Xingsheng Gu

Soft sensor modeling of fermentation processes is crucial to enhance yield and quality. However, the nonlinear and dynamic characteristics of these processes, coupled with variable redundancy, often degrade model performance. A variable selection and soft sensor modeling scheme based on regularized decoupling Transformer (RDTF) is proposed in this study to address these issues. First, a network framework comprising an embedding network, positional encoding, and a multilayer Transformer encoder is employed to extract dynamic nonlinear features. Second, a decoupling layer with mean and variance networks ensures that the latent variables are representative and can independently reflect the information from the original process variables. Third, a regression model is established between these latent variables and quality indicators. Regularization technology, namely, a gradient penalty term in the loss function, allows the model to select the most critical process variables for predicting quality indicators, addressing feature redundancy and collinearity, and improving the model’s performance and robustness. Last, the effectiveness of the proposed RDTF is verified through a simulated penicillin fermentation process case and real penicillin and erythromycin production cases. Across multiple real fermentation cases, the model achieves R² values exceeding 0.95 and consistently outperforms existing models in terms of accuracy and stability. These results highlight RDTF’s potential for industrial applications.

Fault diagnosis is crucial in ensuring the safety and efficient operation of industry processes. However, achieving excellent diagnosis performance in traditional fault diagnosis tasks becomes challenging when the training process lacks test fault information. To address this challenge, a novel model for zero-shot industrial process fault diagnosis based on deep semantic canonical correlation embedding (DSCCE) is proposed in this study. The DSCCE model utilizes an embedding reconstruction model to establish the relationship between fault and their semantic attributes, which is accomplished the task through the transfer of fault semantic attribute descriptions. Initially, DSCCE encodes fault samples and semantic attribute descriptions into an embedding space through two embedding networks. Then, the model employs canonical correlation analysis with two embedding features to assess the consistency between semantic attribute vectors and fault samples. Simultaneously, correlation constraints are applied between fault embedding feature subsets to enhance differential information. Subsequently, the classifier is trained using embedding features to complete the task of zero-shot fault diagnosis. Finally, the effectiveness and superiority of the proposed DSCCE model are verified using two case studies.

Process monitoring plays an essential role in ensuring the safe and efficient operation of multi‐unit plantwide industrial processes. However, complicated nonlinear dynamics of these processes pose enormous challenges to the plantwide process monitoring approaches. In this paper, a novel distributed temporal–spatial neighbourhood enhanced variational autoencoder (DTS‐VAE) monitoring scheme is proposed. The scheme selects the temporal and spatial neighbourhood sets of a current sample from a local unit. Time‐series correlation is utilized to construct temporal representative samples to obtain process dynamic characteristics. Likewise, spatial similarity is employed to construct spatial representative samples to obtain spatial patterns in the data. Then the reconstructed and current samples serve as the inputs for a variational autoencoder to extract features from the current sample and its neighbourhoods. Subsequently, a distributed monitor that considers the temporal–spatial characteristics is established for each unit. Finally, a comprehensive evaluation index is developed using Bayesian fusion strategy to improve monitoring performance. The proposed DTS‐VAE monitoring scheme was effectively verified on the Tennessee Eastman benchmark process and a wastewater treatment plant.