Classification Of Acoustic Emission Signals Research Articles

Enhancing the detection capabilities of nano-avalanches via data-driven classification of acoustic emission signals.

Acoustic emission (AE) is a powerful experimental method for studying discrete and impulsive events termed avalanches that occur in a wide variety of materials and physical phenomena. A particular challenge is the detection of small-scale avalanches, whose associated acoustic signals are at the noise level of the experimental setup. The conventional detection approach is based on setting a threshold significantly larger than this level, ignoring "false" events with low AE amplitudes that originate from noise. At the same time, this approach overlooks small-scale events that might be true and impedes the investigation of avalanches occurring at the nanoscale, constituting the natural response of many nanoparticles and nanostructured materials. In this work, we develop a data-driven method that allows the detection of small-scale AE events, which is based on two propositions. The first includes a modification of the experimental conditions by setting a lower threshold compared to the conventional threshold, such that an abundance of small-scale events with low amplitudes are considered. Second, instead of analyzing several conventional scalar features (e.g., amplitude, duration, energy), we consider the entire waveform of each AE event and obtain an informative representation using dynamic mode decomposition. We apply the developed method to AE signals measured during the compression of platinum nanoparticles and demonstrate a significant enhancement of the detection range toward small-scale events that are below the conventional threshold.

Failure Severity Prediction for Protective-Coating Disbondment via the Classification of Acoustic Emission Signals.

Structural health monitoring is a popular inspection method that utilizes acoustic emission (AE) signals for fault detection in engineering infrastructures. Diagnosis based on the propagation of AE signals along any surface material offers an attractive solution for fault identification. However, the classification of AE signals originating from failure events, especially coating failure (coating disbondment), is a challenging task given the AE signature of each material. Thus, different experimental settings and analyses of AE signals are required to classify the various types of coating failures, and they are time-consuming and expensive. Hence, to address these issues, we utilized machine learning (ML) classification models in this work to evaluate epoxy-based-protective-coating disbondment based on the AE principle. A coating disbondment experiment consisting of coated carbon steel test panels for the collection of AE signals was implemented. The obtained AE signals were then processed to construct the final dataset to train various state-of-the-art ML classification models to divide the failure severity of coating disbondment into three classes. Consequently, methods for the extraction of useful features, the handling of data imbalance, and a reduction in the bias of ML models were also effectively utilized in this study. Evaluations of state-of-the-art ML classification models on the AE signal dataset in terms of standard metrics revealed that the decision forest classification model outperformed the other state-of-the-art models, with accuracy, precision, recall, and F1 score values of 99.48%, 98.76%, 97.58%, and 98.17%, respectively. These results demonstrate the effectiveness of utilizing ML classification models for the failure severity prediction of protective-coating defects via AE signals.

Characterization of optical ae signals at loading of fibre reinforced composites

Characterization of acoustic emission (AE) signals in loaded materials can reveal structural damage and consequently provide early warnings about product failures. Therefore, extraction of the most informative features from AE signals is an important part of the characterization process. This study considers the characterization of AE signals obtained from bending experiments for biocomposite and glass fiber epoxy (GFE) composites at room temperature and low temperature. For the acquisition of AE signals, fiber optic sensors (FOS) are used that can outperform classical electrical sensors under challenging operational environments. In this paper, we propose the extraction of deep features using different machine learning methods. The deep features are compared with extracted standard AE features. Then, the different feature sets are analyzed through discriminant analysis, neural networks, and extreme learning machines, combined with feature selection, to estimate the predictive potential of various feature sets. The proposed signal processing structure is focused on the classification of AE signals to recognize the source material, evaluate the predictive importance of extracted features, and evaluate the ability of used FOS for evaluation of material behavior under challenging low-temperature environments.

Deep learning-based classification of damage-induced acoustic emission signals in UHPC

Acoustic emission (AE) is advantageous in studying and monitoring the damage state of UHPC, and its performance can be further improved if various damage-induced AE signals are classified accurately. The deep learning method is promising to enhance the classification accuracy, but it is limited by the absence of the corresponding AE dataset. In this study, fiber pullout tests and direct tension tests (DTTs) were performed to explore the time–frequency features of various damage-induced AE signals in UHPC. The AE sources can be classified into five categories: matrix cracking, fiber debonding, fiber sliding, fiber scraping, and matrix spalling. A corresponding AE dataset was established after manual pre-labeling, pseudo-labeling with transfer learning, and mix-up data augmenting. Several lightweight convolutional neural networks (CNNs) were trained from scratch based on the dataset, with modified time–frequency spectrograms as data input. The performances of CNN-based classification models are superior to traditional shallow-learning methods. The popular lightweight CNN structure of ResNet18 achieves the highest overall accuracy of 93.94% among adopted CNN structures such as GoogleNet, ResNet18, EfficientNet-b0, and MobileNetV2. The AE signal classification results of DTTs show that fiber-pullout damage and matrix cracking occur intensively at the strain-hardening phase and increase with fiber content. That suggests the increasing fiber bridging and multi-crack propagation in the uniaxial tension of UHPC with higher fiber content.

