Expert System Development Environment Research Articles

Sheet metal cutting and piercing operations planning and tools configuration by an expert system

This paper describes the development of an expert system for both process planning and die design of sheet metal cutting and piercing operations. Knowledge for the system is acquired from practical handbooks, theory and empirical knowledge from industrial partners and is expressed as “crude” rules, transformed by the knowledge engineer into production rules. These are then coded into constructs of the CLIPS expert system development environment. This process is explained using a number of examples. The expert system comprises of five modules: initial calculations (including data input), process planning, finishing operation, die and press selection, and tools selection. Each module draws upon one or more among 18 rule pools defined around the important notions characterising the problem studied. The results of the expert system can be used by both the designer deciding on the production feasibility (manufacturability) for a sheet metal component and by the manufacturer receiving advice either on the hardware needed or on the process plan.

An expert system development environment for introductory AI course projects

This paper describes the use of an expert system development environment as a teaching environment to support a cognitive simulation project in an undergraduate introductory AI course. The use of this development environment, which was originally intended for experienced production system programmers, as a teaching tool for novices, presented challenges on a number of levels. This paper describes the development environment and demonstrates how it can be used to help a student understand programming lesson points, as well as how a student can use it to better understand how a particular system is behaving and whether it matches the students understanding of what it is supposed to be doing.

Knowledge-based supervision and control of wastewater treatment plant: a real-time implementation

The hardware architecture and the software development of a real-time knowledge-based distributed control system for the supervision of a wastewater treatment pilot plant are presented. The operation scheme is based on an A2/O system (anaerobic, anoxic, oxic) and includes organic matter removal, nitrification/denitrification, and Enhanced Biological Phosphorous Removal (EBPR). The hardware architecture involves different supervision levels, including two autonomous process computers (plant control and analysers control) and a PLC. The software architecture includes a Knowledge-Based Expert System (KBES) as the top control system. The KBES has been developed in G2, an expert system development environment based on object-oriented structural design. This system is fed with data obtained from the plant monitoring (in-line, on-line and off-line data) and with actuation data of the lower control levels. Using this information, the KBES supervises the pilot plant in order to help with fault detection and plant maintenance, but also modifies setpoints and other variables of the local control level to adapt the system to the different influent conditions. The overall system has been implemented and validated at pilot scale.

On-board and real-time expert control

Development of an on board real time expert system for controlling engineering systems requires tradeoffs between AI and real time approaches. The article presents an alternative that lies between embedding AI in real time and embedding real time in AI. We used this framework to develop an expert system development environment for maintaining and updating information about an evolving system as its state changes because of abnormal events such as faults, or as a consequence of external actions taken upon the system. We've successfully applied it in several engineering domains such as process control, medical monitoring, and onboard diagnosis. The author explains how it was applied to a system that controls automobile manoeuvring.

Analysis, design, implementation, and deployment of a prototype maintenance advisor expert system for the MK92 fire control system

In an effort to meet the challenges presented by the fiscal realities of today's defense budget, the Department of Defense (DoD) is seeking to exploit technology that promises to decrease operating costs, while improving operational readiness. Efforts which reduce repair costs, system down time, and the reliance upon outside technical representative are of particular interest. The development of the MK92 Maintenance Advisor Expert System (MK92 MAES) is one such effort. This paper describes the design and development of the MK92 MAES for the diagnosis and repair of the MK92 MOD 2 fire control system deployed on U.S. Navy guided missile frigates. System development is presented in terms of an expert system life cycle model which includes a thorough cost/benefit analysis, a novel approach for knowledge acquisition, an implementation strategy using a visual expert system development environment, and a phased deployment strategy. The system was developed by faculty and graduate students at the Naval Postgraduate School in cooperation with the Naval Warfare Center, Port Hueneme Division.

Laconex: A rule‐based implementation to advise on plot‐level land conservation in Vilathikulam, Southeastern India

AbstractKnowledge about land conservation exists along a spatial continuum, represented at the broadest level (with least depth) by international‐level experts who have international‐level expertise, and at the narrowest level (with most depth) by the individual farmer with the most site‐specific knowledge at the plot level. This continuum covers many different aspects of knowledge about land degradation and its amelioration, including technical and cultural knowledge. This paper reports an effort (one in a series of steps) to gather, formalize, codify, and operationalize knowledge about land conservation from two different levels of the continuum. Land conservation knowledge was elicited from farmers and extension agents in Vilathikulam taluk (an area of contiguous villages) in Tamil Nadu, southeastern India, using semi‐structured interviews. The knowledge thus gained was combined with knowledge from the literature on soils and land conservation for the area. This information was organized into factual knowledge and process knowledge, and implemented in the form of general recommendations, constraints, and specific recommendations. The process of arriving at these categories was organized into several steps using a spatial anchor and soil type as keys. These were operationalized in a rule‐based computer program (LAnd CONservation EXpert ‐LACONEX), which offers land conservation advice at the plot level for Vilathikulam taluk, using an expert system development environment.

