Knowledge based engineering support for aircraft component design

TL;DR: The main contribution of the paper is to highlight the development of the KNOMAD methodology and to substantiate its individual steps with sufficient detail to support the application of KNOMad in practice.

TL;DR: A design environment consisting of a framework, a central model and a newly developed conceptual design module, both for parameter and method replacement, are introduced and first results for multi-fidelity calculations are shown.

TL;DR: The objective of the review paper is to identify the foundation and research issues of KBE in the light of parametric, function based, web-oriented modeling.

TL;DR: There is a need for further research on the knowledge sourcing KBE aspect and the integration of KBE systems and AI implementations as a potential solution to develop the extended KBE development process requested by the industry.

TL;DR: The Palo Alto Collaborative Testbed (PACT) as mentioned in this paper is a concurrent engineering infrastructure that encompasses multiple sites, subsystems, and disciplines, including NVisage, a distributed knowledge-based integration environment for design tools; DME (Device Modeling Environment), a model formulation and simulation environment; Next-Cut, a mechanical design and process planning system; and Designworld, a digital electronics design, simulation, assembly, and testing system.

TL;DR: In an attempt to improve the design of products and reduce design changes, cost, and time to market, concurrent engineering or life cycle engineering has emerged as an effective approach to addressing these issues in today's competitive global market as discussed by the authors.

TL;DR: A knowledge based engineering system (KBES) to extend the current capabilities of automotive body-in-white (BIW) engineers to respond dynamically to changes within a rapid timeframe and to assess the effects of change with respect to the constraints imposed upon them by other product cycle factors.

TL;DR: Results show that neural networks have advantages when dealing with data that does not adhere to the generally chosen low order polynomial forms, or data for which there is little a priori knowledge of the appropriate CER to select for regression modeling.