A knowledge based database system for engineering correlations

Abstract

Engineering design frequently relies on empirical data expressed in the form of non-dimensional correlations. These are almost always governed by applicability limits and the engineer is faced with the problem of choosing the right correlation that would provide design data with acceptable accuracy from a large number which are available. A knowledge based database system (KBDS) has been constructed which assists in the simple formulation of a jet impingement application based on which it retrieves and evaluates the relevant correlation from a database. Where the information in the database does not satisfy this specification the system uses knowledge of the application domain to either select suitable correlations for extrapolation or to modify the database query to select alternative information. The constraints which enable new correlations to be added or the knowledge in the network to be extended to include new geometries and flow conditions whilst maintaining the integrity are described. The operation of the KBDS has been demonstrated with a comprehensive database of correlations for the heat transfer due to the impingement of single and multiple air jets. This application provides typical engineering correlations and hence the techniques described are expected to be widely applicable.

Introduction

Correlations based on empirical data are used in heat transfer and in many other engineering domains, for example fluid flow (Miller [1]). Recent development of powerful learning algorithms for artificial neural networks (ANNs) has led to their use in many engineering applications. Thibault and Grandjean [2] employed them to model three problems in heat transfer ranging from the thermocouple to correlations in natural convection. However the process of selecting the most appropriate correlation from relevant publications often presents an engineer with two major problems. Firstly, the number of publications from which the correlations may be extracted is vast. Secondly, correlations contained in individual publications are mostly specific to a particular applicability conditions.

Ideally an intelligent information system needs to be set-up to assist with the retrieval of appropriate correlations and the subsequent determination of the salient design parameter such as heat transfer coefficient, based on a simple description of the domain, say geometry and flow conditions. If such an information system is not to become rapidly out-of-date it must be capable of incorporating newly published information without the need to redesign the system. This feature is usually associated with databases than with knowledge based systems.

Furthermore, in cases where none of the information contained within the system matches the user enquiries, it would be useful for the system to suggest the best approximation by interpreting the heat transfer process described and applying appropriate knowledge. This necessitates an understanding of how and to what degree changes in geometry and flow conditions can affect the parameters and this information should be represented in a knowledge base.

This paper describes the development of an information system, specifically to jet impingement, which satisfies these objectives. The system developed combines the features of a database system with respect to data storage with that of a deductive capability of a knowledge based system (KBS).