Prototype Knowledge-based Expert System Research Articles

A Prototype Knowledge-Based System on Unsteady Open Channel Flow in Water Resources Management

The recent advances in artificial intelligence, coupled with the popularity of personal computers, have led to its widespread application in different domain problems. This paper describes the development of a prototype knowledge-based expert system—an advanced technique of artificial intelligence—as a tool of knowledge transfer and training for personnel in water resources planning and management. Details and a description of the application of the knowledge-based system on design of river network in Hong Kong are also presented.

SITE EXPERT: a prototype knowledge-based expert system

SITE EXPERT: a prototype knowledge-based expert system

SITE EXPERT: a prototype knowledge-based expert system

SITE EXPERT: a prototype knowledge-based expert system

Improving earthmoving estimating by more realistic knowledge

Earthmoving operations are often a very important aspect of a civil engineering project. Very accurate knowledge of the earthmoving operation is often the vital, critical element in the formation of a good and accurate cost estimate and schedule because of its prominent role in influencing costs and time. Inaccuracies are often built into earthmoving estimates by the fairly sweeping assumptions that are made during the estimating process. These problems were revealed in answers to a questionnaire and in interviews with experts. The factors that affect the performance of machines are discussed, including the common types of earthmoving operations. The importance of haul distance in determining which type of equipment should be used is also considered. The selection of equipment and estimation of costs for earthmoving depend heavily on human experience. The means of eliciting human experience are described in detail. Because of this reliance on human experience, a prototype knowledge-based expert system was developed using a shell program. The system is able to select the most appropriate fleet of machines, and estimate the cost, for use as a decision support system in planning an earthmoving operation. Key words: construction, earthmoving, estimating, knowledge, expert system, realistic knowledge.

Preliminary shape definition of structural components using a prototype knowledge-based expert system

A prototype dual-purpose expert system for automatic preliminary shape synthesis of structural components has been developed. The developed prototype is intended to emulate the conceptual-design/preliminary-redesign phases of the engineering design process. The dual purpose of this expert system is to generate preliminary designs which can be used either for basic engineering or as an initial solution to an optimization scheme. Both design phases have been modularized and developed under adequate computational shells. Heuristics are applied in the conceptual design phase to produce an initial definition of the geometric domain. A set of rules was programmed into the inference mechanism for the redesign phase. These rules focus on molding the geometric domain. Modules requiring heuristic support are implemented in a LISP/KEETM environment, those which are computer intensive being C subroutines. The two-dimensional problems of a fillet in a tension bar and of a connecting link are used to illustrate the system. This is part of an ongoing project at the Center for Computer Aids for Industrial Productivity (CAIP) in New Jersey.

Design and development of a KBES for planning and scheduling ready-mixed concrete supply

The aim of this research is to explore the feasibility of knowledge-based expert systems (KBES) for the planning and scheduling of ready-mixed concrete supply. Ready-mixed concrete is a product as well as a service. This implies that the supply of ready-mixed concrete should satisfy the customers’ needs in relation to both quality and supply. Due to the peculiar characteristics of the product which has a ‘shelf life’ of only a few hours and the dynamic nature of the operating environment, the planning and scheduling problems of ready-mixed concrete supply are usually unstructured and complicated. A prototype knowledge-based expert system for the planning and scheduling of ready-mixed concrete supply developed with a leading ready-mixed concrete company in the UK will be presented. This paper begins with a brief summary of the ready-mixed concrete production and delivery process and the importance of its planning and scheduling decisions. This is followed by a discussion of the role, tasks performed, devel...

AI and CAD for earthquake damage evaluation

Lessons learned from destructive earthquakes are recorded in numerous documents, many of which are not readily available to practicing engineers and designers. In order to maximize the utility of the valuable knowledge which has been learned from destructive earthquakes, a new approach is proposed for presenting the performance evaluation and behaviour of buildings stressed or damaged during earthquakes using the expert system paradigm and computer graphics. A prototype knowledge-based expert system, called EXQUAKE2, has been developed for earthquake damage evaluation and knowledge of performance of a common class of buildings in California earthquakes. The knowledge base of EXQUAKE2 contains lessons learned from earthquakes. EXQUAKE2 has been developed on an IBM personal computer using the expert system shell EXSYS Professional. EXQUAKE2 has a graphics interface, developed in Turbo Pascal, for displaying various building configurations and structural details.

