Adding explanation capability to a knowledge-based system: a case study

1993 ◽  
Author(s):  
Susan M. Bridges ◽  
Matthew Lybanon
2019 ◽  
Vol 11 (4) ◽  
pp. 257
Author(s):  
Yousuf Nasser Al Khamisi ◽  
Mohammed Khurshid Khan ◽  
Jose Eduardo Munive Hernandez

2010 ◽  
Vol 1 (4) ◽  
pp. 61-78
Author(s):  
Lei Wang ◽  
Yajie Tian ◽  
Tetsuo Sawaragi ◽  
Yukio Horiguchi

A critical problem in robotic manufacturing is that the task of teaching robotics is rather time-consuming. This has become a serious problem in the present age of cost reduction. Collaboration with a company in the field has revealed that the root cause of this problem is that there is not a common knowledge base in this domain, which can serve as shared and reused knowledge. In robotic manufacturing, the skills and experiences of skilled workers are a form of tacit knowledge that is difficult to be acquired and transferred to other workers and robots. This paper proposes a knowledge-based system for sharing and reusing tacit knowledge in the robotic assembly domain. In this system, a modified EBL (Explanation-based Learning) method is proposed to generalize tacit knowledge from specific robotic programs made by skilled workers. A newly operational criterion is proposed for the generalized tacit knowledge, which demands that it should be expressed understandably by human workers and be reusable by robots to generate programs automatically.


Author(s):  
Ritch Rappel ◽  
Julian Dorscht ◽  
Reena Sahney

The pipeline sector is facing a multi-faceted challenge regarding its workforce. Valuable knowledge is being lost as increasing numbers of technical experts and long-term employees exit the industry (due to retirement). Concurrently, the public spotlight is focused on the environmental impact of the pipeline industry. Therefore, robust construction of new pipelines and effective maintenance of aging infrastructure is increasingly important. Herein lies the challenge — How does the industry transfer the knowledge required to ensure that personnel have suitable competency to maintain the integrity of the pipeline system? A scenario where new personnel efficiently gain knowledge through experience is critical. An important aspect of achieving this is a more systematic and thoughtful approach to knowledge transfer. As part of its fundamental methodology for developing training and alternate methods for knowledge transfer, the team launched an initiative to review the literature and current industry approaches. This was done as a key input to developing a “Knowledge Taxonomy.” This tool simplifies the process for selecting the optimal method for effectively transferring key technical knowledge based on the desired level of competency (e.g., awareness building vs. mastery). Specifically, the team identified a number of consistent themes and combined them with both sound educational theory and industry experience to develop a tool in the form of a practical framework. This Knowledge Transfer Taxonomy was then applied to a specific knowledge gap in industry as a case study. This paper will 1. Summarize, at a high level, the results of the literature review and current approaches; 2. Describe the framework (i.e., Knowledge Taxonomy) developed by the team; 3. Discuss a case study involving the application of this framework to a specific and real challenge; and Through this work, the team identified and developed specific strategies and tactics to effectively overcome some of the barriers to knowledge transfer. These experiences will be shared in the context of a specific situation that typifies the current challenges industry is facing in effective knowledge transfer.


Author(s):  
Ze-Lin Liu ◽  
Yong Chen ◽  
You-Bai Xie

Exploring wide multi-disciplinary solution spaces to create conceptual design solutions is a difficult task for human designers due to lack of sufficient multi-disciplinary knowledge. A viable approach would be to develop a computer-aided system to synthesize the wide variety of knowledge for a given design task. However, the existing design synthesis systems are mainly domain-specific, focusing on conceptual design synthesis in a single or few limited disciplines. Therefore, this article introduces the development of a knowledge-based system for multi-disciplinary conceptual design synthesis, including the establishment of a knowledge base for organizing multi-disciplinary principle solutions and a design synthesis algorithm. The implementation of a prototype software is also reported, with the conceptual design of a solar fountain as a demonstrative case. The results of the case study show that the system can automatically and conveniently generate multi-disciplinary conceptual solutions.


Sign in / Sign up

Export Citation Format

Share Document