Acoustic Emission Signal Characteristics Research Articles

Feature level fusion of vibration and acoustic emission signals in tool condition monitoring using machine learning classifiers

To implement the tool condition monitoring system in a metal cutting process, it is necessary to have sensors which will be able to detect the tool conditions to initiate remedial action. There are different signals for monitoring the cutting process which may require different sensors and signal processing techniques. Each of these signals is capable of providing information about the process at different reliability level. To arrive a good, reliable and robust decision, it is necessary to integrate the features of the different signals captured by the sensors. In this paper, an attempt is made to fuse the features of acoustic emission and vibration signals captured in a precision high speed machining center for monitoring the tool conditions. Tool conditions are classified using machine learning classifiers. The classification efficiency of machine learning algorithms are studied in time-domain, frequencydomain and time-frequency domain by feature level fusion of features extracted from vibration and acoustic emission signature.

Time Series Analysis of Acoustic Emissions in Prefabricated Utility Tunnel During the Sealing Test

Utility tunnel is increasingly applied for underground space development, and its health monitoring becomes attractively important. The acoustic emission (AE) technology is often used for damage monitoring of small-scale specimens made of concrete or rock in the laboratory. In this study, the AE technology is adopted to instrument a novel prefabricated utility tunnel to provide insights into the leakage behavior of the structure during the sealing test. Filtering is conducted on AE data to eliminate the influence of noise interference, especially for data in the pressurization stage. The traditional ring-down count and AE energy are determined from eigenvalue analysis of AE events. It is found that these conventional calculations can be well related to the pattern of internal water pressure, and the Felicity effect is found in the loading process. Furthermore, time series analysis is carried out for each specific pressurization or pressure-holding stage during the sealing test, in which the b-value (an important mean to study the characteristics of AE signal) is evaluated. Results show that the b-value can also be used as a prediction basis for pre-alarming monitoring before the occurrence of seepage failure for utility tunnel.

Interlaminar shear behaviors of 2D needled C/SiC composites under compressive and tensile loading

The interlaminar shear strength of 2D needled C/SiC composites was measured using the double-notch shear test method. Interlaminar shear tests were performed under compressive and tensile loading. Shear stress–strain response and shear strain field evolution were studied using the digital image correlation (DIC) technique. The results show that the interlaminar shear strength of the specimen using the compressive loading method is 15% higher than that of the tensile loading method. Severe shear strain concentration was observed near the upper notch of the tensile loading specimen. Acoustic emission (AE) was utilized to monitor the damage during the tests. Typical damage mechanisms were categorized according to AE signal characteristics. The statistical results show that more matrix cracks were produced in the tensile loading specimen and no separate fiber/matrix debonding signal was detected in both specimens.

Study on interfacial debonding stress and damage mechanisms of C/SiC composites using acoustic emission

Among ceramic matrix composites (CMCs), carbon fiber-reinforced silicon carbide matrix (C/SiC) composites are widely used in numerous high-temperature structural applications because of their superior properties. The fiber–matrix (FM) interface is a decisive constituent to ensure material integrity and efficient crack deflection. Therefore, there is a critical need to study the mechanical properties of the FM interface in applications of C/SiC composites. In this study, tensile tests were conducted to evaluate the interfacial debonding stress on unidirectional C/SiC composites with fibers oriented perpendicularly to the loading direction in order to perfectly open the interfaces. The characteristics of the material damage behaviors in the tensile tests were successfully detected and distinguished using the acoustic emission (AE) technique. The relationships between the damage behaviors and features of AE signals were investigated. The results showed that there were obviously three damage stages, including the initiation and growth of cracks, FM interfacial debonding, and large-scale development and bridging of cracks, which finally resulted in material failure in the transverse tensile tests of unidirectional C/SiC composites. The frequency components distributed around 92.5 kHz were dominated by matrix damage and failure, and the high-frequency components distributed around 175.5 kHz were dominated by FM interfacial debonding. Based on the stress and strain versus time curves, the average interfacial debonding stress of the unidirectional C/SiC composites was approximately 1.91 MPa. Furthermore, scanning electron microscopy (SEM) and energy-dispersive X-ray spectroscopy (EDXS) were used to observe the morphologies and analyze the chemical compositions of the fractured surfaces. The results confirmed that the fiber was completely debonded from a matrix on the fractured surface. The damage behaviors of the C/SiC composites were mainly the syntheses of matrix cracking, fiber breakage, and FM interfacial debonding.

