Essam M. Aboul-Zahab

ANN-based for detection, diagnosis the bearing fault for three phase induction motors using current signal

This paper develop a novel, non-intrusive approach for fault-detection and diagnosis scheme of bearing faults for three-phase induction motor using stator current signals with particular interest in identifying the outer-race defect at an early stage. The most common bearing problem is the outer race defect in the load zone. The empirical mode decomposition (EMD) technique is proposed for analysis of non-stationary stator current signals. The stator current signal is decomposed in intrinsic mode function (IMF) using empirical mode decomposition. The extracted IMFs apply on the wigner-ville distribution (WVD) to have the contour pattern of WVD. Then, artificial neural network is used for pattern recognition that can effectively detect outer-race defects of bearing. The experimental results show that stator current-based monitoring with winger-ville distribution based on EMD yields a high degree of accuracy in fault detection and diagnosis of outer-race defects at different load conditions, also, a more significant and reliable indicator for detection and diagnosis of outer-race defects using artificial neural network. Experimental investigation is done and reported in the paper.

High Impedance Faults Detection in EHV Transmission Lines Using the Wavelet Transforms

High impedance faults (HIFs) are difficult to detect by overcurrent protection relays. This paper presents an ATP/EMTP fault simulations studies based algorithm for high impedance fault detection in extra high voltage transmission line. The scheme recognizes the distortion of the voltage waveforms caused by the arcs usually associated with HIF. The discrete wavelet transform (DWT) based analysis, yields three phase voltage in the high frequency range which are fed to a classifier for pattern recognition. The classifier is based on an algorithm that uses recursive method to sum the absolute values of the high frequency signal generated over one cycle and shifting one sample. A HIF model of distribution is modified for EHV transmission lines. Characteristics of the proposed fault detection scheme are analyzed by extensive simulation studies that clearly reveal that the proposed method can accurately detect HIFs in the EHV transmission lines.

High impedance fault detection in mutually coupled double-ended transmission lines using high frequency disturbances

Coupling Capacitor Voltage Transformer (CCVT) secondary voltages, normally applied to conventional schemes, do not comprise appropriate information for schemes that operate on high frequency fault generated transients. However it is possible to capture the required travelling wave information contained in fault transients using a high frequency tap from a CCVT. This paper presents an ATP/EMTP fault simulations studies based algorithm for half cycle high impedance fault detection. The proposed scheme implemented on two different models of HIF in extra high voltage mutually coupled double- ended transmission lines. The scheme recognizes the distortion of the voltage waveforms caused by the arcs usually associated with HIFs. The high pass filter tap yields three phase voltage in the high frequency range which are fed to Clarkes transformation to decouple the traveling waves of the mutually coupled lines and produces ground mode and aerial modes voltage components to the classifier for pattern recognition. The classifier is based on an algorithm that uses recursive method to sum the absolute values of the high frequency signal generated over one cycle and shifting one sample. Characteristics of the proposed fault detection scheme are analyzed by extensive simulation studies that clearly reveal that the proposed method can accurately detect HIFs in the EHV transmission lines within only half a cycle from the instant of fault occurrence. The reliability of the proposed scheme does not affected by different fault conditions such as fault distance and fault inception angle.

Fault Tolerance of Stator Turn Fault for Three Phase Induction Motors Star-Connected Using Artificial Neural Network

This paper proposes the possibility of developing incipient fault diagnosis and remedial operating strategies, which enable a fault tolerant induction motor star-connected winding with neutral point earthed through a controllable impedance using artificial neural network (ANN). The fault detection and diagnosis is achieved by using a strategy that detects stator turn fault, isolates the faulty components, identifies fault severity and reduces the propagation speed of the incipient stator winding fault. The fault tolerance is obtained by controlled neutral grounding resistor. This allows for continuous free operation of the induction motor even with stator winding faults. The advantage of this strategy is that it does not require any change in the standard drive system. Experimental results demonstrate the validity of the proposed technique.

