Combined expert system/neural networks method for process fault diagnosis
Abstract
A two-level hierarchical approach for process fault diagnosis of an operating system employs a function-oriented approach at a first level and a component characteristic-oriented approach at a second level, where the decision-making procedure is structured in order of decreasing intelligence with increasing precision. At the first level, the diagnostic method is general and has knowledge of the overall process including a wide variety of plant transients and the functional behavior of the process components. An expert system classifies malfunctions by function to narrow the diagnostic focus to a particular set of possible faulty components that could be responsible for the detected functional misbehavior of the operating system. At the second level, the diagnostic method limits its scope to component malfunctions, using more detailed knowledge of component characteristics. Trained artificial neural networks are used to further narrow the diagnosis and to uniquely identify the faulty component by classifying the abnormal condition data as a failure of one of the hypothesized components through component characteristics. Once an anomaly is detected, the hierarchical structure is used to successively narrow the diagnostic focus from a function misbehavior, i.e., a function oriented approach, until the fault can be determined, i.e., a component characteristic-oriented approach. 9more »
- Inventors:
- Issue Date:
- Research Org.:
- Univ. of Chicago, IL (United States)
- OSTI Identifier:
- 100994
- Patent Number(s):
- 5442555
- Application Number:
- PAN: 8-132,888
- Assignee:
- Argonne National Lab., IL (United States)
- DOE Contract Number:
- W-31109-ENG-38
- Resource Type:
- Patent
- Resource Relation:
- Other Information: PBD: 15 Aug 1995
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 99 MATHEMATICS, COMPUTERS, INFORMATION SCIENCE, MANAGEMENT, LAW, MISCELLANEOUS; 32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION; DIAGNOSTIC TECHNIQUES; EXPERT SYSTEMS; NEURAL NETWORKS; INDUSTRIAL PLANTS; ARTIFICIAL INTELLIGENCE; FAILURES; EQUIPMENT; PROCESS CONTROL
Citation Formats
Reifman, J, and Wei, T Y.C. Combined expert system/neural networks method for process fault diagnosis. United States: N. p., 1995.
Web.
Reifman, J, & Wei, T Y.C. Combined expert system/neural networks method for process fault diagnosis. United States.
Reifman, J, and Wei, T Y.C. Tue .
"Combined expert system/neural networks method for process fault diagnosis". United States.
@article{osti_100994,
title = {Combined expert system/neural networks method for process fault diagnosis},
author = {Reifman, J and Wei, T Y.C.},
abstractNote = {A two-level hierarchical approach for process fault diagnosis of an operating system employs a function-oriented approach at a first level and a component characteristic-oriented approach at a second level, where the decision-making procedure is structured in order of decreasing intelligence with increasing precision. At the first level, the diagnostic method is general and has knowledge of the overall process including a wide variety of plant transients and the functional behavior of the process components. An expert system classifies malfunctions by function to narrow the diagnostic focus to a particular set of possible faulty components that could be responsible for the detected functional misbehavior of the operating system. At the second level, the diagnostic method limits its scope to component malfunctions, using more detailed knowledge of component characteristics. Trained artificial neural networks are used to further narrow the diagnosis and to uniquely identify the faulty component by classifying the abnormal condition data as a failure of one of the hypothesized components through component characteristics. Once an anomaly is detected, the hierarchical structure is used to successively narrow the diagnostic focus from a function misbehavior, i.e., a function oriented approach, until the fault can be determined, i.e., a component characteristic-oriented approach. 9 figs.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {1995},
month = {8}
}