Case based reasoning methodology for supervision

Author

Melendez, Joaquim ; Colomer, Joan ; Macaya, Daniel

Author_Institution

EXiT Group, Univ. de Girona, Girona, Spain

fYear

2001

fDate

4-7 Sept. 2001

Firstpage

1600

Lastpage

1605

Abstract

The methodology of case base reasoning (CBR) is proposed to perform supervisory tasks in industrial process. An outlook of main difficulties in applying this methodology in dynamic systems is contrasted with the benefits of applying it. A generic case definition is proposed to achieve supervisory tasks in the domain of dynamic systems. This methodology has been implemented for improving the control of a batch drier chamber. A discussion related to monitoring a discrete events laboratory plant is also discussed. It includes the definition of similarity functions according to time evolution for case retrieving and its use for diagnosis and fault detection.

Keywords

case-based reasoning; process control; production engineering computing; CBR; batch drier chamber; case based reasoning methodology; discrete event laboratory plant monitoring; dynamic systems; fault detection; fault diagnosis; industrial process; supervisory tasks; Cognition; Computer aided software engineering; Fault detection; Monitoring; Process control; Registers; Vectors; Case Based Reasoning (CBR); dynamic systems supervision; expert supervision;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Conference (ECC), 2001 European

Conference_Location

Porto

Print_ISBN

978-3-9524173-6-2

Type

conf

Filename

7076148