Finite Element Analysis using Component Decomposition and Knowledge-Based Control

This paper presents ongoing research into using Artificial Intelligence (AI) techniques to intelligently control finite element thermal analyses. These techniques are used to implement component level decomposition of the physical domain, and to integrate domain information into the analysis process to increase computational efficiency. We have implemented these techniques into a new proof-of-concept finite element program which employs a blackboard architecture to integrate the various numerical and symbolic knowledge sources. The blackboard architecture also supports the storage (and retrieval) of data in an object-oriented form. A test problem involving transient thermal analysis of an integrated circuit package is presented. Use of the proposed method showed a significant decrease in the number of floating point operations required compared to conventional solution technologies. The penalty associated with this saving was approximately a 4% difference in the calculated temperature in the critical region of interest.