Abstract
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. I present a framework for constructing intelligent controllers for computational simulators which can automatically detect a wide variety of problems which lead to low-quality simulation output, using a set of evaluation methods based on knowledge of physics and numerical analysis stored in a data/knowledge base of models and simulations. I describe an experimental implementation of this framework in an intelligent automated controller for a widely used computational fluid dynamics simulator.