High-impedance fault detection in EHV transmission lines

The automatic detection of high impedance faults (HIFs) on transmission systems has been one of the most persistent and difficult problems facing utilities as a major safety concern. The paper presents two approaches to HIF detection in extra high voltage transmission lines. Both schemes analyze the nature and dynamics of the arc phenomenon related to HIFs using voltage waveforms at the relaying point. The first scheme is based on discrete wavelet transform (DWT) analysis while the second analyzes the three phase voltages using high frequency tap of the coupling capacitor voltage transformers. To ensure development of reliable algorithms, an accurate modeling of HIF is utilized with its complex characteristics such as buildup, shoulder as well as nonlinearity and asymmetry. Results of computer simulation using ATP/EMTP on 345 kV transmission line system clearly reveal that each of the proposed methods can accurately detect HIFs in the EHV transmission lines as well as their ability to discriminate clearly between HIFs and various switching conditions.

A new remedial strategy for permanent magnet synchronous motor based on artificial neural network

This paper proposes an effective approach to detect, isolate, and identify fault severity and post fault operation of permanent magnet synchronous motors (PMSM) in the presence of stator winding turn fault. The paper proposes fault tolerant operation of PMSM under post condition with stator winding turn fault by using grounded neutral point through controllable impedance using artificial neural network (ANN). The fault detection and diagnosis is achieved by using a strategy based on the analysis of the ratio of third harmonic to fundamental waveform obtained from Fast Fourier Transform (FFT) of magnitude components of the stator currents. The strategy helps to detect stator turn fault, isolate the faulty components, and estimate different insulation failure percentages and remedial operation of PMSM in the presence of stator winding turn fault. The model of PMSM with stator winding turn fault is simulated at different load conditions using a (2-D) Finite Element Analysis (FEA). Experimental results demonstrate the validity of the proposed technique.

Detection and discrimination between unbalanced supply and phase loss in PMSM using ANN-based protection scheme

Recently, Permanent Magnet Synchronous Motors (PMSM) is one of the most attractive electric machine in industrial applications, therefor must be protected against electrical and mechanical failures for continue their operation safely. However, different kinds of faults are unavoidable in motors during their operational service. Unbalancing in the supply voltage is common in grid supply. However, the unbalance supply and phase loss produces similar symptoms. Therefore, this paper focuses on unbalanced supply condition diagnosis and discrimination between unbalancing in supply and single phasing or phase loss fault based. The proposed technique utilizes the ratio of third harmonic to fundamental of stator line currents and supply voltages using artificial neural network (ANN). The presented approach gives high degree of accuracy in detection and diagnosis of phase loss fault and those due to supply voltages unbalance using artificial neural network. All simulations in this paper are conducted using finite element analysis software. The approach is proven effectively through experimental validation.

Neural network-based technique used for recovery the CCVT primary signal

The coupling capacitor voltage transformers transient response during faults can cause protective relay mal-operation or even prevent tripping. This paper presents the CCVT transient response errors and the use of artificial neural network (ANN) to correct the CCVT secondary waveform distortion. In this paper, an ANN program is developed to recover the primary voltage from the distorted secondary voltage. The ANN is trained to achieve the inverse transfer function of the coupling capacitor voltage transformer (CCVT), which provides a good estimate of the true primary voltage from the distorted secondary voltage. The neural network is developed and trained using MATLAB simulations. The accuracy of the simulation program is confirmed by comparison of its response with that of the target value from the simulation data.

Pre-breakdown photoelectric monitoring of AC gaps

Prebreakdown photoelectric monitoring of gaps is introduced. The photo and electric channels of measurements are discussed in detail. Photo and electric traces obtained for a point-to-plane air gap at natural temperature and pressure and under AC voltage are presented as examples. The gap geometry or gap length does not change the general character of the traces. Distinct relations between the photo and electric traces are presented and discussed relating to the breakdown mechanism. The presence of streamers at successively decreasing intervals leads to a plateauing in the photo trace which is a prebreakdown indicator. It is concluded that the proposed photoelectric monitoring provides a good tool for investigating the prebreakdown and breakdown processes of a gas gap. >