Separation system synthesis: a knowledge-based approach. 2. Gas/vapor mixtures

A description is given for a prototype knowledge-based expert system, the separation synthesis advisor (SSAD), for synthesis of separation sequences for gas/vapor mixtures. The core of the SSAD is the separation synthesis hierarchy (SSH), a highly structured, task-oriented framework for representing separation knowledge. The hierarchy, based on interviews and information from the literature, emulates the approach that an expert process engineer follows. In its current implementation, the SSH is limited to the preliminary sequencing of multicomponent gas/vapor mixtures using the following separation methods: physical absorption; chemical absorption; cryogenic distillation; membrane permeation; molecular sieve adsorption; equilibrium-limited absorption. Several examples of practical industrial separation problems are included

A knowledge-based system for nondestructive testing of polymeric composite components

This paper presents a formalization of the knowledge domain of nondestructive quality control of polymeric composite components. The formalization scheme presented in this paper has been implemented in a prototype knowledge-based expert system (KBES), called NICC for nondestructive inspection of composite components, to help in the quality assurance of these parts. Geometric and bonding characteristics of individual and assembled components are taken into account, as opposed to the better understood evaluation of well-behaved test specimens. The use of nondestructive techniques in the inspection of plastic and polymeric composites is fairly recent and hence, the knowledge required to develop a KBES is still very scattered and not yet fully covered in the literature. This study demonstrates both the feasibility of compiling and representing this knowledge domain and the possibility of translating it into an efficient automated tool capable of giving reliable expert-like advice at low cost. The reasoning process is divided into three stages. In the first stage, a polymetric composite component is completely defined according to features that are relevant for nondestructive inspection. In the second stage, all the discontinuities that may be present in the component are determined. Finally, in the third stage, appropriate nondestructive testing procedures are identified to detect each of the possible discontinuities.

A Knowledge-Based System for Nondestructive Testing of Polymeric Composite Components

Abstract This paper presents a formalization of the knowledge domain of nondestructive quality control of polymeric composite components. The formalization scheme presented in this paper has been implemented in a prototype knowledge-based expert system (KBES), called NICC for nondestructive inspection of composite components, to help in the quality assurance of these parts. Geometric and bonding characteristics of individual and assembled components are taken into account, as opposed to the better understood evaluation of well-behaved test specimens. The use of nondestructive techniques in the inspection of plastic and polymeric composites is fairly recent and hence, the knowledge required to develop a KBES is still very scattered and not yet fully covered in the literature. This study demonstrates both the feasibility of compiling and representing this knowledge domain and the possibility of translating it into an efficient automated tool capable of giving reliable expert-like advice at low cost. The reasoning process is divided into three stages. In the first stage, a polymetric composite component is completely defined according to features that are relevant for nondestructive inspection. In the second stage, all the discontinuities that may be present in the component are determined. Finally, in the third stage, appropriate nondestructive testing procedures are identified to detect each of the possible discontinuities.

A Knowledge-Based System for Nondestructive Testing of Polymeric Composite Components

Abstract This paper presents a formalization of the knowledge domain of nondestructive quality control of polymeric composite components. The formalization scheme presented in this paper has been implemented in a prototype knowledge-based expert system (KBES), called NICC for nondestructive inspection of composite components, to help in the quality assurance of these parts. Geometric and bonding characteristics of individual and assembled components are taken into account, as opposed to the better understood evaluation of well-behaved test specimens. The use of nondestructive techniques in the inspection of plastic and polymeric composites is fairly recent and hence, the knowledge required to develop a KBES is still very scattered and not yet fully covered in the literature. This study demonstrates both the feasibility of compiling and representing this knowledge domain and the possibility of translating it into an efficient automated tool capable of giving reliable expert-like advice at low cost. The reasoning process is divided into three stages. In the first stage, a polymetric composite component is completely defined according to features that are relevant for nondestructive inspection. In the second stage, all the discontinuities that may be present in the component are determined. Finally, in the third stage, appropriate nondestructive testing procedures are identified to detect each of the possible discontinuities.

A prototype knowledge-based expert system for the design and detailing of reinforced concrete beams

Most computer programs developed for reinforced concrete beam design either analyze a given cross section for load capacity or offer a limited solution from which the engineer must continue toward the final design. These programs are very useful in performing many tedious calculations. However, they generally do not offer assistance in areas of design that require intuitive reasoning, experiential knowledge, rules of thumb, and sound engineering judgement. This type of heuristic knowledge has been incorporated into a prototype knowledge-based expert system for reinforced concrete beam design and detailing called BeamEx. BeamEx interacts with the user to advise and establish suitable parameters required for the comprehensive design of rectangular simply supported and continuous beams. It incorporates heuristic rules drawn from the governing Canadian codes and textbooks to design alternative suitable beams which are presented in graphical form. It is shown that a knowledge-based system approach can be used effectively in engineering design by encapsulating domain expertise in a program to complement and check the experience of the users in design. Key words: knowledge-based expert system, reinforced concrete, beams, design, detailing.

