Vacuum bag leak detection for resin infusion: an electric current-based analogy

The presence of leakages in composite manufacturing vacuum bag layups results in undesirable defects and low-quality products. Thus, it is crucial to locate leakages before injecting the resin. A reliable method is to estimate the location of the leakages by monitoring the flowrates of vacuum ports. However, these estimations based on traditional numerical methods often fail because of model inadequacies, extensive size of the vacuum bags, complex geometries and port configurations. Machine learning can be used for estimation, but it requires large datasets to capture the flow characteristics of every possible leakage location of various layup configurations. Generating such datasets in real manufacturing settings is prohibitively time-consuming and labor-intensive. We propose a novel analogy between vacuum bag assemblies and electrical circuits for flowrate data generation. This model has been experimentally validated for various geometries and patterns and acts as an accurate analogue for the real setup with an accuracy of more than 97%. Two machine learning-based models have also been trained with a validation accuracy of 94% that have a suitable prediction in regions far from the boundaries.

Automated summary

The presence of leakages in composite manufacturing vacuum bag layups is a concern for product quality. Traditional numerical methods often fail to estimate the leakage location accurately due to model inadequacies, large vacuum bags, complex geometries, and port configurations. Generating large datasets for machine learning is time-consuming and labor-intensive. A new analogy between vacuum bag assemblies and electrical circuits has been proposed for flowrate data generation, which has shown promising experimental validation and can be an accurate analogue for the real setup. Machine learning models have also been trained with a high validation accuracy of 94%, providing suitable predictions away from the boundaries.