Irene Yu-Hua Gu

Expert System for Classification and Analysis of Power System Events

This paper presents an expert system that is able to classify different types of power system events to the underlying causes (i.e., events) and offer useful information in terms of power quality. The expert system uses the voltage waveforms and distinguishes the different types of voltage dips (fault-induced, transformer saturation, induction motor starting), as well as interruptions (nonfault, fault induced). A method for event-based classification is used, where a segmentation algorithm is first applied to divide waveforms into several possible events. The expert system is tested using real measurements and the results show that the system enables fast and accurate analysis of data from power quality monitors.

Support Vector Machine for Classification of Voltage Disturbances

The support vector machine (SVM) is a powerful method for statistical classification of data used in a number of different applications. However, the usefulness of the method in a commercial available system is very much dependent on whether the SVM classifier can be pretrained from a factory since it is not realistic that the SVM classifier must be trained by the customers themselves before it can be used. This paper proposes a novel SVM classification system for voltage disturbances. The performance of the proposed SVM classifier is investigated when the voltage disturbance data used for training and testing originated from different sources. The data used in the experiments were obtained from both real disturbances recorded in two different power networks and from synthetic data. The experimental results shown high accuracy in classification with training data from one power network and unseen testing data from another. High accuracy was also achieved when the SVM classifier was trained on data from a real power network and test data originated from synthetic data. A lower accuracy resulted when the SVM classifier was trained on synthetic data and test data originated from the power network.

Estimating Interharmonics by Using Sliding-Window ESPRIT

A method is proposed for estimating inter-harmonic frequencies in power system voltage and current signals. The method is based on a spectrum-estimation method known as ldquoestimation of signal parameters via rotational invariance techniquesrdquo (ESPRIT). To allow for a more reliable spectral estimation and to cover nonstationarity in the signal, a sliding-window version of ESPRIT is introduced. This paper describes the basic ESPRIT method as well as sliding-window ESPRIT. The paper discusses the application of the method to one synthetic signal and three measurement signals. It is shown that the method allows for very accurate frequency estimation of interharmonic components. The limitations of the methods, such as line splitting and spurious components, can be overcome by using the coherent information obtained from the sliding-window method. A number of remaining issues are also discussed in this paper.

Robust Visual Object Tracking Using Multi-Mode Anisotropic Mean Shift and Particle Filters

This paper addresses issues in object tracking where videos contain complex scenarios. We propose a novel tracking scheme that jointly employs particle filters and multi-mode anisotropic mean shift. The tracker estimates the dynamic shape and appearance of objects, and also performs online learning of reference object. Several partition prototypes and fully tunable parameters are applied to the rectangular object bounding box for improving the estimates of shape and multiple appearance modes in the object. The main contributions of the proposed scheme include: 1) use a novel approach for online learning of reference object distributions; 2) use a five parameter set (2-D central location, width, height, and orientation) of rectangular bounding box as tunable variables in the joint tracking scheme; 3) derive the multi-mode anisotropic mean shift related to a partitioned rectangular bounding box and several partition prototypes; and 4) relate the bounding box parameter computation with the multi-mode mean shift estimates by combining eigen decomposition, geometry of subareas, and weighted average. This has led to more accurate and efficient tracking where only small number of particles (<;20) is required. Experiments have been conducted for a range of videos captured by a dynamic or stationary camera, where the target object may experience long-term partial occlusions, intersections with other objects with similar color distributions, deformable object accompanied with shape, pose or abrupt motion speed changes, and cluttered background. Comparisons with existing methods and performance evaluations are also performed. Test results have shown marked improvement of the proposed method in terms of robustness to occlusions, tracking drifts and tightness and accuracy of tracked bounding box. Limitations of the method are also mentioned.

Bridging the gap between signal and power

This article focuses on problems and issues related to PQ and power system diagnostics, in particular those where signal processing techniques are extremely important. PQ is a general term that describes the quality of voltage and current waveforms. PQ problems include all electric power problems or disturbances in the supply system that prevent end-user equipment from operating properly.

Categorization and analysis of power system transients

Power system transients are power-quality disturbances that can be harmful to electronic equipment. This paper contributes and provides some solutions to the following issues: 1) to introduce a new way to identify different categories of power system transients based on their underlying causes; 2) to propose a model and analysis tool for oscillatory transients, where emphasis is on finding phenomena and characteristics associated with the underlying causes of transients. A model-based approach, ESPRIT, is applied to a number of simulated voltage waveforms to extract the parameters of oscillatory transients, and the results may be used for identifying and understanding the causes of transients by correlating the major components in transients with the phenomena that may appear in different types of transients and some a priori knowledge of power system settings.

Classification of underlying causes of power quality disturbances: deterministic versus statistical methods

This paper presents the two main types of classification methods for power quality disturbances based on underlying causes: deterministic classification, giving an expert system as an example, and statistical classification, with support vector machines (a novel method) as an example. An expert system is suitable when one has limited amount of data and sufficient power system expert knowledge; however, its application requires a set of threshold values. Statistical methods are suitable when large amount of data is available for training. Two important issues to guarantee the effectiveness of a classifier, data segmentation, and feature extraction are discussed. Segmentation of a sequence of data recording is preprocessing to partition the data into segments each representing a duration containing either an event or a transition between two events. Extraction of features is applied to each segment individually. Some useful features and their effectiveness are then discussed. Some experimental results are included for demonstrating the effectiveness of both systems. Finally, conclusions are given together with the discussion of some future research directions.

Bridge the gap: signal processing for power quality applications

Abstract With an increasing amount of measurement data, automating power quality characterization and classification of disturbances is desirable. This will require combined efforts and knowledge from both electric power systems and signal processing. This paper focuses on several major power quality problems, and some up-to-date signal processing techniques that may offer good solutions to the problems. Some examples and results are also included. Finally, some future research directions are discussed.

Automatic classification of power system events using RMS voltage measurements

Power quality monitors in the occasion of a disturbance can either save the actual voltage waveform that contains the event or the corresponding RMS. The latter option reduces significantly the memory that is needed for saving the event. This paper shows that even with this type of monitoring, analysis of the measurements can be in depth. The paper proposes a method for automatic classification of power system events using RMS voltage measurements. The system is tested with measurements from a distribution network and the results show that classification is possible for the considered types of events. Finally, the limitations of this type of monitoring are shown.

Foreground object detection in changing background based on color co-occurrence statistics

This paper proposes a novel method for detecting foreground objects in nonstationary complex environments containing moving background objects. We derive a Bayes decision rule for classification of background and foreground changes based on inter-frame color co-occurrence statistics. An approach to store and fast retrieve color co-occurrence statistics is also established In the proposed method, foreground objects are detected in two steps. First, both foreground and background changes are extracted using background subtraction and temporal differencing. The frequent background changes are then recognized using the Bayes decision rule based on the learned color co-occurrence statistics. Both short-term and longterm strategies to learn the frequent background changes are proposed Experiments have shown promising results in detecting foreground objects from video containing wavering tree branches and flickering screens/water surface. The proposed method has shown better performance as compared with two existing methods.