Predicting the output power of wind generators is essential to improve grid flexibility, which is vulnerable to power supply variability and uncertainty. Digital twins can help predict the output of a wind turbine using a variety of environmental data generated by real-world systems. This paper dealt with the development of a physics-based output prediction model (P-bOPM) for a 10 MW floating offshore wind turbine (FOWT) for a digital twin. The wind power generator dealt with in this paper was modeled considering the NREL 5 MW standard wind turbine with a semi-submersible structure. A P-bOPM of a 10 MW FOWT for a digital twin was designed and simulated using ANSYS Twin Builder. By connecting the P-bOPM developed for the digital twin implementation with an external sensor through TCP/IP communication, it was possible to calculate the output of the wind turbine using real-time field data. As a result of evaluating the P-bOPM for various marine environments, it showed good accuracy. The digital twin equipped with the P-bOPM, which accurately reflects the variability of the offshore wind farm and can predict the output in real time, will be a great help in improving the flexibility of the power system in the future.

Renewable energy is being adopted worldwide, and the proportion of offshore wind turbines is increasing. Offshore wind turbines operate in harsh weather conditions, resulting in various failures and high maintenance costs. In this paper, a condition diagnosis model for condition monitoring of an offshore wind turbine has been developed. The generator, main bearing, pitch system, and yaw system were selected as components subject to the condition monitoring by considering the failure rate and downtime of the wind turbine. The condition diagnosis model works by comparing real-time and predictive operating data of the wind turbine, and about four years of Supervisory Control and Data Acquisition (SCADA) data from a 2 MW wind turbine was used to develop the model. A deep neural network and an artificial neural network were used as machine learning to predict the operational data in the condition diagnosis model, and a confusion matrix was used to measure the accuracy of the failure determination. As a result of the condition monitoring derived by inputting SCADA data to the designed system, it was possible to maintain the failure determination accuracy of more than 90%. The proposed condition monitoring system will be effectively utilized for the maintenance of wind turbines.

This paper presents the results of an electromagnetic design and numerical analysis conducted on a 10-MW-class second-generation high-temperature superconducting generator (2G HTSG) used in an offshore wind power turbine. To report the operation reliability of 10-MW-class HTSGs employed in off-shore environment, various electric insulation techniques (EITs) for HTS field coils (FCs), such as no-insulation, metal insulation, and metal-insulator transition insulation, are considered in this study. Using the time-transient solver of the three-dimensional (3D) electromagnetic finite element analysis (FEA), we investigated the electromagnetic characteristics of the HTSG with the three EITs in terms of the electrical output of the HTSG and the critical current of the FCs. To analyze the charging characteristic of the HTS FCs with the three EITs in steady-state operation as well as the electrical in transient-state operation, electric equivalent circuit models are built with key parameters based on the electromagnetic FEA results. Finally, the performances of the HTS FCs are discussed and evaluated in terms of the electromagnetic response and stability characteristics.

This paper presented the design and performance analysis of a dynamo-type HTS flux pump for a 10 kW superconducting generator. The HTS field coil of a 10 kW superconducting generator was designed and fabricated. The induced DC current, output voltage, and dynamic resistance of the flux pump connected to the HTS field coil were estimated using electric circuit equations. They were tested at various rotational speeds and air gaps, and the test results were compared with the estimated results. The performance was confirmed by applying a flux pump to the 10 kW superconducting generator. As a result, as the rotational speed of the flux pump increased, the induced DC current of the flux pump connected to the HTS field coil increased proportionally. As the air gap of the flux pump increased, the induced DC current decreased. A sufficient current was induced in the field coil to produce a 10 kW output.

Large-scale High Temperature Superconducting (HTS) wind generators produce strong electromagnetic force and high torque due to the high magnetic load of the machines, which is produced by HTS coils with high excitation current. Therefore, in order to properly maintain the mechanical strength of the HTS coil part, the torque and Lorentz force of the HTS wind generator must be scrutinized and reflected in the design. The authors proposed a method for assessing mechanical and electrical stability of a large-scale HTS wind generator based on a Performance Evaluation System (PES) that has the same characteristics as some of the pole-pairs of the HTS generator. The generator and the PES were analyzed using 3D finite element method. The performance of the HTS coil was evaluated by comparing the tangential, radial force and magnetic field distribution of the 10 MW HTS generator with the PES. The tangential and radial forces of the 10 MW HTS generator were 73 kN and 11 kN, respectively. The tangential, radial forces and magnetic flux density of the HTS coils in the PES were equal to one pole in the 10 MW HTS generator. Therefore, the proposed PES-based generator characteristic evaluation method can be used to estimate the mechanical stability of the generator under a high magnetic field and high torque before manufacturing the HTS wind turbine.

In seaports, the automatic Grab-Type Ship Unloader (GTSU) stands out for its ability to automatically load and unload materials, offering the potential for substantial productivity improvement and cost reduction. Developing a fully automatic GTSU, however, presents a unique challenge: the system must autonomously determine the position of the cargo hold and the coordinates of the working point and identify potential hazards during material loading and unloading. This paper proposes AI models designed to detect cargo holds, extract working points, and support collision risk warnings, utilizing both the LiDAR sensor and the camera in the GTSU system. The model for cargo hold detection and collision warning was developed using image data of the cargo hold and grab, employing the You Only Look Once model. Concurrently, the model responsible for extracting the coordinates of working points for the GTSU system was designed by integrating the cargo hold detection and point cloud processing models. After testing the AI models for the lab-scale GTSU, the results show that the cargo hold detection and collision warning models achieve an accuracy of approximately 96% and 90%, respectively. Additionally, the working point coordinates extracted from the sensor system show a deviation of 5–10% compared to traditional measurements.