Applications of pattern recognition techniques to online fault detection

Conference · Mon Nov 01 00:00:00 EST 1993

OSTI ID:10192955

Singer, R M; Gross, K C ^[1]; King, R W ^[2]

---

1. Argonne National Lab., IL (United States)
2. Argonne National Lab., Idaho Falls, ID (United States)

A common problem to operators of complex industrial systems is the early detection of incipient degradation of sensors and components in order to avoid unplanned outages, to orderly plan for anticipated maintenance activities and to assure continued safe operation. In such systems, there usually are a large number of sensors (upwards of several thousand is not uncommon) serving many functions, ranging from input to control systems, monitoring of safety parameters and component performance limits, system environmental conditions, etc. Although sensors deemed to measure important process conditions are generally alarmed, the alarm set points usually are just high-low limits and the operator`s response to such alarms is based on written procedures and his or her experience and training. In many systems this approach has been successful, but in situations where the cost of a forced outage is high an improved method is needed. In such cases it is desirable, if not necessary, to detect disturbances in either sensors or the process prior to any actual failure that could either shut down the process or challenge any safety system that is present. Recent advances in various artificial intelligence techniques have provided the opportunity to perform such functions of early detection and diagnosis. In this paper, the experience gained through the application of several pattern-recognition techniques to the on-line monitoring and incipient disturbance detection of several coolant pumps and numerous sensors at the Experimental Breeder Reactor-II (EBR-II) which is located at the Idaho National Engineering Laboratory is presented.

• Research Organization: Argonne National Lab., IL (United States)
• Sponsoring Organization: USDOE, Washington, DC (United States)
• DOE Contract Number: W-31109-ENG-38
• OSTI ID: 10192955
• Report Number(s): ANL/RA/CP-79576; CONF-940312-46; ON: DE94002372; TRN: 94:001344
• Resource Relation: Conference: 2. Probabilistic safety assessment and management conference (PSAM),San Diego, CA (United States),20-24 Mar 1994; Other Information: PBD: [1993]
• Country of Publication: United States
• Language: English

Related Subjects

22 GENERAL STUDIES OF NUCLEAR REACTORS
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
REACTOR MONITORING SYSTEMS
EXPERT SYSTEMS
EBR-2 REACTOR
REACTOR INSTRUMENTATION
FAILURES
REACTOR OPERATORS
DETECTION
REACTOR CONTROL SYSTEMS
ARTIFICIAL INTELLIGENCE
PATTERN RECOGNITION
ON-LINE SYSTEMS
PUMPS
REACTOR COOLING SYSTEMS
RELIABILITY
ALGORITHMS
220400
220600
990200
CONTROL SYSTEMS
RESEARCH
TEST
TRAINING
PRODUCTION
IRRADIATION
MATERIALS TESTING REACTORS
MATHEMATICS AND COMPUTERS