PCSEX: An expert system for pump contamination sensitivity evaluation

The Pump Contamination Sensitive Expert System (PCSEX) introduced in this paper is a new package being developed as a complementing technique to present wear test procedures for determining the contaminant tolerance of hydraulic control system pumps. Present wear-test examination of a pump's contaminant tolerance requires special testing facilities and follows a complicated and tedious procedure which is expensive and time consuming work. PCSEX is based on knowledge integration of a large amount of data from previous testing, and expertise acquired from previous experience. It also integrates the defined model or formula associated with a user's particular system structure, and some equations available in research reports. PCSEX has been developed using GURU, an expert system development environment which supports a broad range of integrated knowledge processing capabilities, and allows the production of intelligent application systems.

A knowledge environment for an interactive control system design package

Abstract This paper describes a generic expert system development environment in a computer-aided control system package called SFPACK. The basic command language of the package follows the well-known MATLAB syntax. However, SFPACK has evolved from the MATLAB-derived control environment to a new generation of control system design environment because of the novel knowledge environment developed within the package. SFPACK now supports a richer set of data structures for representing design objects and knowledge in the control environment. In this paper, the features of the knowledge environment is presented. The issue on coupling of symbolic and numeric processing is also discussed. An expert system for control system design is developed in this integrated environment.

Computer-aided design and analysis of linear multivariable control systems using the systematic design approach

A new approach for the design of multivariable feedback control systems in the frequency domain is presented. The techniques handle stability, performance, and robustness aspects of the design problem satisfactorily. The overall approach is systematic and intuitively appealing. A new computer-aided control system design package called SFPACK is developed. This package has implemented the new frequency response design techniques. The package is interactive and command-driven, and it is used as a teaching tool for helping the students to understand the concepts of the design approach. The MAT-LAB-derived control environment in SFPACK is extended to provide the user with an expert system development environment.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

The selection of expert system development environments

The process of choosing (configuring) an expert system development environment is typically characterized as the making of a series of decisions under different types of constraints. The purpose of this paper is to offer a decision making tool for an environment selection (configuration) by describing some of the related knowledge engineering problems, by identifying and classifying typical features of such an environment, and by presenting an algorithm that configures and evaluates the alternatives with respect to user specified criteria.

Architecture of a coupled expert system for optimum design of plate girder bridges

A prototype knowledge-based expert system has been developed for optimum design of steel plate girders used in highway bridges. This expert system, called PG-BRIDGE1, is a coupled system in which AI-based symbolic processing is combined with the traditional numerical processing. Plate girders can be unstiffened or stiffened with single- or doublesided transverse stiffeners. They can be homogeneous or hybrid, made of high-strength flange plates and low-strength web plate. A mathematical optimization algorithm has been developed for minimum weight design of plate girders using the generalized geometric programming technique. The basis of design is the American Association of State Highway and Transportation Officials (AASHTO) specifications. The plate girders are subjected to the live (moving) loads of the AASHTO specifications. The knowledge base and symbolic processing has been developed using the Expert System Development Environment (ESDE). Numerical processing for structural analysis, optimization algorithm and graphics interface have been developed in FORTRAN 77.

A prototype expert system for manufacturing resource planning

Abstract As expert system technology matures, systems builders in all areas are increasingly turning to this branch of software engineering. This paper considers the use of expert systems techniques in the field of manufacturing and gives as an example a prototype developed by Ferranti Computer Systems Ltd., in Cwmbran, The prototype addresses the problems of front end scheduling and the allocation of critical resources for maximum efficiency. The prototype was developed using the Inference ART expert system development environment. The paper traces the incremental development of the prototype from the early data representations to the final, working expert system. The paper demonstrates the rapid prototyping techniques which may be used with expert system tools and to the ease with which ideas may be tested before becoming part of the implementation.

Interfacing an Expert Diagnostic Tool to Real Time Data

SYSTEMS that operate in real-time have stringent operational requirements and are particularly vulnerable to failures in their controls. Accurate fault diagnosis and speedy repairs are essential in such systems. A microcomputer based expert system, CHAMBER2, for control failure diagnosis support in a system of environmentally regulated plant research chambers has been developed. It is a dynamic system and is sufficiently autonomous to be used regularly. The expert system development environment used in this project has the capability to exit the heuristic knowledge base and run high-level language programs, passing information to and from the knowledge base. Using this feature CHAMBER2 has access to data bases and has communications links with the control computer that give it direct access to sensor measurements in real-time. These features minimize the requirement for data entry from the user and increase the availability of accurate data to the expert system. The shell software also provides for cycling through the knowledge base, facilitating real-time operation. When it (CHAMBER2) polls the sensors and finds no problems, it reinitializes the knowledge base and looks again without requesting user observations. The emphasis in this development was on the integration of data bases, sensor data, and cycling in real-time. Future work will emphasize development of feedback from the expert system to the control program.

IPSS: An approach towards automated decisions in CIM systems

Abstract IPSS (Industrial Problem Solving System), a specialized prototype Expert System development environment for operations planning. This hybrid system combines features of knowledge based systems as well as conventional procedural knowledge. IPSS architecture is presented and applications are discussed.