Monitoring of refinery furnace combustion processes based on the classification of visual features of flame images

• Grant number: 14/12446-6
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: August 01, 2014
• End date: March 31, 2015
• Field of knowledge: Engineering - Mechanical Engineering
• Principal Investigator: Flavius Portella Ribas Martins
• Grantee: Mauro Tuyoshi Imamura Junior
• Host Institution: Escola Politécnica (EP). Universidade de São Paulo (USP). São Paulo , SP, Brazil

Abstract

A combustion diagnosis computer system, based on the Dempster-Shafer method and operating on sequences of feature vectors of flame images grabbed in a laboratorial furnace, will be implemented in order to detect combustion abnormal states related to 4 types of defects - extintion, instability, poor nebulization and high or low O2/fuel rate.