Impedance Based Health Monitoring Technique with Probabilistic Neural Network for Possible Wall Thinning Detection of Metal Structures

Abstract

Corrosion of structures and wall thinning of pipes can severely affect the mechanical strength as wall thickness is reduced. Thus a cost effective structural health monitoring technique plays an important role when managing a structure. The electromechanical impedance (EMI) method is a local method that has limited sensing range, resulting in a high cost when covering large areas. In this study, a reattachable EMI method is investigated using a stack of multiple metal plates to conduct an experiment involving thickness reduction. In addition, the main problem of the impedance signatures changing subjected to reattaching the piezoelectric transducer is solved by using the probabilistic neural network algorithm presented for the study. The proposed approach successfully identifies the thickness of two different structures with high accuracy.

A portable bolt-loosening detection system with piezoelectric-based nondestructive method and artificial neural networks

“…Regarding some of previous work related to probabilistic neural networks (PNNs) for damage detection can be found in the literature. 16–18 Palomino et al 16 combined PNN with fuzzy cluster analysis method for identification and classification of two types of damage. de Oliveira and Inman 17 investigated comparing damage identification performance between Fuzzy ARTMAP and PNN subjected to progressive damage.…”

“…de Oliveira and Inman 17 investigated comparing damage identification performance between Fuzzy ARTMAP and PNN subjected to progressive damage. Na and Baek 18 mentioned the importance of monitoring thickness reduction of steel structures and used PNN to detect wall thinning of metal structures.…”