Hybrid fault diagnosis scheme implementation for power distribution systems automation

Power distribution automation and control are import-ant tools in the current restructured electricity markets. Unfortunately, due to its stochastic nature, distribution systems faults are hardly avoidable. This paper proposes a novel fault diagnosis scheme for power distribution systems, composed by three different processes: fault detection and classification, fault location, and fault section determination. The fault detection and classification technique is wavelet based. The fault-location technique is impedance based and uses local voltage and current fundamental phasors. The fault section determination method is artificial neural network based and uses the local current and voltage signals to estimate the faulted section. The proposed hybrid scheme was validated through Alternate Transient Program/Electromagentic Transients Program simulations and was implemented as embedded software. It is currently used as a fault diagnosis tool in a Southern Brazilian power distribution company.

On-line fault diagnostic system for proton exchange membrane fuel cells

In this paper, a supervisor system, able to diagnose different types of faults during the operation of a proton exchange membrane fuel cell is introduced. The diagnosis is developed by applying Bayesian networks, which qualify and quantify the cause-effect relationship among the variables of the process. The fault diagnosis is based on the on-line monitoring of variables easy to measure in the machine such as voltage, electric current, and temperature. The equipment is a fuel cell system which can operate even when a fault occurs. The fault effects are based on experiments on the fault tolerant fuel cell, which are reproduced in a fuel cell model. A database of fault records is constructed from the fuel cell model, improving the generation time and avoiding permanent damage to the equipment. (C) 2007 Elsevier B.V. All rights reserved.

Extended Fault-Location Formulation for Power Distribution Systems

In this paper, an extended impedance-based fault-location formulation for generalized distribution systems is presented. The majority of distribution feeders are characterized by having several laterals, nonsymmetrical lines, highly unbalanced operation, and time-varying loads. These characteristics compromise traditional fault-location methods performance. The proposed method uses only local voltages and currents as input data. The current load profile is obtained through these measurements. The formulation considers load variation effects and different fault types. Results are obtained from numerical simulations by using a real distribution system from the Electrical Energy Distribution State Company of Rio Grande do Sul (CEEE-D), Southern Brazil. Comparative results show the technique robustness with respect to fault type and traditional fault-location problems, such as fault distance, resistance, inception angle, and load variation. The formulation was implemented as embedded software and is currently used at CEEE-D`s distribution operation center.

Phase Distance Relaying With Fault Resistance Compensation for Unbalanced Systems

This letter presents an extension of an existing ground distance relay algorithm to include phase distance relays. The algorithm uses a fault resistance estimation process in the phase domain, improving efficiency in the distance protection process. The results show that the algorithm is suitable for online applications, and that it has an independent performance from the fault resistance magnitude, the fault location, and the line asymmetry.

Development of Control Systems for Safety Instrumented Systems

Safety Instrumented Systems (SIS) are designed to prevent and / or mitigate accidents, avoiding undesirable high potential risk scenarios, assuring protection of people`s health, protecting the environment and saving costs of industrial equipment. The design of these systems require formal methods for ensuring the safety requirements, but according material published in this area, has not identified a consolidated procedure to match the task. This sense, this article introduces a formal method for diagnosis and treatment of critical faults based on Bayesian network (BN) and Petri net (PN). This approach considers diagnosis and treatment for each safety instrumented function (SIF) including hazard and operability (HAZOP) study in the equipment or system under control. It also uses BN and Behavioral Petri net (BPN) for diagnoses and decision-making and the PN for the synthesis, modeling and control to be implemented by Safety Programmable Logic Controller (PLC). An application example considering the diagnosis and treatment of critical faults is presented and illustrates the methodology proposed.

Improving Alzheimer`s Disease Diagnosis with Machine Learning Techniques

There is not a specific test to diagnose Alzheimer`s disease (AD). Its diagnosis should be based upon clinical history, neuropsychological and laboratory tests, neuroimaging and electroencephalography (EEG). Therefore, new approaches are necessary to enable earlier and more accurate diagnosis and to follow treatment results. In this study we used a Machine Learning (ML) technique, named Support Vector Machine (SVM), to search patterns in EEG epochs to differentiate AD patients from controls. As a result, we developed a quantitative EEG (qEEG) processing method for automatic differentiation of patients with AD from normal individuals, as a complement to the diagnosis of probable dementia. We studied EEGs from 19 normal subjects (14 females/5 males, mean age 71.6 years) and 16 probable mild to moderate symptoms AD patients (14 females/2 males, mean age 73.4 years. The results obtained from analysis of EEG epochs were accuracy 79.9% and sensitivity 83.2%. The analysis considering the diagnosis of each individual patient reached 87.0% accuracy and 91.7% sensitivity.

