Department of Electrical Engineering
Permanent URI for this communityhttps://repository.cuilahore.edu.pk/handle/123456789/18
Browse
8 results
Search Results
Item GSM Based Monitoring And Control Of Water Pump System(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2013) Ali Yusaf Khan , Saim-U-Dher , Rizwan Jaffar , She; SP09-BTE-014 , SP09-BTE-050 , SP09-BTE-068 , SP09-BTE-074; Miss Arsla KhanIn this project, we are developing a system that will provide and monitor the functioning parameters of a remotely placed water pump. Sometimes, the user is not present on the actual location of the system. For that, he will have to connect wirelessly with the system. The project is designed to take into account values of temperature and voltage of pump. It also gives the opportunity of controlling the flow of water pumping through the pump. The system will work using GSM technology in which a mobile user will send an SMS to the water pump system and request certain values. The user may also send commands to change the flow of water.Item Performance Improvement of Smart Grid by Implementing Hybrid Load Forecasting Method Using Neural Networks(COMSATS University Islamabad Lahore Campus, 2024) Muhammad Asad,; SP21-REE-004; Dr. Muhammad Farooq-i-Azam Assistant Professor Assistant Profesor [Supervisor]; LHR TP 8065The increasing use of renewable energy resources in power systems worldwide has led to the development of smart grids, which allow for bidirectional communication between supply and demand. Accurate load forecasting is crucial for maximizing the efficiency of these smart grids, as it allows for the switching between renewable and other energy resources, reducing overall costs and transmission losses. Neural network-based load forecasting models are performing better than traditional statistical models. The hybridization of neural network-based models with optimized learning algorithms is the focus of our research. In this work, we propose a novel approach for load forecasting in smart grids. The approach includes four key components: refactoring the smart grid dataset for load forecasting, gathering a highly relevant set of parameters affecting domestic load, constructing four hybrid models with appropriate tuning parameters, and comparative analysis of these models. We devise proper format and structure the data used for load forecasting, ensuring that it is in the best possible form for accurate predictions. We carefully select the most important parameters for medium and short-term load forecasting, ensuring that the model is able to take into account the most relevant factors. We use an empirical approach to determine the best set of parameters for our models, ensuring that they are optimized for accurate predictions.We have modelled three machine learning hybrid models with ANN, hybridized with genetic algorithm, particle swarm optimization, and Levenberg Marquardt, along with one deep learning model RNN-LSTM. Our comparative results show that ANN-GA and ANN-PSO performed better in medium-term forecast with accuracy rates of 93.7 and 98.26 percent, respectively. While ANN-LM and RNN LSTM performed better in short-term forecast achieving accuracy rates of 97 and 99 percent, respectively. Our results demonstrate that our proposed approach is effective in achieving highly accurate load forecasts, making it a valuable tool for optimizing the performance of smart grids. iItem Colour Detection Using Memristive Neural Network(Comsats university islamabad lahore campus, 2021) Junaid Razzaq; , SP19-REE-014 Contributor(s): Dr. Muhammad Naeem Awais, Assistant Profesor [Supervisor]; Dr. Muhammad Naeem Awais, Assistant Profesor [Supervisor]; LHR TP 7603The research on memristors and memristive devices significantly increased after the physical realization of memristor in 2008 at HP Labs. Its potential can be utilized in different applications such as memory technology and analog and digital logic circuit implementations. Since the memristor has the ability to act as a synapse, it has many uses in the field of neuromorphic engineering and machine learning. In this research work, memristor based neural network has been used for colour detection which is usually a primary stage in most of the image processing applications such as road signs detection, face detection, skin colour detection, object detection etc. The memristor bridge synapse which consists of four memristors is very effective in implementing the weights of neural networks at hardware level. SPICE is one of the best software available to simulate very large scale integration circuits. In this report we have built memristor based neural network architecture in HSPICE. Multiple simulations are performed to select the suitable weight update pulse of the memristor bridge synapse. The results of these simulations are discussed in detail in this report. The ideal memristor model is used to implement the memristor bridge synapse. We first normalized the data set of Red, Green and Blue (RGB) values between 0 and 1. Then we trained the memristive neural network to detect the colour in the RGB space. For the purpose of comparison, we have also detected colour using artificial neural network model in python. The comparison of the memristive bridge synapse with the other existing analog synapses and the advantages of memristor bridge synapse over them is discussed as well. The power calculation of the memristive neural network is also presented in this report.Item A Bi-Level Fuzzy Control Algorithm For Load Manage(COMSATS University Islamabad Lahore Campus, 2020) Hafiz Umar Khan,; SP19-REE-015; Dr. Muhammad Naeem Shahzad, Assistant Profesor [Supervisor]; LHR TP 7604The aim of this thesis is to deal with power dynamics of production and consumption by using the Bi-Level Fuzzy Control Algorithm for Load Management of Islanded Multi-Microgrids in the form of a new coordination control reconfiguration scheme has been discussed, in this system many grids in a cluster join and their SOC’s are charged by photovoltaic power. Generation is utilized for charging purpose and to feed the load surge. At time when imbalance of power generation of multiple system or discharging occurs, the fuzzy control algorithm efficiently anticipates in the system and fulfil the need of any other load or soc by any best suitable option in another microgrid system. The findings offered the good capability for these systems in the form of efficient production, less loss of power, more reliability and effectively power the load and charging using central controller. Primary and secondary controllers are being communicate by designed algorithms. These central controllers based on algorithms used to charge and share the power of multigrid in real time to balance the load of system. These systems are very useful in contemporary world. More upgradation is still in the future work of