Year
1996
Abstract
New and highly sophisticated systems are being developed for the control and accounting of nuclear material at US Department of Energy sites. These software systems provide efficient, easy-to-use storage and retrieval of material, control and accounting (MC&A) data that describe transactions involving nuclear materials. In addition to the ability to access these data, it is essential to maintain its integrity. To do so, it is necessary to incorporate site-specific error checking and error handling functions. Inclusion of technology to validate MC&A data increases the utility of these systems. However, the large amounts of data and its complex and diverse nature make manual analysis and evaluation extremely tedious. This paper describes our work in the development of analysis tools to automate the anomaly detection process for the Material Accountability and Safeguards System (MASS) that tracks and records the activities associated with accountable quantities of nuclear material at Los Alamos National Laboratory. Working with the users of the data, we have developed an expert system that is being used to focus the attention of the experts directly on significant phenomena.