Requirement of green supply with higher quality has been consumers’ demand around the globe The electrical power system is expected to deliver undistorted sinusoidal rated voltage and current continuously at rated frequency to the consumers This paper presents a comprehensive review of signal processing and intelligent techniques for automatic classification of the power quality (PQ) events and an effect of noise on detection and classification of disturbances It is intended to provide a wide spectrum on the status of detection and classification of PQ disturbances as well as an effect of noise on detection and classification of PQ events to the researchers, designers and engineers working on power quality More than 150 research publications on detection and classification techniques of PQ disturbances have been critically examined, classified and listed for quick reference

A critical review of detection and classification of power quality events

This paper proposed a novel approach for the Power Quality (PQ) disturbances classification based on the wavelet transform and self organizing learning array (SOLAR) system. Wavelet transform is utilized to extract feature vectors for various PQ disturbances based on the multiresolution analysis (MRA). These feature vectors then are applied to a SOLAR system for training and testing. SOLAR has three advantageous over a typical neural network: data driven learning, local interconnections and entropy based self-organization. Several typical PQ disturbances are taken into consideration in this paper. Comparison research between the proposed method, the support vector machine (SVM) method and existing literature reports show that the proposed method can provide accurate classification results. By the hypothesis test of the averages, it is shown that there is no statistically significant difference in performance of the proposed method for PQ classification when different wavelets are chosen. This means one can choose the wavelet with short wavelet filter length to achieve good classification results as well as small computational cost. Gaussian white noise is considered and the Monte Carlo method is used to simulate the performance of the proposed method in different noise conditions.

A self-organizing learning array system for power quality classification based on wavelet transform

Increasing interest in power quality has evolved over the past decade. This paper surveys the literature for current applications of advanced artificial intelligence techniques in power quality (PQ). Applications of some advanced mathematical tools in general, and wavelet transform in particular, in power quality are also reviewed. An extensive collection of literature covering applications of fuzzy logic, expert systems, neural networks, and genetic algorithms in power quality is included. Literature exposing the use of wavelets in power quality analysis as well as data compression is also cited.

Artificial Intelligence and Advanced Mathematical Tools for Power Quality Applications: A Survey

This paper proposes a fault detection and classification method for medium voltage DC (MVDC) shipboard power systems (SPSs) by integrating wavelet transform (WT) multiresolution analysis (MRA) technique with artificial neural networks (ANNs). The MVDC system under consideration for future all-electric ships presents a range of new challenges, in particular the fault detection and classification issues addressed in this paper. The WT-MRA and Parseval's theorem are employed in this paper to extract the features of different faults. The energy variation of the fault signals at different resolution levels are chosen as the feature vectors. As a result of analysis and comparisons, the Daubechies 10 (db10) wavelet and scale 9 are the chosen wavelet function and decomposition level. Then, ANN is adopted to automatically classify the fault types according to the extracted features. Different fault types, such as short circuit faults on both dc bus and ac side, as well as ground fault, are analyzed and tested to verify the effectiveness of the proposed method. These faults are simulated in real time with a digital simulator and the data are then initially analyzed with MATLAB. The case study is a notional MVDC SPS model, and promising classification accuracy can be obtained according to simulation results. Finally, the proposed fault detection algorithm is implemented and tested on a real-time platform, which enables it for future practical use.

Fault Detection and Classification in Medium Voltage DC Shipboard Power Systems With Wavelets and Artificial Neural Networks

The relevance of power quality (PQ) issues has recently augmented because of the increased use of power electronic equipment, which results in a voltage deviation and current waveforms. The PQ monitoring is covered by two main subjects: the development of PQ indices to quantify the power supply quality and the electrical disturbances detection such as harmonics, sags, swells etc., which allows knowing the conditions of the electric power systems. In this study a review of techniques and methodologies developed for PQ analysis and power disturbance classification is presented in order to show their major characteristics.

Techniques and methodologies for power quality analysis and disturbances classification in power systems: a review

This letter presents a new technique for learning power-quality waveforms. The approach is an intelligent technique based on exploiting the capabilities of adaptive fuzzy logic learning. The development of the mechanism was essential for the completion of an intelligent fuzzy expert system targeting power-quality problems using a mal-operation prediction technique.

An adaptive fuzzy technique for learning power-quality signature waveforms

The paper describes the development of an online fuzzy logic tool capable of controlling the system voltages and VAr resources, as well as processing alarms related to voltage stability. The fuzzy controller monitors system voltages and system VAr resources and generates appropriate control signals to each VAr source in the system to maintain acceptable system voltage levels. The fuzzy alarm processor generates an individual alarm for each voltage region, and a general alarm signal that indicates the overall system condition. The controller/processor has been designed as an on-line, real time tool. The paper presents a prototype fuzzy controller/processor that has been completely designed, programmed, and tested for a four-generator test system. It has been interfaced with power system simulation software to test its performance under on-line conditions.

An on-line fuzzy logic system for voltage/VAr control and alarm processing

This work describes the development of a fuzzy logic tool capable of controlling system voltages and VAr resources, as well as processing alarms related to voltage stability. The fuzzy controller monitors voltages and VAr resources and generates appropriate control signals to each VAr source to maintain acceptable system voltage levels. The fuzzy alarm processor generates an individual alarm for each voltage region, and a general alarm signal that indicates the overall system condition. A prototype fuzzy controller/processor has been interfaced with power system simulation software to test its performance under simulated on-line conditions.

W.R. Anis Ibrahim

Papers

Artificial Intelligence and Advanced Mathematical Tools for Power Quality Applications: A Survey

An adaptive fuzzy technique for learning power-quality signature waveforms

An on-line fuzzy logic system for voltage/VAr control and alarm processing

Wide-area fuzzy logic control of voltage/VAr under simulated online conditions