Ingenieur Vol. 74 Ingenieur Vol 72, April-June 2018 - Page 73

Engineer Maintenance and Operating Handbook Knowledge Acquisition Module Service logbook Equipment & Specification Knowledge Base Expert System Shell User Interface User Inference Engine Rules Regulation Method Rule Based • If... Then... • backward Chaining Figure 2: The designed framework for expert system shell Collapsing - Collapsing the goal is the process whereby the backward chainer tries to determine if the goal has been satisfied. The goal may have been satisfied by the recent addition of new facts caused by the Expansion process. ● ● Asking - The third phase of the backward chainer is where the backward chainer queries the user for the value of a slot once it has determined it cannot find that value on its own. Figure 2 shows a framework design for fault diagnosis of a commercial bus design and manufacturing process. ● ● Application Human experts are able to perform at a high level because they know their areas of expertise. An expert system, as these programmes are often called, uses domain specific knowledge to provide "expert quality" performance in a problem domain. Generally, exper t system developers acquire this knowledge with the help of human domain exper ts, and the system will emulate their methodology and performance. An expert system is a system with both theoretical and practical knowledge focusing on a narrow set of problems. However, an expert system is not human and thus is unable to learn from its own experience. Knowledge in an expert system must be extracted from humans and encoded in a formal language. This is the major task faced by designers of knowledge- intensive problem solvers (Negnevitsky, 2005). Expert systems neither copy the structure of the human mind, nor are they mechanisms for general intelligence. They are practical programmes that use heuristic strategies developed by humans to solve specific classes of problems. Because of the heuristic, knowledge-intensive nature of expert- 71