Vision-Based Damage Detection for One-Fixed-End Structures Based on Aligned Marker Space and Decision Fusion.

It is possible to detect damage in structures based only on vision-system-based assessment of their deformation shape under load. There is, however, a gap between available methods designed to detect damage in beam-like structures and engineering needs for monitoring structures of many different shapes. In this article, a new Aligned Marker Space method of morphing vision data is introduced. The method allows damage detection of any engineering object with one fixed support as if it were a cantilever beam. The paper also presents a new fusion technique to combine the results of several damage-detection methods for an increase in accuracy and sensitivity. The methods are tested based on numerical simulation of various structures, a blender-based simulation, and a set of practical experiments in which crane structures are subjected to damage of different sizes and locations. The optimization of damage detection methods' metaparemeters is performed using an evolutionary algorithm designed to find the Pareto front of the solutions. The assessment of the influence of different factors, like camera position, damage position, or repetition of the experiment, is provided.