Repository logo
 

Research Publications (Engineering and Built Environment)

Permanent URI for this collectionhttp://ir-dev.dut.ac.za/handle/10321/215

Browse

Subject: search.filters.subject.Power system

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    High impedance fault detection protection scheme for power systems distribution networks
    (Elsevier BV, 2022) Moloi, Katleho; Davidson, Innocent
    Protection schemes are used in safe‐guarding and ensuring the reliability of an electrical power network. Developing an effective protection scheme for high impedance fault (HIF) detection remains a challenge in research for protection engineers. The development of an HIF detection scheme has been a subject of interest for many decades and several methods have been proposed to find an optimal solution. The conventional current‐based methods have technical limitations to ef‐ fectively detect and minimize the impact of HIF. This paper presents a protection scheme based on signal processing and machine learning techniques to detect HIF. The scheme employs the discrete wavelet transform (DWT) for signal decomposition and feature extraction and uses the support vec‐ tor machine (SVM) classifier to effectively detect the HIF. In addition, the decision tree (DT) classi‐ fier is implemented to validate the proposed scheme. A practical experiment was conducted to ver‐ ify the efficiency of the method. The classification results obtained from the scheme indicated an accuracy level of 97.6% and 87% for the simulation and experimental setups. Furthermore, we tested the neural network (NN) and decision tree (DT) classifiers to further validate the proposed method
  • Thumbnail Image
    Item
    Investigation of voltage unbalance in low voltage electric power distribution network under steady state mode
    (IEEE, 2017-11) Taiwo, Ogunboyo Patrick; Tiako, Remy; Davidson, Innocent E.; Okafor, K.C.; Atimati, E.E.; Achumba,, I.E.
    © 2017 IEEE. With the ever increasing use of semiconductor devices and information technology (ICT) equipment in the industry's, homes and offices voltage quality are gaining meaningful attention to both industry and the electric utility. Poor voltage quality cause unusually large economic losses all over the world, since voltage quality problem is one of the major power quality disturbances. This report provides an investigative study on the typical 11/0.4 kV, low voltage electric power distribution network. The network was modelled with standard network parameters for low voltage typical electric power distribution network using MATLAB/Simulink Sim Power System tool box. Results obtained from simulation with distribution feeder length 0.5 km for unbalanced 3-phase loads are within the acceptable nominal voltage tolerance range of ± 5 % of the nominal voltage value at the customer's terminal. While this is admissible for customers close to the infeed terminal, it was established that an inadmissible poor voltage reaches the customers at the end of the distribution network for network lengths 0.8 km to 5 km. Voltages measured here were less than the standard allowable limit of 0.95 p.u, of nominal voltage value. The summary of the paper gives recommendations on effective methods for enhancing voltage profile and correcting the unbalanced voltage to an allowable standard.