<p>Polyimides (PIs) are widely used in industry owing to their excellent mechanical properties and thermomechanical stability, which depend not only on molecular structure but also on processing conditions. In this study, we present a machine-learning-based strategy for predicting and optimizing the mechanical properties of PI materials by explicitly incorporating processing information into predictive models. Three machine learning models were developed to evaluate PI structures together with thermal imidization parameters, with the aim of improving the prediction accuracy of mechanical properties and enhancing the interpretability of structure-processing-property relationships. By analyzing structural and processing descriptors, key factors influencing tensile strength, Young’s modulus, and elongation at break were identified. The results indicate that, in addition to molecular descriptors, processing-related features plays a substantial role on multiple mechanical properties. Based on the trained models, we further developed an automated tool that accepts a SMILES representation of a PI structure as input and outputs the predicted mechanical properties along with the corresponding processing conditions associated with optimal performance. This work provides a data-driven framework for guiding PI material design and process optimization, and offers a practical basis for future experimental validation. Our proposed approach is readily extendable to other polymer systems and polymer composites where processing plays an important role in determining mechanical behavior.</p>