D. Johari

Fuzzy logic controller on DC/DC boost converter

This paper describes the design of a fuzzy logic controller using voltage output as feedback for significantly improving the dynamic performance of boost dc-dc converter by using MATLAB@Simulink software. The objective of this proposed methodology is to develop fuzzy logic controller on control boost dc-dc converter using MATLAB@Simulink software. The fuzzy logic controller has been implemented to the system by developing fuzzy logic control algorithm. The design and calculation of the components especially for the inductor has been done to ensure the converter operates in continuous conduction mode. The evaluation of the output has been carried out and compared by software simulation using MATLAB software between the open loop and closed loop circuit. The simulation results are shown that voltage output is able to be control in steady state condition for boost dc-dc converter by using this methodology.

Artificial neural network (ANN) application in dissolved gas analysis (DGA) methods for the detection of incipient faults in oil-filled power transformer

Power transformer is one of the fundamental equipments in the power system. Transformer breakdown or damage may interrupt power distribution and transmission operation, as well as incur high repair cost. Thus, detection of incipient faults in power transformer is essential and it has become an interesting topic to study. This paper presents the application of artificial neural network (ANN) in detecting incipient faults in power transformers by using dissolved gas analysis (DGA) technique. DGA is a reliable technique to detect incipient faults as it provides wealth of information in analyzing transformer condition. For this project, ANN was developed to classify seven types of transformer condition based on three combustible gas ratios. The development involves constructing several ANN designs and selecting network with the best performance. The gas ratio are based on IEC 60599 (2007) standard while historical data were used in the training and testing processes. The selected ANN design yields a very satisfactory result where it can make a reliable classification of transformer condition with respect to combustible gas generated.

Comparative study of Fuzzy Logic controller and Proportional Integral Derivative controller on DC-DC Buck Converter

The main objective of this document is to compare the performance between Fuzzy Logic controller (FLC) and Proportional Integral Derivative controller (PIDC) in improving the performance of DC/DC Buck Converters. The evaluation of the output has been carried out and compared by software simulation using MATLAB Simulink. Fuzzy logic controller has been implemented to the system by developing fuzzy logic control algorithm. The signals will be processed based on the fuzzy logic rules-based and PID algorithm.

Artificial Neural Network Based Technique for Lightning Prediction

Malaysia has high lightning and thunderstorm occurrences throughout the year. A vast amount of its data have been recorded which allows various lightning-related studies to be conducted. This paper presents the application of artificial neural network (ANN) in predicting the occurrence of lightning events based on historical lightning and meteorological data. ANN, which was inspired by the way biological nervous systems process information, is utilized in this study due to its strong pattern recognition capabilities; implemented through learning patterns and relationships in data. A two layer back-propagation neural network has been developed to predict the occurrence of lightning at least four hours prior to its arrival. Several network structures, training algorithms and activation functions have been rigorously tested in order to obtain the most suitable network with high accuracy and convergence capability, while the perfection of the developed network was conducted through postprocessing, indicated by the closeness of correlation coefficient to unity. The computation burden experienced in this study in achieving the converged solution has been alleviated by the introduction of indicator module to the original features of the training and testing patterns.

Optimized Artificial Neural Network for the detection of incipient faults in power transformer

This paper presents optimized Artificial Neural Network to identify and detect incipient faults in power transformer. This study involved the development of Artificial Neural Network (ANN) models and embedding Evolutionary Programming (EP) as the computational technique to optimize the built ANN. The optimized ANN is namely as EPANN. As one of the most important equipment in electrical power system, the condition of the equipment need to be monitored closely to avoid any disturbances since its operating status directly influences reliability and stability of the overall power system. Historical industrial data of Dissolved Gas Analysis (DGA) were used and the analysis works are based on IEC 60599 (2007) standard. Based on the acquired findings, the EPANN is proven yields a very satisfactory result compared to non optimized ANN.

