Batch processes have multimode characteristics, and the existing methods of mode partition for batch processes ignore the causal relationship between the process characteristics and the mode centers, which directly affects the accuracy and reasonableness of the mode partition results and the prediction precision and generalizability of the models. A method for the online prediction of quality variables based on deep causal clustering-relevance vector machine (DCC-RVM) for multimode batch processes is proposed in this work. By combining density peak clustering, with the strong nonlinearity of the batch process data, the deep features of the process data are first extracted using a deep autoencoder. The process model for batch processes based on long short-term memory (LSTM) is then constructed, with the causal relationship between mode centers and the LSTM process model as a constraint, and the mode centers selection strategy is constructed to obtain reasonable mode centers; Subsequently, by considering the temporal features of the process data, the non-mode center samples are assigned to the corresponding modes based on the relative distance between samples, and the partition points and data sets are obtained for each mode; Finally, the quality variable prediction model for each mode is established using RVM, and the batch process quality variable is predicted online. The experimental results show that the mode partition by DCC is reasonable. The root mean square error (RMSE) and R2 for predictiions using our DCC-RVM model are 0.010 4 and 0.999 5, respectively.
密度峰值聚类(density peaks clustering,DPC)算法通过非迭代的方式获得聚类结果[13-14]。刘聪等[15]将DPC引入间歇过程模态划分,通过样本点间的K近邻关系定义样本点分配策略,将非模态中心样本分配至所属模态,然后利用各模态的数据集建立预测模型。然而间歇过程数据的高维特征限制了质量变量预测模型的精度。针对该问题,周新杰等[16]提出一种基于改进密度峰值聚类的模态划分方法,提高了间歇过程模态划分的合理性,建立的多模态质量变量预测模型具有较高的预测精度。受操作切换的影响,间歇过程的过程特性存在阶段性变化,使得整个过程具有多个模态中心,过程特性与模态中心具有稳定的因果关系,引入因果关系约束模态中心的选择并分配非模态中心样本点,获得准确的模态划分结果,能够进一步提高质量变量预测模型的预测精度。
CHANGP, DINGC H. Monitoring multi⁃domain batch process state based on fuzzy broad learning system[J]. Expert Systems with Applications, 2022, 187: 115851.
[2]
LIUK, ZHAOX Q, MOUM, et al. Quality prediction of multi⁃stage batch process based on integrated ConvBiGRU with attention mechanism[J]. Applied Intelligence, 2025, 55: 123.
[3]
SUNY N, QINW, XUH W, et al. A multiphase information fusion strategy for data⁃driven quality prediction of industrial batch processes[J]. Information Sciences, 2022, 608: 81-95.
[4]
RENJ C, LIUD, WANY. VMD⁃SEAE⁃TL⁃based data⁃driven soft sensor modeling for a complex industrial batch processes[J]. Measurement, 2022, 198: 111439.
[5]
JIC, MAF Y, WANGJ D, et al. Profitability related industrial⁃scale batch processes monitoring via deep learning based soft sensor development[J]. Computers and Chemical Engineering, 2023, 170: 108125.
[6]
ZHANGS M, BAOX L. Phase partition and online monitoring for batch processes based on Harris hawks optimization[J]. Control Engineering Practice, 2023, 138: 105554.
[7]
CHUF, WANGJ C, ZHAOX, et al. Transfer learning for nonlinear batch process operation optimization[J]. Journal of Process Control, 2021, 101: 11-23.
[8]
WANGZ J, CHENB, ZHENGY, et al. Sparse representation and modified density peak clustering⁃based state identification for multimode processes[J]. Measurement Science and Technology, 2023, 34: 025016.
[9]
GUOR X, ZHANGN, WANGJ Q, et al. Phase partition and identification based on a two⁃step method for batch process[J]. Transactions of the Institute of Measurement and Control, 2018, 40(16): 4472-4483.
[10]
LUN Y, GAOF R, WANGF L. Sub⁃PCA modeling and on⁃line monitoring strategy for batch processes[J]. AIChE Journal, 2004, 50(1): 255-259.
[11]
NGY S, SRINIVASANR. An adjoined multi⁃model approach for monitoring batch and transient operations [J]. Computers and Chemical Engineering, 2009, 33(4): 887-902.
[12]
LUOL J, BAOS Y, MAOJ F, et al. Fuzzy phase partition and hybrid modeling based quality prediction and process monitoring methods for multiphase batch processes[J]. Industrial & Engineering Chemistry Research, 2016, 55(14): 4045-4058.
[13]
YANH, WANGM Z, XIEJ Y. ANN⁃DPC: density peak clustering by finding the adaptive nearest neighbors[J]. Knowledge⁃Based Systems, 2024, 294: 111748.
[14]
ZANGW K, LIUX C, MAL L, et al. DPC⁃MFP: an adaptive density peaks clustering algorithm with multiple feature points[J]. Neurocomputing, 2025, 618: 129060.
LIUC, XIEL, YANGH Z. Multi⁃model soft sensor development for penicillin fermentation process based on improved density peak clustering[J]. CIESC Journal, 2021, 72(3): 1606-1615. (in Chinese)
ZHOUX J, WANGJ L, AIX C, et al. IDPC⁃RVM based online prediction of quality variables for multimode batch processes[J]. CIESC Journal, 2022, 73(7): 3120-3130.(in Chinese)
[19]
XUM L, LIY H, LIR X, et al. EADP: an extended adaptive density peaks clustering for overlapping community detection in social networks[J]. Neurocomputing, 2019, 337: 287-302.
[20]
FENGZ K, ZHANGJ S, NIUW J. A state⁃of⁃the⁃art review of long short⁃term memory models with applications in hydrology and water resources[J]. Applied Soft Computing, 2024, 167: 112352.
SHAOC S, LOUW, YANL M. Optimization of algorithm of similarity measurement in high⁃dimensional data[J]. Computer Technology and Development, 2011, 21(2): 1-4.(in Chinese)
[23]
QIUK P, WANGJ L, ZHOUX J, et al. Soft sensor based on localized semi⁃supervised relevance vector machine for penicillin fermentation process with asymmetric data[J]. Measurement, 2022, 202: 111823.
[24]
NGUYENT H T, DINHD T, SRIBOONCHITTAS, et al. A method for k⁃means⁃like clustering of categorical data[J]. Journal of Ambient Intelligence and Humanized Computing, 2023, 14(11):15011-15021.
[25]
BIROLG, ÜNDEYC, ÇINARA. A modular simulation package for fed⁃batch fermentation: penicillin production[J]. Computers and Chemical Engineering, 2002, 26(11): 1553-1565.
[26]
HODSONT O. Root⁃mean⁃square error (RMSE) or mean absolute error(MAE): When to use them or not[J]. Geoscientific Model Development, 2022, 15: 5481-5487.