文献类型：期刊文献

英文题名：VAE-Driven Feature Learning with Context-Aware Attention and ResNet Gradient Optimization: Applied to Industrial Hydrocracking Processes

作者：Fan, Chen[1];Xu, Haodong[1];Wang, Xindong[1];Long, Jian[1]

机构：[1]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China

年份：2026

卷号：65

期号：9

起止页码：5087

外文期刊名：INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH

收录：;EI(收录号：20261120249287);WOS:【SCI-EXPANDED(收录号:WOS:001705061800001)】；

语种：英文

外文关键词：Complex networks - Deep learning - Extraction - Learning systems

摘要：This study proposes a deep learning model that combines a Variational Autoencoder (VAE), a Residual Network (ResNet), and a Squeeze-and-Excitation Network (SENet) for nonlinear modeling of complex industrial devices and, for the first time, applies the channel attention mechanism (SENet, Squeeze-and-Excitation Network) to hydrocracking modeling. This model extracts the latent low-dimensional feature space of input data through the VAE, and it combines the powerful feature extraction capability of ResNet with the adaptive feature-weight allocation mechanism of SENet to achieve efficient modeling of complex systems. Compared with traditional methods, this network structure has improved prediction accuracy by 2.4% in data-driven modeling of hydrocracking. The experimental results show that the model can effectively handle high-dimensional nonlinear data, demonstrates a superior performance in the modeling of hydrocracking units, and has wide applicability to common nonlinear conversion processes.