Untitled in english

Author(s)

Ricardo de Carvalho Destro

• Document type: Master's Dissertation
• Press: São Paulo.
• Institution: Universidade de São Paulo (USP). Escola Politécnica (EP/BC)
• Defense date: 2002-01-30

Examining board members

Zsolt Laszlo Kovacs; Orlando Del Bianco Filho; Flávio Almeida de Magalhães Cipparrone

• Advisor: Zsolt Laszlo Kovacs

Abstract

In this work, initially, some of the critical problems involved in the design and development of an automatic diagnostic system for complex electromechanical systems are examined. After that, some techniques based on statistical models, artificial intelligence methods and combinations of both are presented for the solution of these problems. The practical feasibility of the proposed techniques is evaluated by the development and field testing of an automatic diagnostic system for automatic teller machines. (AU)