Introduction:

Expert systems are a class of computer programs that can advise, analyze, categorize, communicate, consult, design, diagnose, explain, explore, forecast, form concepts, identify, interpret, justify, learn, manage, monitor, plan, present, retrieve, schedule, test, and tutor.  They address problems normally thought to require human specialist for their solution.

Benefits:

• Reduced error due to automation of tedious, repetitive or critical tasks
• Reduced manpower and time required for system testing and data analysis
• Reduced costs through acceleration of fault observations
• Increased visibility into the state of the managed system

Capabilities:

• Develop functional system requirements
• Coordinate software development
• Perform knowledge acquisition, process analysis, data analysis, system verification
• Design, develop, and implement an intelligent system using G2 software products

Experience/Applications:

Expert System Development (Diagnostics):   An Automated Diagnostic System (ADS) was developed to perform non-invasive checkout of a launch vehicle propulsion system.  ADS was designed for use during vehicle preparation for launch and pre-launch activities.  It may also be used for post flight operations and data analysis. Current methods of propulsion system checkout typically involve manual data analysis via measurement strip charts, limited system health checks, intrusive manual leaks checks, and other activities which have a high degree of risk.  Such testing can potentially result in creating problems and damaging components in the process of verifying that the system is problem-free.  The diagnostic system, which processes and interprets information from online sensors, was developed using G2, a graphical, object-oriented development environment for intelligent applications.  ADS provides mid to high-level monitoring and control of a main propulsion system testbed, which is displayed in Figure 1.  ADS combines features such as an animated schematic of the testbed, limit indicators, rule-based reasoning, and neural network analysis to provide diagnostics, and automation of testing and checkout procedures required for the testbed.

Figure 1.  ADS Test bed Schematic

Other Applications:

• Engineering Assistant/Consultant –aid engineers in performing tasks such as structural damage assessments, finite element analysis, critique chip designs, evaluate software, identify the root cause of problems, perform capacity planning and inventory management
• Sensor Validation –provide validation of sensors by monitoring sensor measurements and analyzing the propagation and affects of the predicted and actual performance throughout the system
• Process Automation – provide automated, comprehensive and continuous data monitoring, control the movement of parts through a manufacturing cell, issue supervisory control commands to machine tools, and provide autonomous control of various processes and subsystems

References:

1. "Automated Diagnostics & Systems Checkout Using G2/NeurOn-Line", Jonathan D. Patterson, Proceedings of the AIAA Defense & Space Programs Conference, Huntsville, AL, October 1998.
    
2. "An Application of G2 and NeurOn-Line to an Automated Propulsion Diagnostic System", Ruby D. Lathon, Jonathan Patterson, Proceedings of the 1997 Gensym Users Society Worldwide Conference , Paris, France, April 1997.
    
3. An Intelligent Strategy Discriminator for an Automated Guided Vehicle System, Ruby D. Lathon, Master's Thesis, University of Alabama in Huntsville, 1995.
    
4. "Design of an Intelligent Manufacturing Scheduling System", L. Interrante, A. Claassen, R. Lathon, in Proceedings of the 3^rd IERC, January 1994.
    
5. Artificial Intelligence, A Knowledge-Based Approach, Firebaugh, Morris W., PWS-Kent Publishing Company, pp. 335 (1993).
    
6. G2 - Gensym Intelligent Systems Software Products, http://www.gensym.com