Effect of loading rate on fracture behaviors of shale under mode I loading

In this study, the effect of loading rate on shale fracture behaviors was investigated under dynamic and static loading conditions. Cracked straight through Brazilian disc (CSTBD) shale specimens were tested with a split Hopkinson pressure bar (SHPB) setup and INSTRON1346 servo-testing machine under pure mode I loading conditions. During the test, the crack propagation process was recorded by high-speed (HS) camera, and the acoustic emission (AE) signal generated by the fracture was collected by acoustic emission (AE) system. At the same time, crack propagation gauge (CPG) was used to measure the crack propagation velocity of the specimen. The results show that the crack propagation velocity and fracture toughness of shale have a positive correlation with the loading rate. The relationship among the crack propagation velocity, the fracture toughness and the loading rate is established under the static loading condition. In addition, the characteristics of AE signals with different loading rates are analyzed. It is found that the AE signals generated by microcrack growth decrease with the increase of loading rates. Meanwhile, the turning point of cumulative counting moves forward as the loading rate increases, which shows that the AE signal generated by shale fracture at low loading rate mainly comes from the initiation and propagation of microcracks, while at high loading rate it mainly comes from the formation of macro large-scale cracks. The fracture mechanism that causes shale fracture toughness and crack propagation velocity to vary with loading rate is also discussed based on the analysis results of AE signals.

Monitoring of the High-Technology Nailing of CFRTP Material under Ultrasonic Vibration by Acoustic Emission Method

In this study, the potential to monitor the high-technology nailing of carbon fiber reinforced thermoplastic material (CFRTP) under ultrasonic vibration was investigated by acoustic emission (AE) method. AE signals were detected by a piezoelectric AE sensor during high-technology nailing under ultrasonic vibration. This paper describes some experimental results on AE signal characteristics and observation of the high-technology nailing. In order to investigate the effects of machining condition, we focused on RMS voltage, which is dependent on the energy parameter of the AE signal. It was found that the AE method is a useful method of monitoring high-technology nailing.

Evaluation of internal microcrack evolution in red sandstone based on time–frequency domain characteristics of acoustic emission signals

Rocks are commonly used as building stone and construction materials in many engineering applications. To study the internal microcrack evolution characteristics of red sandstone specimens during deformation and failure, a uniaxial compression experiment was conducted based on RMT-150C rock mechanics, PCI-II acoustic emission (AE), and the strain acquisition testing systems. For eight red sandstone specimens, the relationships among axial stress, axial strain, acoustic emission events rate, and average frequency centroid were established. The variability of the AE events rate and average frequency centroid of the specimens was analyzed for five cracking levels. Additionally, the relationship between the loading stress corresponding to the minimum average frequency centroid of the AE signals and the peak stress during deformation and failure of the red sandstone specimens was discussed, and critical failure precursor characteristics revealed. Moreover, statistical analysis of the AE signal distribution characteristics of different frequency bands and amplitudes during rock deformation and failure was performed. Based on the difference between the AE signal duration ratio and the specimen rise time, a method for extracting AE characteristic signals during deformation and failure was proposed. Time-frequency analysis was performed on the extracted AE characteristic signals and results showed that the signals were closely related to the axial stress–strain change in the specimens, and were affected by the degree and development of internal microcracks. The wave peaks of the crack closure and linear elastic deformation stage AE characteristic signal frequency domain waveforms are relatively scattered. The wave peaks of the frequency-domain waveforms of the AE characteristic signals during stable and unstable crack growth stages are relatively concentrated.

Evaluating the sensitivity of acoustic emission signal features to the variation of cutting parameters in milling aluminum alloys: Part A: frequency domain analysis

It is known that adequate knowledge of the sensitivity of acoustic emission signal parameters to various experimental parameters is indispensable. According to the review of the literature, a lack of knowledge was noticeable concerning the behavior of acoustic emission parameters under a broad range of machining parameters. This becomes more visible in milling operations that include sophisticated chip formation morphology and significant interaction effects and directional pressures and forces. To remedy the aforementioned lack of knowledge, the effect of the variation of cutting parameters on the time and frequency features of acoustic emission signals, extracted and computed from the milling operation, needs to be investigated in a wide aspect. The objective of this study is to investigate the effects of cutting parameters including the feed rate, cutting speed, depth of cut, material properties, as well as cutting tool coating/insert nose radius on computed acoustic emission signals featured in the frequency domain. Similar studies on time-domain signal features were already conducted. To conduct appropriate signal processing and feature extraction, a signal segmentation and processing approach is proposed based on dividing the recorded acoustic emission signals into three sections with specific signal durations associated with cutting tool movement within the work part. To define the sensitive acoustic emission parameters to the variation of cutting parameters, advanced signal processing and statistical approaches were used. Despite the time features of acoustic emission signals, frequency domain acoustic emission parameters seem to be insensitive to the variation of cutting parameters. Moreover, cutting factors governing the effectiveness of acoustic emission signal parameters are hinted. Among these, the cutting speed and feed rate seem to have the most noticeable effects on the variation of time–frequency domain acoustic emission signal information, respectively. The outcomes of this work, along with recently completed works in the time domain, can be integrated into advanced classification and artificial intelligence approaches for numerous applications, including real-time machining process monitoring.

