Accession Number:



Practical Machine Learning, Causal Learning and Bayesian Belief Networks for System Simulation, Test and Predictive Maintenance

Descriptive Note:

[Technical Report, Briefing Charts]

Corporate Author:

Carnegie-Mellon University, Software Engineering Institute

Personal Author(s):

Report Date:


Pagination or Media Count:



The following concepts represent current SEI research and customer support of programs within the USAF and Navy. Although machine learning and deep learning are not novel in their application, our complement of causal learning to segregate true causal influence from spurious correlation enable us to go one step further in providing more actionable models.The avionics system depicted in these slides could be any system. The methodology would be unchanged across domains. We first discuss potential improvement in system simulation and test via machine and causal learning followed by improvement in system diagnosis via BBNs informed from machine and causal learning.


Subject Categories:

  • Computer Programming and Software
  • Cybernetics

Distribution Statement:

[A, Approved For Public Release]