Semi-supervised modeling and soft sensing of chemical product components based on ladder networks
TENG Chaopeng1, JI Cheng1, MA Fangyuan1,2, WANG Jingde1, SUN Wei1
1. College of Chemical Engineering, Beijing University of Chemical Technology, Beijing 100029, China; 2. Wuxi Research Institute of Applied Technologies, Tsinghua University, Wuxi 214072, China
Abstract：[Objective] During chemical production, the different sampling frequencies of different variables generate a substantial amount of unlabeled data, which is challenging to use effectively, resulting in data waste. Additionally, distributed control systems frequently produce noisy data due to environmental interference and aging measurement instruments, complicating soft sensing modeling. Furthermore, in semi-supervised tasks, unsupervised components can undermine the accuracy of supervised tasks. To address these issues, this study proposes a semi-supervised soft sensing method for product quality based on a ladder network, enabling accurate, timely determination of key product quality and enhancing operational efficiency. [methods] A two-step variable screening method—maximum mutual information (MIC) followed by minimum redundancy maximum relevance (mRMR)—was used to screen auxiliary variables. MIC was first applied to eliminate low-correlation variables, and mRMR was then used to remove redundant variables among the auxiliary set, yielding an optimal selection for modeling. The ladder network-based soft sensing method was then established, improving noise resistance by injecting disturbances into each encoder layer and reconstructing noise-free features layer by layer through the decoder. Skip connections were added between encoders and decoders to extract more information from unlabeled data, enhancing focus on supervised tasks and strengthening the model's robustness and generalization. [Results] This method was applied to the methanol-to-olefin (MTO) process, termed DMTO. The MIC and mRMR screening reduced 203 auxiliary variables to an optimal 50. After preprocessing, several soft sensor models were established to compare outcomes. Results showed that unlabeled samples improved the effectiveness of supervised soft sensing tasks, with the proposed method enhancing various evaluation metrics. Residual analysis further indicated that the predicted residuals of the ladder network-based semi-supervised method closely aligned with a standard normal distribution, validating the method's superiority. [Conclusions] Compared with supervised and other semi-supervised learning methods, the ladder network demonstrates superior prediction accuracy and generalization in soft sensing ethylene products in the DMTO process. The proposed approach offers promising applications for real-time monitoring and control of product quality in chemical production.
滕潮鹏, 纪成, 马方圆, 王璟德, 孙巍. 基于梯形网络的半监督建模及化工产品组分软测量[J]. 清华大学学报（自然科学版）, 2025, 65(5): 825-832.
TENG Chaopeng, JI Cheng, MA Fangyuan, WANG Jingde, SUN Wei. Semi-supervised modeling and soft sensing of chemical product components based on ladder networks. Journal of Tsinghua University(Science and Technology), 2025, 65(5): 825-832.
[1] JI C, SUN W. A review on data-driven process monitoring methods:Characterization and mining of industrial data[J]. Processes, 2022, 10(2):335. [2] OUALI Y, HUDELOT C, TAMI M. An overview of deep semi-supervised learning[EB/OL].(2020-07-06)[2024-09-13] . https://doi.org/10.48550/arXiv.2006.05278. [3] LI Z, JIN H P, DONG S L, et al. Semi-supervised ensemble support vector regression based soft sensor for key quality variable estimation of nonlinear industrial processes with limited labeled data[J]. Chemical Engineering Research and Design, 2022, 179:510-526. [4] KINGMA D P, REZENDE D J, MOHAMED S, et al. Semi-supervised learning with deep generative models[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal, Canada:ACM, 2014:3581-3589. [5] YANG X L, SONG Z X, KING I, et al. A survey on deep semi-supervised learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(9):8934-8954. [6] VAN ENGELEN J E, HOOS H H. A survey on semi-supervised learning[J]. Machine Learning, 2020, 109(2):373-440. [7] RASMUS A, VALPOLA H, HONKALA M, et al. Semi-supervised learning with ladder networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems. Montreal, Canada:ACM, 2015:3546-3554. [8] 武昊.基于深度学习的化工过程软测量建模方法研究[D].北京:北京化工大学, 2023. WU H. Research on soft sensor modeling of chemical process based on deep learning[D]. Beijing:Beijing University of Chemical Technology, 2023.(in Chinese) [9] RESHEF D N, RESHEF Y A, FINUCANE H K, et al. Detecting novel associations in large data sets[J]. Science, 2011, 334(6062):1518-1524. [10] LUO L, HE G, CHEN C, et al. Adaptive data dimensionality reduction for chemical process modeling based on the information criterion related to data association and redundancy[J]. Industrial&Engineering Chemistry Research, 2022, 61(2):1148-1166. [11] PENG H C, LONG F H, DING C. Feature selection based on mutual information:Criteria of max-dependency, max-relevance, and min-redundancy[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(8):1226-1238. [12] 孙慧峰,刘桂莲. DMTO与SMTO甲醇制烯烃工艺的能耗分析及优化节能[J].石化技术与应用, 2021, 39(4):234-241. SUN H F, LIU G L. Energy consumption analysis and optimization of energy saving of DMTO and SMTO methanol to olefin process[J]. Petrochemical Technology&Application, 2021, 39(4):234-241.(in Chinese) [13] MA F Y, JI C, WANG J D, et al. Soft sensor modeling method considering higher-order moments of prediction residuals[J]. Processes, 2024, 12(4):676.
2025, Vol. 65 
