Batch process monitoring using multiphase AR-PCA optimized with PDPSO

doi:10.11949/j.issn.0438-1157.20180369

CIESC Journal ›› 2018, Vol. 69 ›› Issue (9): 3914-3923.DOI: 10.11949/j.issn.0438-1157.20180369

Previous Articles Next Articles

Batch process monitoring using multiphase AR-PCA optimized with PDPSO

GAO Xuejin^1,2,3,4, HUANG Mengdan^1,2,3,4, QI Yongsheng⁵, WANG Pu^1,2,3,4

1. Department of Information Science, Beijing University of Technology, Beijing 100124, China;
2. Engineering Research Center of Digital Community, Ministry of Education, Beijing 100124, China;
3. Beijing Laboratory for Urban Mass Transit, Beijing 100124, China;
4. Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing 100124, China;
5. School of Electric Power, Inner Mongolia University of Technology, Huhhot 010051, Inner Mongolia, China

Received:2018-04-03 Revised:2018-06-17 Online:2018-09-05 Published:2018-09-05
Supported by:
supported by the National Natural Science Foundation of China (61640312,61763037), the Natural Science Foundation of Beijing (4172007) and Beijing Municipal Education Commission Fund.

PDPSO优化多阶段AR-PCA间歇过程监测方法

高学金^1,2,3,4, 黄梦丹^1,2,3,4, 齐咏生⁵, 王普^1,2,3,4

1. 北京工业大学信息学部, 北京 100124;
2. 数字社区教育部工程研究中心, 北京 100124;
3. 城市轨道交通北京实验室, 北京 100124;
4. 计算智能与智能系统北京市重点实验室, 北京 100124;
5. 内蒙古工业大学电力学院, 内蒙古呼和浩特 010051

通讯作者: 齐咏生
基金资助:
国家自然科学基金项目（61640312，61763037）；北京市自然科学基金项目（4172007）；北京市教育委员会资助项目。

Abstract

Abstract:

To overcome the problem of batch process caused by the traditional process dynamics multistage characteristic, the multiphase auto regression-principal component analysis (AR-PCA) monitoring method is proposed based on affine propagation (AP) clustering optimized with a population diversity-based particle swarm optimization algorithm (PDPSO). The method introduced PDPSO method to improve the AP clustering. It avoided the blindness of common method that indirectly chose the preference based on the clustering evaluation index. Then we established the AR-PCA model for the data samples of the multiphase fermentation process to eliminate the dynamic characteristics of each stage and the auto-and-cross-correlation between variables. Finally, the PCA model is established for the residual of the AR model for fault monitoring of the batch process. The method is applied to the process of penicillin fermentation. Experiments show that the method can effectively divide the process into different phases and reduce the false and leak alarms.

Key words: batch process, population diversity, particle swarm optimization, affine propagation clustering, autoregressive principal component analysis

摘要：

针对间歇过程固有的多阶段特性和动态性，提出基于种群多样性的自适应惯性权重粒子群算法（PDPSO）优化的多阶段自回归主元分析（AR-PCA）间歇过程监测方法。该方法引入了PDPSO算法指导AP聚类偏向参数的选取，避免了传统方法依据聚类评价指标选取参考度时的盲目性。对PDPSO优化AP聚类的多阶段发酵过程的数据样本建立AR-PCA模型能够消除各阶段的动态性及变量之间的自相关和互相关影响。最后，对自回归（AR）模型的残差矩阵建立主成分分析（PCA）模型用于发酵过程监测。将该方法应用到青霉素发酵过程，并与传统方法进行对比，结果表明，该方法能够有效进行间歇过程阶段划分并降低故障的漏报和误报。

关键词: 间歇过程, 种群多样性, 粒子群优化, 仿射传播聚类, 自回归主元分析

CLC Number:

TP277

GAO Xuejin, HUANG Mengdan, QI Yongsheng, WANG Pu. Batch process monitoring using multiphase AR-PCA optimized with PDPSO[J]. CIESC Journal, 2018, 69(9): 3914-3923.

高学金, 黄梦丹, 齐咏生, 王普. PDPSO优化多阶段AR-PCA间歇过程监测方法[J]. 化工学报, 2018, 69(9): 3914-3923.

