An integrated real-time control methodology is introduced to mitigate process-induced challenges, namely temperature overshoot, uneven cure, and interfacial shear stress, during the autoclave curing of Carbon Fiber-Reinforced Polymer (CFRP) composites. First, a high-fidelity Finite Element (FE) model incorporating tool-part interaction is developed to reveal the curing process of the composites, wherein the interaction is characterized by friction interface modeling with experimentally measured cure-dependent friction coefficients. The accuracy of FE model is confirmed through experimental tests on a doubly curved T-stiffened composite panel. This validated model then generates a dataset of curing temperature profile and associated defect information, which is used to train a customized Long Short-Term Memory (LSTM) neural network. We culminate in a real-time control framework that actively optimizes the curing process by integrating LSTM-based state prediction with Q-learning-driven decision logic. The optimized thermal profile demonstrates a clear performance enhancement over the traditional multi-dwell approach, achieving marked reductions in temperature difference, Degree of Cure (DoC) difference and tool-part interface shear stress, which provides more insights for intelligent composite manufacturing.

With the U-shaped leading edge made of aramid laminate as the focus of this study, we have developed models for both the curing temperature field and the curing deformation field, aiming to unravel the underlying mechanisms of its curing deformation. Our investigation delves into the various influence patterns of core materials, the sequence of the inner skin laying-up, and the structure of the leading edge on the overall curing deformation of the component. The findings reveal that rigid foam characterized by a high elastic modulus effectively supports the inner skin under curing pressure, thereby minimizing internal defects and curing deformation within the core material. Compared with the core material, the sequence of the inner skin laying-up and the design of the leading edge structure exert a more profound influence on the curing deformation of the component. Taking into account the post-curing neck-in and torsional deformation stemming from the component’s asymmetry, we have found that employing the [0/45/−45/0/0/0/45] laying-up sequence for the inner skin achieves minimal curing deformation.

The Z-pinning technology can effectively improve the interlaminar properties of composite materials, yet the implantation of Z-pins causes fiber distortion, resin-rich zones, and reduced in-plane properties. This paper proposes a numerical method to predict the in-plane compressive properties of Z-pinned composites, with curing effects into consideration. A representative unit cell model is established by analyzing the fine morphology of the Z-pinned structure. Considering the time-dependent properties of the cure process, we develop a coupled thermo-chemo-mechanical multi-field model for Z-pinned structures. The residual stress field obtained from the previous calculation is introduced as a predefined field in the calculation of in-plane compressive performance, and the simulated results are in good agreement with the experimental results. It is found that a large amount of residual stress accumulates around the Z-pin during the cure. Therefore, under compressive loads, weaker material properties around the Z-pin will first develop crack defects, gradually extending to the resin-rich regions. The presence of fiber orientation, resin-rich regions, and cure-induced residual stresses significantly reduce the in-plane compressive performance of Z-pinned composites.

This paper presents an experimental investigation of the Mode Ⅱ delamination resistance of curved CFRP laminates reinforced with Z-pins. A Pre-Hole Z-pinning (PHZ) process is developed to reduce the in-plane damage of the Z-pinned laminates. The microstructural observation of the Z-pinned laminate specimens indicates that the PHZ process can effectively decrease the defects including the Z-pin offset angle and the area of eyelet zone. The influences of the volume fraction and diameter of Z-pin on the fracture toughness and the delamination crack growth rate of the specimens under End Notch Flexure (ENF) loading are then determined experimentally. The test results show that Z-pin increases the interlayer stiffness of the laminate. The delamination crack growth rate is reduced with the increase of Z-pin diameter and volume fraction, and a reduction up to 40% is achieved compared with the specimens without pins. Furthermore, the Mode Ⅱ fracture toughness is significantly improved with the increase of Z-pin volume fraction. When Z-pin volume fraction increases by 1%, the achieved fracture toughness is about 200% higher compared to the unpinned laminates.