A Crack Characterization Method for Reinforced Concrete Beams Using an Acoustic Emission Technique

Abstract

This study aims at characterizing crack types for reinforced concrete beams through the use of acoustic emission burst (AEB) features. The study includes developing a solid crack assessment indicator (CAI) accompanied by a crack detection method using the k-nearest neighbor (k-NN) algorithm that can successfully distinguish among the normal condition, micro-cracks, and macro-cracks (fractures) of concrete beam test specimens. Reinforced concrete (RC) beams undergo a three-point bending test, from which acoustic emission (AE) signals are recorded for further processing. From the recorded AE signals, crucial AEB features like the rise time, decay time, peak amplitude, AE energy, AE counts, etc. are extracted. The Boruta-Mahalanobis system (BMS) is utilized to fuse these features to provide us with a comprehensive and reliable CAI. The noise from the CAI is removed using the cumulative sum (CUMSUM) algorithm, and the final CAI plot is used to classify the three different conditions: normal, micro-cracks, and fractures using k-NN. The proposed method not only for the first time uses the entire time history to create a reliable CAI, but it can meticulously distinguish between micro-cracks and fractures, which previous works failed to deal with in a precise manner. Results obtained from the experiments display that the CAI built upon AEB features and BMS can detect cracks occurring in early stages, along with the gradually increasing damage in the beams. It also soundly outperforms the existing method by achieving an accuracy (classification) of 99.61%, which is 17.61% higher than the previously conducted research.

Using Deep Learning to Detect Defects in Manufacturing: A Comprehensive Survey and Current Challenges

“…The traditional detection methods are highly focused. For instance, Osmosis testing technology [ 53 ] is only suitable for detecting defects in highly permeable and non-porous materials and have certain advantages over other general methods. However, most of the traditional detection methods still need to rely on manual assistance to complete, especially when a certain amount of instrument debugging is required before testing, and the equipment development cost is high, which is not highly adaptable and limited by the equipment life and manufacturing accuracy.…”

A Lightweight Deep Learning-Based Approach for Concrete Crack Characterization Using Acoustic Emission Signals

“…Habib et al [24] proposed a complete framework for crack characterization of the RC beams that not only provided a reliable crack assessment indicator (CAI), but also conducted precise classification of the normal condition and micro and macro-cracks. They also used a wrapper-based feature selection algorithm name Boruta that provided a robust solution for crucial feature selection.…”

“…This can be very effective since the output feature scale can be reduced resulting in a reduction of the number of parameters needed for the model and the maintenance of the translation variance. Max pooling [24] is vastly used in most cases in the pooling layer.…”

“…It requires extensive domain knowledge and human expertise to select features that can be effective while performing classification tasks for multiple crack types. • Some of the works undertook feature selector algorithms for selecting relevant features ( [23], [24]). However, we have to keep in mind that the computation complexity is already high since we have to extract AE features using multiple loops for huge chunks of data.…”

“…Furthermore, fluctuating, unpredictable, and non-linear behavior of the AE features resulting in imprecise crack classification and characterization can be avoided too. • Since there are no direct feature extraction processes like the methods proposed in [23], [24], no feature selection algorithm is necessary. This helps to get rid of an added layer of complexity.…”