The ability to understand the implications of the geometry of solid objects is an important aspect of intelligent behavior. This paper presents work designed to enable reasoning with relatively loose conceptualizations of geometry. The method operates by comparing target geometry to known geometry, and involves the manipulation of models based upon prototypes. In particular, three techniques of simplification, approximation, and transformation are discussed. Finally, an application of the method to the domain of stress concentration prediction is presented.

Computational simulation of physical systems generally requires human experts to set up a simulation, run it, evaluate the quality of the simulation output, and repeatedly invoke the simulator with modified input until a satisfactory output quality is achieved. This reliance on human experts makes use of simulators by other programs difficult and unreliable, though invocation of simulators by other programs is critical for important tasks such as automated engineering design optimization. Presented is a framework for constructing intelligent controllers for computational simulators that can automatically detect a wide variety of problems that lead to low-quality simulation output, using a set of evaluation methods based on knowledge of physics and numerical analysis stored in a data/knowledgebase of models and simulations. An experimental implementation of this framework in an intelligent automated controller for a widely used computational fluid dynamics simulator is described.

The assessment of damage of structural concrete elements relies on the engineering judgment of the person in charge of the inspection and evaluation. This paper describes a rule-based prototype expert system developed to assist an engineer engaged in the task of assessing postearthquake damage to structural concrete elements in the task of providing guidance for inspection as well as criteria for evaluation and courses of action to take afterwards. The expert system, called DASE, identifies the most likely failure modes that may be developed by columns or beams of a damaged building, determines the severity of damage and, suggests immediate actions to take afterwards, such as rehabilitation procedures or tests, to maintain an acceptable local safety level. Floor damage classification and restoration guidelines can also be provided, assuming that all of the structural components in a building's floor have been inspected. The Analytic Hierarchy Process has been implemented as the overall framework to determine the severity of damage, since it allows judgments and personal values to be represented in a systematic and rational manner. DASE provides graphics that customize the user interface and an explanation facility. The knowledge acquisition process consisted primarily of the analysis of documented knowledge found through literature research.

The paper describes a novel means of performing calculus operations on poorly understood engineering functions using networks of radial Gaussian neurons. The network architecture and training algorithm used for this purpose is described briefly. Once trained, a network can be converted into a form that provides the differential or integral of the learned function, by a simple substitution of the type of activation function used at the hidden neurons. A range of substitute activation functions, for conversion to first- and second-order partial differential and integral forms of the network, are derived. Following this, the technique is tested on a selection of calculus operations for two example civil engineering problems: assessing motion in tall structures; and modeling moisture penetration in porous materials. The converted networks produced in these experiments provide accurate models of the actual differentials and integrals of the function the original networks had been taught. A method of improving the accuracy of results by training the original network beyond the region in which the converted networks operate, is described. The paper concludes by identifying some areas for further development of the technique.

The design of even the simplest product requires thousands of decisions. Yet few of these decisions are supported with methods on paper or on computers. Is this because engineering design decisions do not need support or is it because techniques have yet to be developed that are usable on a wide basis? In considering this question a wide range of decision problem characteristics need to be addressed. In engineering design some decisions are made by individuals, others by teams – some are about the product and others about the processes that support the product – some are based on complete, consistent, quantitative data and others on sparse, conflicting, qualitative discussions. To address the reasons why so little support is used and the characteristics of potentially useful decision support tools, a taxonomy of decision characteristics is proposed. This taxonomy is used to classify current techniques and to define the requirements for an ideal engineering design decision support system.