School of Electrical Engineering and Technology (SEET)

Permanent URI for this communityhttp://197.211.34.35:4000/handle/123456789/34

School of Electrical Engineering and Technology (SEET)

Browse

Search Results

Now showing 1 - 10 of 73
  • No Thumbnail Available
    Item
    Classification and Severity Estimation of Eccentricity Faults in Salient Pole Synchronous Machine using Deep Learning
    (IEEE, 2025) Yusuf, Latifa; Moa, Belaid; Ilamparithi, Thirumarai Chelvan
    The presented research work is focused on the classification and severity estimation of eccentricity faults in Salient Pole Synchronous Machines. Building on our comparative study of Artificial Neural Network and Convolutional Neural Network for eccentricity fault classification, we propose an end-to-end deep learning model, namely Hierarchical Convolutional Neural Network, for eccentricity classification and severity estimation. The deep learning model inherently consists of an eccentricity detection component for fault classification and a severity estimation component for fault quantification. The deep learning model is built using the experimental data of a 3-phase, 2-kW, salient pole synchronous machine. The machine is subjected to 20%, 40%, and 60% severities of static and dynamic eccentricity faults under different loading conditions. Stator line currents and line-to-line voltages obtained from different operating conditions are used to train, validate and test the proposed model. To enhance the model's performance, time delay construction was incorporated to augment the datasets and carefully evaluate the impact of selected raw input features, specifically stator currents and voltages, as well as the load. Among the evaluated scenarios, the use of voltage with time delay (V, TD) as input features produced the best results, achieving 100% classification accuracy and a root mean square error of 0.0046 for static eccentricity and 0.0188 for dynamic eccentricity estimation. Results indicate that the model performs excellently in fault classification and severity estimation. Compared to traditional machine learning models, the presented model is an end-to-end deep learning architecture devoid of manual feature extraction and is robust to load variations.
  • No Thumbnail Available
    Item
    EFFECTS OF UNIFIED POWER FLOW CONTROLLER (UPFC) ON DISTANCE RELAY TRIPPING CHARACTERISTICS IN THE NORTH-CENTRAL NIGERIAN 330kV NETWORK
    (Nigerian Journal of Technology (NIJOTECH), 2015-10) Yusuf, Latifa
    This paper investigates the effects of UPFC on Distance Relay tripping characteristics in the Nigerian 330kV (North-Central) Network. Its operation is based on impedance measurement at the relaying point. However, the system performance is often impeded by certain operational or structural factors such as load angle, the voltage magnitude ratio at the line ends, pre-fault line loading, and short circuit levels at the line ends. The Unified Power Flow controllers (UPFC) incorporated into the Nigerian 330kV (North-Central) Network were modelled in the environment of Power System Computer Aided Design (PSCAD) and kept within the protected zone of the relay to increase the Apparent Resistance, causing the relay to malfunction. Therefore, it is deduced by simulation analysis that the presence of UPFC in a faulted transmission line loop, protected by distance relay, greatly affects the trip boundaries of the distance relay by setting it to either an over-reaching or an under-reaching state. Hence, the tripping characteristics of distance relay with UPFC located at various points with respect to a fault on a transmission line culminated in three scenarios, the results of which are presented and discussed in this paper.
  • No Thumbnail Available
    Item
    Analysis of Reluctance Synchronous Motor Under Hybrid Fault Condition
    (IEEE, 2023-09) Ghalavand, Fatemeh; Yusuf, Latifa; Ilamparithi, Thirumarai Chelvan
    A small degree of static eccentricity is inevitable due to manufacturing tolerances and assembly imperfections. Therefore, when stator inter-turn fault happens, it is important to analyze it along with static eccentric condition. Unfortunately, there is not much literature that analyzes such a condition. This paper focuses on the analysis of a Reluctance Synchronous Machine (RSM) when subjected to stator inter-turn and static eccentricity faults simultaneously. In particular, the work focuses on determining the impact of relative position between the minimum airgap point and the stator inter-turn fault. The goal of the paper is achieved by simulating a 1.5 hp, 4-pole, RSM using Finite Element (FE) software. Line current data is captured under different fault conditions and motor current signature analysis is carried out. Furthermore, the lower sideband harmonic frequency is reconstructed in time domain using Inverse Fourier Fast Transform. Clarke’s transformation is applied on the reconstructed harmonic frequency currents to estimate the alpha, beta components. Afterwards, Principal Component Analysis (PCA) is implemented on the alpha, beta currents. The major benefits of the work include establishing the impact of hybrid faults on motor current signatures, developing a new measure to predict the relative position of the point of minimum airgap.
