Expert Module Research Articles

Transfer Pricing-integrating expert systems in MIS environments

The use of Transfer Pricing, an expert system module that replaces and improves on a Cobol program, to determine the value at which a product is transferred from one location to another across international boundaries, is discussed. In presenting the case history of Transfer Pricing, the author stresses three themes: (1) integration into the MIS environment, (2) advantage of the expert system approach, and (3) why the expert system approach gives rise to these advantages. The system is considered from both the user's and the developer's perspective. >

SESFAC: A Scheduling Expert System for Flexible Assembly Cell

Control of a flexible assembly cell is a complex task due to its multi-operation nature and to its dynamically changing states resulting in numerous alternatives. Usually, cell control is done hierarchically and encompasses operation scheduling and real-time control activities. This paper discusses the design of a knowledge-based scheduling system for a flexible assembly cell. The system integrates disruptions and can be connected to a real-time cell controller. It is composed of a static database, a dynamic database, expert modules and is driven by an asynchronous clock The knowledge is hierarchically organized in the distinct expert modules, each standing for a decision level. The scheduler is characterized by a “scheduling in advance” methodology, and this capability is to he used on- or off-line.

SEDAF: AN INTELLIGENT EDUCATIONAL SYSTEM FOR MATHEMATICS

The field of artificial intelligence and education, in which AI techniques and methodologies are used to build sophisticated intelligent educational systems, is developing rapidly. In this paper we present an intelligent educational system for teaching high school and college students how to analyze and draw graphs of mathematical functions. The system, named SEDAF, has been developed in a knowledge engineering environment and runs on a Lisp-machine workstation. We illustrate the various modules constituting SEDAF: the user interface; an expert module, capable of solving problems in the subject domain; a diagnosis module, which points out possible reasons for students' errors; a student modeling module, capable of building an explicit representation of the learning status of the student; and a remedial subsystem, called a therapy module, constituted by means-ends tutorial rules that execute teaching actions on the base of the status of the student model. The goal of the presentation is to stress the innov...

Knowledge-based system for assignment of parts to machine cells

This paper presents a decision tool for assignment of parts to machining cells. A modelling system and associated expert modules: analyser, synthesiser and recogniser have been developed to perform the automatic and dynamic assignment of parts directly from a feature-based CAD modelling system to manufacturing cells. It is based on the knowledge acquired from design features of parts and manufacturing processes. Feature-based representation of components structure and related machining operations is presented. The proposed algorithm allows the integration of CAD and CAM. Some elements of expert systems, pattern recognition and finite-state automata are applied in this research. Symbolic strings containing the design and machining attributes of components are analysed using knowledge rules and syntactic pattern recognition techniques, then cell inference and part assignment are carried out. A case study is included to illustrate the feasibility of the above approaches. This research, provides some useful contributions for both CAD and CAM integration as well as parts assignment for cellular manufacturing.

Expertise of ICAI: Development requirements

The purpose of this paper is to (a) examine the functional characteristics of intelligent computer-assisted instruction (ICAI), (b) propose a structural model that defines expertise requirements for the development of an ICAI system and suggests procedures for integrating the required expertise into a system, and (c) discuss the requirements of a multidisciplinary cooperative effort for its development. After examining four functional components of ICAI systems (expertise module, student-model module, tutorial module, and interface module) and their interrelationships in a typical ICAI model, six intelligent characteristics of ICAI systems are discussed. They are: (a) the generation of instructional presentations, (b) a mixed initiative between the system and student, (c) the ability to model the student's learning process, (d) a qualitative decision making function in instructional process, (e) an inferencing function in instructional diagnostic and prescriptive process, and (f) a self-improving function. In the proposed expertise requirement model, we discuss three different kinds of expertise (domain expertise, domain engineering expertise, and instructional expertise) and technical issues required to integrate the different kinds of expertise into a system. Finally, a multidisciplinary cooperative effort for the development of an ICAI system is recommended in a schematic form.

