Nasir A. Al-geelani

Hybrid regrouping PSO based wavelet neural networks for characterization of acoustic signals due to surface discharges on H.V. glass insulators

A hybrid algorithm combining Regrouping Particle Swarm Optimization (RegPSO) with wavelet radial basis function neural network referred to as (RegPSO-WRBF-NN) algorithm is presented which is used to detect, identify and characterize the acoustic signals due to surface discharge activity and hence differentiate abnormal operating conditions from the normal ones. The tests were carried out on clean and polluted high-voltage glass insulators by using surface tracking and erosion test procedure of international electro-technical commission 60,587. A laboratory experiment was conducted by preparing the prototypes of the discharges. A very important step for the WRBF network training is to decide a proper number of hidden nodes, centers, spreads and the network weights can be viewed as a system identification problem. So PSO is used to optimize the WRBF neural network parameters in this work. Therefore, the combination method based on the WRBF neural network is adapted. A regrouping technique called as a Regrouping Particle Swarm Optimization (RegPSO) is also used to help the swarm escape from the state of premature convergence, RegPSO was able to solve the stagnation problem for the surface discharge dataset tested and approximate the true global minimizer. Testing results indicate that the proposed approach can make a quick response and yield accurate solutions as soon as the inputs are given. Comparisons of learning performance are made to the existing conventional networks. This learning method has proven to be effective by applying the wavelet radial basis function based on the RegPSO neural network in the classification of surface discharge fault data set. The test results show that the proposed approach is efficient and revealed a very high classification rate.

Sugeno fuzzy PID tuning, by genetic-neutral for AVR in electrical power generation

Integrated model is developed by combining genetic algorithm (GA), radial basis function neural network (RBF-NN) and Sugeno fuzzy logic approaches.Optimal PID gains obtained by the proposed RBF-NN tuning for various operating conditions are used to develop the rule base of the Sugeno fuzzy system.The RBF-NN is used to enhance the PID parameters obtained from GA.Enhanced PID parameters are used to design Sugeno fuzzy PID controller tuned by excitation parameter (Ke, ?e) of the AVR system to improve the systems response. We report a novel design method for determining the optimal proportional-integral-derivative (PID) controller parameters of an automatic voltage regulator (AVR) system, using a combined genetic algorithm (GA), radial basis function neural network (RBF-NN) and Sugeno fuzzy logic approaches. GA and a RBF-NN with a Sugeno fuzzy logic are proposed to design a PID controller for an AVR system (GNFPID). The problem for obtaining the optimal AVR and PID controller parameters is formulated as an optimization problem and RBF-NN tuned by GA is applied to solve the optimization problem. Whereas, optimal PID gains obtained by the proposed RBF tuning by genetic algorithm for various operating conditions are used to develop the rule base of the Sugeno fuzzy system and design fuzzy PID controller of the AVR system to improve the systems response (~0.005s). The proposed approach has superior features, including easy implementation, stable convergence characteristic, good computational efficiency and this algorithm effectively searches for a high-quality solution and improve the transient response of the AVR system (7E-06). Numerical simulation results demonstrate that this is faster and has much less computational cost as compared with the real-code genetic algorithm (RGA) and Sugeno fuzzy logic. The proposed method is indeed more efficient and robust in improving the step response of an AVR system.

Identification of acoustic signals of surface discharges on glass insulator under different contamination levels

Surface discharge is a common phenomenon that normally occurs on the insulator surface under wet contamination condition. The generation of small sparks from the surface discharge would develop many types of signals. In this work an acoustic method is used to detect and capture the signals of surface discharges. The tests were carried out on cleaned and polluted glass insulators by using surface tracking and erosion test procedure of IEC 587. Three conditions of contamination levels were considered, which are light, medium and heavy based on ESDD levels. A laboratory experiment was done by making the models of these discharges. The test equipment including antennas as a means of detection and digital processing techniques for signal analysis were used. Wavelet signal processing was used to recover the surface discharge acoustic signal by eliminating the noises of many natures. Experimental results shows that the actual signals of surface discharge are related to the levels of insulator contamination.

Identification and Extraction of Surface Discharge Acoustic Emission Signals Using Wavelet neural network

A hybrid model incorporating wavelet and feed forward back propagation neural network (WFFB-NN) is presented which is used to detect, identify and characterize the acoustic signals due to surface discharge (SD) activity and hence differentiate abnormal operating conditions from the normal ones. The tests were carried out on cleaned and polluted high voltage glass insulators by using surface tracking and erosion test procedure of IEC 60587. A laboratory experiment was conducted by preparing the prototypes of the discharges. This study suggests a feature extraction and classification algorithm for SD classification, which when combined together reduced the dimensionality of the feature space to a manageable dimension. Wavelet signal processing toolbox is used to recover the surface discharge acoustic signals by eliminating the noisy portion and to reduce the dimension of the feature input vector. The test results show that the proposed approach is efficient and reliable. The error during training process was acceptable and very low which attained 0.0074 in only 14 iterations.

Characterization of leakage current on high voltage glass insulators using wavelet transform technique

The measurement and analysis of leakage current (LC) for condition-based monitoring and as a means of predicting flashover of polluted insulators has attracted a lot of research in recent years. Leakage current plays an important role in the detection of insulators condition. This paper proposes a method for reducing the noise included in the current signal. The tests were carried out on cleaned and polluted glass insulators by using surface tracking and erosion test procedure of IEC 60587. Wavelet analysis method is used to compress the leakage current data. Experimental results shows that the actual signals of leakage current are related to the levels of insulator contamination.

Optical detection and evaluation of partial discharge on glass insulator

In this paper, assessment based on surface discharge detection and analysis on polluted glass insulators are investigated. The sparks generated due to surface discharge could produce many types of signals. In this study, the optical fibre method is used for the detection of partial discharge signals that happened due to surface discharges. Experiments on both types of clean and polluted glass insulators were used by applying the surface tracking and erosion test procedure according to IEC 60587. Considering the surface discharges a laboratory experiment was performed in which three levels of high voltages (5kV, 10kV and 15kV) were applied. In these tests fibers optic cable as a sensor along with digital processing techniques for signal processing was implemented. Then wavelet analysis was used for signal processing to recover the surface discharge signal by a fibre optic sensor. The results show that the actual signals of surface discharge are associated with the contamination levels of insulators. These results confirm that by using the fibre optic sensor technique the detection of surface discharge on the high voltage glass insulator is possible.