Search

This paper presents a deep neural network (DNN)‐based model to recognize fishing vessels. In Taiwan, the vast majority of small fishing vessels are not equipped with an automatic identification system (AIS). As a consequence, the staff in a fishing port administration become heavily loaded when monitoring and managing the fishing vessels accessing a port. The workload is expected to be eased using this work. For the first time in the literature, a captured fishing vessel image was converted to a 128‐dimensional embedding for recognition purposes. The presented model gave a false positive rate (FPR) as low as 1.13% and an accuracy up to 99.47% at threshold = 0.772379. Finally, all the performance metrics, namely, the true positive rate (TPR), the FPR, precision and accuracy, are actually functions of the threshold which can be specified by users to meet specific requirements. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

Following the theory and method of the 'same‐phase power supply scheme', as declared in United States and Taiwan patents, a novel power supply method is proposed to reduce damage to users when the supply power is in shortage. This paper proposes using the equivalent model function blocks, as built by MATLAB/Simulink, for simulations of the probable line‐to‐line and single line‐to‐ground faults in a distribution system when the power supply mode is switched from 'normal' to 'same‐phase'. The simulation results prove that, when the power supply is switched to the 'same‐phase' power supply mode, all the short‐circuit fault currents are a little lower than that in the 'normal' power supply mode, and the maximum difference is less than 3%. Therefore, when the supplying power of the system is in shortage or the power distribution system has a short‐circuit fault between phase lines, the system can be directly switched to the 'same‐phase' power supply mode and can continue supplying power to the essential and basic loads for life‐support and people's livelihoods. © 2019 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc. [ABSTRACT FROM AUTHOR]

This paper proposes the optimal planning of soft starter characteristics for a large drain motor based on simulated annealing (SA). First, the planning of the soft starter characteristics is formulated as an optimization problem with minimal motor starting time; then, the constraints of the motor starting energy, power quality requirements, and minimal cost of transmission line are constructed. The system framework of an actual case in Taiwan is used as the basis of this study with simulation. Before and after the installation of three sets of soft starters, measuring instruments are used in the field to investigate the changes of current and voltage during the motor starting, thus establishing the database of current swell and voltage sag. The searching algorithm based on the SA method is developed by the program MATLAB, such that the soft starter can regulate the minimal motor starting time and meet the above-mentioned constraints. According to the model of the system circuit and the characteristic parameters constructed by an actual case, the simulation results verify the superiority of the proposed SA method. © 2014 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc. [ABSTRACT FROM AUTHOR]