Statistical time features for global corrosion assessment in a truss bridge from vibration signals

Truss-type structures are commonly used for configuring civil structures such as bridges, roof supports, cranes, among others. However, they are susceptible to suffer different types of damage such as cracks, loosened bolts, and corrosion, being the latter one of the most common and aggressive ones. In this paper, it is explored the application of statistical time features (STFs) extracted from raw vibration signals of truss-type bridges under dynamic excitation for assessing their health condition. Then, the Kruskal-Wallis method (KWM) is used for determining the most discriminating STFs and a feature reduction criterion is applied to select the most useful ones for assessing the structure's condition. The selected STF is employed for configuring a decision tree and thus determining the condition of the structure automatically. The effectiveness of the proposal is verified under three levels of corrosion damage (i.e., incipient, moderate and severe), which are artificially generated. For the analysis, the tri-axial vibrations are explored. Results show that the proposal can identify damage from an incipient damage condition. An accuracy of 100% is reached using only a sensor placed on the structure. (C) 2020 Elsevier Ltd. All rights reserved.