Uma aplicação baseada em sistemas imunológicos artificiais para detecção de falhas em uma plataforma de abastecimento

• Autor(a) principal: Lima, Robson Pacífico Guimarães
• Data de Publicação: 2013
• Tipo de documento: Dissertação
• Idioma: por
• Título da fonte: Biblioteca Digital de Teses e Dissertações da UFPB
• Texto Completo: https://repositorio.ufpb.br/jspui/handle/tede/5293
• topic: Algoritmo de Seleção Negativa; Detecção de Falhas; Controlador Fuzzy; Negative Selection Algorithm; Fault Detection; Fuzzy Controller; ENGENHARIAS::ENGENHARIA ELETRICA

In this work, an Artificial-Immune-System based anomaly detection system applied to Water Supply System is presented. At normal working, the pressure level into the system is controlled by a Fuzzy Control System. As the Water Supply System is composed of pressure sensors, valves, pumps, and other devices, faults in these devices causing abnormal disturbances can occur. An algorithm of Artificial-Immune-System, namely, the Negative Selection Algorithm, is the base of the proposed anomaly detection system. The Negative Selection Algorithm verifies abnormal system conditions based on the normal system conditions. Experimental results show that the proposed system is effective in order to detect anomaly.