Towards a Diagnostic Tool for Diagnosing Joint Pathologies: Supervised Learning of Acoustic Emission Signals.

Acoustic emission (AE) testing detects the onset and progression of mechanical flaws. AE as a diagnostic tool is gaining traction for providing a tribological assessment of human joints and orthopaedic implants. There is potential for using AE as a tool for diagnosing joint pathologies such as osteoarthritis and implant failure, but the signal analysis must differentiate between wear mechanisms—a challenging problem! In this study, we use supervised learning to classify AE signals from adhesive and abrasive wear under controlled joint conditions. Uncorrelated AE features were derived using principal component analysis and classified using three methods, logistic regression, k-nearest neighbours (KNN), and back propagation (BP) neural network. The BP network performed best, with a classification accuracy of 98%, representing an exciting development for the clustering and supervised classification of AE signals as a bio-tribological diagnostic tool.

Classification of acoustic emission signals in wood damage and fracture process based on empirical mode decomposition, discrete wavelet transform methods, and selected features

The nondestructive testing technology of generated acoustic emission (AE) signals for wood is of great significance for the evaluation of internal damages of wood. To achieve more accurate and adaptive evaluation, an AE signals classification method combining the empirical mode decomposition (EMD), discrete wavelet transform (DWT), and linear discriminant analysis (LDA) classifier is proposed. Five features (entropy, crest factor, pulse factor, margin factor, waveform factor) are selected for classification because they are more sensitive to the uncertainty, complexity, and non-linearity of AE signals generated during wood fracture. The three-point bending load damage experiment was implemented on sample wood of beech and Pinus sylvestris to generate original AE signals. Evaluation indexes (precision, accuracy, recall, F1-score) were adopted to assess the classification model. The results show that the ensemble classification accuracies of two tree species reach 94.58% and 90.58%, respectively. Moreover, compared with the results of the original AE signal, the accuracy of the AE signal processed by the methods proposed is increased by 27.68%. It indicates that the EMD and DWT signal processing methods and selected features improve the classification accuracy, and this automatic classification model has good AE signal recognition performance.

Acoustic Emission Signal Classification Using Feature Analysis and Deep Learning Neural Network

With the development of artificial intelligence in recent years, deep learning has been widely used in mechanical system signal classification but the impact of different feature extractions on the efficiency and effectiveness of deep learning neural networks is more important. In this study, a vehicle classification based on engine acoustic emission signal in the time domain, the frequency domain and the wavelet transform domain for deep learning network techniques is presented and compared. In signal classification, different feature extractions will show in different decomposition levels and can be used to recognize the various acoustic conditions. In the experimental work, as engines from 10 different ground vehicles operate, the measured sound signal is converted into a digital signal, and the established data set is classified and identified by the deep learning method. The number of samples, identification rate and identification time in the various signal domains are compared and discussed in this study. Finally, the experimental results and data analysis show that by using the wavelet signal and the deep learning method, excellent identification time and identification rate can be achieved, compared with traditional time and frequency domain signals.

Method of Analysis and Classification of Acoustic Emission Signals to Identify Pre-Seismic Anomalies

Method of Analysis and Classification of Acoustic Emission Signals to Identify Pre-Seismic Anomalies

Modelling of Acoustic Emission Signals Due to Fiber Break in a Model Composite Carbon/Epoxy: Experimental Validation and Parametric Study

The present paper focuses on experiments and numerical simulation of the acoustic emission (AE) signals due to fiber break in a model composite. AE signals are related to wave effects due to the source, the propagation medium and the sensor. For quantitative AE analysis, it is very important to understand the effect of the piezoelectric sensors and propagation on the “primitive” AE signals. In this study, we investigate the influence of sensors, thickness, and position of the fiber by finite element simulations. This parametric study can allow an enlargement of the library for supervised classification of AE signals.

Classification of acoustic emission signals generated from journal bearing at different lubrication conditions based on wavelet analysis in combination with artificial neural network and genetic algorithm

This paper presents the results of acoustic emission (AE) investigation for monitoring lubrication conditions of a journal bearing under various operating conditions. Hydrodynamic Lubrication (HL), Mixed Lubrication (ML), and Boundary Lubrication (BL), are the basic types of the fluid film lubrication. The aim of this investigation is to identify effective frequencies and most useful features of the AE signals for classification of the lubrication types. Continuous wavelet transform (CWT) and time domain signal analysis methods are used for feature extraction of the recorded AE signals. Then, Genetic Algorithms (GAs) in combination with Artificial Neural Networks (ANNs) are applied to select and classify the extracted features. The experimental results showed that the proposed system using AE signal is effective.