Multifractal Analysis of Acoustic Emissions during Hydraulic Fracturing Experiments under Uniaxial Loading Conditions: A Niutitang Shale Example

Fracture characterization is essential for estimating the stimulated reservoir volume and guiding subsequent hydraulic fracturing stimulations in shale reservoirs. Laboratory fracturing experiments can help provide theoretical and technical guidance for field operations. In this study, hydraulic fracturing experiments on the shale samples from Niutitang Formation in Hunan Province (China) under a uniaxial loading condition are conducted. The multifractal method is used to analyze the acoustic emission (AE) signals and characterize fracture initiation and propagation. The hydraulic fracturing process can be divided into three stages based on the characteristics of AE signals: the initial stage, the quite stage, and the fracturing stage. The multifractal analysis results showed that: (1) the value of the spectrum width, Δα, continues to increase as the energy accumulates until the fracturing stage starts; and (2) the difference in the multifractal spectrum values, Δf, reflects the relationship between small and large signal frequencies and can quantify the fracture scale, i.e., the lower the Δf, the larger the fracture scale and vice versa. The results were further verified using a time-frequency analysis of the AE signals and micro-CT scanning of the samples. This study demonstrates that the multifractal method is feasible for quantitatively characterizing hydraulic fractures and can aid field hydraulic fracturing operations.

Understanding the damage evolution of sapphire under scratching from AE signals

In this paper, the study on damage evolution of sapphire induced in scratching process using acoustic emission (AE) technology was carried out. Single-grit scratches with ramp scratch depth were conducted on C-plane of sapphire with AE signal monitoring. Groove microstructure after scratching shows that the damage evolution process is mainly determined by the interactions among cracks, specimen surface and groove boundary. To evaluate the damage evolution, the AE waveform indexes, i.e. fractal and frequency characteristics, were fully analyzed and correlated with groove microstructure of specimen after tests. It is found that the fractal dimension (FD) can identify the three basic damage modes as well as various damage behaviors during scratching process. In addition, the model of damage evolution is further proposed. The frequency characteristics of AE signals are distinctive to various damage behaviors during their evolution, especially to the occurrences of the critical damages and removal modes. Furthermore, the characteristic frequency band (CFB) of AE signals was extracted. It is found that FD of the reconstructed AE signals in CFB (86.8–161.4 KHz herein) can highlight damage details and features during initial damage stage of sapphire in scratch test effectively.

Structural condition monitoring and identification of laser cladding metallic panels based on an acoustic emission signal feature optimization algorithm

Laser cladding technology has become a central issue in industrial research and application recently. Due to the complexity of the processing and the difficulty of quantitative analysis, it is particularly important to effectively and reliably detect the forming quality of the cladding layer. Therefore, the laser cladding processing condition of metallic panels is monitored and identified based on acoustic emission technology in this article. Consequently, laser cladding acoustic emission signal of 316L stainless steel plate is first collected, and a multi-domain acoustic emission signal feature extraction method based on time–frequency domain and waveform parameters is constructed by integrating time–frequency, empirical, and inter-relationship diagraph analysis. Moreover, a feature optimization approach based on t-distributed stochastic neighbor embedding algorithm is proposed, which combines with correlation analysis to realize the de-redundancy and optimization of acoustic emission signal features. In addition, on the basis of optimizing the characteristics of acoustic emission signal, laser cladding acoustic emission signals under three technological parameters are collected. Second, a laser cladding condition identification method, which is a least square support vector machine algorithm based on niche particle swarm optimization, is proposed. The optimal parameter combination of niche particle swarm optimization algorithm is mainly selected to improve the accuracy of identification and classification. The results demonstrate the proposed t-distributed stochastic neighbor embedding feature optimization method can effectively extract the sensitive information related to the processing condition in the feature space, and the optimization of least square support vector machine parameters through niche particle swarm optimization can significantly improve the identification rate of classification. Specifically, the feasibility of the proposed t-distributed stochastic neighbor embedding–niche particle swarm optimization–least square support vector machine model to analyze laser cladding acoustic emission signal characteristics is verified, and the effectiveness of acoustic emission–based structural condition monitoring and identification of laser cladding plate-like structures is also demonstrated.

