Advisory Expert System Research Articles

FACES (forming attachments of components expert system) and issues of its development

FACES is an advisory expert system. It helps design engineers in the task of selecting a suitable attachment for a joint. The attachment can come from any of the three joining technologies: fasteners, adhesives and welding. This paper presents the system's functionality and design. Issues of knowledge engineering and implementation are briefly tackled too. Potential future developments are mentioned at the end.

Framework for Computer-Aided Systems Design

Advanced computer technology, analytical methods, graphics capabilities, and expert systems contribute to significant changes in the design process. Continued progress is expected. Achieving the ultimate benefits of these computer-based design tools depends on successful research and development on a number of key issues. A fundamental understanding of the design process is a prerequisite to developing these computer-based tools. A hierarchical systems design approach is described’, and methods by which computers can assist the designer are examined. A framework is presented for developing computer-based design tools for power plant design. These tools include expert experience bases, tutorials, aids in decision making, and tools to develop the requirements, constraints, and interactions among subsystems and components. Early consideration of the functional tasks is encouraged. Methods of acquiring an expert’s experience base is a fundamental research problem. Computer-based guidance should be provided in a manner that supports the creativity, heuristic approaches, decision making, and meticulousness of a good designer.

Nutrition advisor expert system

Nutrition advisor expert system

Exploring the Impact of Face-to-Face Collaborative Technology on Group Writing

Click to increase image sizeClick to decrease image size Additional informationNotes on contributorsMarjorie HortonMarjorie Horton is a Senior Research Engineer at the EDS Center for Advanced Research in Ann Arbor, Michigan. She received her Ph.D. in experimental psychology from Stanford University in 1982. Formerly, she was an Assistant Professor in Experimental Psychology at the University of California, Santa Cruz. She has also worked at IBM in human factors engineering and technical marketing. Her research interests include computer-supported cooperative work and human-computer interaction. She is a member of the Association for Computing Machinery (ACM) and the ACM Special Interest Groups on Computer-Human Interaction (SIGCHI) and Office Information Systems (SIGOIS).Priscilla RogersPriscilla S. Rogers is an Assistant Professor of Communications and Director of the M.B.A. Writing Program at the University of Michigan School of Business Administration. She received her Ph.D. in history and criticism from the University of Michigan in 1986. Prior to joining the faculty at the Michigan Business School, she was a Teaching Fellow and Lecturer in the University of Michigan Communication Department and the Michigan Business School. Her research interests include analysis of management documents, managerial writing assessment, and collaborative writing in managerial contexts. She is on the Editorial Board of the Management Communication Quarterly and The Journal of Business Communication and serves on the Association of Business Communication Research Committee.Laurel AustinLaurel Austin received an M.S.E. in industrial and operations engineering at the University of Michigan and is currently a Ph.D. candidate in the Department of Social and Decision Sciences at Carnegie Mellon University. Prior to beginning her doctoral program, she was involved in research on computer-supported cooperative work at the EDS Center for Advanced Research and expert systems design at the Industrial Technology Institute. She has also worked at Andersen Consulting. Her research interests include individual and group decision making and the use of information technology in the workplace.Michael McCormickMichael Mccormick is a Research Analyst at the EDS Center for Advanced Research in Cambridge, Massachusetts. He received his B.A. in cognitive science and Asian studies from the University of Michigan in 1989. Prior to joining the Center for Machine Intelligence, he was a research assistant in the Department of Psychology at the University of Michigan. His research interests include human-computer interaction, cognitive development, and innovative technology in education. He is a member of the Association for Computing Machinery (ACM), the Boston Computer Society (BCS), Computer Professionals for Social Responsibility (CPSR) and the United States Parachute Association (USPA).

EELIAS—A Prototype Library Expert System

ABSTRACTThis paper describes a prototype expert system developed for the Science Engineering Library at Monash University. The expert system aims to provide teaching and advisory function to guide the user to the main sources of literature in the area of electrical and computer systems engineering, with provision for extension to other engineering courses. The expert system was developed using a very cheap expert system shell to indicate that the feasibility and initial development of such advisory expert systems can be done at a reasonable price.

Building a user model implicitly from a cooperative advisory dialog

This paper reviews existing methods for building user models to support adaptive, interactive systems, identifies sigificant problems with these approaches, and describes a new method for implicitly acquiring user models from an ongoing user-system dialog. Existing explicit user model acquisition methods, such as user edited models or model building dialogs put additional burden on the user and introduce artificial model acquisition dialogs. Hand coding stereotypes, another explicit acquisition method, is a tedious and error-prone process. On the other hand, implicit acquisition techniques such as computing presuppositions or entailments either draw too few inferences to be generally useful, or too many to be trusted. In contrast, this paper describes GUMAC, a General User Model Acquisition Component that uses heuristic rules to make default inferences about users' beliefs from their interaction with an advisory expert system. These rules are based on features of human action and conversation that constrain people's behavior and establish expectations about their knowledge. The application of these rules is illustrated with two examples of extended dialogs between users and an investment advisory system. During the course of these conversations, GUMAC is able to acquire an extensive model of the users' beliefs about the aspects of the domain considered in the dialog. These models, in turn, provide the sort of information needed by an explanation generator to tailor explanations the advisory system gives to its users.