many researchers to comprehend the unending power consumption and production rise.Item Deep Learning Based Hand Gesture Recognition Using(comsats university islamabad lahore campus, 2021) Rija Sohail,; SP19-REE-017; Dr. Khuram ALi, Assistant Profesor [Supervisor]; LHR TP 7469In last couple of decades, much work has been done on Human Activity Recognition (HAR). HAR is a broad research area and excelled in many applications such as security, health care, gaming, intelligent environments and activity of daily living. One of the main applications of HAR is Hand Gesture Recognition (HGR). Hand gesture recognition is a complex classification problem. Previous studies show that different sensor technologies and different classification approaches have been used for gesture recognition. But still certain aspects need to be addressed so that the robustness and reliability of the gesture- based models can be improved. This research work is comprising of four traditional machine learning models SVM, KNN, Random Forest, Decision Tree and three deep learning models RNN-LSTM, CNN-LSTM and CNN. These seven models are developed and implement for the hand gesture data acquired from IMU. These models are then evaluated on the basis of different parameters. The analysis of result shows that deep learning-based models are clearly the best choice to be used for HGR systems.Item A Novel Renewable Powered Stand Alone Electric(COMSATS University Islambad Lahore Campus, 2021) Hira Asghar,; SP19-REE-002; Dr. Muhammad Jawad, Assistant Profesor [Supervisor]; LHR TP 7476The depletion of fossil fuels, gradually increasing environmental pollution and global warming lead to the electrification of the transport sector because the transport sector is one of the main reasons for the rising environmental concerns. However, the increasing number of electric vehicles (EVs) entering the power grid upsurges the electricity demand from the grid as it requires a massive amount of electricity to fulfill its charging needs. The existing electric grid and EV infrastructure is not capable enough to support increasing penetration of EVs, therefore the anticipated increase in the EV count brings new challenges regarding the EV charging needs. Most of the existing works have shared a common drawback of charging EVs by electricity provided from the electric grid. Thus, the primary purpose of utilizing EVs as a solution to decrease pollution is emitted due to the shifting of carbon emission from transportation to the electricity generation sector. This necessitates the usage of renewable energy resources, for instance, solar and wind energy to charge the electric vehicles to attain the environmental and economic benefits of EVs. Although renewable energy seems to be a promising solution due to its instability it may lead to an insufficient energy supply and cause an incomplete or interrupted charging of EVs.Item Artificial Neural Network Modeling Approach For(Publisher COMSATS University Islambad Lahore Campus, 2021) Syed Muhammad Saad Farooq; , SP19-REE-001; Dr. Mujtaba Hussain Jaffery, Assistant Profesor [Supervisor]; lhr tp 7464circulating Fluidized Bed (CFB) gasifiers are used to convert solid fuel into liquid fuel. Artificial Neural Network (ANN) and Neuro-fuzzy controllers have immense potential to improve the efficiency of the gasifier because Circulating Fluidized Bed gasifiers exhibit complex computational behavior and nonlinear process, based on their thermodynamic and electrochemistry. The focus of this report is to discuss Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) modeling approach to estimate solid circulation rate at high pressure in the Circulating Fluidized Bed gasifier. The data obtained on laboratory scale prototype in chemical engineering laboratory which is already published in the literature review to observe the flow rate of biomass solid fuel. Both, ANN and ANFIS model worked on 217 samples of experimental data, in which pressure (𝑏𝑎𝑟 − 𝑎𝑏𝑠), single mean diameter (SMD), total valve opening (𝑐𝑚/𝑠), mass flow rate (𝑔/𝑠) and riser dp (𝑚𝑚 − 𝐻20) have been included as the major focus of the study. Moreover, Neural Network toolbox and Neuro fuzzy toolbox are used in MATLAB 2019a. These two different architectures of neural network i.e. Artificial Neural Network (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS) use four input features and one output feature with multiple neurons in the hidden layers, to estimate the flow of solid particles in the riser. The output results are compared based on their Mean Square Error (MSE), Regression analysis(𝑅2), Mean Average Error (MAE) and Mean Absolute Percentage Error (MAPE). This report discusses in detail about the superiority of Neuro-Fuzzy controller over Artificial Neural Network. Each input is important variable for Artificial Neural Network (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS) model for the improvement of Circulating Fluidized Bed performance in terms of syngas and input feedstock to boiler.Item Health Assessment Of Human Knee Using Acoustic(Publisher COMSATS University Islambad Lahore Campus, 2023) Zeeshan Arif; SP19-REE-011; Dr, Khurram Ali, Assistant Profesor [Supervisor]Based on the analysis of 116 healthy and 116 osteoarthritic knees, this thesis details the discovery of knee Acoustic Emission (AE) as a helpful tool for the health assessment of the human knee. Knee Osteoarthritis (KOA) is a widely spread disease all over the world which arises because of damage to the joint cartilage and subchondral bone. The main factors, which increase KOA, are unhealthy lifestyle, injuries, and aging. Currently, diagnosis mainly depends on symptoms reported by patients and medical tests like X-rays and Magnetic resonance imaging (MRI). Symptoms start to appear over a years. Current diagnosis methods have some limitations and approachability issues because of the heavy machinery required to perform these tests and the cost of the test is also the main factor that this disease is not identified on time. One of the major limitations is that these tests are carried out when the body is in a static position and doctors get no visualization of the knee performance in normal functional movement. In this research, we are purposing a cost-effective method to get the status of knee health in its normal functional movement by studying the AE produced during the movement of the knee. We tried to identify the presence of OA in the knee and also tried to figure out how we can suggest the severity of the disease by using AEs. Hardware was developed with the collaboration of LUMS hardware was capable to listen to the acoustic sounds from the knee. The hardware setup includes the piezoelectric sensor, piezo film lab amplifier, and NI-DAQ USB6009. The signal is acquired from the knee joint by attaching the piezoelectric sensor with the help of double-sided tape.