![]() |
|||
![]()
|
![]() |
![]() |
![]() |
Design. DESIGNER assists in general design processes (MacCallum, 1982). A key characteristic in the design of engineering systems is complexity: a designer's task to specify the characteristics of a system, given a set of required functional objectives to be achieved in a given environment. The system works with basic concepts in the design process and applies them to a generic task in order to produce an acceptable design. The system was developed at the University of Strathclyde, Great Britain. GOES, Graphics-Oriented Expert Shell, is a shell built inside a standard CAD environment (Langley et al., 1995). It is intended to associate logical engineering design procedures with graphical representations, and is particularly useful for managing and documenting large-scale control and automation design activities. GOES operates as an intelligent CASE tool, and eases the task of identifying, assembling, and parametrizing function block subroutines of distributed control systems. It was developed at CMS-CAD Inc., Montreal, Que., Canada. SATURN is a constraint-system shell that provides knowledge integration and reasoning features suited to supporting concurrent engineering approaches to design (Fohn et al., 1994). SATURN is a logic-based constraint modeling system, tightly coupled with a relational database, and supported by a truth maintenance system. The system was developed at North Carolina State University, Raleigh, NC. XpertRule Configurator assists in the development of a rule-based expert system for product design. It aids in building the rule-based system for correctly selecting and configuring product components. A user can generate a physical component hierarchy using a graphical configuration tree editor and rule sets associated with different configuration tasks. It is commercially available from Attar Software, Harvard, MA. Diagnosis. D-IAL, Diagnosis Intelligent Automation Language, assists with the development of manufacturing facility maintenance expert systems (Hori et al., 1992). D-IAL uses the best first-search algorithm and has a plausible reasoning mechanism based on the Dempster-Shafer probability. This plausible reasoning mechanism propagates defect probability in a search tree to maintain the consistency of the defect probabilities. It is written in C so that diagnostic expert systems developed on the shell can operate on workstations and/or personal computers. The system was developed at Mitsubishi Electric Corp., Amagasaki, Japan. EKO is an object-oriented shell for developing a diagnostic expert system (Ivashchenko et al., 1994). The shell, though providing general features, was developed for use in evaluating the state of hydraulic structures. It contains a database, programs that work with data arriving from sensors, facilities for storing data concerning the state of hydraulic structures, statistical data processing capability, and software for constructing and updating behavioral regression models. EKO has been used to design a computer-based system of diagnostic testing at the Charvak Hydraulic Engineering Center situated 70 km from Tashkent, Russia. FMEAssit is an expert system development tool to aid in the design of model-based fault diagnosis systems for the Space Station (Carnes and Cutts, 1987). It assists engineers in the complex task of tracking failures and their effects on the system. It was developed using LISP Flavors by Boeing of Huntsville, AL. HYDRA, Hybrid Reasoning and Knowledge Acquisition Workbench, assists in the development of diagnostic expert systems. It is based on a custom system developed for Daimler-Benz's Mercedes Benz passenger and utility vehicle service centers. HYDRA provides model-based, symptom-failure-oriented, and case-based diagnostic capabilities for diagnosing system failures. HYDRA is commercially available from Itanis International, Pittsburgh, PA. IDEA is a model-based expert system development tool that assists technicians in identifying component failures in electro/mechanical devices (PC AI, 1990). IDEA employs a model-based reasoning strategy to build and deploy applications, based on the concept that if users know how a device works, as opposed to the way it fails, users can build a diagnostic application. It allows an organization to combine models, graphics, hypertext on-line documentation, linkage to management reporting systems, and traditional decision support into comprehensive diagnostic applications. It runs on IBM ATs and compatibles. The system is commercially available from AI Squared, Chelmsford, MA. MARPLE is a model-based reasoning tool for producing intelligent diagnostics (Cowles et al., 1990). The system consists of a set of design tools to build application-specific models and rules, and a set of core procedures that run the model and isolate faults. MARPLE was used to implement an expert system for diagnosis of spacecraft power systems. It was developed on the Texas Instruments microExplorer by TRW. MTK, Model ToolKit, is a model-based reasoning tool that was developed for the design of model-based expert systems (Erickson and Rudokas, 1987). MTK has particular value for building diagnostic expert systems, but can also be used for control applications where a model of the system under control can be defined. It was developed by NASA Ames Research Center and used in the design of TEXSYS, an expert system for controlling the operations of the Space Station's thermal control system. MTK runs on a Symbolics 3670 workstation. PARAGON is an expert system development tool that interacts with the knowledge engineer to model a satellite (Golden, 1987). The developed system can be used for fault diagnosis using a model-based reasoning approach. PARAGON is generic in that it can be used for modeling other types of systems for fault diagnosis purposes. It was developed by Ford Aerospace of Sunnyvale, California. PRODE, PROspective Diagnosis Expert, is a shell for building expert systems based on prospective diagnosis (Gini and Sassaroli, 1995). Two kinds of knowledge contribute to modeling the diagnostic process. Failure knowledge expresses cause-effect relations between faults as well as the relations between the result of tests and the "degree-of-belief" about the presence of a fault. Strategic knowledge contains criteria to guide the selection of the appropriate action. A criterion refers to a particular viewpoint (such as the cost of a test or the estimated occurrence of a fault) and its application orders or prunes the set of the actions to take with respect to this viewpoint. Prospective diagnosis evolves acquiring new data to increase the knowledge about the system while the strategic criteria guides in this choice. The inference engine proceeds, alternating data acquisition and focusing, until the most probable cause of the malfunction is found and a repair is executed. PRODE was developed at Politecnico di Milano, Milano, Italy. TestBench is an environment for creating a diagnostic expert system. It provides four ways to represent knowledge: rules, decision trees, failure hierarchy, and case-based reasoning. The user creates the system using a graphical interface, which includes a tool palette. TestBench also offers a video display window, which can be used to show the user how to perform diagnostic procedures. It is commercially available from Carnegie Group, Pittsburgh, PA.
|
![]() |
|
Use of this site is subject certain Terms & Conditions. Copyright (c) 1996-1999 EarthWeb, Inc.. All rights reserved. Reproduction in whole or in part in any form or medium without express written permission of EarthWeb is prohibited. Please read our privacy policy for details. |