NASA Logo, National Aeronautics and Space Administration

MARGInS - Model-based Analysis of Realizable Goals In Systems

MaARGInS framework Design and validation of a safety-critical system requires advanced capabilities that support understanding the system behavior in nominal and off-nominal situations. MARGInS is a framework that enables the user to create customized machine learning and statistical tool chains for analyzing and predicting the behavior of a complex, hybrid system.

MARGInS Orion Results MARGInS contains set of machine learning and statistical algorithms for multivariate clustering, treatment learning, critical factor determination, time-series analysis, event prediction, and safety-boundary detection and characterization.

Key Benefits

  • Supports system testing
  • Configurable – to find novel features in test suites, determine classes of behavior, propose new experiments that can efficiently explore the boundaries between classes of behavior, and to create visualizations and reports.

Applications

Studies with Orion Padabort-1 and EFT-1, IFCS Adaptive Flight Control, Terminal TSAFE, QFCS, and ACAS-X.

References


Updated December 2017


Active Members

Misty Davies
Yuning He

First Gov logo
NASA Logo - nasa.gov