By Topic

Automated error recovery in manufacturing systems through learning and reasoning

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
S. J. Chang ; Dept. of Electr. Comput., & Syst. Eng., Rensselaer Polytech. Inst., Troy, NY, USA ; G. Goldbogen ; F. DiCesare

Error recovery in manufacturing systems, is addressed and an error recovery approach based on the integration of explanation-based and analogy-based learning is proposed. The knowledge representation for the proposed learning technique is based on the object-oriented modeling concept. A new concept, called perspective, is defined to capture the causal relationship between two objects in analogy-based learning. Depending on the perspectives, different causal relationships between two objects can be derived. This allows the integration to take place. The authors structure task operations into class hierarchies and model these operations as composite objects. This modeling concept allows the manufacturing activities to be facilitated by objects and establishes the causal relationships between task operations through objects. A methodology for matching operations is developed on the basis of this modeling concept, the explanation, and the concept of perspectives. This methodology allows the analogous task and its recovery plan to be matched and retrieved. The development of the learning technique, the proposed learning recovery approach, and an example to illustrate the objects, causal relations, and learning are presented

Published in:

Intelligent Control, 1990. Proceedings., 5th IEEE International Symposium on

Date of Conference:

5-7 Sep 1990