A Generalized Adaptive Framework for Automating Design Review Process: Technical Principles

Abstract

Design review is the process of evaluating a design against its requirements to verify the performance of the design and identify issues before construction takes place. The cited methods for automating the design review process are either based on proprietary, domain-specific or hard-coded rule-based representations, which may be successful in their particular implementations, but they have the drawbacks of being costly to sustain, inflexible to change, lack generalized framework of rules and regulations modeling that can adapt to various engineering design realms, and thus don’t support an open neutral standard. They are often referred to as ‘Black Box’ approaches. This study proposes a new comprehensive framework that minimizes the shortcomings of the cited methods. Building regulations for example, are legal documents written and authorized by people to be interpreted and applied by professionals. They are barely precise as formal logic. Engineers can read those documents and translate them into scientific notations and software applications. They can extract any information they need, reason about it, and apply it at various levels of precision. How these extraction and application are carried out is a critical component of automating design review process. The primary project goal is to address this issue by focusing on the development of a Generalized Adaptive Framework (GAF) for an open standard [based on Industry Foundation Classes (IFC)] that enables automating the design review processes to attain design efficiency and cost-effectiveness. The objectives of this paper include: (a) the conceptual and theoretical development of a framework that is adaptive to the target domain and supports an open standard for transforming the written design regulations and rules into a computable model, and (b) defining the different modules needed for the automation of the design review process.