高学金,李学凤,齐咏生

• 1:北京工业大学信息学部
• 2:数字社区教育部工程研究中心
• 3:城市轨道交通北京实验室
• 4:计算智能与智能系统北京市重点实验室

摘要(Abstract)：

针对间歇过程中因忽略数据在阶段划分中的非线性，导致故障监测精度低的问题，提出一种基于扩散距离的信息熵模糊C均值(DDEFCM)多阶段长短期记忆网络的自动编码器(LSTM-AE)间歇过程故障监测方法。首先为了自动识别聚类个数，利用信息熵描述批处理后的二维时间片矩阵。再采用扩散距离对模糊C均值聚类(FCM)算法进行改进，解决欧式距离不能表征数据非线性的问题，有效划分间歇过程的稳定阶段，然后利用轮廓系数划分过渡阶段。最后建立多阶段LSTM-AE监测模型。利用青霉素发酵数据和大肠杆菌实际生产数据对该方法进行验证，结果表明所提方法不仅可以提升阶段划分性能，还能更加准确地进行故障监测。

关键词(KeyWords)： 间歇过程;非线性;扩散距离;阶段划分;故障监测

Abstract:

Keywords:

基金项目(Foundation): 北京市自然科学基金(4222041,4192011)

作者(Author): 高学金,李学凤,齐咏生

参考文献(References)：

• [1] YAO Y, GAO F. A survey on multiphase statistical modeling methods for batch processes[J]. Annual Reviews in Control, 2009,33(2):172-183.
• [2] SIMOGLOU A, GEORGIEVA P, MARTIN E B, et al. On-line monitoring of a sugar crystallization process[J]. Computers&Chemical Engineering, 2005, 29(6):1411-1422.
• [3] LAWRENCE X Y. Pharmaceutical quality by design:Product and process development, understanding, and control[J].Pharmaceutical Research, 2008, 25(10):781-791.
• [4] LU N, GAO F, YANG Y, et al. PCA-based modeling and on-line monitoring strategy for uneven-length batch processes[J].Industrial&Engineering Chemistry Research, 2004, 43(13):3343-3352.
• [5] ZHANG S M, ZHAO C H, GAO F R. Incipient fault detection for multiphase batch processes with li mited batches[J]. IEEE Transactions on Control Systems Technology, 2017, 27(1):103-117.
• [6] 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.
• [7] RENDALL R, CHIANG L H, REIS M S. Data-driven methods for batch data analysis-A critical overview and mapping on the complexity scale[J]. Computers&Chemical Engineering, 2019, 124:1-13.
• [8] ZHU J L, GAO F R. Similar batch process monitoring with orthogonal subspace alignment[J]. IEEE Transactions on Industrial Electronics, 2018, 65(10):8173-8183.
• [9] LUO L K, YAO Y, GAO F R, et al. Mixed-effects Gaussian process modeling approach with application in injection molding processes[J]. Journal of Process Control, 2018, 62:37-43.
• [10]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.GAO X J, MENG L J, WANG H, et al. Fault monitoring of batch processes based on substep time-space JITL-MKPLS[J]. Journal of Chemical Engineering of Chinese Universities, 2021, 35(1):127-139.
• [11] WANG R, EDGAR T F, BALDEA M, et al. A geometric method for batch data visualization, process monitoring and fault detection[J]. Journal of Process Control, 2018, 67:197-205.
• [12] 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.
• [13]高学金,刘腾飞,徐子东,等.基于循环自动编码器的间歇过程故障监测[J].化工学报, 2020, 71(7):3172-3179.GAO X J, LIU T F, XU Z D, et al. Intermittent process fault monitoring based on recurrent autoencoder[J]. CIESC Journal, 2020,71(7):3172-3179.
• [14] LU N, GAO F, WANG F. A sub-PCA modeling and online monitoring strategy for batch processes[J]. AIChE Journal, 2004, 50(1):255-259.
• [15] BEZDEK J C. Pattern recognition with fuzzy objective function algorithms[J]. Advanced Applications in Pattern Recognition,1981, 22(1171):203-239.
• [16] VERMA H, GUPTA A, KUMAR D. A modified intuitionistic fuzzy C-means algorithm incorporating hesitation degree[J]. Pattern Recognition Letters, 2019, 122:45-52.
