Expert systems—another frontier for industrial engineering

Expert systems are receiving increasing attention both in the academic and the practical words. This article examines the following area of potential interaction between industrial engineering and expert systems: except systems as a consultant, expert systems as a modeling tool and its integration with decision support systems, expert systems as a tutor, and the contribution of expert systems to the implementation of solutions based on quantitative analysis. Representatives examples of relevant systems are cited. Mutual benefits are expected as a result of the interaction between industrial engineering and expert systems.     

Beyond decision support systems: The role of operations research in expert systems

It is time to borrow techniques from operations research and software engineering in order to improve today's expert systems technology. Expert systems, the next wave beyond decision support systems, are being developed in many specific domains. There are, however, some major research issues that need to be addressed in order to advance the state-of-the-art in expert systems. Operations research methods could augment and resolve some of these research issues, as discussed in this paper.     

On commercial expert systems projects

The development process of expert systems obeys to rules, which have no counterparts in traditional software engineering techniques. To a certain extent they even contradict them.

AI engineers in charge of the realization of industrial expert systems must be aware of this situation and be prepared to respond to it by providing technology transfer. As long as this transfer to the customers has not happened, commercial expert system projects will lead to frustration and compromises hampering the achievement of the economic objectives set to the projects. For the time being technology transfer must be a major task of AI companies.     

Do you believe in the advantage of expert systems in industrial ergonomics?

Reasons for reservations about accepting the recommendations of industrial ergonomics are first explored. A knowledge deficiency is ascertained which results in a general dependency on ergonomic experts. The experts, however, are rarely able to communicate their knowledge in a form applicable by a practitioner. The development and employment of expert systems suitable for use in work design problems are proposed to resolve this dilemma. The question of whether an interest in expert systems for industrial ergonomics can be assumed is considered. The necessary conditions for the successful development and introduction of expert systems for industrial ergonomics are derived. The extent to which currently available expert system technology can support the typical procedures in industrial ergonomics is subsequently examined.     

Design of expert systems for integrated production automation

An approach to the design of expert systems for integrated production automation is presented. The major components in an integrated manufacturing system consist of corporate planning, marketing planning, research and development, engineering design, production planning, manufacturing, warehousing, and product distribution. These components are linked by management information flow, technology information flow, as well as materials flow. An intelligent computer is used to integrate information flow and to control materials flow. This paper discusses characteristics of the future factory, elements of knowledge based systems, and the design of computer based expert systems for production planning, for engineering design, and for integrated manufacturing.     

Software engineering technology innovation - Turning research results into industrial success

This paper deals with the innovation of software engineering technologies. These technologies are methods and tools for conducting software development and maintenance. We consider innovation as a process consisting of two phases, being technology creation and technology transfer. In this paper, we focus mainly on the transfer phase.Technology transfer is of mutual interest to both academia and industry. Transfer is important for academia, because it shows the industrial relevance of their research results to, for example, their sponsoring authorities. Showing the industrial applicability of research results is sometimes referred to as valorization of research. Nowadays, valorization is often required by research funding bodies. The transfer is important for industries, because innovating their development processes and their products is supportive in gaining a competitive edge or remaining competitive in their business. We describe the technology transfer phase by means of three activities: technology evaluation, technology engineering, and technology embedding. The technology evaluation activity is perceived as the main gate between the technology creation phase and the technology transfer phase. With two case studies, originating from the Dutch high-tech systems industry, we will illustrate the activities in the transfer phase.In addition to the process we will also define the main roles in a software engineering technology innovation, namely: the technology provider (academic research, industrial research and technology vendor) and the technology receiver (industrial development). With those roles we also address the issues concerning the ownership of technologies.     

The role of the industrial engineer in developing expert systems

The most popular area of Artificial Intelligence application today is in expert systems. This paper contains a discussion of expert systems, otherwise known as knowledge-based systems and knowledge systems. The principal components of an expert system, and the evolution of expert systems are presented. The suitability of a task to an expert system is proposed. When a task is suitable for an expert system application, the system must be developed by a knowledge engineer. The methodology that the knowledge engineer must go through to develop an expert system is demostrated. Industrial engineers have formal training in many areas which can be useful when assumming the role of knowledge engineer. These areas of industrial engineering and how they are beneficial is discussed. What the future may hold in store is also pondered.     