Classification of breast masses using a committee machine of artificial neural networks

This work proposes a new approach using a committee machine of artificial neural networks to classify masses found in mammograms as benign or malignant. Three shape factors, three edge-sharpness measures, and 14 texture measures are used for the classification of 20 regions of interest (ROIs) related to malignant tumors and 37 ROIs related to benign masses. A group of multilayer perceptrons (MLPs) is employed as a committee machine of neural network classifiers. The classification results are reached by combining the responses of the individual classifiers. Experiments involving changes in the learning algorithm of the committee machine are conducted. The classification accuracy is evaluated using the area A. under the receiver operating characteristics (ROC) curve. The A, result for the committee machine is compared with the A, results obtained using MLPs and single-layer perceptrons (SLPs), as well as a linear discriminant analysis (LDA) classifier Tests are carried out using the student's t-distribution. The committee machine classifier outperforms the MLP SLP, and LDA classifiers in the following cases: with the shape measure of spiculation index, the A, values of the four methods are, in order 0.93, 0.84, 0.75, and 0.76; and with the edge-sharpness measure of acutance, the values are 0.79, 0.70, 0.69, and 0.74. Although the features with which improvement is obtained with the committee machines are not the same as those that provided the maximal value of A(z) (A(z) = 0.99 with some shape features, with or without the committee machine), they correspond to features that are not critically dependent on the accuracy of the boundaries of the masses, which is an important result. (c) 2008 SPIE and IS&T.

Kernel machines for epilepsy diagnosis via EEG signal classification: A comparative study

Objective: We carry out a systematic assessment on a suite of kernel-based learning machines while coping with the task of epilepsy diagnosis through automatic electroencephalogram (EEG) signal classification. Methods and materials: The kernel machines investigated include the standard support vector machine (SVM), the least squares SVM, the Lagrangian SVM, the smooth SVM, the proximal SVM, and the relevance vector machine. An extensive series of experiments was conducted on publicly available data, whose clinical EEG recordings were obtained from five normal subjects and five epileptic patients. The performance levels delivered by the different kernel machines are contrasted in terms of the criteria of predictive accuracy, sensitivity to the kernel function/parameter value, and sensitivity to the type of features extracted from the signal. For this purpose, 26 values for the kernel parameter (radius) of two well-known kernel functions (namely. Gaussian and exponential radial basis functions) were considered as well as 21 types of features extracted from the EEG signal, including statistical values derived from the discrete wavelet transform, Lyapunov exponents, and combinations thereof. Results: We first quantitatively assess the impact of the choice of the wavelet basis on the quality of the features extracted. Four wavelet basis functions were considered in this study. Then, we provide the average accuracy (i.e., cross-validation error) values delivered by 252 kernel machine configurations; in particular, 40%/35% of the best-calibrated models of the standard and least squares SVMs reached 100% accuracy rate for the two kernel functions considered. Moreover, we show the sensitivity profiles exhibited by a large sample of the configurations whereby one can visually inspect their levels of sensitiveness to the type of feature and to the kernel function/parameter value. Conclusions: Overall, the results evidence that all kernel machines are competitive in terms of accuracy, with the standard and least squares SVMs prevailing more consistently. Moreover, the choice of the kernel function and parameter value as well as the choice of the feature extractor are critical decisions to be taken, albeit the choice of the wavelet family seems not to be so relevant. Also, the statistical values calculated over the Lyapunov exponents were good sources of signal representation, but not as informative as their wavelet counterparts. Finally, a typical sensitivity profile has emerged among all types of machines, involving some regions of stability separated by zones of sharp variation, with some kernel parameter values clearly associated with better accuracy rates (zones of optimality). (C) 2011 Elsevier B.V. All rights reserved.

Further improvements on impedance-based fault location for power distribution systems

In this study, further improvements regarding the fault location problem for power distribution systems are presented. The proposed improvements relate to the capacitive effect consideration on impedance-based fault location methods, by considering an exact line segment model for the distribution line. The proposed developments, which consist of a new formulation for the fault location problem and a new algorithm that considers the line shunt admittance matrix, are presented. The proposed equations are developed for any fault type and result in one single equation for all ground fault types, and another equation for line-to-line faults. Results obtained with the proposed improvements are presented. Also, in order to compare the improvements performance and demonstrate how the line shunt admittance affects the state-of-the-art impedance-based fault location methodologies for distribution systems, the results obtained with two other existing methods are presented. Comparative results show that, in overhead distribution systems with laterals and intermediate loads, the line shunt admittance can significantly affect the state-of-the-art methodologies response, whereas in this case the proposed developments present great improvements by considering this effect.

