Expert diagnostic system with inference generator

Details Expert diagnostic system with inference generator Expert diagnostic system with inference generator

1999-02-26

2003-03-04

Starks, Jr., Wilbert L. (Department: 2121)

Data processing: artificial intelligence

Knowledge processing system

Creation or modification

C706S052000

Reexamination Certificate

active

06529893

ABSTRACT:

BACKGROUND AND SUMMARY OF THE INVENTION
The present invention relates generally to expert diagnostic systems. More particularly, the invention relates to an expert system capable of assisting experts in documenting failure attributes of a functional system as well as subsequent users in diagnosing the functional system.
Recent inroads into the area of artificial intelligence and expert systems have uncovered many applications in which computers can make decisions traditionally left to humans. Such applications include managing the healthcare of individual patients, troubleshooting elevator systems, and identifying likely failure points in digital data processing systems.
In general, active components and passive components can be coupled together to create various functional systems such as mechanical systems, electrical systems, and biological systems. Each of these functional systems has failure attributes associated with the system's components and couplings. Failure attributes typically comprise the failure modes of the components and couplings, as well as the failure symptoms associated with each failure mode.
For example, a conveyor system with a drive motor bolted to a foundation block is a common functional system. The drive motor could have the failure modes of a bent shaft, a warped rotor, a cracked magnet, etc. The bent shaft and the warped rotor failure modes may exhibit the same failure symptom of fluctuating belt velocity, while the cracked magnet failure mode may have a failure symptom of low torque. Typically, when a mechanic or user observes the failure symptom of fluctuating belt velocity, it would be helpful to know that this symptom means the drive motor either has a bent shaft or a warped rotor. However, the coupling between the drive motor and the foundation block also has a set of failure modes which could lead to the very same failure symptom. The user would therefore need to know to check the coupling between the drive motor and the foundation block as well as the drive motor. Considering the high number of components and couplings in a typical functional system, and the difficulty in identifying every possible component and coupling failure, it is clear that troubleshooting can become too difficult for a relatively inexperienced user.
Users must therefore often rely heavily on documentation provided by either the designer of a functional system, or an expert in the relevant field such as a product engineer. This reliance frequently leads to difficulties due to oversight on behalf of the expert in documenting the failure attributes and troubleshooting techniques, as well as subsequent changes in knowledge of the functional system as a result of the “learning process.”
Expert systems draw from the concept that an expert in any given field has a unique methodical approach to solving a particular problem in the relevant field. The value of the expert system is found in the fact that different experts may have different approaches to solving the same problem. As such, the expert system looks to combine the various methodical approaches of experts in the given field to create a comprehensive knowledge base to draw from when similar problems arise in the future. Expert systems are therefore useful to experts in a given field as a consultation “second opinion” and to non-experts as a decision making tool.
A typical knowledge base may include rule-based information relating to a given set of input parameters. Generally, the knowledge base is authored by a knowledge engineer with one or more experts in the given field providing the input parameters and raw decisional rules. Once the knowledge base has been authored, users of varying expertise may use the expert system to make decisions or solve problems. Several difficulties arise, however, with such an expert system. As noted above, one problem is the fact that any expert system is only as dependable as the expert or experts providing the information contained in the knowledge base. This “human factor” often causes either unrecognized decision making processes, or merely forgotten information.
While certain technology-specific expert systems have been used for diagnostic purposes, the concept of a fully trainable documentation system in conjunction with a fully trainable diagnostic system is new to the art. In other words, current techniques fail to address the fact that the process of creating a knowledge base lends itself to artificial intelligence just as much as the subsequent diagnostic process. Therefore, while traditional expert systems treat diagnosis of a functional system as a one-dimensional specialized activity, the reality is that effective diagnosis begins at the authoring stage.
For a more complete understanding of the invention, its objects and advantages, reference may be had to the following specification and to the accompanying drawings.


REFERENCES:
patent: 4697243 (1987-09-01), Moore et al.
patent: 4803040 (1989-02-01), Gross
patent: 4967368 (1990-10-01), Bolling et al.
patent: 4972453 (1990-11-01), Daniel, III et al.
patent: 5001714 (1991-03-01), Stark et al.
patent: 5208745 (1993-05-01), Quentin et al.
patent: 5265035 (1993-11-01), Reifman et al.
patent: 5293556 (1994-03-01), Hill et al.
patent: 5351247 (1994-09-01), Dow et al.
patent: 5442555 (1995-08-01), Reifman et al.
patent: 5469463 (1995-11-01), Polich et al.
patent: 5517405 (1996-05-01), McAndrew et al.
patent: 5687212 (1997-11-01), Kinser, Jr. et al.
patent: 6091846 (2000-07-01), Lin et al.
Vasandani, V.; Govindaraj, T., Knowledge organization in intelligent tutoring systems for diagnostic problem solving in complex dynamic domains, Systems, Man and Cybernetics, IEEE Transactions on, vol.: 25 7, Jul. 1995, pp.: 1076-1096.*
Kyungseob Yoon; Changjong Wang, Authoring system for the development of ITS, TENCON '94. IEEE Region 10's Ninth Annual International Conference. Theme: Frontiers of Computer Technology. Proceedings of 1994, Aug. 22-26, 1994, pp.: 97-101 vol. 1.*
Warren, J.R.; Warren, D.E.; Freedman, R.W., Interviewing expertise in primary care medicine: a knowledge-based support system, System Sciences, 1994. vol. III: Information Systems: Decision Support and Knowledge-Based Systems, Proceedings of the Twenty-Se, Jan. 1994.*
Uthurusamy, R.; Means, L.G.; Godden, K.S.; Lytinen, S.L., Extracting knowledge from diagnostic databases, IEEE Expert [see also IEEE Intelligent Systems] vol. 8 6, Dec. 1993, pp.: 27-38.*
Bonfa, I.; Maioli, C.; Sarti, F.; Milandri, G.L.; Dal Monte, P.R., HERMES: an expert system for the prognosis of hepatic diseases, Artificial Neural Networks and Expert Systems, 1993. Proceedings., First New Zealand International Two-Stream Conference on, Nov. 1993.*
Vasandani, V.; Govindaraj, T.; Mitchell, C.M., An intelligent tutor for diagnostic problem solving in complex dynamic systems, Systems, Man and Cybernetics, 1989. Conference Proceedings., IEEE International Conference on , Nov. 14-17, 1989, pp.: 772 v.*
Ng, C.K.; Chow, K.P., An expert system for diagnosis of electronic equipment using structural model and trouble-shooting heuristics, TENCON '89. Fourth IEEE Region 10 International Conference, Nov. 22-24, 1989, pp.: 669-673.*
Vasandani, V.; Govindaraj, T., Knowledge representation and human-computer interaction in an intelligent tutor for diagnostic problem solving, Systems, Man and Cybernetics, 1990. Conference Proceedings., IEEE International Conference on, Nov. 4-7, 1990, Pa.*
Norbert Fuhr; Integration of probabilistic fact and text retrieval; Proceedings of the Fifteenth Annual International ACM SIGIR conference on Research and development in information retrieval, Jun. 21-24, 1992, pp. 211-222.

Affiliated with

Also associated with

Rating

Expert diagnostic system with inference generator does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Expert diagnostic system with inference generator, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Expert diagnostic system with inference generator will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3031722