DocumentCode :
2422762
Title :
Expert supervision based on cases
Author :
Meléndez, Joaquim ; Colomer, Joan ; de la Rosa, Josep Lluis
Author_Institution :
IIia & LEA-SICA, Universitat de Girona, Spain
fYear :
2001
fDate :
15-18 Oct. 2001
Firstpage :
431
Abstract :
The paper focuses on taking advantage of large amounts of data that are systematically stored in plants (by means of SCADA systems), but not exploited enough in order to achieve supervisory goals (fault detection, diagnosis and reconfiguration). The methodology of case base reasoning (CBR) is proposed to perform supervisory tasks in industrial processes by re-using the stored data. The goal is to take advantage of experiences, registered in a suitable structure as cam, avoiding the tedious task of knowledge acquisition and representation needed by other reasoning techniques as expert systems. An outlook of CBR terminology and basic concepts are presented. The adaptation of CBR in performing expert supervisory tasks, taking into account the particularities and difficulties derived from dynamic systems, is discussed. A special interest is focused in proposing a general case definition suitable for supervisory tasks. Finally, this structure and the whole methodology is tested in a application example for monitoring a real drier chamber.
Keywords :
case-based reasoning; computerised monitoring; diagnostic expert systems; drying; fault diagnosis; knowledge acquisition; knowledge representation; process control; case base reasoning; drier chamber; expert supervision; expert systems; fault diagnosis; industrial process control; knowledge acquisition; knowledge representation; monitoring; supervisory tasks; Computer aided software engineering; Expert systems; Fault detection; Fault diagnosis; Knowledge acquisition; Monitoring; SCADA systems; Sensor phenomena and characterization; Terminology; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Emerging Technologies and Factory Automation, 2001. Proceedings. 2001 8th IEEE International Conference on
Conference_Location :
Antibes-Juan les Pins, France
Print_ISBN :
0-7803-7241-7
Type :
conf
DOI :
10.1109/ETFA.2001.996399
Filename :
996399
Link To Document :
بازگشت