The development of an expert system for the characterization of containers of contaminated waste

摘要

Scientists at the Mississippi State University Diagnostic Instrumentation and Analysis Laboratory and the Idaho National Engineering and Environmental Laboratory are developing an expert system to aid in the determination of the proper disposition of containers of transuranic and low-level-alpha-contaminated waste generated as a byproduct of Department of Energy defense-related programs. This system will consider a variety of information such as real-time radiography and the data from both passive and active neutron assay systems to classify the containers into one of the two categories—those that meet the requirements for being shipped to the Waste Isolation Pilot Plant in New Mexico and those that do not. We describe the development of a prototype of the expert system. We also describe the approach used to represent and reason with information from a variety of sources as well as the uncertainty that is inherent in such information. We discuss the strengths and weaknesses of the various artificial intelligence techniques that were considered for use in the expert system.