Repository logo
 

Theses and dissertations (Engineering and Built Environment)

Permanent URI for this collectionhttp://ir-dev.dut.ac.za/handle/10321/10

Browse

Filters

2005 - 200932020 - 20232

Settings

Subject: search.filters.subject.Artificial intelligence

Search Results

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item
    Modeling and performance analysis of artificial intelligence (AI) based controllers for AVR of a synchronous generator (SG)
    (2023-05) Mazibuko, Ntombenhle; Akindeji, Kayode Timothy; Sharma, Gulshan
    An automatic voltage regulator (AVR) is an electronic device used to control, adjust, and maintain a constant voltage level at the stator terminals of a synchronous generator (SG). Hence, the voltage stability of a power system network is affected by AVR’s performance. Maintaining constancy and stability of the nominal voltage level in power systems remains a major control problem. Another critical reason for effective control of the generator's terminal voltage is that real line losses are determined by the real and reactive power flows and variation in terminal voltage has a large effect on reactive power flow and thus on these losses. A large power system consists of several synchronous generators that operate in synchronism; the terminal voltage and frequency are to be kept constant with minimal variation to ensure the stability of the power system. The voltage stability of a synchronous generator is highly affected when the terminal voltage varies above the nominal acceptable range. To maintain a constant voltage at a SG’s terminal, an AVR is used. The performance of an AVR is highly dependent on efficient controller design, which improves the output of the AVR by restoring the voltage of the synchronous generator to its nominal value in the presence of disturbances. The selection of a suitable controller is one of the most challenging aspects of AVR system design. This study presents the design, modeling, and performance analysis of an AVR system employing a Proportional Integral and Derivative (PID) controller, a Fuzzy Logic controller (FLC), and a Model Predictive Controller (MPC) for the performance enhancement and transient response of the AVR system with these controllers. Initially, a transfer function is used to develop a mathematical model of an AVR in order to observe its step response when the terminal voltage of a generator is disturbed. A PID controller is then added to the system and tuned to enhance the step response of an AVR. The third model develops and implements an AVR system based on MPC, while the final model implements an FLC for an AVR system. Simulating the models in Matlab Simulink 2021a, the results have demonstrated the need for a controlling mechanism to enhance the dynamic performance of the AVRS, and MPC has shown to be the most effective controller.
  • Thumbnail Image
    Item
    Artificial intelligence based solar/diesel hybrid water pumping system
    (2021-12-01) Moyo, Ranganai Tawanda; Tabakov, Pavel Y.
    Solar energy powered systems are increasingly being implemented in different areas due to the advances in solar energy technologies. Some of the major areas for solar energy applications include solar water heating, solar electric power generation, and solar water pumping. Solar water pumping has become the most adopted solar energy technology in the last decade. It has been considered as an attractive way to provide water in remote areas. A major advantage of using solar water pumps is that they are naturally matched with solar irradiation since usually water demand is high in summer when solar irradiation has its maximum values. However, solar energy powered systems are weather dependent. In most cases, a solar energy source has to be combined with another energy source to form a hybrid system to overcome the demerits of using solar alone. This thesis provides the detailed design, modelling and analysis of an Artificial Intelligence (AI) based solar/diesel hybrid water pumping system. This research aims to develop an optimization model that uses AI techniques to maximize the solar energy output and manage the energy flow within the solar/diesel hybrid water pumping. Thus, the proposed system is composed of solar photovoltaic modules, battery bank, Variable Speed Diesel Generator (VSDG), Adaptive Neuro-Fuzzy Inference System (ANFIS) based Maximum Power Point Tracking (MPPT) controllers and an Energy Management Controller (EMC). The EMC, which is based on Fuzzy Logic (FL), is responsible for managing the flow of energy throughout the hybrid system to ensure an undisturbed power supply to the water pump. The PV array, battery bank, VSDG are all sized to power a 5Hp DC water pump and the ANFIS based MPPT controllers are proposed for improving the efficiency of PV modules. The modelling of the system components is performed in the MATLAB/Simulink environment. For evaluation of the proposed system, several case scenarios were considered and simulated in the MATLAB/Simulink environment. The simulation results revealed the effectiveness of the proposed ANFIS based MPPT controllers since the controllers were able to extract maximum available power from PV modules for both steady-state and varying weather conditions. The proposed EMC demonstrated the successful management and control of the energy flow within the hybrid system with less dependency on the VSDG. The EMC was also able to regulate the charging and discharging of the battery bank.
  • Thumbnail Image
    Item
    Object motion detection, extraction and filtering using ANN ensembles
    (2009) Moorgas, Kevin Emanuel; Govender, Poobalan
