Emilio García Moreno

Hybrid Analysis in the Latent Nestling Method Applied to Fault Diagnosis

This paper presents the Latent Nestling Method (LNM) formalization in hybrid systems. For the proposed LNM, it is necessary to include places of continuous or differential character, allowing the analysis of continuous dynamical variable. This paper is a continuation of our previous papers , . Here, the LNM is exploited to analyze the extension to hybrid systems. One of the contributions of this work is a practical application of the LNM in hybrid systems. The case study is the Lubrication and Cooling system of a Wind Turbine Gearbox. The model of the system is built using colored Petri nets formalism and the classic techniques of continuous and hybrid Petri nets. Simulation results are presented to validate some key concepts of the formalization in hybrid systems.

Intelligent alarm management

An ergonomic problem for the plant operators has appeared in the modern electronic control systems, in which configure an alarm is very easy. We present a methodology and an intelligent software tool to manage alarms and make early fault detection and diagnosis in industrial processes, integrating three techniques to detect and diagnose faults. The three techniques use available information in industrial environments: The alarms of the electronic control system; the fault knowledgebase of the process, formulated in terms of rules; and a simplified model used to detect disturbances in the process. A prototype in a Fluid Catalytic Cracking process is shown.

Integration of techniques and alarm sequences for fault detection and diagnosis

This work has been developed around the integration of techniques for the early fault detection and diagnosis in industrial processes. It has been considered the sequence of the alarms of a fluidized catalytic Cracking Unit and its use in early fault detection and diagnosis. The specific objectives are process safety, operational reliability and alarm management. The aim of this work and previous research work is to increase process safety and operational reliability and to decrease the number of alarms that are presented to the operators of industrial plants, contributing to the appropriate fault detection and troubleshooting. First we make a review of our drivers for the fault detection and diagnosis and their integration. Its application is subsequently displayed in a set of data associated with a real fault of a fluidized catalytic cracking plant. Then we discuss the techniques proposed for integration and the issue of the development of an intelligent software tool for the early fault detection and diagnosis, which is already in operation at one of the crude oil refineries in Colombia.

Augmentation Channel Design for a Marine Current Turbine in a Floating Cogenerator

In this paper we present a Hydro-Wind Kinetics Integrated Module for Renewable Energy Generation. HYWIKIM is a floating device combining wind and marine current generators for generating renewable energy. Its purpose is to exploit resources in an integrated manner using wind and current turbines in offshore plants thereby optimizing the financial investment. Our research focuses on the design and analysis of different types of augmentation channels to increase efficiency using shrouded Marine Current Turbines (MCTs) in conditions of low intensity flows.

Fault Diagnosis of Electric Transmission Lines using Modular Neural Networks

This paper proposes a new method for fault diagnosis in electric power systems based on neural networks. With this method the diagnosis is performed by assigning a neural module for each type of component of the electric power system, whether it is a transmission line, bus or transformer. The neural modules for buses and transformers comprise two diagnostic levels which take into consideration the logic states of switches and relays, both internal and back-up. The neural module for transmission lines also has a third diagnostic level which takes into account the oscillograms of fault voltages and currents, as well as the frequency spectrums of these oscillograms, in order to verify if the transmission line had in fact been subjected to a fault. One important advantage of the diagnostic system proposed is that its implementation does not require the use of a network configurator for the system; it does not depend on the size of the power network, nor does it require retraining of the neural modules if the power network increases in size, making its application possible to only one component, a specific area, or the whole context of the power system.

Aplicación a un proceso químico de la metodología de anidamiento latente para el diagnóstico de fallos

Este articulo presenta un nuevo enfoque para la deteccion y diagnostico de fallos (SDDF) en sistemas hibridos denominado de Anidamiento Latente de Fallos. La misma esta basada en el uso de Redes de Petri Coloreadas (RdPCs) que aportan su capacidad intrinseca de sintesis y de implementacion en modelos realizables. Esta tecnica se contrapone al clasico fenomeno de explosion combinacional que se produce mediante la utilizacion de metodologias basadas en Maquinas de Estados Finitos (MEFs).