基于联合典型变量矩阵的多阶段发酵过程质量相关故障监测

doi:10.11949/0438-1157.20211294

摘要/Abstract

摘要：

为考虑发酵过程的质量变量和动态特征对于阶段划分的影响，提出了一种基于联合典型变量矩阵的多阶段发酵过程质量相关故障监测方法。首先，将历史三维数据沿批次方向展开，对每个时间片矩阵进行典型相关分析（canonical correlation analysis， CCA），得到融合过程变量和质量变量信息的联合典型变量矩阵，对其进行K均值聚类，实现基于静态特征的第1步划分；然后采用慢特征分析（slow feature analysis， SFA）算法提取表征过程动态性的慢特征，对其进行聚类实现第2步划分。最后综合分析两步划分结果，将生产过程划分为不同的稳定阶段和过渡阶段，并在划分的子阶段中分别建立CCA监测模型进行质量相关故障监测。该方法通过静态和动态特征的变化实现两步划分，准确区分强动态变化与阶段切换，有效提高质量相关的故障监测模型精度。青霉素仿真平台与大肠杆菌实际生产数据验证了所提方法的可行性和有效性。

关键词: 发酵, 间歇式, 多阶段, 联合典型变量矩阵, 典型相关分析, 故障监测, 算法

Abstract:

In order to consider the influence of the quality variables and dynamic characteristics of the fermentation process on the stage division, a multi-phase fermentation process quality-related fault monitoring method based on the joint canonical variable matrix is?proposed. Firstly, the 3D data were unfolded along the batch direction. Canonical correlation analysis (CCA) was performed on each time slice matrix to obtain the joint canonical variable matrices, which were equipped with process variables and quality variables, and K-mean algorithm was used to realize first partition. Then slow feature analysis (SFA) was used to extract the slow characteristics of the process dynamics, and the K-mean algorithm was used for the second partition. Finally, the production process was divided into different stable phases and transition phases through the comprehensive analysis of the two-step division results. The CCA monitoring model was established in each phase after partition for quality-related fault detection. According to the changes of static and dynamic characteristics, this method can accurately distinguish the strong dynamics and the phase boundaries by a two-step partition, also e?ectively improve the accuracy of quality-related fault monitoring. The feasibility and effectiveness of the proposed algorithm were illustrated by a penicillin simulation platform and an industrial application of E. coli fermentation, respectively.

Key words: fermentation, batch-wise, multi-phase, joint canonical variable matrix, canonical correlation analysis, fault monitoring, algorithm

中图分类号:

TP 273

高学金, 何紫鹤, 高慧慧, 齐咏生. 基于联合典型变量矩阵的多阶段发酵过程质量相关故障监测[J]. 化工学报, 2022, 73(3): 1300-1314.

Xuejin GAO, Zihe HE, Huihui GAO, Yongsheng QI. Quality-related fault monitoring of multi-phase fermentation process based on joint canonical variable matrix[J]. CIESC Journal, 2022, 73(3): 1300-1314.

