In the shipbuilding industry, the non-destructive testing for welding quality inspection is mainly used for the permanent storage of the testing results and the radio-graphic testing which can visually inspect the interior of the welded part. Experts are required to properly detect the test results and it takes a lot of time and cost to manually Interpret the radio-graphic testing image of the structure over 500 blocks. The algorithms that automatically interpret the existing radio-graphic testing images to extract features through image pre-processing and classify the defects using neural networks, and only partial automation is performed. In order to implement the feature extraction and classification in one algorithm and to implement the overall automation, this paper proposes a method of automatically detecting welding defect using Faster R-CNN which is a deep learning basis. We analyzed the data to learn algorithms and compared the performance improvements using data augmentation method to artificially increase the limited data. In order to appropriately extract the features of the radio-graphic testing image, two internal feature extractors of Faster R-CNN were selected, compared, and performance evaluation was performed.

Welding defects must be inspected to verify that the welds meet the requirements of ship welded joints, and in welding defect inspection, among nondestructive inspections, radiographic inspection is widely applied during the production process. To perform nondestructive inspection, the completed weldment must be transported to the nondestructive inspection station, which is expensive; consequently, automation of welding defect detection is required. Recently, at several processing sites of companies, continuous attempts are being made to combine deep learning to detect defects more accurately. Preprocessing for welding defects in radiographic inspection images should be prioritized to automatically detect welding defects using deep learning during radiographic nondestructive inspection. In this study, by analyzing the pixel values, we developed an image preprocessing method that can integrate the defect features. After maximizing the contrast between the defect and background in radiographic through CLAHE (contrast-limited adaptive histogram equalization), denoising (noise removal), thresholding (threshold processing), and concatenation were sequentially performed. The improvement in detection performance due to preprocessing was verified by comparing the results of the application of the algorithm on raw images, typical preprocessed images, and preprocessed images. The mAP for the training data and test data was 84.9% and 51.2% for the preprocessed image learning model, whereas 82.0% and 43.5% for the typical preprocessed image learning model and 78.0%, 40.8% for the raw image learning model. Object detection algorithm technology is developed every year, and the mAP is improving by approximately 3% to 10%. This study achieved a comparable performance improvement by only preprocessing with data.

This paper predicts the wake-induced vibration of tandem cylinders with pivoted rotational or translational motion using the fluid–structure interaction technique. Large eddy simulation using a dynamic Smagorinsky subgrid-scale model is applied for the turbulent flow. Structural computation is applied to obtain the displacement of the downstream cylinder in the cross-flow direction. Conditions such as damping ratio, natural frequency, and mass ratio of pivoted rotational motion are the same as those of translational motion. The computational conditions are $Re=3790,\hspace{0.17em}8470\hspace{0.17em}\text{and}\hspace{0.17em}15\hspace{0.17em}160$ , corresponding to $U^{*}=5.0,\hspace{0.17em}11.2\hspace{0.17em}\text{and}\hspace{0.17em}20.0$ , respectively. The unsteady characteristics of lift, drag, and cross-flow motion of tandem cylinders are investigated. Distributions of pressure, ${\lambda }_2$ criterion, vorticity, and streakline are also investigated. Finally, the energy harvesting capability of the pendulum system is compared with the translation system.

Directional drilling involves three sections—vertical, curved, and horizontal—and is used for drilling offshore wells and mining unconventional resources. The initial design of a well trajectory is important because the total length of the well trajectory is associated with the drilling cost; furthermore, the drag force and torque may cause buckling and damage the drill pipe. The well trajectory should be optimized considering the length and load of drill pipes. In this study, a new method of optimizing directional well trajectory is used to formulate the objective function considering the length, drag, and torque. To verify the applicability of this method, we applied it to an actual oil well and a theoretical oil well. The results obtained show that the use of the proposed method in the initial design of drilling trajectory can reduce the torque by up to 15%, drag by 2.6%, and length by 8.5% for the two models used in this study. This method is safer as it reduces the risk of buckling compared to the design that relies on the previous designer’s experience, and it reduces the trajectory length; thus, it can save time and costs of drilling.

Flow-induced vibration (FIV) is a phenomenon in which the flow passing through a structure exerts periodic forces on the structure. Most studies on FIVs focus on suppressing this phenomenon. However, the Marine Renewable Energy Laboratory (MRELab) at the University of Michigan, USA, has developed a technology called the vortex-induced vibration for aquatic clean energy (VIVACE) converters that reinforces FIV and converts the energy in tidal currents to electrical energy. This study introduces the experimental data of the VIVACE converter and the associated method using deep neural networks (DNNs) to predict the dynamic responses of the converter. The DNN was trained and verified with experimental data from the MRELab, and the findings show that the amplitudes and frequencies of a single cylinder in the FIV predicted by the DNN under various test conditions were in good agreement with the experimental data. Finally, based on both the predicted and experimental data, the optimal power envelope of the VIVACE converter was generated as a function of the flow speed. The predictions using DNNs are expected to be more accurate as they can be trained with more experimental data in the future and will help to substantially reduce the number of experiments on FIVs.