A Signals Intelligence Approach to Automated Assessment of Instrument Capabilities

Abstract

This paper describes a novel approach using machine learning and artificial intelligence techniques to analyze, describe and assess stimulus and sensor signal characteristics to create a robust and comprehensive description of Automatic Test Equipment (ATE) instrument capabilities. This approach results in a machine language representation providing a more thorough and accurate assessment of ATE stimulus and sensor capabilities that supports digital, analog, and radio frequency (RF) signals and is especially useful for complex RADAR, SONAR, Infrared and other signals where English and natural language descriptions are difficult or impossible to construct. This is accomplished within the structure of IEEE-Std 1641–2010, Signal and Test Definition, with extensions proposed to support machine language renderings of signal descriptions. This approach facilitates use of generic and commercial automated tools and enhances the possibility for interoperability of tools and test programs across DoD ATE.