  • No Thumbnail Available
    Item
    Analysis of Double Salient Reluctance Machine Using Total Surface Gap Area
    (2nd International Engineering Conference (IEC2017) Federal University of Technology, Minna, Nigeria, 2017-06-12) Enesi, A. Y; Ejiogu, E. C; Anih, L. U
    In this paper, we analyze the stator-rotor design of a double salient reluctance machine using total surface gap area. The high number of poles in a 4-phase reluctance machine makes it suitable for the analysis. An expression is derived for the total surface gap area which includes the sum of the area of the air-gap (between the inner stator radius and the outer rotor radius), the area between the gaps of the stator poles and the area between the gaps of the rotor poles. The rated torque and the rated power output are expressed through the total surface gap area and the geometrical parameters. The total surface gap area is used to predict the torque ripple and the average torque developed by the machine for different pole arcs, air gaps, number of poles, number of phases and frequencies which are investigated by MATLAB simulation. The stator and the rotor of the machine are drawn by ANSYS software for the purpose of visualization.
  • No Thumbnail Available
    Item
    Parametric osicillations in electric oscillatory system
    (3rd International Engineering Conference (IEC2019), Federal University of Technology, Minna, Nigeria, 2019-06-12) Enesi A.Y; Ejiogu E.C
    The paper presents the parametric oscillations generated in an electric oscillatory system. Parametric oscillations are oscillations that are periodically modulated with time. The modulation depth and the carrier frequency are investigated by MATLAB/Simulink Model developed from Mathieu's equation. With this model, parametric oscillations are generated. The maximum and minimum amplitudes of oscillations for each characteristic number, a and the characteristic parameter, q is determined. The time taken for one oscillation (which is the period) for each characteristic number and characteristics perameter is determined. The relationship between the carrier frequency, the modulation depth and the characteristic number are established through graphical illustrations. These are approximate results of the solutions of Mathieu equation in electric oscillatory system.
  • No Thumbnail Available
    Item
    Permanent Magnet Synchronous Generator Connected to a Grid via a High Speed Sliding Mode Control
    (2022-06-12) Omokhafe J. Tola; Edwin A. Umoh; Enesi A. Yahaya; Osinowo E. Olusegun
    Wind power generation has recently received a lot of attention in terms of generating electricity, and it has emerged as one of the most important sources of alternative energy. Maximum power generation from a wind energy conversion system (WECS) necessitates accurate estimation of aerodynamic torque and system uncertainties. Regulating the wind energy conversion system (WECS) under varying wind speeds and improving the quality of electrical power delivered to the grid has become a difficult issue in recent years. A permanent magnet synchronous generator (PMSG) isused in the grid-connected wind-turbine system under investigation,followed by back-to-back bidirectional converters. The machine-sideconverter (MSC) controls the PMSG speed, while the grid-side converter(GSC) controls the DC bus voltage and maintains the unity power factor.The control approach is second-order sliding mode controls, which are usedto regulate a nonlinear wind energy conversion system while reducingchattering, which causes mechanical wear when using first-order slidingmode controls. The sliding mode control is created using the modifiedsuper-twisting method. Both the power and control components are builtand simulated in the same MATLAB/Simulink environment. The studysuccessfully decreased the chattering effect caused by the switching gainowing to the high activity of the control input.
  • No Thumbnail Available
    Item
    Artificial Neural Network Application for Error Estimation in Wireless Sensor Network
    (IEEE Forum (ICSTEM), 2017-05-06) Agajo, J., Kolo, J. G., Maliki, D., Umar, B. U., Inalegwu, O. C.
    This paper comes up with an error estimation model for Wireless Sensor Nodes,, the integrity of data received after transmission within a signal coverage range less or equal to 45 metres is analysed, Neural Network linear regression method was used to evolve resolve equation that compares error with weight of data received as δ℮(w) against δwij , an equation for error rate was also evolved after carefully comparing between data packet transmitted and Packet received, error rate er for sensor node was calculated to be 0.00918 thereby establishing the fact that expected packet to be received for every data transmitted is the product of er and Packet Transmitted.