References 30

[1]	GUO H, LI H G. On-line batch process monitoring with improved multi-way independent component analysis[J]. Chinese Journal of Chemical Engineering, 2013, 21(3):263-270.
[2]	NOMIKOS P, MACGREGOR J F. Monitoring batch processes using multiway principal component analysis[J]. AIChE Journal, 1994, 40(8):1361-1375.
[3]	MACGREGOR J F, JAECKLE C, KIPARISSIDES C, et al. Process monitoring and diagnosis by multiblock PLS methods[J]. AIChE Journal, 1994, 40(5):826-838.
[4]	LOU Z J, SHEN D, WANG Y Q. Preliminary-summation-based principal component analysis for non-Gaussian processes[J]. Chemometrics and Intelligent Laboratory Systems, 2015, 146:270-289.
[5]	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.
[6]	GE Z Q, SONG Z H, ZHAO L P, et al. Two-level PLS model for quality prediction of multiphase batch processes[J]. Chemometrics and Intelligent Laboratory Systems, 2014, 130:29-36.
[7]	QIN S J. Survey on data-driven industrial process monitoring and diagnosis[J]. Annual Reviews in Control, 2012, 36(2):220-234.
[8]	LUO L J, BAO S Y, MAO J F, et al. Quality prediction and quality-relevant monitoring with multilinear PLS for batch processes[J]. Chemometrics and Intelligent Laboratory Systems, 2016, 150:9-22.
[9]	LIU Y, ZHAO S, WANG Q, et al. Learning more distinctive representation by enhanced PCA network[J]. Neurocomputing, 2017, 275:924-931.
[10]	LIU Y, LIANG Y, GAO Z, et al. Online flooding supervision in packed towers:an integrated data-driven statistical monitoring method[J]. Chemical Engineering and Technology, 2018, 41(3):436-446.
[11]	LIU Y, HSEUH B F, GAO Z, et al. Flooding prognosis in packed columns by assessing degree of steadiness (DOS) of process variable trajectory[J]. Industrial and Engineering Chemistry Research, 2016, 55(40):10744-10750.
[12]	LI H G, SONG R Q, LIU J W. Low-dimensional feature fusion strategy for overlapping neuron spike sorting[J]. Neurocomputing, 2018, 281:152-159.
[13]	WANG F, WANG Q, NIE F, et al. Efficient tree classifiers for large scale datasets[J]. Neurocomputing, 2018, 284:70-79.
[14]	WANG Z, HU H, ZHANG L, et al. Discriminatively guided filtering (DGF) for hyperspectral image classification[J]. Neurocomputing, 2017, 275:1981-1987.
[15]	GE Z Q, SONG Z H, GAO F R. Review of recent research on data-based process monitoring[J]. Industrial and Engineering Chemistry Research, 2013, 52:3543-3562.
[16]	CAI F, TIAN X M, CHEN S. A process monitoring method based on noisy independent component analysis[J]. Neurocomputing, 2014, 127:231-246.
[17]	QIN Y, ZHAO C H, WANG X Z, et al. Subspace decomposition and critical phase selection based cumulative quality analysis for multiphase batch processes[J]. Chemical Engineering Science, 2017, 166:130-143.
[18]	FEI Z S, LIU K L. Online process monitoring for complex systems with dynamic weighted principal component analysis[J]. Chinese Journal of Chemical Engineering, 2016, 24(6):775-786.
[19]	张子羿, 胡益, 侍洪波. 一种基于聚类方法的多阶段间歇过程监控方法[J]. 化工学报, 2013, 64(12):4522-4528. ZHANG Z Y, HU Y, SHI H B. Multi-stage batch process monitoring based on a clustering method[J]. CIESC Journal, 2013, 64(12):4522-4528.
[20]	QIN S J. Process data analytics in the era of big data[J]. AIChE Journal, 2014, 60(9):3092-3100.
[21]	LÜ Z M, YAN X F, JIANG Q C. Batch process monitoring based on multiple-phase online sorting principal component analysis[J]. ISA Transactions, 2016, 64:342-352.
[22]	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.
[23]	ZHANG C, ZHAO H T. Order clustering based sub-stage division and its application to batch process monitoring[C]//Control Conference. IEEE, 2016:6482-6487.
[24]	YU J, QIN S J. Multiway Gaussian mixture model based multiphase batch process monitoring[J]. Industrial and Engineering Chemistry Research, 2009, 48(18):8585-8594
[25]	FREY B J, DUECK D. Clustering by passing messages between data points[J]. Science, 2007, 315:972-976.
[26]	CHOI S W, MORRIS J, LEE I B. Dynamic model-based batch process monitoring[J]. Chemical Engineering Science, 2008, 63:622-636.
[27]	胡永兵, 高学金, 李亚芬, 等. 基于仿射传播聚类子集主元分析的间歇过程监测方法[J]. 化工学报, 2016, 5(5):1989-1997. HU Y B, GAO X J, LI Y F, et al. Clean production of pharmaceutical crystallization[J]. CIESC Journal, 2016, 5(5):1989-1997.
[28]	王志文, 刘毅, 高增梁. 时变间歇过程的2D-PID自适应控制方法[J]. 化工学报, 2016, 67(3):991-997. WANG Z W, LIU Y, GAO Z L. 2D-PID adaptive control method for time-varying batch processes[J]. CIESC Journal, 2016, 67(3):991-997.
[29]	高学金, 崔宁, 张亚潮, 等. 基于粒子群优化MICA的间歇过程故障监测[J].仪器仪表学报, 2015, 36(1):152-159. GAO X J, CUI N, ZHANG Y C, et al. Subset multiway principal component analysis monitoring for batch process based on affinity propagation clustering[J]. Chinese Journal of Scientific Instrument, 2015, 36(1):152-159.
[30]	YU H H, CHEN Y Y, HASSAN G S, et al. Prediction of the temperature in a Chinese solar greenhouse based on LSSVM optimized by improved PSO[J]. Computers and Electronics in Agriculture, 2016, 122:94-102.

