A comparative study of glass fiber content (Gc) measurement methods was conducted using actual glass fiber reinforced plastic laminates from the hull plate of a 26-ton yacht. Two prototype side hull plates with the design Gc (40 wt.%) and higher Gc (64 wt.%) were prepared. Four methods were used to study the samples: the calculation method suggested by classification societies’ rules; two direct measurement methods using either calipers and scales or a hydrometer; and the burn-off method, wherein the resin matrix is combusted from the laminates. The results were compared and analyzed to identify the accuracy and benefits of each method. The rule calculation method was found to be effective if the quality of the manufacturing process is known. However, fabrication errors in the laminate structures cannot be detected. Additionally, while direct methods are used to measure the density of glass fibers using measurements of the densities of raw materials and laminates, the volume of inner defects occurring during the fabrication of laminates could not be considered. Finally, it was found that the burn-off method measures Gc and considers the defect volume (voids) inside laminates as well as the non-uniformity of the external shape.

The study aims to improve the previous theory-based algorithm on the lightweight design of laminate structures of a composite ship based on the mechanical properties of fiber, resin, and laminates obtained from experiments. From a case study on using a hydrometer to measure the specific gravity of e-glass fiber woven roving fabric/polyester resin used as the raw material for the hull of a 52 ft composite ship, the equation for calculating the weight of laminate was redefined, and the relationship between decreasing mechanical properties and increasing glass content was determined from the results of material testing according to ASTM D5083 and ASTM D790. After applying these experimental data to the existing algorithm and improving it, a possible laminate design that maximizes the specific strength of the composite material was confirmed. In a case study that applied the existing algorithm based on rules, the optimal lightweight design of composite structures was achieved when the weight fraction of e-glass fiber was increased by 57.5% compared with that in the original design, but the improved algorithm allowed for an increase of only 17.5%.

In order to proceed with shipbuilding scheduling involving hundreds of hull blocks of ships, it is important to mark the locations of the hull blocks with the correct block identification number. Incorrect information about the locations and the identification numbers of hull blocks causes disruption in the shipbuilding scheduling process of the shipyard. Therefore, it is necessary to have a system for tracking the locations and identification numbers of hull blocks in order to avoid time loss due to incorrectly identified blocks. This paper proposes a method to mark the identification numbers, which are necessary for the tracking system of hull blocks. In order to do this, 3 CNN (convolutional neural network) models, VGG-19, Resnet-152V2, and Densenet-201, are used to classify the hull blocks. A set of multi-view images acquired from 3D CAD data are used as training data to obtain a trained CNN model, and images from 3D printer-printed hull block models are used for the test of the trained CNN model. The datasets used for training and prediction are Non-Thr and Thr datasets, that each included both binarized and non-binarized datasets. As a result of end-to-end classification experiments with Non-Thr datasets, the highest prediction accuracy was 0.68 with Densenet-201. A total of 4050 experimental conditions were constructed by combining the threadhold of the Thr training and testing dataset. As a result of experiments with Thr datasets, the highest prediction accuracy of 0.96 was acquired with Resnet-152V2, which was trained with a threshold of 72 and predicted with a threshold of 50. In conclusion, the classification of ship hull blocks using a CNN model with binarized datasets of 3D CAD data is more effective than that using a CNN model with non-binarized datasets.

This study proposes a method for detecting internal defects in wind turbine blades using deep learning, eliminating the reliance on inspectors’ experiments. To address the class imbalance problem inherent in defect detection environments, synthetic thermographic datasets were generated using a synthetic data generation technique. To minimize the domain gap between synthetic and real thermographic data, preprocessing with a transformation module was employed, enhancing the similarity between datasets. ResNet-50, DenseNet-121, and Vision Transformer (ViT) models were trained on the synthetic dataset, and their defect detection performance was evaluated on real thermographic data. The results validated the effectiveness of the transformation module in improving the similarity between synthetic and real data, particularly enhancing precision and recall.