Black Swift: A machine learning software for predicting and improving UAS maintenance schedules

Black Swift Technologies LLC (BST) proposes a feasibility study that will consider our current avionics monitoring system as a baseline toward building a highly capable preventative maintenance solution based around USAF assets. We will consider improvements upon the current state-of-the art through the use of unsupervised ML algorithms to provide early warning and diagnostics of potential critical system failures on small UAS. We will gather critical data for the study from avionics data that the USAF already collects, and if this data proves insufficient, we have developed a set of monitoring nodes which we employ in our proprietary avionics that we can use to install aboard candidate platforms to supplement the data sets and implement ML algorithms for real-time analysis and feedback. BST has the capabilities to use these during this Phase I trial if stakeholders want to gather real-time data of their UAS vehicles. Primarily, we will work to obtain useful data from sources in the USAF, while performing any algorithm work on our own systems.