Automatic crack classification by exploiting statistical event descriptors for Deep Learning

TL;DR

This paper presents a deep learning-based method combining statistical event descriptors and neural networks to accurately classify different crack modes from acoustic emission data, aiding early structural damage detection.

Contribution

It introduces a novel integration of deep neural networks with statistical analysis for crack classification, improving accuracy in SHM applications.

Findings

Achieves 92% accuracy in classifying crack modes

Effective in early damage detection

Enhances SHM technology design

Abstract

In modern building infrastructures, the chance to devise adaptive and unsupervised data-driven health monitoring systems is gaining in popularity due to the large availability of big data from low-cost sensors with communication capabilities and advanced modeling tools such as Deep Learning. The main purpose of this paper is to combine deep neural networks with Bidirectional Long Short Term Memory and advanced statistical analysis involving Instantaneous Frequency and Spectral Kurtosis to develop an accurate classification tool for tensile, shear and mixed modes originated from acoustic emission events (cracks). We investigated on effective event descriptors to capture the unique characteristics from the different types of modes. Tests on experimental results confirm that this method achieves promising classification among different crack events and can impact on the design of future on structural health monitoring (SHM) technologies. This approach is effective to classify incipient damages with 92% of accuracy, which is advantageous to plan maintenance.