From gini@pico.cs.umn.edu Wed Oct 6 15:29:58 EDT 1993 Article: 19073 of comp.ai Xref: crabapple.srv.cs.cmu.edu comp.ai:19073 Newsgroups: comp.ai Path: crabapple.srv.cs.cmu.edu!honeydew.srv.cs.cmu.edu!das-news.harvard.edu!noc.near.net!howland.reston.ans.net!darwin.sura.net!news-feed-2.peachnet.edu!umn.edu!pico.cs.umn.edu!gini From: gini@pico.cs.umn.edu (Maria Gini) Subject: Detecting and Resolving Errors in Manufacturing Message-ID: Sender: news@news2.cis.umn.edu (Usenet News Administration) Nntp-Posting-Host: pico.cs.umn.edu Organization: University of Minnesota, Twin Cities Date: Tue, 5 Oct 1993 22:45:32 GMT Lines: 79 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= SIGMAN Workshop on Detecting and Resolving Errors in Manufacturing Systems AAAI 1994 Spring Symposium Series March 21-23, 1994 Stanford University, California =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= This symposium will bring together researchers working on troubleshooting, diagnosis, monitoring, and recovery from errors in manufacturing applications. The main purpose is to bring together people from manufacturing with people from AI to discuss how AI techniques and methodologies can be used to address the problems of detecting and resolving errors. The symposium will provide a forum for reviewing the state of the art and for proposing new avenues of exploration. Any system designed to perform a manufacturing task must have ways of detecting and recovering from errors. Timely detection of anomalies in the behavior of the system is essential for its continuous safe operation. This involves preventing or minimizing the occurrence of faults through robust design, detecting abnormal conditions, isolating faults, and finding ways of maintaining safe operation despite the presence of faults. The manufacturing environment is often sufficiently uncertain and dynamic, and the manufacturing systems are sufficiently complex to make detection and recovery from errors a major task. The purpose of this symposium is to analyze these issues and propose how to create manufacturing systems able to achieve their tasks despite unpredicted contingencies. Area of interest include (but are not limited to): - reliability technology (reliability analysis, fault trees, event trees, etc) - monitoring (model-based monitoring, fault-model based monitoring, detection of trends and prediction of anomalies, etc) - error detection (sensor modeling, recognition of abnormal conditions, sensor interpretation, etc) - error analysis (explanation of failures, causal modeling, troubleshooting techniques, etc) - planning (sensor planning, repairing plans that fail, generation of recovery procedures, etc) - scheduling (generating robust schedules, detecting and recovering from schedule execution errors, etc) Papers addressing these and related issues in the area of manufacturing will be considered. Work in progress, innovative ideas, field based studies, experimental results in real manufacturing environments, and completed projects will be of interest. Both practical and theoretical work is welcome, but preference will be given to descriptions of implemented systems. The best papers will be consider for a special issue of a journal and/or a book on this subject. Those interested in attending should submit an abstract or short position paper, three pages maximum. Please submit three copies (hardcopy submission only!) by October 15, 1993 to: Maria Gini 4-192 EE/CSci Building 200 Union St SE Minneapolis, MN 55455 phone: (612) 625-5582 fax: (612) 625-0572 e-mail: gini@cs.umn.edu PROGRAM COMMITTEE: Robert D. Borchelt, University of Wisconsin-Milwaukee Frank DiCesare, Rensselaer Polytechnic Institute Bruce Donald, Cornell University Mark Drummond, NASA Ames Research Center Maria Gini (chair), University of Minnesota Damian Lyons, Philips Laboratories SCHEDULE: October 15, 1993 Papers due November 15, 1993 Acceptance/rejection notices mailed January 31, 1994 Camera-ready papers due February 15, 1994 Registration deadline for invitees March 1, 1994 Final registration deadline March 21-23 Symposium at Stanford Univ.