Expert configurator for concurrent engineering: Came´le´on software and model

This paper, dealing with discrete production systems, has two goals. The first one is to identify cases in which the use of expert configurator software is a significant improvement for concurrent engineering achievement. Since the industrial implementation of these configurators is often tricky, the second issue of this paper is to present a model that allows to specify the industrial problem before implementation. This paper is divided into three sections. We first quickly recall the main trends of concurrent engineering and the related expert configurator interests. Then, the basic behavior and solutions for expert configurators are presented and the modeling requirements are pointed out. The third part is dedicated to the presentation, illustrated with an example, of our model and our method.     

Expert systems for engineering design

Abstract: An expert system embodies a humun expert's domain-specific knowledge and skill, acquired and refined over years of experience. A number of problems in diagnosis and engineering design can be solved by Using current expert-system techniques. This paper enumerates the main components of such problems and the steps that are taken in solving them. A few prototypical articificial intellegence systems embody techniques that can be applied to engineering problems. These are surveyed, and their relevance to components of design problems is discussed. Some expert systems in design domains are summarized, with emphasis on aspects that can illustrate wider applicability of the techniques. A number of avenues of further research are evident, and the area of engineering design offers rich opportunities for advancing the state-of-the-art in expert systems. An annotated selective bibliography is included     

智能混合系统研究综述

作为人工智能的两个主要研究方向,专家系统 和神经网络在过去的几十年中均取得了很大的成功,但二者又存在一些各自的缺陷,不能单 独解决一些复杂的工程实际问题．因此,智能混合系统就成为当今人工智能研究领域中的一 个非常重要且具有很大实用价值和广阔发展前景的研究领域．本文分析比较了专家系统和神 经网络的基本特点,论述智能混合系统的研究现状并指出存在的一些问题．     

Industrial Applications of Software Synthesis via Category Theory—Case Studies Using Specware

Over the last two years, we have demonstrated the feasibility of applying category-theoretic methods in specifying, synthesizing, and maintaining industrial strength software systems. We have been using a first-of-its-kind tool for this purpose, Kestrel's Specware^TM software development system. In this paper, we describe our experiences and give an industrial perspective on what is needed to make this technology have broader appeal to industry. Our overall impression is that the technology does work for industrial strength applications, but that it needs additional work to make it more usable. We believe this work marks a turning point in the use of mathematically rigorous approaches to industrial strength software development and maintenance.It is interesting to note that when this technology is applied to software systems whose outputs are designs for airplane parts, the design rationale that is captured is not only software engineering design rationale, but also design rationale from other engineering disciplines (e.g., mechanical, material, manufacturing, electrical, human factors, etc.). This suggests the technology provides an approach to general systems engineering that enables one to structure and reuse engineering knowledge broadly.     

PRODUCTION SYSTEMS FOR PROCESS CONTROL: ADVANCES AMD EXPERIENCES

Abstract

Production systems are still regarded as one of the most important paradigms for solving complex tasks. However, in embedded control systems production systems have not yet been applied intensively. We identify open issues for production systems in process control by exemplary presenting two industrial fielded expert systems. We describe how these expert systems have been applied to process control, discuss lessons learned, and show how practical experience has influenced our own research activities. Finally we identify future research directions of general importance.     

控制理论研究中的几个挑战性的问题

论述了控制理论研究中的几个挑战性的问题,认为控制理论属于技术性的学科。在工程应用中控制理论从建模、控制、优化三个方面碰到了一些挑战性命题,对此提出了一些看法。提出了工业噪声的建模问题。通过工业控制实践工作中所遇到的问题,指出了采用智能的方法来处理控制系统的性能与鲁棒性之间的矛盾。提出藉助于专家系统自适应地调整可行域来解决大规模工程命题,指明了控制理论研究与应用之间良性互动的循环发展过程。     

THE TECHNOLOGY TRANSFER OF EXPERT SYSTEMS Overcoming Barriers to Commercialization

Expert systems extend the current commercial advantage of information systems from clerical to intellectual applications. As expert systems increasingly find acceptance in the marketplace, the focus is no longer on successful research, but on successful project management. Return on investment is a critical factor that must be taken into account for a successful expert systems implementation. A great deal of preparation must be done, however, before technology transfer can be carried out in an organization. This article discusses the process of transferring expert systems technology.     

