文献类型：期刊文献

英文题名：Multi-scale feature fused stacked autoencoder and its application for soft sensor modeling

作者：Li, Zhi[1,2,3,4];Xia, Yuchong[2];Long, Jian[2];Liu, Chensheng[2];Zhang, Longfei[2]

机构：[1]East China Univ Sci & Technol, State Key Lab Ind Control Technol, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[3]Huzhou Inst Ind Control Technol, Huzhou 313099, Peoples R China;[4]East China Univ Sci & Technol, Engn Res Ctr Proc Syst Engn, Minist Educ, Shanghai 200237, Peoples R China

年份：2025

卷号：81

起止页码：241

外文期刊名：CHINESE JOURNAL OF CHEMICAL ENGINEERING

收录：;EI(收录号：20251918384156);WOS:【SCI-EXPANDED(收录号:WOS:001532563600001)】；

基金：Acknowledgements This work was supported by the National Key Research and Development Program of China (2023YFB330780 0) , National Nat-ural Science Foundation of China (62394343, 62373155) , Major Science and Technology Project of Xinjiang (No. 2022A01006-4) , State Key Laboratory of Industrial Control Technology, China (Grant No. ICT2024A26) and Fundamental Research Funds for the Central Universities.

语种：英文

外文关键词：Multi-scale feature fusion; Soft sensors; Stacked autoencoders; Computational chemistry; Chemical processes; Parameter estimation

摘要：Deep Learning has been widely used to model soft sensors in modern industrial processes with nonlinear variables and uncertainty. Due to the outstanding ability for high-level feature extraction, stacked autoencoder (SAE) has been widely used to improve the model accuracy of soft sensors. However, with the increase of network layers, SAE may encounter serious information loss issues, which affect the modeling performance of soft sensors. Besides, there are typically very few labeled samples in the data set, which brings challenges to traditional neural networks to solve. In this paper, a multi-scale feature fused stacked autoencoder (MFF-SAE) is suggested for feature representation related to hierarchical output, where stacked autoencoder, mutual information (MI) and multi-scale feature fusion (MFF) strategies are integrated. Based on correlation analysis between output and input variables, critical hidden variables are extracted from the original variables in each autoencoder's input layer, which are correspondingly given varying weights. Besides, an integration strategy based on multi-scale feature fusion is adopted to mitigate the impact of information loss with the deepening of the network layers. Then, the MFF-SAE method is designed and stacked to form deep networks. Two practical industrial processes are utilized to evaluate the performance of MFF-SAE. Results from simulations indicate that in comparison to other cutting-edge techniques, the proposed method may considerably enhance the accuracy of soft sensor modeling, where the suggested method reduces the root mean square error (RMSE) by 71.8%, 17.1% and 64.7%, 15.1%, respectively. (c) 2025 The Chemical Industry and Engineering Society of China, and Chemical Industry Press Co., Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.