Abstract
This study addresses the challenge of predicting final properties in batch processes with highly uneven durations, using the ibuprofen production process as a case study. Novel methodologies are proposed and compared against traditional regression algorithms, which rely on batch trajectory synchronization as a pre-processing step. The performance of each method is evaluated using established metrics. The data for this study were generated using Aspen Plus V12 simulation software, focused on batch reactors. To handle the unequal-length trajectories in batch processes, this research constructs a dual-transformer deep neural network with multi-head attention and layer normalization mechanism to extract shared information from the high-dimensional, uneven-length manipulated variable profiles into latent space, generating equal-dimensional latent codes. As an alternative strategy for representation learning, a dual-autoencoder framework is also employed to achieve equal-dimensional representations. The representation vectors are then used as inputs for downstream deep learning models to predict the target variables, achieving an accuracy with an R² score exceeding 0.9.