Continuing minimal-defect production under material integrity cyberattacks

Material integrity cyberattacks induce manufacturing-driven defects in parts and compromise their operational functionality. The socio-economic cost of monitoring-based part disposal and production stoppage necessitates rapid in-process recovery from continued defect formation. But cyberattacks can circumvent existing real-time control methods by introducing intermittent, random, and a-priori unknown perturbations of exogenous process conditions. We present a novel AI-based framework to address this issue and examine its capabilities for the example of Fused Filament Fabrication (FFF), demonstrating real-time recovery from attack-induced inter-road voids with unprecedented sub-road spatial resolution.