Classification of acoustic emission signals using wavelets and Random Forests : Application to localized corrosion

This paper aims to propose a novel approach to classify acoustic emission (AE) signals deriving from corrosion experiments, even if embedded into a noisy environment. To validate this new methodology, synthetic data are first used throughout an in-depth analysis, comparing Random Forests (RF) to the k-Nearest Neighbor (k-NN) algorithm. Moreover, a new evaluation tool called the alter-class matrix (ACM) is introduced to simulate different degrees of uncertainty on labeled data for supervised classification. Then, tests on real cases involving noise and crevice corrosion are conducted, by preprocessing the waveforms including wavelet denoising and extracting a rich set of features as input of the RF algorithm. To this end, a software called RF-CAM has been developed. Results show that this approach is very efficient on ground truth data and is also very promising on real data, especially for its reliability, performance and speed, which are serious criteria for the chemical industry.

The influence of grain size on acoustic emission characteristic in commercial-purity zirconium during tensile deformation

The influence of grain size on acoustic emission (AE) behavior during tension test in commercial-purity zirconium was investigated under a constant nominal strain rate at room temperature. Two deformation modes, dislocation slip and mechanical twinning, were found to be the physical sources for AE. The statistical analysis from metallographs showed that the quantity of mechanical twin gradually increased as grain size and tension strain increase. With grain size increased, the activity and intensity of the AE signals increased. The frequency distribution of the AE waveforms showed that two kinds of AE source were active with distinct frequency components during tension. By means of AE signal classification, the characteristic of AE due to dislocation slip and deformation twin were discussed respectively. The results showed that although dislocation was the dominant deformation mode, the primary AE source changed from dislocation to twin with the grain size increase. The AE activity due to twin was consistent with the metallographic evidence relating to the tensile deformation process.

Deformation mechanisms underlying tension–compression asymmetry in magnesium alloy ZK60 revealed by acoustic emission monitoring

This study is aimed at clarifying the microscopic mechanisms that determine a pronounced asymmetry of plastic deformation with respect to tension and compression in magnesium alloys, even having a random texture. The specific object of the present investigation is the Mg–Zn–Zr alloy ZK60. The mechanisms in question are based on a synergistic interplay between dislocation slip and deformation twinning. The details of the relative contributions of these principal processes were studied by monitoring the acoustic emission (AE) underpinned by robust AE signal classification developed recently. Through the cluster analysis of AE time series in spectral domain, the sequences of the predominant deformation mechanisms were identified for early stages of cyclic loading with opposite directions of the first loading excursion into tension or compression.

Development of an artificial neural network processing technique for the analysis of damage evolution in pultruded composites with acoustic emission

Acoustic Emission (AE) is a promising technique for the damage detection and the real-time structural monitoring of composite lightweight structures; however data interpretation and discrimination among failure modes from AE data is difficult to be carried out without proper data processing techniques. In this paper, a neural-network based classification of AE signals from tensile tests of pultruded glass-fiber specimens is proposed. A self-organizing map is trained with AE data from one specimen; then the map is clustered with the k-means algorithm. The optimal number of clusters is chosen by a voting procedure that takes into account a number of quality indexes; then the clustered neural network is used to classify AE data from other specimen. Results have shown that the classifier built from a smooth specimen was able to correctly classify other specimens with the same and with a different material layup, and is capable of recognizing signals from notched specimens, thus providing interesting and encouraging indications in view of the application on real structures.

A modal acoustic emission signal classification scheme derived from finite element simulation

The ability of broadband modal acoustic emission to classify the most common forms of damage mechanisms occurring within a polymer matrix composite material with rod type geometry has been shown. The composite under study was a unidirectional hybrid polymer matrix composite material, with carbon and glass fibers reinforcing a high temperature epoxy matrix. Signal discrimination was achieved through the development of a classification scheme derived from explicit finite element simulation of the most common deformation mechanisms. The classification scheme identified the type of failure mechanism, as well as the material of origin, based upon the spectral content of the signal which is directly influenced by the wave modes that propagate. The classification scheme was used to evaluate the effect that atmospheric aging at elevated temperature had on the hybrid composite subjected to flexure loading at various time periods. Advantages of the proposed method include computational efficiency, the ability to inherently account for geometric and material boundary layer reflections, as well as the ability to be readily adapted to complex part geometries.

