Search for: All records

Abstract. The Vacuum-Assisted Resin Infusion Molding (VARIM) process is widely used in wind turbine blade manufacturing due to its cost-effectiveness and reliability. However, challenges such as prolonged curing cycles and defects caused by non-uniform cure remain persistent. To address these issues, multizone heating systems have been developed to enable independent temperature control across blade sections. Yet, optimizing the temperature profile in each zone is computationally intensive, requiring detailed modelling of curing kinetics and heat transfer mechanisms. To overcome these challenges, in this work, a machine learning (ML) based digital twin of the VARIM process was developed using a time-distributed long short-term memory (LSTM) network trained on data generated by a high-fidelity multiphysics solver. The model achieved a predictive accuracy of 96.7 % in replicating the resin curing behavior. Its time-distributed architecture effectively captures the spatial – temporal dependencies across multiple zones, allowing precise prediction of the degree-of-cure evolution. Paired with a gradient-free optimization algorithm, the digital twin reduced curing time by 12.5 % while improving cure uniformity. This AI-driven framework eliminates costly trial-and-error experimentation, and provides a scalable, adaptive solution for improving both quality and productivity in wind turbine blade manufacturing, with strong potential for extension to other composite manufacturing processes. 

Abstract Resin uptake plays a critical role in the stiffness‐to‐weight ratio of wind turbine blades in which sandwich composites are used extensively. This work examines the flexural properties of nominally half‐inch thick sandwich composites made with polyvinyl chloride (PVC) foam cores (H60 and H80; PSC and GPC) at several resin uptakes. We found that the specific flexural strength and modulus for the H80 GPC sandwich composites increase from 82.04 to 90.70 kN · m/kg and 6.03 to 7.13 MN · m/kg, respectively, with 11.0% resin uptake reduction, which stands out among the four core sandwich composites. Considering reaching a high stiffness‐to‐weight ratio while preventing resin starvation, 32% to 38% and 40% to 45% resin uptakes are adequate ranges for the H80 PSC and GPC sandwich composites, respectively. The H60 GPC sandwich composites have lower debonding toughness than H60 PSC due to stress concentration in the smooth side skin‐core interphase region. The ailure mode of the sandwich composites depends on the core stiffness and surface texture. The H60 GPC sandwich composites exhibit core shearing and bottom skin‐core debonding failure, while the H80 GPC and PSC sandwich composites show top skin cracking and core crushing failure. The findings indicate that an appropriate range of resin uptake exists for each type of core sandwich composite, and that within the range, a low‐resin uptake leads to lighter blades and thus lower cyclic gravitational loads, beneficial for long blades.