Multimodal LSTM with Data Augmentation for Predicting Rubber Compound Cure Properties in Industrial Batch Processes

Predicting scorch time (t5) of rubber compounds is critical in industrial polymer manufacturing to avoid premature vulcanization and ensure product quality. This study presents an LSTM-based multimodal deep learning model to forecast t5 by integrating online time-series plant sensor data with scalar process parameters from the mixing operation. Key preprocessing steps, including feature normalization and interpolation, were applied to harmonize disparate data sources. To address a highly imbalanced distribution of scorch times in the data set, a synthetic data augmentation strategy was introduced, effectively expanding underrepresented t5 ranges without additional experiments. The augmented LSTM model achieved high predictive accuracy, outperforming baseline models and maintaining robust performance even for extreme scorch time values. The model was validated using online data from a full-scale industrial rubber compounding plant. Results demonstrate that this multimodal augmented modeling approach substantially improves t5 prediction, highlighting its potential for batch-end process monitoring and subsequent adjustment of process conditions. Implementing the proposed model in an industrial setting can enable proactive adjustments for future batches during compounding, thereby reducing scrap, enhancing safety, and ensuring consistent product quality in chemical manufacturing processes.