EPAS: an emitter piloting advisory expert system for IC emitter deposition : Ying-Kuei Yang. IEEE Trans. Semicond. Mfg3(2), 45 (1990)

EPAS: an emitter piloting advisory expert system for IC emitter deposition : Ying-Kuei Yang. IEEE Trans. Semicond. Mfg3(2), 45 (1990)

The student as knowledge engineer: A constructivist model for science education

THE KNOWLEDGE ENGINEERING PROCESS, whereby a knowledge engineer works closely with a domain expert to build an expert system, is known to improve both the knowledge engineer’s and the expert’s understanding of the domain. Moreover, building an expert system is a lot like constructing a scientific theory: both activities result in the creation of an explanatory or problem-solving model of some particular domain. Mindful of this, an attempt was made to exploit the pedagogical potential of the knowledge engineering process by using it as a means of “teaching” a group of junior high school students how to do botanical classification. Serving as knowledge engineers, the students developed an expert advisory system capable of identifying tree specimens from descriptions of their gross morphology. Our observations indicated that the students not only mastered the target knowledge, but also enjoyed the opportunity to take a somewhat different approach to this standard junior high school subject. The apparent success of this experiment supports the claim that the knowledge engineering process can serve as an innovative model for science education. The model encourages a more creative, constructivist approach to teaching certain science concepts and skills, while at the same time fostering the improvement of logic, communication and independent learning skills.

Computer-aided generation of monitoring strategy for complex machine tool monitoring systems

The machine tool monitoring and diagnostic systems of the near future must incorporate — in a homogeneous, coherent manner — the monitoring functions at present fulfilled by different equipment; moreover, they must significantly surpass the performance of previous ones. The expectable complexity of these new systems involves significant problems in their application. The users must be equipped with computer aids to generate the most suitable monitoring algorithms and to describe these for the monitoring system. Therefore, after describing a multipurpose, multiprocessor-based machine tool monitoring system, three approaches for the computer-assisted generation of monitoring strategy and the programming of complex monitoring systems are outlined. Pattern-recognition-based learning, offline simulation of machining for monitoring purposes and a programming advisor expert system are illustrated.

EPAS: an emitter piloting advisory expert system for IC emitter deposition

Emitter piloting is a difficult diffusion process in IC manufacturing. The decision for the adjustment of the piloting drive cycle is a heuristic-oriented task. An expert system, the emitter piloting advisory system (EPAS), is used at Harris Semiconductor to advise fab operators on how to adjust piloting cycle time for emitters based on knowledge extracted from the most experienced engineer. EPAS consists of an input filter to validate the input parameter values; a knowledge base containing the knowledge extracted from the domain expert; a limited learning mechanism for dynamically calculating a better estimate of initial drive time for the next lot; a convergence control mechanism to control the rule inference so that the result of an inference is always closer to the conclusion; a user facility module containing many LISP-based modules developed to let the expert, engineers, and operators maintain the system by themselves; and a user-friendly interface. One EPAS operation example is provided.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

A statistics-based system for treatment plant operation

This paper describes work toward development of a convenient computer system to improve everyday operation and control of the wastewater treatment process. The goal is to help the operator detect the problems in the process and to select appropriate control actions. The system comprises subsystems for a data base management, data analysis including several statistical methods, and an expert advisory system. The statistical methods investigated include construction of external reference distributions, computation of moving averages, graphical methods, discriminant functions for early detection of upsets, and several kinds of control charts. The latter two methods are still under development and are not built into the system. Reference distributions are used to help define the fuzzy terms such as high and low for the conditions of the variables involved in the expert system control rules. The system is written in dBase-III and Lotus-123 and has a user-friendly interface for the communication between the user and the system.

The graphics advisor: a prototypical advisory expert system

The Graphics Advisor is an expert system that helps users of the Los Alamos Integrated Computing Network select the graphics library that is best suited to the characteristics of a specific graphics application. The implementation of the system, using a commercial expert system development tool, is described. Delivery options are discussed. Although the domain knowledge of the Graphics Advisor is oriented toward libraries that are supported by the Computing and Communications Division at Los Alamos, it exemplifies a class of knowledge-based systems that are potentially useful in a variety of advisory situations.

An advisory expert system for designing fire prescriptions

Prescribed fire is used to manipulate forest ecosystems to accomplish a variety of resource management objectives. To develop prescriptions that successfully achieve these objectives, managers use information from a variety of sources. These include results of scientific research and of their own experience. Much of the knowledge of expert practitioners has never been collected and made available to others. An expert system is being developed using rule-based inference and frame-based inheritance to integrate technical and heuristic information, and interpret it for application. Site data and the manager's objectives for treating the site with prescribed fire are inputs to the expert system. The system develops a fire prescription: ranges of acceptable fire effects, a description of the desired fire treatment, and a range of conditions under which to burn to achieve the desired treatments and effects. The system documents its results.

