US 12,296,978 B1
Systems and methods for aerial vehicle mission and maintenance planning
Nathan D. Plawecki, Melbourne, FL (US); Kenneth A. Crooks, Melbourne, FL (US); Angel A. Lopez De Victoria, Melbourne, FL (US); and David M. Wernert, Melbourne, FL (US)
Assigned to NORTHROP GRUMMAN SYSTEMS CORPORATION, Falls Church, VA (US)
Filed by Nathan D. Plawecki, Melbourne, FL (US); Kenneth A. Crooks, Melbourne, FL (US); Angel A. Lopez De Victoria, Melbourne, FL (US); and David M. Wernert, Melbourne, FL (US)
Filed on Mar. 31, 2021, as Appl. No. 17/218,336.
Int. Cl. B64D 45/00 (2006.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01); G07C 5/00 (2006.01); G07C 5/08 (2006.01)
CPC B64D 45/00 (2013.01) [G06N 5/04 (2013.01); G06N 20/00 (2019.01); G07C 5/008 (2013.01); G07C 5/0808 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
generating component reliability data indicative of a reliability of a component of an aerial vehicle of a plurality of aerial vehicles in a standby configuration based on a current age of the component, by utilizing a machine learning algorithm;
updating a dynamic reliability model of a plurality of dynamic reliability models for the aerial vehicle based on the component reliability data, each dynamic reliability model of the plurality of dynamic reliability models characterizing a reliability of one of the plurality of aerial vehicles, wherein each dynamic reliability model of the plurality of dynamic reliability models identifies a logical and/or functional connection between components of a respective aerial vehicle and wherein updating the dynamic reliability model includes updating a node reliability value for a respective component of the dynamic reliability model to the component reliability data;
identifying a subset of aerial vehicles of the plurality of aerial vehicles in the standby configuration that comprises a mission critical component in a reliable state, based on a fleet analysis of the plurality of dynamic reliability models;
executing each dynamic reliability model of the plurality of dynamic reliability models to compute an indication of vehicle reliability for each aerial vehicle of the plurality of aerial vehicles;
computing a mission of success probability for each aerial vehicle of the plurality of aerial vehicles based on a respective indication of vehicle reliability;
outputting the mission of success probability for each aerial vehicle of the plurality of aerial vehicles on a graphical user interface (GUI), the GUI including a mission reliability object indicating the mission of success probability for each aerial vehicle of the plurality of aerial vehicles, a system status object that indicates a status of a plurality of systems associated with each aerial vehicle of the plurality of aerial vehicles and a mission flight plan indicating phases of a selected aerial vehicle during a mission;
identifying a given aerial vehicle of the plurality of aerial vehicles for implementing the mission based on an evaluation of the mission of success probability for each aerial vehicle of the plurality of aerial vehicles; and
selecting the aerial vehicle of the plurality of aerial vehicles in the standby configuration that provide a greatest probability of mission success for execution of the mission.