Intelligent Systems for Engineering: A Knowledge-based Approach
When men of knowledge impart this knowledge, I do not mean they will convince your reason. I mean they will awaken in you the faith that it is so. - Sri Krishna, Bhagavadgita BACKGROUND The use of computers has led to significant productivity increases in the en gineering industry. Most ofthe computer-aided engineering applications were . restricted to algorithmic computations, such as finite element programs and circuit analysis programs. However, a number ofproblems encountered in en gineering are not amenable to purely algorithmic solutions. These problems are often ill-structured; the term ill-structured problems is used here to de note problems that do not have a clearly defined algorithmic solution. An experienced engineer deals with these ill-structured problems using his/her judgment and experience. The knowledge-based systems (KBS) technology, which emerged out of research in artificial intelligence (AI), offers a method ologyto solve these ill-structuredengineering problems. The emergenceofthe KBS technology can be viewed as the knowledge revolution: other important events that led to increased productivity are the industrial revolution (17th century); the invention of the transistor and associated developments (first half of the 20th century); and the world-wide web (towards the end of the 20th century). Kurzweil, in a lecture at M. LT on December 3, 1987, linked the progress of automation to two industrial revolutions: the first industrial PREFACE xxxii revolution leveraged our physical capabilities, whereas the second industrial revolution - the knowledge revolution - is expected leverage oUr mental ca pabilities.
19 pages matching extracted in this book
Results 1-3 of 19
What people are saying - Write a review
We haven't found any reviews in the usual places.
List of Figures
List of Tables
49 other sections not shown
Other editions - View all
abstraction action ACTIVE stock analysis application approach Artificial Intelligence associated backward chaining behavior blackboard blackboard system breadth-first search case-based case-based reasoning causal Chapter clothes pin components Computer configuration space connected constraints defined depicted depth-first search described developed device discussed domain Editor ellipsoidal equations evaluation example Expert Systems floor-sys-1 FONM forward chaining frame function genetic algorithms goal headlights heuristics hierarchy hypothesis IEEE implemented inference mechanism initial input instantiate involves KBES knowledge representation knowledge-base language learning logic machine match neural network nodes object object-oriented object-oriented programming operators optimal output panel parameters pattern primitive problem solving procedure programming qualitative reasoning region relations relationships representation represented rule-based rules search methods Section selected semantic networks shown in Figure simulated annealing slab slot solution solver specific starting system strategy structure subgoals task techniques tion variables vector