Meta-cognitive RBF Network and its Projection Based Learning algorithm for classification problems

‘Meta-cognitive Radial Basis Function Network’ (McRBFN) and its ‘Projection Based Learning’ (PBL) algorithm for classification problems in sequential framework is proposed in this paper and is referred to as PBL-McRBFN. McRBFN is inspired by human meta-cognitive learning principles. McRBFN has two components, namely the cognitive component and the meta-cognitive component. The cognitive component is a single hidden layer radial basis function network with evolving architecture. In the cognitive component, the PBL algorithm computes the optimal output weights with least computational effort by finding analytical minima of the nonlinear energy function. The meta-cognitive component controls the learning process in the cognitive component by choosing the best learning strategy for the current sample and adapts the learning strategies by implementing self-regulation. In addition, sample overlapping conditions are considered for proper initialization of new hidden neurons, thus minimizes the misclassification. The interaction of cognitive component and meta-cognitive component address the what-to-learn, when-to-learn and how-to-learn human learning principles efficiently. The performance of the PBL-McRBFN is evaluated using a set of benchmark classification problems from UCI machine learning repository and two practical problems, viz., the acoustic emission signal classification and the mammogram for cancer classification. The statistical performance evaluation on these problems has proven the superior performance of PBL-McRBFN classifier over results reported in the literature.

Acoustic Emission Signal Classification Based On Support Vector Machine

A classification of acoustic emission signals ha s great significance. The best parameters of the RBF kernel had obtained by using grid optimization method, and the classifier had built to achieve the identification and classification of acoustic emission signals. The simulation results show that support vector machine can effectively distinguish different acoustic emission signal and noise signal. DOI: http://dx.doi.org/10.11591/telkomnika.v10i5.1387

Fast learning complex-valued classifiers for real-valued classification problems

In this paper, we present two fast learning complex-valued, single hidden layer neural network classifiers namely, ‘bilinear branch-cut complex-valued extreme learning machine (BB-CELM)’ and ‘phase encoded complex-valued extreme learning machine (PE-CELM)’ to solve real-valued classification problems. BB-CELM and PE-CELM use the bilinear transformation with a branch-cut at 2π and the phase encoded transformation, respectively, at the input layer to transform the feature space from the real domain to complex domain ( $${\Re \rightarrow \mathbb{C}}$$ ). A complex-valued activation function of the type of hyperbolic secant employed at the hidden layer maps the complex-valued feature space to a hyper dimensional complex space ( $${\mathbb{C}^m \rightarrow \mathbb{C}^K\quad K > m}$$ ). BB-CELM and PE-CELM are trained by choosing the hidden layer parameters randomly and computing the output weights analytically. Therefore, these classifiers require minimal computational effort during the training process. The performances of these classifiers are evaluated on a set of benchmark classification problems from the UCI machine learning repository and a practical acoustic emission signal classification problem. The results of the performance study highlight the superior classification ability of BB-CELM and PE-CELM classifiers.

The classification of acoustic emission signals of 304 stainless steel during stress corrosion process based on K‐means clustering

PurposeThe purpose of this paper is to classify and identify the acoustic emission (AE) signals of 304 stainless steel during stress corrosion process.Design/methodology/approachThe corrosion behavior of a specimen during slow strain rate testing (SSRT) in acidic NaCl solution was studied. The AE signals during the corrosion process were classified based on K‐means cluster algorithms; meanwhile, the characteristics of different AE sources were analyzed.FindingsThe results indicated that the AE characteristics of different AE sources, such as pitting, cracking, and bubble break‐up, differ significantly. The 304 stainless steel was prone to the occurrence of stress corrosion cracking under the SSRT condition in acidic NaCl solution.Originality/valueThe characteristics of different AE sources during corrosion process were gained for the first time, which could be of much help in analyzing and judging the corrosion situation.

Fast learning Circular Complex-valued Extreme Learning Machine (CC-ELM) for real-valued classification problems

In this paper, we present a fast learning fully complex-valued extreme learning machine classifier, referred to as ‘Circular Complex-valued Extreme Learning Machine (CC-ELM)’ for handling real-valued classification problems. CC-ELM is a single hidden layer network with non-linear input and hidden layers and a linear output layer. A circular transformation with a translational/rotational bias term that performs a one-to-one transformation of real-valued features to the complex plane is used as an activation function for the input neurons. The neurons in the hidden layer employ a fully complex-valued Gaussian-like (‘ sech’) activation function. The input parameters of CC-ELM are chosen randomly and the output weights are computed analytically. This paper also presents an analytical proof to show that the decision boundaries of a single complex-valued neuron at the hidden and output layers of CC-ELM consist of two hyper-surfaces that intersect orthogonally. These orthogonal boundaries and the input circular transformation help CC-ELM to perform real-valued classification tasks efficiently. Performance of CC-ELM is evaluated using a set of benchmark real-valued classification problems from the University of California, Irvine machine learning repository. Finally, the performance of CC-ELM is compared with existing methods on two practical problems, viz., the acoustic emission signal classification problem and a mammogram classification problem. These study results show that CC-ELM performs better than other existing (both) real-valued and complex-valued classifiers, especially when the data sets are highly unbalanced.