Expert parts assignment in cellular manufacturing using pattern recognition

This paper presents a new tool for on-going decision making needed to assign parts to flexible manufacturing cells, in support of the dynamic dispatching and scheduling required for day-to-day operation. A CAM-oriented modelling system and associated expert modules: Analyzer, Synthesizer and Recognizer have been developed to perform the automatic and dynamic assignment of parts to manufacturing cells directly from a feature-based CAD modelling system. It is based upon knowledge of both the part design features and manufacturing processes. Feature-based representation of components structure and related machining operations is presented. The proposed technique represents a new and generic methodology for integrating CAD and CAM. Artificial intelligence techniques such as expert systems, pattern recognition and finite-state automata are applied in this research. Symbolic strings containing the design and machining attributes of components are analyzed using knowledge of rules and syntactic pattern recognition techniques, then cell inference and part assignment are carried out using domain specific expert rules. Two case studies are included to illustrate the feasibility of these approaches for rotational and prismatic parts. It is believed that this research provides some useful contributions for both CAD and CAM integration as well as parts assignment techniques for cellular manufacturing.

A distributed control architecture for an autonomous mobile robot

This paper describes a Distributed Control Architecture for an autonomous mobile robot. We start by characterizing the Conceptual Levels into which the various problem-solving activities of a mobile robot can be classified. In sequence, we discuss a Distributed Control System that provides scheduling and coordination of multiple concurrent activities on a mobile robot. Multiple Expert Modules are responsible for the various tasks and communicate through messages and over a Blackboard. As a testbed, the architecture of a specific system for Sonar-Based Mapping and Navigation is presented, and a distributed implementation is described.

COATS: an Expert Module for Optimal Tool Selection

After an introduction in which the usefulness of expert systems in the field of process planning is discussed, the paper describes an expert module for fully automatized tool selection in turning operations: the module is a part of a process planning package developed by the authors. The structure of the module includes a knowledge base where production rules IF-THEN can be easily created, edited and deleted by means of an interactive program and a dictionary without being a software specialist, in order to fit the module to different industrial environments. Each rule must be written together with a “weight” evaluated upon the basis of each tool parameter and its influence on cutting process: a reference guide is given for this purpose. After consulting the rules the module proposes the best toolholder-insert couples found in properly created tool files. The “score” of each tool selected is computed by rules weight. Tests carried out have given good results some of which are here described. Then an approach to self learning is described, which allows the module to improve its knowledge base upon the basis of experience, properly evaluated by a monitoring and diagnostic program: automatic creation of new rules is so possible. The advantages of this module are flexibility and possibility to be directly connected with workshop environment.

RED: A red-cell antibody identification expert module

We describe a software module in an expert system RED, which interprets data related to red cell antibody identification. There are three portions to this module: the problem-solving component, which incorporates the knowledge required for antibody identification as a hierarchy of programs. The programs in the hierarchy organize within themselves small pieces of knowledge represented in the form of production rules, which are capable of making judgments concerning a specific hypothesis; an intelligent data base for storage of patient data, red cell attributes, and test results; the "overview critic" portion, which combines the atomic hypotheses judged favorably by the antibody programs into a unified judgment concerning the case. Overview makes the decision to terminate processing with a conclusion about which antibodies are actually present and what specific further tests need to be performed to resolve any remaining ambiguities.

The PSI Program Model Builder - synthesis of very high-level programs

A system called the Program Model Builder (PMB) is being designed and implemented to perform the basic operations required to synthesize and modify programs. PMB plays a central role as one of the expert modules of the PSI (ψ) program synthesis system. PMB builds a complete and consistent program model from small chunks of program specification received from other (ψ) experts. PMB must deal with the fact that these program fragments often omit details and may be incomplete, ambiguous, inconsistent, nonspecific, and arbitrarily ordered. The initial version of PMB has successfully synthesized a few program models from fragments. This work includes the evolution of a very high-level program modelling language, the identification and codification of useful very high-level programming knowledge including equivalence transformations, and the implementation of a rule-based problem solving system embodying this knowledge.

The PSI Program Model Builder - synthesis of very high-level programs

A system called the Program Model Builder (PMB) is being designed and implemented to perform the basic operations required to synthesize and modify programs. PMB plays a central role as one of the expert modules of the PSI (ψ) program synthesis system. PMB builds a complete and consistent program model from small chunks of program specification received from other (ψ) experts. PMB must deal with the fact that these program fragments often omit details and may be incomplete, ambiguous, inconsistent, nonspecific, and arbitrarily ordered. The initial version of PMB has successfully synthesized a few program models from fragments. This work includes the evolution of a very high-level program modelling language, the identification and codification of useful very high-level programming knowledge including equivalence transformations, and the implementation of a rule-based problem solving system embodying this knowledge.