Broad Learning System Combined With Feature Weighted Stacked Target-Related Laplacian Autoencoder for Industrial Quality Prediction

In industrial processes, accurate quality prediction is essential for optimizing operations and ensuring product consistency. However, the inherent complexity of industrial processes typically involves a large number of monitoring variables, accompanied by significant challenges such as high nonlinearity and data redundancy. To address this issue, this paper proposes the Broad Learning System combined with a Feature Weighted Stacked Target-Related Laplacian Autoencoder (BLS-FW-STLapAE). The proposed model innovatively incorporates hidden layer features extracted by the Stacked Target-Related Laplacian Autoencoder (STLapAE) into the feature nodes of the Broad Learning System (BLS). This approach addresses the issue of insufficient feature extraction caused by random mapping in BLS. This integration enables the model to capture both local geometric structures and key target-related features, significantly enhancing predictive performance in complex industrial environments. Additionally, mutual information (MI) is introduced in STLapAE to evaluate the correlation between features and the target variable, further improving the model’s ability to capture relevant information about the target variable and ensuring that all relevant information is effectively utilized. Finally, the feasibility and practical value of the proposed algorithm were validated on benchmark public datasets and two real-world industrial applications: Penicillin Fermentation and Solid Propellant Manufacturing. The superior predictive performance demonstrated across these tests enables operators to proactively adjust process parameters and prevent quality deviations, thereby significantly improving production safety and reducing operational costs in such high-risk chemical engineering domains.