Data-Driven Damage Classification Using Guided Waves in Pipe Structures

Abstract

Damage types are important for structural condition assessment, however, for conventionally guided wave-based inspections, the characteristics extracted from the guided wave packets are usually used to detect, locate and quantify the damages, but not classify them. In this work, the data-driven method is proposed to classify the common damages in the pipe utilizing the guided wave signals obtained from numerous damage detection tests. The fundamental torsional mode T(0,1) is selected to conduct the guided wave-based damage detection to reduce the complexity of signal processing for its almost non-dispersive property. A total of 520 groups of experimental data under different degrees of damage were obtained to verify the proposed method. Finally, with help of a deep neural network (DNN) algorithm, all response data from the damages in the pipes were all clearly classified with quite high probability.