For multiphase batch process, the characteristics of process data under various batches differ. Consequently, the soft sensor model built for a particular working condition is inapplicable to other working conditions. Besides, each batch can be divided into several phases whose characteristics are probably different. To address the above problems, a soft sensor model based on phase division and transfer learning strategy is proposed. First, transfer learning strategy is adopted to construct a soft sensor model applicable to various working conditions. Specifically, geodesic flow kernel based on linear local tangent space alignment (LLTSA-GFK) algorithm is designed. By projecting process data to the common manifold subspace, the distribution difference of data between various batches is reduced and the performance of the soft sensor model is enhanced. In addition, sequence-based fuzzy clustering and just-in-time learning (JITL) are adopted to solve the multistage characteristic for batch process. The root-mean-square error (RMSE), coefficient of determination , and mean absolute error (MAE) are adopted to compare the conventional soft sensing approach (i.e., partial least-square regression based on JITL, support vector regression, and back propagation neural network) with the proposed approach. The superiority of the proposed model is verified by a fed-batch penicillin fermentation process.
BirolGÜndeyCÇinarA (2002) A modular simulation package for fed-batch fermentation: Penicillin production. Computers & Chemical Engineering26(11): 1553–1565.
2.
ChuFWangJCZhaoX, et al. (2021) Transfer learning for nonlinear batch process operation optimization. Journal of Process Control101: 11–23.
3.
GeZQSongZHWangPL (2014) Probabilistic combination of local independent component regression model for multimode quality prediction in chemical processes. Chemical Engineering Research & Design92(3): 509–521.
4.
GongBQShiYShaF, et al. (2012) Geodesic flow kernel for unsupervised domain adaptation. In: Proceedings of the 2012 IEEE conference on computer vision and pattern recognition, Providence, RI, USA, 16–21 June, pp. 2066–2073. New York: IEEE.
5.
GopalanRLiRNChellappaR (2011) Domain adaptation for object recognition: An unsupervised approach. In: Proceedings of the 2011 international conference on computer vision, Barcelona, 6–13 November, pp. 999–1006. New York: IEEE.
6.
JiCMaFYWangJD, et al. (2023) Profitability related industrial-scale batch processes monitoring via deep learning based soft sensor development. Computers & Chemical Engineering170: 108125.
7.
LiZWangPGaoXJ, et al. (2019) Online prediction of quality-related variables for batch processes using a sequential phase partition method. The Canadian Journal of Chemical Engineering97(9): 2483–2497.
8.
LinYPJungTP (2017) Improving EEG-based emotion classification using conditional transfer learning. Frontiers in Human Neuroscience11: 334.
9.
LiuJXLiuTChenJH (2018) Sequential local-based Gaussian mixture model for monitoring multiphase batch processes. Chemical Engineering Science181: 101–113.
10.
LiuTZZhangXRGuYF (2019a) Unsupervised cross-temporal classification of hyperspectral images with multiple geodesic flow kernel learning. IEEE Transactions on Geoscience and Remote Sensing57(12): 9688–9701.
11.
LiuWTHeSDMouJP, et al. (2023) Digital twins-based process monitoring for wastewater treatment processes. Reliability Engineering & System Safety238: 109416.
12.
LiuYYangCLiuKX, et al. (2019b) Domain adaptation transfer learning soft sensor for product quality prediction. Chemometrics and Intelligent Laboratory Systems192: 103813.
13.
LuoLJBaoSYMaoJF, et al. (2016) Fuzzy phase partition and hybrid modeling based quality prediction and process monitoring methods for multiphase batch processes. Industrial & Engineering Chemistry Research55(14): 4045–4058.
14.
MowbrayMKayHKayS, et al. (2022) Probabilistic machine learning based soft-sensors for product quality prediction in batch processes. Chemometrics and Intelligent Laboratory Systems228: 104616.
15.
RodriguezALaioA (2014) Clustering by fast search and find of density peaks. Science344(6191): 1492–1496.
16.
SamatAGambaPAbuduwailiJ, et al. (2016) Geodesic flow kernel support vector machine for hyperspectral image classification by unsupervised subspace feature transfer. Remote Sensing8(3): 234.
17.
ShanXXLuYLiQL, et al. (2021) Model-based transfer learning and sparse coding for partial face recognition. IEEE Transactions on Circuits and Systems for Video Technology31(11): 4347–4356.
18.
TangXCLiY (2020) Phase division and transition modeling based on the dominant phase identification for multiphase batch process quality prediction. Transactions of the Institute of Measurement and Control42(5): 1022–1036.
19.
WangJDFengWJChenYQ (2018a) Visual domain adaptation with manifold embedded distribution alignment. In: Proceedings of the 26th ACM international conference on multimedia, Seoul, Republic of Korea, 22–26 October, pp. 402–410. New York: Association for Computing Machinery (ACM).
20.
WangJLQiuKPLiuWM, et al. (2018b) Unsupervised-multiscale-sequential-partitioning and multiple-SVDD-model-based process-monitoring method for multiphase batch processes. Industrial & Engineering Chemistry Research57(51): 17437–17451.
21.
WangJLQiuKPWangRT, et al. (2021) Development of soft sensor based on sequential kernel fuzzy partitioning and just-in-time relevance vector machine for multiphase batch processes. IEEE Transactions on Instrumentation and Measurement70: 2509110.
22.
WangWLiHJDingZM, et al. (2023) Rethinking maximum mean discrepancy for visual domain adaptation. IEEE Transactions on Neural Networks and Learning Systems34(1): 264–277.
23.
WangXGRenJLiuS (2018c) Distribution adaptation and manifold alignment for complex processes fault diagnosis. Knowledge-Based Systems156: 100–112.
24.
WeissKKhoshgoftaarTMWangDD (2016) A survey of transfer learning. Journal of Big Data3(1): 9.
25.
YangDPengXYeZC, et al. (2021) Domain adaptation network with uncertainty modeling and its application to the online energy consumption prediction of ethylene distillation processes. Applied Energy303: 117610.
26.
YooHByunHEHanD, et al. (2021) Reinforcement learning for batch process control: Review and perspectives. Annual Reviews in Control52: 108–119.
27.
ZhangTHYangJZhaoDL, et al. (2007) Linear local tangent space alignment and application to face recognition. Neurocomputing 70(7–9): 1547–1553.
28.
ZhangZMYanGWQiaoTZ, et al. (2022) Multi-source unsupervised soft sensor based on joint distribution alignment and mapping structure preservation. Journal of Process Control109: 44–59.
29.
ZhangZWChenHHLiSM, et al. (2020) A novel geodesic flow kernel based domain adaptation approach for intelligent fault diagnosis under varying working condition. Neurocomputing376: 54–64.
30.
ZhangZYZhaHY (2004) Principal manifolds and nonlinear dimensionality reduction via tangent space alignment. SIAM Journal on Scientific Computing26(1): 313–338.
31.
ZhaoSCYueXYZhangSH, et al. (2022) A review of single-source deep unsupervised visual domain adaptation. IEEE Transactions on Neural Networks and Learning Systems33(2): 473–493.
32.
ZhaoXQLiuKHuiYY (2023) Fault monitoring of batch process based on multi-stage optimization regularized neighborhood preserving embedding algorithm. Transactions of the Institute of Measurement and Control45(1): 89–103.
33.
ZhuangFZQiZYDuanKY, et al. (2020) A comprehensive survey on transfer learning. Proceedings of the IEEE109(1): 43–76.