• [17] KHALILIA M A, BEZDEK J, POPESCU M, et al. Improvements to the relational fuzzy C-means clustering algorithm[J]. Pattern Recognition, 2014, 47(12):3920-3930.
• [18] WU Z, WU Z, ZHANG J. An improved FCM algorithm with adaptive weights based on SA-PSO[J]. Neural Computing and Applications, 2017, 28(12):3113-3118.
• [19]王骏,刘欢,蒋亦樟,等.堆叠隐空间模糊C均值聚类算法[J].控制与决策, 2016, 31(9):1671-1677.WANG J, LIU H, JIANG Y Z, et al. Stacked hidden space fuzzy C-means clustering algorithm[J]. Control and Decision, 2016,31(9):1671-1677.
• [20] COIFMAN R R, LAFON S. Diffusion maps[J]. Applied and Computational Harmonic Analysis, 2006, 21(1):5-30.
• [21] LAFON S, LEE A B. Diffusion maps and coarse-graining:A unified framework for dimensionality reduction, graph partitioning, and data set parameterization[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(9):1393-1403.
• [22] KORONAKI E D, NIKAS A M, BOUDOUVIS A G. A data-driven reduced-order model of nonlinear processes based on diffusion maps and artificial neural networks[J]. Chemical Engineering Journal, 2020, 397:125475.
• [23] TANG X C, LI Y. Phase division and transition modeling based on the dominant phase identification for multiphase batch proces s quality prediction[J]. Transactions of the Institute of Measurement and Control, 2020, 42(5):1022-1036.
• [24] MALLAK A, FATHI M. Sensor and component fault detection and diagnosis for hydraulic machinery integrating LSTM autoencoder detector and diagnostic classifiers[J]. Sensors, 2021, 21(2):433.
• [25]高学金,刘爽爽,高慧慧.基于多变量卷积神经网络的发酵过程故障监测[J].高校化学工程学报, 2020, 34(6):1511-1519.GAO X J, LIU S S, GAO H H. Fault monitoring of fermentation processes based on multivariable convolution neural network[J].Journal of Chemical Engineering of Chinese Universities, 2020, 34(6):1511-1519.
• [26] YAN W W, GUO P J, GONG L, et al. Nonlinear and robust statistical process monitoring based on variant autoencoders[J].Chemometrics&Intelligent Laboratory Systems, 2016, 158:31-40.
• [27] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780.
• [28]郭新辰,郗仙田,樊秀玲,等.基于半监督的模糊C-均值聚类算法[J].吉林大学学报(理学版), 2015, 53(4):705-709.GUO X C, XIAO X T, FAN X L, et al. Fuzzy c-means clustering algorithm based on semi-supervised learning[J]. Journal of Jilin University, 2015, 53(4):705-709.
• [29]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(8):1447-1450.QIU T, DING Y J, WU Z S. Sensor fault detection statistics based on principal component analysis[J]. Journal of Tsinghua University(Science and Technology), 2006(8):1447-1450.
• [30]王普,曹彩霞,高学金,等.基于扩展得分矩阵的多阶段间歇过程质量预测[J].高校化学工程学报, 2019, 33(3):664-671.WANG P, CAO C X, GAO X J, et al. Quality prediction of multiphase batch processes based on extended score matrices[J].Journal of Chemical Engineering of Chinese Universities, 2019, 33(3):664-671.
• [31]王普,李春蕾,高学金,等.基于角结构统计量的MKECA间歇过程故障监测[J].仪器仪表学报, 2017, 38(1):174-180.WANG P, LI C L, GAO X J, et al. Research on batch process monitoring method based on multi-way kernel entropy component analysis and angular structure statistic[J]. Chinese Journal of Scientific Instrument, 2017, 38(1):174-180.
• [32] BIROL G, UNDEY C, CINAR A. A modular simulation package for fed-batch fermentation:Penicillin production[J]. Computers and Chemical Engineering, 2002, 26(11):1553-1565.