Artificial neural networks have been used in different fields of artificial intelligence, and more specifically in machine learning. Although, other machine learning options are feasible in most situations, but the ease with which neural networks lend themselves to different problems which include pattern recognition, image compression, classification, computer vision, regression etc. has earned it a remarkable place in the machine learning field. This research exploits neural networks as a data mining tool in predicting the number of times a student repeats a course, considering some attributes relating to the course itself, the teacher, and the particular student. Neural networks were used in this work to map the relationship between some attributes related to students' course assessment and the number of times a student will possibly repeat a course before he passes. It is the hope that the possibility to predict students' performance from such complex relationships can help facilitate the fine-tuning of academic systems and policies implemented in learning environments. To validate the power of neural networks in data mining, Turkish students' performance database has been used; feedforward and radial basis function networks were trained for this task. The performances obtained from these networks were evaluated in consideration of achieved recognition rates and training time.
This paper proposes a modified three-phase inverter from the developed H-bridge structure having multilevel functionality. The proposed topology can generate 7-levels of phase voltages and 13-levels of line voltages. Simple control methods such as fundamental frequency control method can be applied to the proposed topology. By adding three single-phase transformers, galvanic isolation is created for use in three-phase Dynamic Voltage Restorer systems. The proposed three-phase inverter utilizes less number of components; dc sources, semiconductor switches and driver circuits. Lower rated power switches with reduced blocking voltages are also used. These attributes make the proposed topology less complex in-terms of architecture and control. Comprehensive analysis of the proposed three-phase multilevel inverter and other presented topologies are investigated with respect to levels of output voltage, driver circuit quantity, dc voltage count, total component quantity and standing voltage. Details of the appropriate control technique employed is explained. Finally, practicability of the proposed inverter is validated by simulation using EMTDC/PSCAD software and experimental prototype.
11 February 2025 in International Journal of Information Technology
Generating electric power by photovoltaic systems largely depends on multiple factors such as weather condition, panel orientation, panel efficiency, inverter efficiency, etc. These factors directly affect the magnitude of the PV output power. The first grid-tied photovoltaic power plant in Northern Cyprus is the K?b-Tek solar panel station located in Serhatkoy with a capacity of 1.275 MW. The aim of this paper is to comprehensively investigate K?b-Tek solar panel station considering investment made, plant efficiency, performance ratio, capacity factor and also determine the potential impact on levels of output power when a single axis solar tracking system is incorporated into the plant design. K?b-Tek solar panel station is at a fixed tilt angle of 24.840. Furthermore, other locations such as Famagusta, Girne and Lefkosa are investigated by simulation to determine their viability/suitability for the construction of similar photovoltaic power plants. The simulations are done using the technical parameters of K?b-Tek solar panel station as a model. Simulation results for these three locations are validated by comparing the magnitude of power produced by the actual plant (K?b-Tek solar panel station) and the simulated plants. PVsyst software is used for the simulation. Finally, the payback period of the actual plant and the simulated plants are determined.
This paper proposes a new cascaded three-phase multilevel inverter based on a cascaded submultilevel and single-phase H-bridge structure. The voltage source of the traditional single-phase H-bridge is replaced with the proposed cascaded submultilevel. Cascading two basic units forms the submultilevel unit. The basic and submultilevel units generate positive voltage only hence the need for an H-bridge to generate both polarities of load voltage. Five algorithms of source voltage are proposed and the optimal algorithm selected to generate the peak load voltage and output levels. The proposed three-phase cascaded multilevel inverter generates 31-level of load voltage. The per-phase component distribution of the proffered inverter are twelve power switches, four dc sources and twelve driver circuits accordingly. Principal merits of the proposed 31-level inverter are high quality load waveforms, production of high levels of load voltage utilizing reduced component quantity, simple cascaded layout, decreased inverter area, minimal inverter cost, minimum inverter losses and utilizing lower rated switches. Also, the proposed topology is highly suited for employment in PV-DVR and other power systems. To validate these advantages of the proposed multilevel inverter, contrastive analysis of the proposed inverter and existing topologies are studied. Finally, the functionality of the proposed inverter is substantiated by simulation in PSCAD/ EMTDC software.