An indexing system of corrosion failures for case-based reasoning

Conference · Tue Oct 01 04:00:00 EDT 1996

OSTI ID:367739

Roberge, P R ^[1]; Trethewey, K R ^[2]

---

1. Royal Military Coll., Kingston, Ontario (Canada). Dept. of Chemistry and Chemical Engineering
2. Univ. of Southampton (United Kingdom). Dept. of Engineering Materials

The difficulties associated with the committal of human expert knowledge to computers for the development of more effective knowledge-based systems have raised the possibility of mimicking the process of reasoning from previous experiences. Experts are known to make proficient decisions based more upon analogy with similar events and situations than the kind of sequential mechanisms used in many algorithmic approaches. For many years, both law and business schools have used cases as the foundation for knowledge in their respective disciplines. Computer reasoning by analogy, a technique known as Case-Based Reasoning (CBR) has met with tangible success in such diverse human decision-making applications as banking, autoclave loading, tactical decision-making, and foreign trade negotiations. Failure analysts and corrosion engineers also reason by analogy when faced with new situations or problems. The CBR approach is particularly valuable in cases containing ill-structured problems, uncertainty, ambiguity, and missing data. Dynamic environments can also be tackled, or when there are shifting, ill-defined and competing objectives. Cases where there are action feedback loops, multiple human involvement, and multiple and potentially changing organizational goals and norms can also be tackled. This paper describes a method of indexing case histories for use in a case-based reasoning system in support of failure analysis.

• OSTI ID: 367739
• Report Number(s): CONF-960389--
• Country of Publication: United States
• Language: English

Related Subjects

36 MATERIALS SCIENCE
99 GENERAL AND MISCELLANEOUS
CORROSION
DATA ACQUISITION
DATA ANALYSIS
DATA BASE MANAGEMENT
DATA PROCESSING
EXPERT SYSTEMS
FAILURE MODE ANALYSIS
INFORMATION RETRIEVAL
INFORMATION SYSTEMS
MATERIALS
PROGRAMMING