图/表 16

参考文献 36

1	Zhang S M, Zhao C H, Gao F R. Incipient fault detection for multiphase batch processes with limited batches[J]. IEEE Transactions on Control Systems Technology, 2019, 27(1): 103-117.
2	于蕾, 邓晓刚, 曹玉苹, 等. 基于变量分组DTW-MCVA的不等长间歇过程故障检测方法[J]. 化工学报, 2019, 70(9): 3441-3448.
	Yu L, Deng X G, Cao Y P, et al. Fault detection method of unequal-length batch process based on VGDTW-MCVA[J]. CIESC Journal, 2019, 70(9): 3441-3448.
3	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.
4	Tulsyan A, Garvin C, Undey C. Industrial batch process monitoring with limited data[J]. Journal of Process Control, 2019, 77: 114-133.
5	Qin S J, Zheng Y Y. Quality-relevant and process-relevant fault monitoring with concurrent projection to latent structures[J]. AIChE Journal, 2013, 59(2): 496-504.
6	Zhang Y W, Zhang Y. Process monitoring, fault diagnosis and quality prediction methods based on the multivariate statistical techniques[J]. IETE Technical Review, 2010, 27(5): 406-420.
7	Chen Z W, Liu C, Ding S X, et al. A just-in-time-learning-aided canonical correlation analysis method for multimode process monitoring and fault detection[J]. IEEE Transactions on Industrial Electronics, 2021, 68(6): 5259-5270.
8	彭开香, 张丽敏. 基于核典型相关性-熵成分分析的工业过程质量检测方法[J]. 控制与决策, 2021, 36(12): 2999-3006.
	Peng K X, Zhang L M. A quality monitoring method for industrial process based on kernel canonical correlation-entropy component analysis[J]. Control and Decision, 2021, 36 (12): 2999-3006.
9	褚菲, 彭闯, 贾润达, 等. 基于多尺度核JYMKPLS迁移模型的间歇过程产品质量的在线预测方法[J]. 化工学报, 2021, 72(4): 2178-2189.
	Chu F, Peng C, Jia R D, et al. Online prediction method of batch process product quality based on multi-scale kernel JYMKPLS transfer model[J]. CIESC Journal, 2021, 72(4): 2178-2189.
10	贾润达, 毛志忠, 王福利. 基于KPLS模型的间歇过程产品质量控制[J]. 化工学报, 2013, 64(4): 1332-1339.
	Jia R D, Mao Z Z, Wang F L. KPLS model based product quality control for batch processes[J]. CIESC Journal, 2013, 64(4): 1332-1339.
11	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.
12	胡益, 王丽, 马贺贺, 等. 基于核PLS方法的非线性过程在线监控[J]. 化工学报, 2011, 62(9): 2555-2561.
	Hu Y, Wang L, Ma H H, et al. Online nonlinear process monitoring using kernel partial least squares[J]. CIESC Journal, 2011, 62(9): 2555-2561.
13	赵春晖, 王福利, 姚远, 等. 基于时段的间歇过程统计建模、在线监测及质量预报[J]. 自动化学报, 2010, 36(3): 366-374.
	Zhao C H, Wang F L, Yao Y, et al. Phase-based statistical modeling, online monitoring and quality prediction for batch processes[J]. Acta Automatica Sinica, 2010, 36(3): 366-374.
14	Yu W K, Zhao C H. Recursive exponential slow feature analysis for fine-scale adaptive processes monitoring with comprehensive operation status identification[J]. IEEE Transactions on Industrial Informatics, 2019, 15(6): 3311-3323.
15	Yu J, Qin S J. Multiway Gaussian mixture model based multiphase batch process monitoring[J]. Industrial & Engineering Chemistry Research, 2009, 48(18): 8585-8594.
16	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.
17	Zhao C H, Wang F L, Lu N Y, et al. Stage-based soft-transition multiple PCA modeling and on-line monitoring strategy for batch processes[J]. Journal of Process Control, 2007, 17(9): 728-741.
18	Ng Y S, Srinivasan R. An adjoined multi-model approach for monitoring batch and transient operations[J]. Computers & Chemical Engineering, 2009, 33(4): 887-902.
19	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.
	Li Z, Wang P, Gao X J, et al. Information increment matrix based quality prediction for multi-phase batch processes[J]. CIESC Journal, 2018, 69(12): 5164-5172.
20	Zhao C H, Sun Y X. Step-wise sequential phase partition (SSPP) algorithm based statistical modeling and online process monitoring[J]. Chemometrics and Intelligent Laboratory Systems, 2013, 125: 109-120.
21	Qin Y, Zhao C H, Gao F R. An iterative two-step sequential phase partition (ITSPP) method for batch process modeling and online monitoring[J]. AIChE Journal, 2016, 62(7): 2358-2373.
22	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.
	Zhao C H, Yu W K, Gao F R. Data analytics and condition monitoring methods for nonstationary batch processes-current status and future[J]. Acta Automatica Sinica, 2020, 46(10): 2072-2091.
23	Hotelling H. Relations between two sets of variates[J]. Biometrika, 1936, 28(3/4): 321-377.
24	Yang Y Q, Xu L, Hu C Y. Extended adjacency matrix indices and their applications[J]. Journal of Chemical Information and Computer Sciences, 1994, 34(5): 1140-1145.
25	Wiskott L, Sejnowski T J. Slow feature analysis: unsupervised learning of invariances[J]. Neural Computation, 2002, 14(4): 715-770.
26	Shang C, Huang B, Yang F, et al. Slow feature analysis for monitoring and diagnosis of control performance[J]. Journal of Process Control, 2016, 39: 21-34.
27	Zhang H Y, Deng X G, Zhang Y C, et al. Dynamic nonlinear batch process fault detection and identification based on two-directional dynamic kernel slow feature analysis[J]. The Canadian Journal of Chemical Engineering, 2021, 99(1): 306-333.
28	齐咏生, 王普, 高学金, 等. 一种新的多阶段间歇过程在线监控策略[J]. 仪器仪表学报, 2011, 32(6): 1290-1297.
	Qi Y S, Wang P, Gao X J, et al. Novel online monitoring strategy for multiphase batch processes[J]. Chinese Journal of Scientific Instrument, 2011, 32(6): 1290-1297.
29	Shang C, Huang B, Yang F, et al. Probabilistic slow feature analysis-based representation learning from massive process data for soft sensor modeling[J]. AIChE Journal, 2015, 61(12): 4126-4139.
30	Zhang H Y, Tian X M, Deng X G, et al. Multiphase batch process with transitions monitoring based on global preserving statistics slow feature analysis[J]. Neurocomputing, 2018, 293: 64-86.
31	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.
32	刘毅, 王海清. Pensim仿真平台在青霉素发酵过程的应用研究[J]. 系统仿真学报, 2006, 18(12): 3524-3527.
	Liu Y, Wang H Q. Pensim simulator and its application in penicillin fermentation process[J]. Journal of System Simulation, 2006, 18(12): 3524-3527.
33	Freeman J. A user's guide to principal components[J]. Journal of the Operational Research Society, 1992, 43(6): 641.
34	Kassidas A, MacGregor J F, Taylor P A. Synchronization of batch trajectories using dynamic time warping[J]. AIChE Journal, 1998, 44(4): 864-875.
35	Kourti T. Multivariate dynamic data modeling for analysis and statistical process control of batch processes, start-ups and grade transitions[J]. Journal of Chemometrics, 2003, 17(1): 93-109.
36	Wang X C, Wang P, Gao X J, et al. On-line quality prediction of batch processes using a new kernel multiway partial least squares method[J]. Chemometrics and Intelligent Laboratory Systems, 2016, 158: 138-145.

