Data‐Driven Design of High‐Performance Polyimides With Enhanced Heat Resistance and Dielectric Properties

Abstract The evolution of electronic technology, such as high‐speed, high‐frequency, and high‐density integrated circuits, imposes higher performance requirements on advanced functional materials like polyimides. However, the prolonged development cycle linked with conventional trial‐and‐error methods results in a noticeable gap between material research and its practical application. Here, a materials genome approach is proposed to accelerate the discovery of polyimides exhibiting exceptional dielectric properties under elevated temperatures and high frequencies. To address the scarcity of data, theoretical high‐frequency dielectric properties are derived by employing the Havriliak‐Negami dielectric relaxation model to complement experimental data. With the augmented data of polyimides, a multi‐task learning model is proposed with hierarchical neural networks for the dielectric properties and conventional neural networks for the glass transition temperature. Structural design via genetic algorithms is implemented to engineer polyimide structures with enhanced dielectric properties. Several polyimides with high comprehensive performance are generated, and experimental validation is conducted. Shapley additive explanations analysis reveals crucial structural elements influencing the performance. The research framework established in this work can guide the design of other polymeric functional materials.