Electrical Engineering

Permanent URI for this collection


Recent Submissions

Now showing 1 - 5 of 333
  • Item
    Enhanced Control Strategy for Single-Phase Grid-Tie Inverter with Repetitive Learning Controller
    (2024) Yahya Naser; Hassan Bargouth
    Photovoltaic (PV) power being supplied to the utility grid is becoming increasingly popular as the world’s power demand continues to rise. Solid-state inverters are the key technology that enables the integration of PV systems into the grid. Inverters are used to convert the DC voltage obtained from the PV system to AC voltage, which is then fed to the grid. Hysteresis control is typically used to control the inverter to regulate the real and reactive power injected from the PV into the grid. However, in this project, the real and reactive power will be controlled using a different technique, namely the PI controller in addition to the repetitive controller. The repetitive controller will compensate for any errors introduced by the PI controller in tracking the sinusoidal reference, as shown in Figure 1. Figure 1: PV multi-level-based Grid The project will first be simulated in MATLAB Simulink. The hardware components include a microcontroller, current, voltage sensors, H-bridge, and transformer to implement both the PI and the repetitive controllers, in addition to generating a PWM signal to the H-bridge to control the injection of real and reactive power into the grid.
  • Item
    AIEN Artificial Intelligence Electrical Nose
    (2024) Ameer Abo liel; Malath Ghazal
    nspired by the high drug smuggling crime rates all over the world, and due to the fact that current mechanisms of drug detection in airports cause discomfort to many travelers worldwide, the need for new reformed detection mechanisms is constantly growing. Using trained K9 dogs could cause many fearful scenarios that could cause trauma to innocent patients. The new mechanism we are presenting to you shows instantaneous results about the material detected. This project presents an artificial intelligence electronic nose (AIEN) for detecting and identifying various odors and substances. The AIEN utilizes MQ gas sensors and machine learning algorithms to analyze and classify different volatile organic compounds. A filtration system with ethanol is implemented to ensure accurate results between samples. The device also incorporates DC and AC fans and motors controlled by a microcontroller to automate the sampling process. Extensive testing produced consistent characteristic odor profiles and plots for different substances like perfumes and alcoholic beverages. The fusion of gas sensor technology with artificial intelligence offers an innovative approach to processing complex olfactory data. AIEN provides a proof of concept for the capabilities of intelligent odor detection systems in fields ranging from quality control to law enforcement
  • Item
    Online Signature Recognition Using CNN &RNN
    (2022) Ekram Othman; Maram Bani jabber
    Signature is widely used in human daily lives, and serves as a supplementary characteristic for verifying human identity. However, there is rare work of verifying signature. In this paper, we propose a few deep learning architectures to tackle this task, ranging from CNN, RNN to CNN-RNN compact model. We also improve Path Signature Features by encoding temporal information in order to enlarge the discrepancy between genuine and forgery signatures. Our numerical experiments demonstrate the effectiveness of our constructed models and features representations, also the experimental results indicate significant error reduction and accuracy enhancement in comparison with state of the art counterparts.
  • Item
    Offline Signature Recognition Using ANN
    (2021) Ekram Othman; Maram Bani jabber [11611935]
    A person’s signature is an important vital feature for a person that can be used to verify human identity, so we used the artificial neural network method to recognize the signature, and it consists of simple elements that work in parallel, these elements are inspired by the biological nervous system. The principle of its work is that the signature is captured and presented to the user in a form picture. Signature verification can be classified into online signature verification and offline signature verification. Online verification is based on dynamic capturing of signatures when they are made whereas Offline verification generally uses a scanned image of signatures. The objective of this project is to focus on the offline model of verification where several signatures are put through various processes before finally verifying it to be true or forged through Artificial Neural Networks (ANN). . To perform verification or identification of a signature, several steps must be performed. These steps are: * Image pre-processing * Feature extraction * Neural Network Training From many algorithms and methods with different accuracy percentages In this project we propose a human signature recognition system based canny edge detection and pattern averaging and back propagation neural network system.
  • Item
    Traffic sign recognition by using convolutional neural network
    (2023) Sondos Khatatbeh; Salam Nazzal
    In recent years there has been a rapid increase in technology that brought changes in human’s life which helps us to make tasks so easier even the complex management systems. traffic sign recognition is one of the important factor to be considered. To recognize the traffic signs we build a model using convolutional neural networks and this model will recognize the traffic signs. This algorithm is optimized by different optimizers’ algorithm such as Adam, AdaDelta, AdaGrad, RMSprop and SGD. The SGD algorithm achieved most accuracy so we consider it for optimizing our CNN model. It is implemented by using python platform.