参数	取值范围	参数	取值范围
初始值		控制参数
产生热/kcal	0	底物流温度/K	296~297
反应物体积/L	100~105	搅拌功率/W	29~31
青霉素浓度/(g/L)	0	pH	5~5.05
底物浓度/(g/L)	14~18	底物流加速率/ (L/h)	0.039~0.045
二氧化碳浓度/ (mmol/L)	0.5~1	通风速率/(L/h)	8~9
菌体浓度/(g/L)	0.1	反应器温度/K	298~299
溶解氧浓度/(mmol/L)	1~1.2
反应器温度/K	298~299
pH	4.5~5.5

参数	取值范围	参数	取值范围
初始值		控制参数
产生热/kcal	0	底物流温度/K	296~297
反应物体积/L	100~105	搅拌功率/W	29~31
青霉素浓度/(g/L)	0	pH	5~5.05
底物浓度/(g/L)	14~18	底物流加速率/ (L/h)	0.039~0.045
二氧化碳浓度/ (mmol/L)	0.5~1	通风速率/(L/h)	8~9
菌体浓度/(g/L)	0.1	反应器温度/K	298~299
溶解氧浓度/(mmol/L)	1~1.2
反应器温度/K	298~299
pH	4.5~5.5

变量编号	变量名称	变量单位	变量编号	变量名称	变量单位
x₁	通风速率	L/h	x₇	pH	—
x₂	搅拌功率	W	x₈	反应器温度	K
x₃	底物流温度	K	x₉	产生热	kcal/h
x₄	溶解氧浓度	%	x₁₀	冷水流加速率	L/h
x₅	反应物体积	L	y₁	菌体浓度	g/L
x₆	CO₂浓度	mmol/L	y₂	产物浓度	g/L

变量编号	变量名称	变量单位	变量编号	变量名称	变量单位
x₁	通风速率	L/h	x₇	pH	—
x₂	搅拌功率	W	x₈	反应器温度	K
x₃	底物流温度	K	x₉	产生热	kcal/h
x₄	溶解氧浓度	%	x₁₀	冷水流加速率	L/h
x₅	反应物体积	L	y₁	菌体浓度	g/L
x₆	CO₂浓度	mmol/L	y₂	产物浓度	g/L

故障批次	故障变量	故障类型	幅值/%	开始时刻/h	终止时刻/h
1	搅拌速率	阶跃故障	10	200	400
2	底物流加速率	斜坡故障	15	200	400