Carbon fiber-reinforced polymer (CFRP) composites are widely used in aerospace due to their excellent strength-to-weight ratio and tailorable properties. However, these properties critically depend on the CFRP curing cycle. The commonly adopted manufacturer-recommended curing cycle (MRCC), designed to accommodate the most conservative conditions, involves prolonged curing times and high energy consumption. To overcome these limitations, this study proposes an efficient and adaptable method to determine the optimal curing cycle. The effects of varying heating rates on resin dynamic and isothermal–exothermic behavior were characterized via reaction kinetics analysis using differential scanning calorimetry (DSC) and rheological measurements. The activation energy of the reaction system was substituted into the modified Sun–Gang model, and the parameters were estimated using a particle swarm optimization algorithm. Based on the curing kinetic behavior of the resin, CFRP compression molding process orthogonal experiments were conducted. A weighted scoring system incorporating strength, energy consumption, and cycle time enabled multidimensional evaluation of optimized solutions. Applying this curing cycle optimization method to a commercial epoxy resin increased efficiency by 247.22% and reduced energy consumption by 35.7% while meeting general product performance requirements. These results confirm the method’s reliability and its significance for improving production efficiency.

Carbon fiber reinforced polymer (CFRP) components require precise curing process control to ensure quality, but traditional phenomenological cure kinetics models face limitations in handling nonlinearity and data diversity. This study addresses the challenges in modeling the cure kinetics of carbon fiber reinforced polymer (CFRP) composites, where traditional phenomenological models lack generalizability and neural networks suffer from robustness issues due to their numerous hyperparameters and data dependency. To overcome these limitations, a novel machine learning model called the angle information-enhanced radial basis function (RBF) model is proposed, which integrates both Euclidean distance and angular relationships between data points to improve prediction stability and accuracy. The performance of this machine learning approach is systematically compared against an autocatalytic model and a neural network using dynamic DSC data from T700/2626 epoxy resin at multiple heating rates. The angle-enhanced RBF model balances accuracy, efficiency, and robustness, offering a reliable data-driven alternative for CFRP cure kinetics prediction without requiring extensive data or complex hyperparameter optimization, thus facilitating better process control in manufacturing.