  • No Thumbnail Available
    Item
    Evaluation of Speech Quality Based on QoS Key Performance Index (KPI): A Survey
    (Federal University of Technology Minna, 2017-05-06) Gbadamosi, A. S., & Maliki, D.
    The utmost contest between cellular operators have left the customers highly selective with the quality of speech based on the quality of service (QoS) experienced. In order to quantitatively and qualify the network performance based on speech quality, different key performance indicators (KPI) used, are classified to aid data collection methods that are used to reduce impairment as its affect speech are discussed and classified according to their operational mode. It provides a detailed report about the perceptuality of speech quality and its statistical expectation of the network. Each of these techniques has its advantages and disadvantages as applied to underscore the network performance from a user’s point of view. These techniques evaluate degradation caused by various impairments in cellular networks. Its I s our hope that, if user get hold of these applications, it will go a long way to keep cellular operators on their toes
  • No Thumbnail Available
    Item
    Development of A Model for Generation of Examination Time Using Genetic Algorithm
    (Federal University of Technology Minna, 2019-04-22) Ahmed, A., Umar, B. U., Abdullahi, I. M., Maliki, D., Anda, I., & Kamaldeen, J. A
    Examination time table scheduling problem is one of the complexes, NP-complete and typical combinational optimization problem faced by the university community across the globe. Many researches have studies the problem due to its NP-complete nature and highly-multi-constrained problem which seeks to find possible scheduling for courses. Creating an examination timetable for university is a very difficult, time-consuming and the wider complex problem of scheduling, especially when the number of students and courses are high. Several factors are responsible for the problem: increases number of students, the aggregation of schools, changes in educational paradigms, among others. In most universities, the examination time table schedule is usually ended up with various courses clashing with one another. I order to solve this problem of time table scheduling for University examination and effective utilization of resources, this research proposed a model for examination time table generation using Genetic Algorithm (GA) probabilistic operators. GA has been successful in solving many optimization problems, including University time table. This is based on the fact that GA is accurate, precise, free from human error and robust for complex space problem. GA theory was also covered with emphasis on the use of fitness function and time to evaluate the result. The effects of altered mutation rate and population size are tested. By using Genetic algorithm, we are able to reduce the time required to generate a timetable which is more accurate, precise and free of human errors. The implication of this research is a solution, minimizing the time taken in timetable allocation and the clashing that usually characterize time table schedule.
  • No Thumbnail Available
    Item
    An Improved Rain Activated Automatic Window
    (Biennial Engineering Conference, School of Engineering and Engineering Technology (SEET), 2013) Oyewobi S. Stephen; Okwori M; Achonu A. O; Waheed A. M
    Meteorological conditions like temperature, wind, clouds, and precipitation (rainfall) influence the condition of comfort inside a house, especially through wind doors and windows; hence the need for proper control activator (either to is close aimed or at open) having of window control made convenient to home owners by the use of a switch to open windows in a an improved automatic window with rain or close the window. The design was conceived after observing the stress mechanical windows give us in our control of it to let air and light come into the house; therefore, advancement in electronics technology was used to design this automatic window. However, unlike existing automatic windows, a rain sensor has been included in this work to help shut the window automatically when rain is falling. To achieve this, a moisture sensor is incorporated in the design to sense rainfall, a forward and reversing DC Motor to move the window pane back and forth, a bistable circuit to control the movement of the DC Motor and a power supply to power the system.The design of ble circult to control work effectively in convenient control of windows for the comfort of the homes and in protecting the homes from rainfall. Keywords: Automatic window, rain activator, mechanical window, electronics, DC motor.