A knowledge-based expert system for inferring vegetation characteristics

A prototype knowledge-based expert system VEG is presented that focuses on extracting spectral hemispherical reflectance using any combination of nadir and/or directional reflectance data as input. The system is designed to facilitate expansion to handle other inferences regarding vegetation properties such as total hemispherical reflectance, leaf area index, percent ground cover, phosynthetic capacity, and biomass. This approach is more robust and accurate than conventional extraction techniques previously developed.

Applying knowledge-based expert systems to provide guidance for the safe storage of coal

The application of a prototype knowledge-based expert system for spontaneous heating, essh, in surface coal stockpiling operations is described. A brief review of earlier studies concerning the assessment of self-heating risk in stockpiles is presented. Based upon extensive analyses of the incidents of coal storage problems with spontaneous heating, the paper identifies the significant contributory factors which may have caused them. The stacking and precautionary techniques, or the rules of thumb, accumulated from years of experience and research, with particular reference to the safe storage of coal, are also discussed. This high level knowledge is further refined and consolidated into a knowledge-based expert system which aims to replicate the reasoning of human experts in reaching a decision. The system assesses the spontaneous combustion risk by using certainty factor techniques. It is capable of identifying common faults and recommending systematic procedures and methods for inexperienced engineers in handling stockpiles being planned, under construction and in use. Future development of the current system in surface mining operations is highlighted. The approach outlined in this paper offers a new managerial technique and shows how the incidents of spontaneous heating, weathering of coal and environmental impact can be minimized or avoided entirely through appropriate storage and handling, by applying an expert system approach.

A hierarchical expert system for design of floors in highrise buildings

A prototype knowledge-based expert system, called COFDEX (for COmposite Floor Design EXpert), has been developed for integrated design of composite floors in multistory buildings in accordance with the 1986 American Institute of Steel Construction (AISC) Load and Resistance Factor Design (LRFD) Specification. Design options include design for practical minimum cost or for minimum depth. Developed in the expert system programming environment GURU, COFDEX is a coupled system with a hierarchical structure in which procedural modules interact with rule sets and data bases. The expert system COFDEX demonstrates how AI technology complements the traditional numerical processing in automating the complicated process of engineering design and developing highly interactive software packages.

A knowledge-based expert system for planning and design of agroforestry systems

Computer-based Expert Systems that use knowledge, facts, and reasoning techniques to solve problems, normally requiring the abilities of human experts, are increasingly being used in many activities. The United Nations University (UNU) Agroforestry Expert System (AES) is a first attempt to apply this technique to agroforestry. UNU-AES is a prototype Knowledge-Based Expert System (KBES) designed to support land-use (agricultural, forestry, etc.) officials, research scientists, farmers, and individuals interested in maximizing benefits gained from applying agroforestry management techniques in developing countries. This prototype addresses the options for alley cropping, a promising agroforestry technology which has potential applicability when used under defined conditions in the tropics and subtropics. Alley cropping involves the planting of crops in alleys or interspaces between repeatedly pruned hedgerows of fast-growing, preferably leguminous, woody perennials. The primary benefits from this technique include nutrient enrichment, soil improvement, and erosion control. UNU-AES, which is the first known attempt at the application of expert system procedures in the field of agroforestry, uses a total of 235 decision rules to develop its recommendations. With the inclusion of more climatic and socio-economic data and improved advisory recommendations, UNU-AES can be expanded to provide advice on alley cropping in more diverse geographical and ecological conditions and eventually address other agroforestry techniques.

Application of a coupled system for optimum design of plate girder bridges

A prototype knowledge-based expert system has been developed for minimum weight design of steel plate girder highway bridges. This expert system, called PG-BRIDGE1, is a coupled system in which AI-based symbolic processing is combined with traditional numerical processing. The architecture of the system has been presented in an accompanying article 1. This paper presents an application and abbreviated consultation with PG-BRIDGE1.

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.

STEELEX: A coupled expert system for integrated design of steel structures

Most expert systems developed so far are concerned with symbolic processing of a knowledge base. Solution of complex engineering problems often requires substantial numerical processing in addition to symbolic processing of heuristics and experiential knowledge. In this paper, we present STEELEX, a prototype knowledge-based expert system for integrated design of building structures consisting of moment-resisting steel frames. STEELEX is a coupled system in which AI symbolic processing is combined with conventional numerical processing. STEELEX produces the final detailed design including the beam-column connections ready for fabrication. In addition, it can explain the basis of design and the principles behind the design specification. STEELEX has been developed using a domain-specific tool called SDL (for Structural Design Language). Implemented in the INTERLISP environment, SDL provides a design problem-solving environment using a hierarchical cooperating specialists paradigm. STEELEX has a debugging facility and provides a multiwindow graphics interface for drawing isometric as well as orthographic views of the steel frame and beam-column connections.