    This research is devoted to the development of an intelligent image motion detection system based on artificial neural networks (ANN’s). Object motion detection, non-stationary image isolation and extraction, and image filtering is investigated, with the intention of developing a system that will overcome some of the shortcomings associated with the performance of conventional motion detection systems. Motion detection and image extraction finds popular application in medical imagery and engineering based diagnostics systems. Conventional image processing systems utilise Digital Signal Processing (DSP) to perform the non-stationary image motion detection function. Aliasing and filtering are problematic processes in DSP based image processing systems. The proposed ANN motion detection system overcomes some of these shortcomings. The study compares the performance of conventional DSP systems to that of the proposed ANN based system. The excellent noise immunity, ability to generalise and robustness of the ANN system is exploited in the design of the motion detection system. The ANN’s are arranged as ensembles in order to improve the computation time of the proposed motion detection system. A hybrid system comprising DSP and ANN ensembles is also proposed in the study. The hybrid system exploits the positive characteristics of DSP and ANN’s within a single system. The performance of the pure ANN system and the hybrid system is compared to that of DSP systems, using the image’s signal-to-noise ratio and computation times as a basis for comparison.
  • Thumbnail Image
    Item
    Design and implementation of an intelligent vision and sorting system
    (2009) Li, Zhi; Govender, Poobalan
    This research focuses on the design and implementation of an intelligent machine vision and sorting system that can be used to sort objects in an industrial environment. Machine vision systems used for sorting are either geometry driven or are based on the textural components of an object’s image. The vision system proposed in this research is based on the textural analysis of pixel content and uses an artificial neural network to perform the recognition task. The neural network has been chosen over other methods such as fuzzy logic and support vector machines because of its relative simplicity. A Bluetooth communication link facilitates the communication between the main computer housing the intelligent recognition system and the remote robot control computer located in a plant environment. Digital images of the workpiece are first compressed before the feature vectors are extracted using principal component analysis. The compressed data containing the feature vectors is transmitted via the Bluetooth channel to the remote control computer for recognition by the neural network. The network performs the recognition function and transmits a control signal to the robot control computer which guides the robot arm to place the object in an allocated position. The performance of the proposed intelligent vision and sorting system is tested under different conditions and the most attractive aspect of the design is its simplicity. The ability of the system to remain relatively immune to noise, its capacity to generalize and its fault tolerance when faced with missing data made the neural network an attractive option over fuzzy logic and support vector machines.
  • Thumbnail Image
    Item
    Diesel engine performance modelling using neural networks
    (2005) Rawlins, Mark Steve
    The aim of this study is to develop, using neural networks, a model to aid the performance monitoring of operational diesel engines in industrial settings. Feed-forward and modular neural network-based models are created for the prediction of the specific fuel consumption on any normally aspirated direct injection four-stroke diesel engine. The predictive capability of each model is compared to that of a published quadratic method. Since engine performance maps are difficult and time consuming to develop, there is a general scarcity of these maps, thereby limiting the effectiveness of any engine monitoring program that aims to manage the fuel consumption of an operational engine. Current methods applied for engine consumption prediction are either too complex or fail to account for specific engine characteristics that could make engine fuel consumption monitoring simple and general in application. This study addresses these issues by providing a neural network-based predictive model that requires two measured operational parameters: the engine speed and torque, and five known engine parameters. The five parameters are: rated power, rated and minimum specific fuel consumption bore and stroke. The neural networks are trained using the performance maps of eight commercially available diesel engines, with one entire map being held out of sample for assessment of model generalisation performance and application validation. The model inputs are defined using the domain expertise approach to neural network input specification. This approach requires a thorough review of the operational and design parameters affecting engine fuel consumption performance and the development of specific parameters that both scale and normalize engine performance for comparative purposes. Network architecture and learning rate parameters are optimized using a genetic algorithm-based global search method together with a locally adaptive learning algorithm for weight optimization. Network training errors are statistically verified and the neural network test responses are validation tested using both white and black box validation principles. The validation tests are constructed to enable assessment of the confidence that can be associated with the model for its intended purpose. Comparison of the modular network with the feed-forward network indicates that they learn the underlying function differently, with the modular network displaying improved generalisation on the test data set. Both networks demonstrate improved predictive performance over the published quadratic method. The modular network is the only model accepted as verified and validated for application implementation. The significance of this work is that fuel consumption monitoring can be effectively applied to operational diesel engines using a neural network-based model, the consequence of which is improved long term energy efficiency. Further, a methodology is demonstrated for the development and validation testing of modular neural networks for diesel engine performance prediction.