Intelligent Approach for Fault Diagnosis in Power Transmission Systems Using Support Vector Machines

This paper presents an approach for identifying the faulted line section and fault location on transmission systems using support vector machines (SVMs) for diagnosis/post-fault analysis purpose. Power system disturbances are often caused by faults on transmission lines. When fault occurs on a transmission system, the protective relay detects the fault and initiates the tripping operation, which isolates the affected part from the rest of the power system. Based on the fault section identified, rapid and corrective restoration procedures can thus be taken to minimize the power interruption and limit the impact of outage on the system. The approach is particularly important for post-fault diagnosis of any mal-operation of relays following a disturbance in the neighboring line connected to the same substation. This may help in improving the fault monitoring/diagnosis process, thus assuring secure operation of the power systems. In this paper we compare SVMs with radial basis function neural networks (RBFNN) in data sets corresponding to different faults on a transmission system. Classification and regression accuracy is reported for both strategies. Studies on a practical 24-Bus equivalent EHV transmission system of the Indian Southern region is presented for indicating the improved generalization with the large margin classifiers in enhancing the efficacy of the chosen model.

Intelligent prediction of ground vibration in coal formations using ANN

The present paper details the prediction of blast induced ground vibration, using artificial neural network. The data was generated from five different coal mines. Twenty one different parameters involving rock mass parameters, explosive parameters and blast design parameters, were used to develop the one comprehensive ANN model for five different coal bearing formations. A total of 131 datasets was used to develop the ANN model and 44 datasets was used to test the model. The developed ANN model was compared with the USBM model. The prediction capability to predict blast induced ground vibration, of the comprehensive ANN model was found to be superior.

Estimación de la capacidad de carga turística de la Reserva Natural Volcán Mombacho, Granada, Nicaragua

Este estudio identifica los principales factores que inciden en la determinación de la CCT de los senderos El Cráter, El Puma y El Cafetal de la Reserva Natural Volcán Mombacho. La Capacidad de carga turística se consideró tal y como propone Cifuentes en su metodología, en tres niveles: Capacidad de Carga Física (CCF), Capacidad de Carga Real (CCR) y Capacidad de Carga Efectiva (CCE) (Cifuentes, M. 1999). Se estimó la Capacidad de Manejo (CM) de la RNVM, en 74.24%, obteniendo en el sendero El Cráter una CCE de 442 visitas/día, en el sendero El Puma de 93 visitas/día, y en el sendero El Cafetal de 753 visitas/día. Si se lograse un incremento de la CM en un 80%; el sendero El Cráter in crementaría su CCE a 476 visitas/día; el sendero El Puma a 101 visitas/día; y el sendero El Cafetal a 811 visitas/día. Este escenario está calculado para visitantes con propósitos eco turísticos. Debido a que las visitas de estudiantes de colegio, muestran un comportamiento diferente, se realizó el cálculo considerando dichos elementos en los factores de corrección para los Sendero El Cráter y El Cafetal (El Puma no es frecuentado por estudiantes de colegio). La CCE para estudiantes en el sendero El Cráter fue de 236 visitas/día, con una CM del 74.24%, y para un escenario del 80% de CM se calcula en 255 visitas/día; para el sendero El Cafetal se calculó en 403 visitas/día a un 74.24% de CM y 434 visitas/día a una CM del 80%. Las visitas máximas reportadas para el año 2003 fueron en los meses de Enero y Junio, con 298 y 305 visitas/día; en el año 2002 se reportan los meses de Marzo y Mayo con 366 y 298 visitas/día; la visitación al Sendero El Cráter no excede aún la CCE calculada, no así si los visitantes fueran estudian tes de colegio. Si la tendencia de la visitación continua incrementándose con los años, se requerirá que la administración de la RNVM restringa el número de visitas en los períodos picos de las mismas.

Path Planner for Intelligent Laser Surface Modification

An optimal algorithm of manufacturing path planner for intelligent laser surface modification is presented. Elements included in the optimal objective have been analyzed. A 6-D manufacture trace that satisfies the requirements of special craft and 5-axis laser processing robot system has been generated from the path planner by method of parallel section in which combinations of modification spots size with curvature of processing surfaces and modification craft parameters are considered. Related experiments have been successfully carried out with the computer integrated multifunctional laser manufacturing system.

The Intelligent Measuring Sub-System in the Computer Integrated and Flexible Laser Processing System

Based on the computer integrated and flexible laser processing system, develop the intelligent measuring sub-system. A novel model has been built to compensate the deviations of the main frame, a new-developed 3-D laser tracker system is applied to adjust the accuracy of the system. Analyzing the characteristic of all kinds of automobile dies, which is the main processing object of the laser processing system, classify the types of the surface and border needed to be measured and be processed. According to different types of surface and border, develop 2-D adaptive measuring method based on B?zier curve and 3-D adaptive measuring method based on spline curve. During the data processing, a new 3-D probe compensation method has been described in details. Some measuring experiments and laser processing experiments are carried out to testify the methods. All the methods have been applied in the computer integrated and flexible laser processing system invented by the Institute of Mechanics, CAS.