-way models[J]. Chemical Engineering Science, 2000, 55(7): 1225-1235. DOI: 10.1016/S0009-2509(99)00408-X.
[9] ZHAO C H, WANG F L, MAO Z Z, et al. Improved knowledge extraction and phase-based quality prediction for batch processes[J]. Industrial & Engineering Chemistry Research, 2008, 47(3): 825-834. DOI: 10.1021/ie0707063.
[10] DOAN X T, SRINIVASAN R, BAPAT P M, et al. Detection of phase shifts in batch fermentation via statistical analysis of the online measurements: a case study with rifamycin B fermentation[J]. Journal of Biotechnology, 2007, 132(2): 156-166. DOI: 10.1016/j.jbiotec.2007.06.013.
[11] CAMACHO J, PICÓ J. Multi-phase principal component analysis for batch processes modelling[J]. Chemometrics and Intelligent Laboratory Systems, 2006, 81(2): 127-136. DOI: 10.1016/j.chemolab.2005.11.003.
[12] LU N Y, GAO F R, WANG F L. Sub-PCA modeling and on-line monitoring strategy for batch processes[J]. AIChE Journal, 2004, 50(1): 255-259. DOI: 10.1002/aic.10024.
[13] CAMACHO J, PICÓ J, FERRER A. Multi-phase analysis framework for handling batch process data[J]. Journal of Chemometrics, 2008, 22(11/12): 632-643. DOI: 10.1002/cem.1151.
[14] WANG Y J, MAO Z Z, JIA M X, et al. Stage-based variable sampling period modeling and on-line monitoring strategy for uneven-length batch processes[C]// The 26th Chinese Control and Decision Conference (2014 CCDC). Piscataway, NJ: IEEE, 2014: 4501-4506. DOI: 10.1109/CCDC.2014.6852975.
[15] LI W Q, ZHAO C H, SUN Y X. Sequential tnequal-iength phase identification and modelling method for fault detection of varying-duration batch processes[J], Cotrol Theoy & Application, 2015, 32: 1226-1232. DOI: 10.7641/CTA.2015.50238.
[16] PENG K X, LI Q Q, ZHANG K, et al. Quality-related process monitoring for dynamic non-Gaussian batch process with multi-phase using a new data-driven method[J]. Neurocomputing, 2016, 214: 317-328. DOI: 10.1016/j.neucom.2016.06.018.
[17] ZHAO L P, YANG J Y. Batch process monitoring based on quality-related time-batch 2D evolution information[J]. Sensors, 2022, 22(6): 2235. DOI: 10.3390/s22062235.
[18] 李征, 王普, 高学金, 等. 基于信息增量矩阵的多阶段间歇过程质量预测[J]. 化工学报, 2018, 69(12): 5164-5172. DOI: 10.11949/j.issn.0438-1157.20180570.
[19] 胡磊, 刘强, 吴永建, 等. 间歇过程动态潜结构阶段划分与在线监控[J]. 控制理论与应用, 2022, 39(2):307-316. DOI:10.7641/CTA.2021.00817.
[20] ZHENG J J, ZHANG X Y, LIU Y X, et al. Fast sparse PCA via positive semidefinite projection for unsupervised feature selection[EB/OL]. (2023-10-25)[2024-12-20]. https://www.techrxiv.org/users/684400/articles/678866-fast-sparse-pca-via-positive-semidefinite-projection-for-unsupervised-feature-selection. DOI: 10.36227/techrxiv.20976760.v2.
[21] LI J W, MA R J, DENG M S, et al. A comparative study of clustering algorithms for intermittent heating demand considering time series[J]. Applied Energy, 2024, 353: 122046. DOI: 10.1016/j.apenergy.2023.122046.
[22] 喻思婷, 彭靖静, 彭振赟. 矩阵方程的秩约束最小二乘对称半正定解及其最佳逼近[J]. 广西师范大学学报(自然科学版), 2022, 40(4): 136-144. DOI: 10.16088/j.issn.1001-6600.2021092301.
[23] ZHU P F, HU Q H, ZHANG C Q, et al. Coupled dictionary learning for unsupervised feature selection[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2016, 30(1): 2422 - 2428. DOI: 10.1609/aaai.v30i1.10239.
[24] 周桥, 翟江涛, 荚东升, 等. 基于卷积门控循环神经网络的Web攻击检测方法[J]. 广西师范大学学报(自然科学版), 2023, 41(6): 51-61. DOI: 10.16088/j.issn.1001-6600.2023022203.
[25] 邱天, 丁艳军, 吴占松. 基于主元分析的故障可检测性的统计指标比较[J]. 清华大学学报(自然科学版), 2006, 46(8): 1447-1450. DOI: 10.16511/j.cnki.qhdxxb.2006.08.026.
[26] BIROL G, ÜNDEY C, ÇINAR A. A modular simulation package for fed-batch fermentation: penicillin production[J]. Computers & Chemical Engineering, 2002, 26(11): 1553-1565. DOI: 10.1016/S0098-1354(02)00127-8.
[27] BAJPAI R K, REUβ M. A mechanistic model for penicillin production[J]. Journal of Chemical Technology and Biotechnology, 1980, 30(1): 332-344. DOI: 10.1002/jctb.503300140.
[28] YUE H H, QIN S J. Reconstruction-based fault identification using a combined index[J]. Industrial & Engineering Chemistry Research, 2001, 40(20): 4403-4414. DOI: 10.1021/ie000141+.
[29] 高学金, 李学凤, 齐咏生. 基于扩散距离的信息熵FCM多阶段LSTM-AE间歇过程故障监测[J]. 高校化学工程学报, 2023, 37(1):120-130. DOI:10.3969/j.issn.1003-9015.2023.01.015.
[30] 姚红娟. 基于数据驱动的间歇过程在线监测与质量预测方法研究[D]. 兰州: 兰州理工大学, 2023. DOI: 10.27206/d.cnki.ggsgu.2023.000026.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed