Detection of System Compromise in Additive Manufacturing Using Video Motion Magnification

Three-dimensional printing systems have expanded the access to low cost, rapid methods for attaining physical prototypes or products. However, a cyber attack, system error, or operator error on a 3D-printing system may result in catastrophic situations, ranging from complete product failure, to small types of defects which weaken the structural integrity of the product. Such defects can be introduced early-on via solid models or through G-codes for printer movements at a later stage. Previous works have studied the use of image classifiers to predict defects in real-time and offline. However, a major restriction in the functionality of these methods is the availability of a dataset capturing diverse attacks on printed entities or the printing process. This paper introduces an image processing technique that analyzes the amplitude and phase variations of the print head platform arising through induced system manipulations. The method uses an image sequence of the printing process to perform an offline spatio-temporal video decomposition to amplify changes attributable to a change in system parameters. The authors hypothesize that a change in the amplitude envelope and instantaneous phase response as a result of a change in the end-effector translational instructions to be correlated with an AM system compromise. Two case studies are presented, one verifies the hypothesis with statistical evidence in support of the method while the other studies the effectiveness of a conventional tensile test to identify system compromise. The method has the potential to enhance the robustness of cyber-physical systems such as 3D printers.