Batch process monitoring using multiphase AR-PCA optimized with PDPSO

PDPSO优化多阶段AR-PCA间歇过程监测方法

PDF (PC)

Knowledge

Cited

Abstract

Cite this article

share this article

References 30

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Wei LI, Xiaoming WANG, Dongnian JIANG, Yajie LI, Chenglong LIANG. Prediction of octane number of finished gasoline blend based on SHPSO-GA-BP [J]. CIESC Journal, 2020, 71(7): 3191-3200.
[2]	Biming ZHENG, Bin SHI, Liexiang YAN. Optimization of batch production scheduling under multi-factor uncertain conditions [J]. CIESC Journal, 2020, 71(3): 1246-1253.
[3]	Tao CAI, Bo YANG, Hongguang LI. Chemical process multivariate time series predictions based on time-delay-mining fuzzy time cognitive maps [J]. CIESC Journal, 2020, 71(3): 1095-1102.
[4]	Lei YU, Xiaogang DENG, Yuping CAO, Kaiqi LU. Fault detection method of unequal-length batch process based on VGDTW-MCVA [J]. CIESC Journal, 2019, 70(9): 3441-3448.
[5]	Limin WANG, Libin LU, Furong GAO, Donghua ZHOU. Infinite horizon linear quadratic hybrid fault-tolerant control for multi-phase batch process [J]. CIESC Journal, 2019, 70(2): 541-547.
[6]	Junren BAI, Jun YI, Qian LI, Ling WU, Xuemei CHEN. Multi-objective optimization of QPSO for thereaction-regeneration process [J]. CIESC Journal, 2019, 70(2): 750-756.
[7]	Xiaozheng GUO, Linlin LIU, Lei ZHANG, Jian DU. Property integration of batch process based on interceptors in semi-continuous operation [J]. CIESC Journal, 2019, 70(2): 516-524.
[8]	ZHOU Xinzhi, SHAO Lun, LI Rongkun, ZHAO Chengping, DONG Chenlong. Research on temperature prediction model for microwave heating based on wavelet denoising and improved PSO-SVM [J]. CIESC Journal, 2018, 69(S2): 291-299.
[9]	XU Wenxing, WANG Wanhong, WANG Fang, LIU Cai, JING Shaoxing, ZHAO Guoxin. Intrusion detection of industrial control system based on PSOGSA feedforward neural network [J]. CIESC Journal, 2018, 69(S2): 350-357.
[10]	GAO Yan, ZHAO Zhonggai, LIU Fei. DMFA-based multi-objective optimization for fermentation processes [J]. CIESC Journal, 2018, 69(6): 2594-2602.
[11]	ZHANG Lei, ZHANG Xiaogang, CHEN Hua. Soft sensors for multi-stage batch processes based on Gath-Geva algorithm and kernel extreme learning machine [J]. CIESC Journal, 2018, 69(6): 2576-2585.
[12]	CHANG Peng, QIAO Junfei, WANG Pu, GAO Xuejin, LI Zheng. Monitoring non-Gaussian and non-linear batch process based on multi-way kernel entropy component analysis [J]. CIESC Journal, 2018, 69(3): 1200-1206.
[13]	LIU Xiaofeng, LUAN Xiaoli, LIU Fei. Recursive optimization of batch processes based on load cosine similarity in latent variable space [J]. CIESC Journal, 2018, 69(3): 1167-1172.
[14]	YAN Xueli, HAN Yuxin, GU Xingsheng. Improved schedule model for batch production by state unit network [J]. CIESC Journal, 2018, 69(3): 913-922.
[15]	WANG Jianlin, MA Linyu, LIU Weimin, QIU Kepeng, YU Tao. Batch process monitoring by kernel similarity-based support vector data description [J]. CIESC Journal, 2017, 68(9): 3494-3500.