Energy expert: An expert system for architects

Principles of Expert Systems have been applied in different knowledge-rich domains such as geology, medicine, engineering and computer science. Not much effort has, however, been done to develop expert systems in architecture. This paper presents a prototype advisory expert system, called ENERGY EXPERT which we have developed for the schematic design phase of an architectural design project. ENERGY EXPERT quickly computes the approximate energy performance of a building in a year, analyzes the energy performance, and gives advice to the designer on possible ways of improving the design. The suggested modifications are intended to make the building more energy efficient and help cut down on heating and cooling costs. ENERGY EXPERT is a rule-based expert system written in Turbo Prolog. The paper also describes the principles of a rule-based expert system.

FireCode: a case study in the application of expert-systems techniques to a design code

FireCode is an expert advisory system for assisting building designers to check their plans against the requirements of a fire safety code. This application of expert-systems methodology is rather unusual because much of the knowledge is already available in written form, reducing the effort required for development. However, expert assistance was still required to handle a number of problems in the interpretation of the written code, such as incomplete and ambiguous requirements. These problems are likely to be met during the development of any expert system based on regulations or codes of practice. A strong parallel exists between the development of an expert system and the development of a code of practice; they are both concerned with the formalisation of knowledge. An important conclusion of this work is that the parallel development of an expert system will assist in the formulation of a code of practice.

Canadian Petroleum Research —Digging In For The Long Term

Abstract Canadian petroleum research ranges from exploration technology to development of highly refined petrochemicals. Studies on permafrost and ice mechanics are examples of diversified Arctic research programs being undertaken by many industry, university and governmental research groups. New seismic evaluation methods, the forerunner of advanced expert systems, are assisting exploration directed toward relatively small complicated oil reservoirs in the western basin. More efficient processes for recovering the large resources of heavy crude and natural bitumen are under active testing, including horizontal wells and follow-up processes to apply after steam stimulation. Research on the extraction of mined oil sands is improving the commercially applied technologies as well as providing technology alternatives for new projects. New approaches for upgrading heavy oil and bitumen have been identified and are under active study. Research in the petroleum products area has led to the introduction of new, high-detergency gasoline. Field testing of various alternative fuels, including oxygenated fuels and dual gaseous/liquid fuels, is under way. The severity of Canadian winters has provided fertile ground for the development of advanced low temperature lubricants, and increased attention is being applied to lubricants suitable for the new high-temperature engines coming on the market. Introduction The recent downturn in the petroleum industry has had a significant effect on the level, and nature, of the industry's commitment to research and development. Many companies have trimmed their R&amp;D budgets and focused more of their remaining effort on shorter-term projects closer to the mainstream of their business. In spite of this retrenchment, technology development and application is still recognized as a key ingredient for competitive survival. Significant research activity in the core areas continues, and important longer term step-out technologies are being aggressively pursued. The shortage of funds has put renewed emphasis on collaborative work, and a number of joint industry programs have been established. One of the remarkable features of petroleum R&amp;D in Canada is its breadth, From off-shore exploration to the development of highly refined petrochemical products, It has not been possible to include all current projects in the following summary statements, but the ones which have been described amply demonstrate the scope and complexity of the research under way. Expected impacts of the projects are provided in Table 1. Upstream R&amp;D Exploration Research in the Arctic The earliest application of marine technology in Canada's Arctic (at least by Europeans) was in support of whaling or for exploration (such as the search for the Northwest Passage). Today, the major incentive to Arctic operations is the recovery of minerals, primarily oil and gas, and this has led to a complex set of research requirements. Under the auspices of the Arctic Petroleum Operator's Association (APOA) (now Frontier Division of the Canadian Petroleum Association) well over 200 joint industry research studies have been conducted in the general topic areas of:—permafrost,—ice mechanics and ice forces,—waves and wave action of islands,—offshore soils and foundations,—oil spill control,—environmental base line studies,—offshore platforms, including caisson islands, and—pipelines.

An expert advisory system for government regulations: knowledge acquisition methodology

A methodology is described for building knowledge base systems that handle the knowledge found in regulations, specifications and other similar documents. The approach involves manually translating the document into a simple, English-like language. which combines a production rule approach with constraints, hierarchies and scripts. Our methodology structures the process of translation and verification using several software tools. The retrieval process is based on various types of deduction and associative indexing of rules and facts. Though our example is travel regulations, the method is general enough to be useful for most technical material, such as software description, design or service specifications, or training manuals.

Expert Systems in a Managerial Context

At present, there is a wide range of expert systems reported as working or under development, with the number and scope increasing rapidly. They have been under development for a number of years, both as an academic study within the general area of artificial intelligence and in the industrial/medical fields. The recent increased body of experiments and working systems is due at least partly to the development of purpose‐ specific computer programming languages such as Prolog and Lisp and commercially available packages called expert system shells. Whereas traditional computer software is designed to handle data and computation, the new expert system software tools are intended to handle deductive logic in the form of rules and relations between knowledge elements. Systems can be developed in‐house or alternatively a specialist consultant can undertake this work on their client's behalf. Expert systems specifically designed for helping managers are not common at present but there is a group of management advisory expert systems available from PPL. Similar management advisory systems will become more common particularly in view of the increasing availability and use of microcomputers at all levels of management.