Paradigms for knowledge-based systems in industrial engineering

When developing expert systems, expertise lies not only in formulating the knowledge to be put into the knowledge base, but also in deciding upon the knowledge representation and inference mechanism most suited to the application. Six detailed knowledge bases demonstrate the application of various AI-based systems to industrial engineering problems. They illustrate a number of approaches: expert systems, which are based upon practical experience; decision systems, which derive from modelling skills; and situation-action systems, which rely on production process design skills. The six paradigms presented describe a logical expert system for selecting material handling equipment; a multi-valued expert system for selecting a dispatching rule for automatic guided vehicles; a profile matching expert system for selecting project management software; a confidence building expert system for selecting a machine feeder; a tandem decision system for developing a production schedule; and a situation-action system for controlling job allocation in a flexible manufacturing cell. The relationships between these various paradigms and the characteristics of problems to which they can be applied are categorized by the nature of the expert and his expertise; the features of the environment; the decision or decisions to be taken; and the manner in which AI-system performance can be evaluated. A knowledge base is proposed for determining which architecture is most appropriate for a given application.     

Expert systems applied to problems in geographic information systems: Introduction, review and prospects

This paper critically reviews current expert system developments relevant to geographic information systems, and identifies several research topics for application of expert system technology in geographic information systems. We have identified four major problem domains of geographic information systems in which expert system technology has been applied—automated map design, terrain/feature extraction, database management/user interface, and geographic decision support systems. Efforts in each problem domain are critically reviewed. Considering the accomplishments and shortcomings of efforts to date, we identify areas likely to gain importance in this field. Our view of these prospects is moderated by constraints of current technology and a realistic view of current efforts. Future research will place more emphasis on formal representation of both knowledge and uncertainty. Another future research area will be the development of advanced tools for geographic knowledge acquisition. Finally, better methods for working with large-scale geographic databases will be needed.     

机电产品数字化工业设计多目标评价关键技术

论文从工业设计的理念和方法出发,阐述了计算机辅助技术进行机电产品数字化工业设计多目标评价的理论和方法。并以专家系统技术为基本框架构建了支持产品数字化设计的计算机辅助设计评价原型系统,确定了评价目标树,评价目标树模版库,评价目标库以及评价工具集等四个系统功能模块,并详细讨论了这四个模块结构、内容的构建和实现过程。为面向机电产品的数字化工业设计多目标评价提供了新思路、新方法。最后,通过产品实例验证了该技术在设计中的应用。     

An analysis of environmental expert system applications

This study outlines the current state of expert system technology in environmental protection. The paper defines general characteristics of expert systems and identifies the kind of problems in environmental protection which are well suited for expert system use. This study introduces, classifies and briefly describes twenty-one expert system approaches from Canada and the F.R.G., many of them still in an early development state.The analysis and evaluation show that not many expert systems are in actual use for practical environmental decision making. Finally the areas with the highest potential for successful employment of today's expert system technology are identified and a number of research needs stated. More progress is needed towards truly operational, “intelligent” (i.e. AI-based) environmental information systems.     

NEURAL NETWORKS IN CONSULTING ENGINEERING MANAGEMENT: A FRAMEWORK FOR BID-DECISION MANAGEMENT

Neural networks are devoted mainly to solving ill-structured problems. The field of consulting engineering embraces many such problems from environmental engineering to engineering management. It is a proper and adequate business environment in which to be assisted by the technology of expert (rule and nonrule based) systems. The paper describes a specialized framework for the use of neural networks in consulting engineering management mainly for the complex and unstructured business of bid-decision on large scale projects and other engineering consulting tasks.