AN INFORMATION PROCESSING MODEL OF KNOWLEDGE SYSTEMS

Real-time knowledge-based systems (KBSs) are increasingly used to monitor and control real-time processes. Although a KBS may perform well on the average in terms of computation time, it may fail to deliver results while meeting deadlines in some critical cases. This is not acceptable in a hard real-time system where all timing constraints imposed by the environment must be continuously observed by the embedded computer and the failure to meet a single deadline may be catastrophic. Thus the technology for building a new generation of real-time KBSs must be developed before we can rely on these smart systems to perform complex, safety-critical monitoring and control functions in a real-time environment as we currently do on embedded software programs implemented in procedural languages. In this article, we examine some fundamental issues in the design and development of real-time KBSs including (1) response time analysis, and (2) rule-base optimization and synthesis. >

Artificial intelligence can assist in industrial control in many ways, but this paper concentrates on the role of knowledge-based systems in the areas of control, detection and diagnosis of faults, scheduling and planning. The paper argues that the application of knowledge-based techniques can provide a unification of these and other activities, and outlines the requirements of knowledge representation and inference techniques that are needed to make such systems a reality. The advances in hardware, including sensors as well as computers, that will be driven by and in turn stimulate the introduction of the knowledge-based industrial control systems are also considered.

This work is concerned with the design and construction of a yarn brushing machine to produce and monitor such yarns by means of the application of knowledge-based, computer vision and on-line control systems. Part I describes an investigation into the effects that input yarn properties and changes in machine parameters have on the characteristics of the brushed yarn.

In Memoriam: Dr. Clive L. Dym (1942–2016)

Design shells: A formalism for prototype refinement in knowledge-based design systems

Knowledge-based Systems and Expert Systems, in particular, are expensive to build and difficult to validate and debug because of their complexity and dynamism. Therefore, it is not easy for knowledge engineer and domain expert to identify the gaps and mistakes in knowledge base. Unit testing is unable to cover validation process at all stages, in many cases manual thorough review of decision process is needed. In this paper we spot main approaches to validation and verification issue and describe a component that helps to debug a knowledge base by visualising execution of rules that derive a particular result. This component is developed for Knowledge-based Systems built on Drools Platform1 and we demonstrate application of this component in a knowledge-based engineering system for structural optical design.

A coupled knowledge-based expert system for design of liquid-retaining structures

Knowledge-based approach and system for assembly oriented design, Part I: the approach

A central problem for the design of knowledge-based systems is the so-called knowledge acquisition bottleneck. Knowledge acquisition is crucial for the quality and efficiency of a planned knowledge-based system. These systems are always based on one or several knowledge bases, whose contents are an influential quality factor for the system's result. For that reason, it is evident that a consistent approach to knowledge acquisition is of great importance. In relation to the problem domain the knowledge-based system is intended for, the knowledge acquisition can be highly problematic. While, for example, in technical problem domains, the access to expert knowledge can usually be achieved in an acceptable manner, the acquisition of medical knowledge for formalisation and usage in an information system is not possible without difficulty.

Abstract. Highlights A knowledge-based rapid design system for combine chassis is proposed. The object-oriented knowledge representation uniformly describes the multi-source heterogeneous design knowledge. The multivariate linear regression analysis ratiocinates further unknown design principles behind existing products. Abstract. In the design of agricultural machinery, the lack of systematic and structured knowledge utilization systems results in low development efficiency and poor reusability of design knowledge. This paper considers the design of a combine chassis, and focuses on the application of knowledge-based rapid design to agricultural machinery. As a typical sophisticated agricultural machine, combines have a complicated design that requires the integration of multiple disciplines according to the crop types, production areas, and ability of the designers. Hence, a knowledge-based design system for a wheeled combine chassis is proposed. By integrating object-oriented technology with a mixed reasoning strategy, multi-source heterogeneous design knowledge can be applied in completing the chassis design task. To date, there are more than 2000 design ideas and 350 parameter models in the knowledge database. In addition, tacit design knowledge acquired by a knowledge discovery method can be employed to perfect the design and improve the reliability of the product. The design of a combine chassis demonstrates that the knowledge-based rapid design of agricultural machinery is completely feasible, and the design system significantly reduces the design workload, shortens the development cycle, and improves design efficiency and knowledge utilization.