Comparing finite state machine test coverage criteria

To plan testing activities, testers face the challenge of determining a strategy, including a test coverage criterion that offers an acceptable compromise between the available resources and test goals. Known theoretical properties of coverage criteria do not always help and, thus, empirical data are needed. The results of an experimental evaluation of several coverage criteria for finite state machines (FSMs) are presented, namely, state and transition coverage; initialisation fault and transition fault coverage. The first two criteria focus on FSM structure, whereas the other two on potential faults in FSM implementations. The authors elaborate a comparison approach that includes random generation of FSM, construction of an adequate test suite and test minimisation for each criterion to ensure that tests are obtained in a uniform way. The last step uses an improved greedy algorithm.

Diagnosis and treatment of extraction sockets in preparation for implant placement: report of three cases

This article addresses diagnostic parameters that should be assessed in the treatment of extraction sockets with dental implant placement by presenting three case reports that emphasize the relevance of the amount of remaining bone walls. Diagnosis was based on the analysis of clinical and radiographic parameters (e.g.: bone defect morphology, remaining bone volume, presence of infections on the receptor site). Case 1 presents a 5-wall defect in the maxillary right central incisor region with severe root resorption, which was treated with immediate implant placement. Cases 2 and 3 present, respectively, two- and three-wall bone defects that did not have indication for immediate implants. These cases were first submitted to a guided bone regeneration (GBR) procedure with bone graft biomaterial and membrane barriers, and the implants were installed in a second surgical procedure. The analysis of the preoperative periodontal condition of the adjacent teeth and bone defect morphology is extremely important because these factors determine the choice between immediate implant or GBR treatment followed by implant installation in a subsequent intervention.

Diagnosis and root canal treatment in a mandibular premolar with three canals

This paper presents a case report of a left mandibular second premolar with three canals and three different apical foramina. A 39-year-old male patient presented to our clinic with pain in the mandibular left second premolar. Initially, pain was caused by cold stimulus and later was spontaneously. The intraoral clinical examination revealed a fractured amalgam restoration with occlusal caries. Percussion and cold (Endo-Frost) tests were positive. The radiographic examination showed the presence of two roots. The probable diagnosis was an acute pulpitis. After access cavity, it was observed remaining roof of the pulp chamber and mild bleeding in the tooth lingual area, indicating the possible presence of a third canal. The endodontic treatment was completed in a single session using Root ZX apex locator and K3 NiTi rotary system with surgical diameter corresponding to a .02/45 file in the three canals and irrigation with 1% sodium hypochlorite. The canals were obtured with gutta-percha cones and Sealer 26 using the lateral condensation technique. After 1 year of follow-up, the tooth was asymptomatic and periapical repair was observed radiographically. Internal alterations should be considered during the endodontic treatment of mandibular second premolars. The correct diagnosis of these alterations by the analysis of preoperative radiographs can help the location of two or more canals, thereby avoiding root therapy failure.

Computed tomography and scintigraphy exams for diagnosis and treatment planning of the condylar osteochondroma: a case report

PURPOSE: To report an uncommon case of osteochondroma affecting the mandibular condyle of a young patient and to illustrate the important contributions of different imaging resources to the diagnosis and treatment planning of this lesion. CASE DESCRIPTION: A 24-year-old female patient with the chief complaint of an increasing facial asymmetry and pain in the left pre-auricular region, revealing a reduced mouth opening, mandibular deviation and posterior cross-bite over a period of 18 months. Panoramic radiography revealed an enlargement of the left condyle, whereas computed tomography (CT) sections and three-dimensional CT showed a well-defined bone growth arising from condylar neck. The scintigraphy exam showed an abnormal osteogenic activity in the left temporomandibular joint. The condyle was surgically removed and after 18 months follow-up the panoramic radiography and CT scans showed no signs of recurrence. CONCLUSION: Although osteochondroma is a benign bone tumor that rarely arises in cranial and maxillofacial region, it should be considered in the differential diagnosis of slow-growing masses of the temporomandibular area and the use of different imaging exams significantly contribute to the correct diagnosis and treatment planning of this pathological condition.

Infectious endocarditis caused by Nocardia sp.: histological morphology as a guide for the specific diagnosis

Nocardia is a rare opportunistic agent, which may affect immunocompromised individuals causing lung infections and exceptionally infective endocarditis (IE). There are few reports of IE caused by Nocardia sp., usually involving biological prostheses but rarely in natural valves. Its accurate microbiological identification may be hampered by the similarity with Rhodococcus equi and Corynebacterium spp. Here we report a case of native mitral valve IE caused by this agent in which the clinical absence of response to vancomycin and the suggestion of Nocardia sp. by histology pointed to the misdiagnosis of Corynebacterium spp. in blood cultures. The histological morphology can advise on the need for expansion of cultivation time and use of extra microbiological procedures that lead to the differential diagnosis with Corynebacterium spp. and other agents, which is essential to establish timely specific treatment, especially in immunocompromised patients.