Reactive Power Planning for transmission loss minimization

Total system losses of the power system relate to the reactive power management in the network. This paper presents a method to minimize the system losses by utilizing Reactive Power Planning (RPP) approach. In this technique, the control variables of RPP were formulated as an optimization problem and Multiagent Immune Evolutionary Programming (MAIEP) was engaged to determine the optimal solution of these variables. In order to evaluate the effectiveness of the proposed technique, the total system losses during pre optimization was compared with the system losses during post optimization at IEEE 30 bus system. The results revealed that the proposed technique has the merit in addressing the above problem.

Artificial neural network-based forecast for electricity consumption in Malaysia

An essential element of electric utility resource planning is the long term forecast of the electricity consumption. This paper presents an approach to forecast annual electricity consumption by using artificial neural network based on historical data for Malaysia. It involves developing several ANN designs and selecting the best network that can produce the best results in terms of its accuracy. The network is developed by means of economical conditions and how the variables are going to be changed in the following years. After obtaining the most reliable model, ANN is used to forecast the electricity consumption. The developed ANN model yields very satisfactory results and as a result, the range of electricity consumption can be successfully obtained.

Modeling of power system dynamic devices incorporated in Dynamic Computation for Power Systems (DCPS) for transient stability analysis

An electrical power system consists of many individual dynamic devices connected together to form a large and complex dynamic system. To analyze the behavior of such devices, its physical model needs to be transformed into mathematical model before it can be solved on a computer. In electric utility practices, the aspect of modeling and computational methods for power system dynamic devices such as generator, exciter and governor has not been given much attention by many engineers because such tasks could be solved using commercial software packages. The two most important requirements of such software packages are; i) the correct input data and assumptions; and ii) the output results that can be analyzed and understood. Hence, there was a lack of understanding of the modeling and computational methods and also the limitations of the individual dynamic devices. This paper presents the fundamental modeling and computation methods related to power system dynamics and performing the power system transient stability analysis by using Dynamic Computation for Power Systems (DCPS) software package. This C/C++ based software has been developed for research purposes and can be used to simulate load flow and transient stability analysis. The Improved Euler Method has been employed in this software to solve the mathematical model of power system dynamic devices namely synchronous generator, turbine-governor and exciter. The results showed that this software has been successfully developed to perform the transient stability analysis. The effect of varying load demand on the critical clearing time, tCCT has been tested on heavily loaded IEEE 9-bus test system when three phase fault is applied at bus 5. The simulation results showed that the critical clearing time decreases linearly with increasing load demand.

Thunderstorm forecasting by using artificial neural network

Thunderstorm is a form of weather characteristic containing strong wind, lightning, heavy rain and sometimes snow or hail. It can be associated with a cloud type of cumulonimbus. Depending on its type, thunderstorm has great potential to produce serious damage to human life and property. Therefore, there are many sophisticated instrument used to record weather data such as Doppler radar and satellite. By using these data, based on the statistical, mathematical or soft computing technique can be done in order to predict the occurrence the weather characteristic. This project presents the application of artificial neural network (ANN) in forecasting the thunderstorm occurrence in Shah Alam based on the meteorological data. Therefore, several three-layer feed-forward back-propagation ANNs were developed in Matlab and each network was evaluated by using cross-validation technique. A network with the best performance in terms of its R-value was selected as the best design. Thus, the forecasting of thunderstorm occurrence can be successfully done.

The Taguchi- Artificial Neural Network approach for the detection of incipient faults in oil-filled power transformer

This paper presents hybrid Taguchi-Artificial Neural Network to detect incipient faults in oil-immersed power transformer. It involved the development of Artificial Neural Network (ANN) designs and embedding Taguchi methodology to fine tune the parameters of a backpropagation feed-forward ANN. Detection of incipient faults in power transformer is essential because it is one of the fundamental equipments in the power system. Dissolved gas analysis technique was used as it has been found as a reliable technique to detect incipient faults as it provides wealth of information in analyzing transformer condition. This study is based on IEC 60599 (2007) standard and historical data were used in the training and testing processes. Comparative studies were conducted between heuristic ANN design and optimized hybrid Taguchi-Neural Network. The results show the effectiveness of the optimized neural network using Taguchi methodology.