The International Maritime Organization aims for net-zero carbon emissions in the maritime industry by 2050. Among various alternatives, route optimization holds an important place as it does not require any additional component-related costs. Especially for wind-assisted ships, the effectiveness of different sailing systems can be improved significantly through route optimization. However, finding the ship’s optimal route is computationally expensive when the totality of possible weather conditions is taken into consideration. To determine the optimal route that minimizes energy consumption, an energy model based on the environmental conditions, ship route and ship speed was built using artificial neural networks. The energy consumed for given input data was calculated using a ship dynamics model and a database was generated to train the artificial neural networks, which predict how much energy is consumed depending on the route followed in given environmental conditions. Then, such networks were exploited to derive the optimal routes for all the relevant operational conditions. It was found that route optimization can reduce the overall ship energy consumption depending on the weather conditions of the environment by up to 9.7% without any increase in voyage time and by up to 35% with a 10% delay in voyage time. The proposed methodology can be applied to any ship by training real weather conditions and provides a framework for reducing energy consumption and greenhouse gas emissions during the service life of ships.

Rotor sails are one of the promising solutions to reducing the energy consumption and CO₂ emissions of ships. Previous studies focused on how rotor sails affect ship dynamics and energy consumption. In the present study, an optimization-based workflow was proposed to find the optimal design of a rotor sail based on given environmental conditions for a target ship. Since the performance of a rotor sail depends on both operational conditions and the design of the rotor sail, a two-level optimization problem was proposed to separate the optimization of operational conditions and rotor sail design. At the operational level, the spin ratio of a given rotor sail was optimized at each time step under different environmental conditions. Then, the design of the rotor sail was optimized on the design level considering the initial cost of rotor sails and the average operational cost of the ship depending on the environmental conditions and their probabilities. The reductions in energy consumption of ships having optimal rotor sail designs, considering 5-year, 10-year, 15-year, and 20-year investment plans were found to be 0.34%, 2.7%, 3.91%, and 4.29%, respectively. When more severe environmental conditions were assumed for the 10-year investment plan, the diameter of the rotor sail increased and the reduction in energy consumption increased from 2.7% to 4.06%.

A machine learning method was applied to solve an inverse airfoil design problem. A conditional VAE-WGAN-gp model, which couples the conditional variational autoencoder (VAE) and Wasserstein generative adversarial network with gradient penalty (WGAN-gp), is proposed for an airfoil generation method, and then, it is compared with the WGAN-gp and VAE models. The VAEGAN model couples the VAE and GAN models, which enables feature extraction in the GAN models. In airfoil generation tasks, to generate airfoil shapes that satisfy lift coefficient requirements, it is known that VAE outperforms WGAN-gp with respect to the accuracy of the reproduction of the lift coefficient, whereas GAN outperforms VAE with respect to the smoothness and variations of generated shapes. In this study, VAE-WGAN-gp demonstrated a good performance in all three aspects. Latent distribution was also studied to compare the feature extraction ability of the proposed method.

Human gait varies based on personal characteristics, the existence of walking problems, or variability of gait parameters. Identifying the sources of variations is significant in detecting walking problems, designing orthotic/prosthetic products, etc. What are the types of variations in joint angles and ground reaction forces? How do age, sex, height, weight, and walking speed affect the distribution of the modes? In this study, temporal variations in the joint angles and ground reaction forces were obtained using singular value decomposition. Then, the relationships among age, sex, height, weight, walking speed, and the coefficients obtained by singular value decomposition were investigated using Pearson’s correlation coefficient matrix. The first mode of joint angles and ground reaction forces represent the overall characteristics; the first six modes of joint angles and the first two modes of ground reaction forces express 99.9% of the gait parameter space. We concluded that the walking speed dramatically affects joint kinematics and ground reaction forces. In addition, the effects of age, gender, height, and weight on the joint kinematics and ground reaction forces were also found, but with less contribution. The temporal behavior of the joint angles and ground reaction forces was expressed using a few coefficients due to singular value decomposition. The effects of age, sex, weight, height, and walking speed on the modes were found. The proposed method can be applied to understand the progression of an abnormality, and design orthotic/prosthetic products etc. in future studies.