Knowledge-based turbomachinery design system via a deep neural network and multi-output Gaussian process

The Internet and World Wide Web (WWW) are now evolving as an important communication technology and a major information resource provider for industry. This paper discusses the development and implementation of a knowledge-based gear design and manufacturing system over the Internet to create new integrated design and manufacturing environments. By providing access to an interactive web-based support system, any designer with a WWW browser becomes a potential user of this on-line design system. Once connected, the designer follows the system instructions and submits the necessary input data on the appropriate web pages. The server receives a request from a client and invokes a CGI (Common Gateway Interface) program that processes the information provided through the user Interface. The CGI parses the data and has the ability to remotely run the knowledge-based gear design system that integrates knowledge about all aspects of gear design and manufacturing and provides powerful reasoning and decision-making capabilities for reducing the time between gear tooth creation, detailed design and manufacturing process specification via the Internet. When the execution is completed, full specifications definition, geometry, kinematic-loads and stresses are determined through Finite Element Analysis (FEA) within ANSYS, VRML models of the gear pair and gearbox assembly including gears, shafts, bearings and housing are exported according to the designer requests and sent back to designer on the web browser. To accomplish this, a combination of HTML, JavaScript, VRML, CGI Script and C++ is used. Finally, an example on spur gear design utilizing a parallel gearbox design model configuration is discussed.

Purpose – Guidelines for the design of knowledge-based e-learning usability systems are absent from the current recognized set of usability design heuristics and from an established evaluation methodology of e-learning system developments. Such systems can help Web designers and instructional designers design for different user needs and decide which properties are of a higher priority, thus meriting more design and development efforts. The authors aim to help students develop higher-order thinking skills, such as application, evaluation and syntheses of knowledge. Design/methodology/approach – The authors applied Merrill ' s first principles of instruction and usability properties as pedagogical and usability design guidelines, knowledge management (KM) and hierarchical task analysis as methodological knowledge bases. The authors proposed a KM e-learning usability framework which frames our mapping of Web usability attributes to e-learning usability properties. The authors aim to investigate whether adopting Merrill ' s first principles of instruction and usability properties as knowledge-based guidelines/design factors would help learners develop higher-order thinking skills and whether this design would result in positive technology acceptance. The authors also developed a method matrix to map the selected methods of cognitive engineering to its potential uses in the KM e-learning usability framework of this paper and mapped e-learning usability tools with components in the KM e-learning usability system. Findings – Findings indicated that our design effectively helped learners to demonstrate higher-order thinking skills and positive technology acceptance, promising indications toward the design and development of knowledge-based usability frameworks and systems. Research/limitations/implications – The sample size of this paper is small. Hence, conclusions are not generalizable at this moment. Originality/Value – The authors’ contributions are twofold: First, the authors proposed a KM e-learning usability framework, which frames the mapping of KM processes to e-learning principles and usability properties. Second, the authors proposed a method matrix which maps the selected methods of cognitive engineering to its potential uses in their KM e-learning usability framework. Based on these mappings and focusing on the usability properties navigation and learning support, the authors used ICT/Web2.0 tools to present/visualize information more clearly and more sensibly/manageably to students, to help trigger new knowledge and develop higher-order thinking skills, such as application, evaluation and syntheses of knowledge and articulate information from different perspectives throughout the KM life cycle.

Evaluating the success of a knowledge acquisition (KA) task is difficult and expensive. Most evaluation approaches rely on the expert themselves, either directly, or indirectly by relying on data previously prepared with the help of experts. In incremental KA, knowledge base (KB) errors are monitored and corrected by an expert. Thus, during its evolution a record of the knowledge based system (KBS) performance is usually easy to keep. We propose to integrate with the incremental KA process, an evaluation process based on a statistical analysis to estimate the effectiveness of the KBS, as the KBS is actually evolved. We tailor such an analysis for Ripple Down Rules (RDR), which is an effective incremental KA methodology where a record of the KBS performance can be easily derived and updated as new cases are processed by the system. An RDR KB is a collection of rules with hierarchical exceptions, which are entered and validated by the expert in the context of their use. This greatly facilitates the knowledge maintenance task which, characteristically in RDR, overlaps with the incremental KA process. The work in this paper aims to overlap evaluation with maintenance and development of the knowledge base. It also minimises the major expense in deploying the RDR KBS, that of keeping a domain expert on-line during maintenance and the initial period of deployment. The expert is not kept on-line longer than it is absolutely necessary. We use the structure and semantics of an evolving RDR KB, combined with proven machine learning statistical methods, to estimate the added value in every KB update, as the KB evolves. Using these values, the decisionmakers in the organisation employing the KBS can apply a cost-benefit analysis of the continuation of the incremental KA process. They can then determine when this process, involving keeping an expert on-line, should be terminated.

Computer environments for design and designers