Evaluation of crack growth stage of sapphire under scratching based on AE signals

For hard-brittle materials, crack initiation and growth is an important factor to determine the surface quality of components during machining process. In this paper, the crack growth stage of sapphire was investigated based on acoustic emission (AE) signals through single-grit scratch experiments. The AE waveform indexes, i.e. fractal and frequency characteristics, were fully analyzed and correlated with groove microstructure of specimen after tests. The research shows that the specimen undergo four stages of crack growth successively as scratch depth increasing. It is found that the fractal dimension (FD) and frequency characteristics of AE signals are distinctive to various damage behaviors and be used to evaluate crack growth stage induced in machining process effectively. Especially, the FD distribution is sensitive to the occurrences of the critical damages and removal modes resulting from crack growth in scratch procedure. This paper can shed light on the control of surface integrity and subsurface damage of hard-brittle materials in ultra-precision manufacturing.

Bidirectional Gated Recurrent Deep Learning Neural Networks for Smart Acoustic Emission Sensing of Natural Fiber–Reinforced Polymer Composite Machining Process

Abstract Natural fiber–reinforced polymer (NFRP) composites are increasingly considered in the industry for creating environmentally benign product alternatives. The complex structure of the fibers and their random distribution within the matrix basis impede the machinability of NFRP composites as well as the resulting product quality. This article investigates a smart process monitoring approach that employs acoustic emission (AE)—elastic waves sourced from various plastic deformation and fracture mechanisms—to characterize the variations in the NFRP machining process. The state-of-the-art analytic tools are incapable of handling the transient dynamic patterns with long-term correlations and bursts in AE and how process conditions and the underlying material removal mechanisms affect these patterns. To address this gap, we investigated two types of the bidirectional gated recurrent deep learning neural network (BD-GRNN) models, viz., bidirectional long short-term memory and bidirectional gated recurrent unit to predict the process conditions based on dynamic AE patterns. The models are tested on the AE signals gathered from orthogonal cutting experiments on NFRP samples performed at six different cutting speeds and three fiber orientations. The results from the experimental study suggest that BD-GRNNs can correctly predict (around 87 % accuracy) the cutting conditions based on the extracted temporal-spectral features of AE signals.

Smart machining: Monitoring of CFRP milling using AE and IR

In aerospace industry, polymers reinforced with carbon fibre offer several advantages, such as weight/strength ratio and corrosion resistance. However, the manufacturing process is complex, especially the machining of composite materials, due to their specific properties and characteristics. The detection and prediction of surface finishing and occurrence of defects during manufacturing using non-destructive techniques is industrially useful, in terms of fomenting automated manufacturing systems to increase productivity and quality control. Acoustic emission signal processing is being successful in mechanical tests for determining material defects, more recently used as a method for manufacturing evaluation of machined parts. This paper focused in the machining process of CFRP plate, in terms of surface finishing evaluation with comprehension of process phenomenology using analyses of temperature and acoustic emission signal features. The aim of this paper is to show the possibility of online monitoring of the cutting process and to understand mechanism behind variables of control, with comparisons of different milling parameters and focusing in their impacts in acoustic emission signals and surface finishing, with suggestions of evaluation and prediction methods of machined surface quality using mainly acoustic emission signals.

Monitoring of material-removal mechanism in micro-electrical discharge machining by pulse classification and acoustic emission signals

Micro-electrical discharge machining is a stochastic process where the interaction between the materials and the process parameters are difficult to understand. Monitoring of the process becomes necessary to achieve the dimensional accuracy of the micro-featured components. Although thermo-mechanical erosion is the most accepted material-removal mechanism, it fails to explain the material removal with very short pulse duration. Alternative postulate like electrostatic force-induced stress yielding provides a stronger argument, rising ambiguity over the material-removal process in the micro-electrical discharge machining regime. In this work, it was found that the stress waves released from the material during micro-electrical discharge-machining process indicate material removal by mechanical deformation and fracture mechanism. These stress waves were captured using the acoustic emission sensor. The discharge pulses were captured by voltage measurement and classified using voltage gradient and machining time duration into three major categories, open pulse, normal pulse and arc pulse. The acoustic emission signal features were extracted and identified by time–frequency–energy distribution analysis. A feed-forward back-propagation neural network mapping of the pulse instances was performed with the obtained acoustic emission signature. The time–frequency–energy distribution analysis of the acoustic emission and the scanning electron microscope images of the craters provide conclusive evidence that the material is removed by mechanical stress and fracture. The feed-forward back-propagation network model was trained to predict the discharge categories of the pulse instances with AE signal inputs which can be used for monitoring the material-removal mechanism in micro-electrical discharge machining operation.

Multiscale acoustic emission of C/SiC mini-composites and damage identification using pattern recognition

Abstract In this paper, multiscale acoustic emission (AE) signal analysis was applied to acoustic emission data processing to classify the AE signals produced during the tensile process of C/SiC mini-composites. An established unsupervised clustering algorithm was provided to classify an unknown set of AE data into reasonable classes. In order to correctly match the obtained classes of the AE signals with the damage mode of the sample, three scales of materials were involved. Single fiber tensile test and fiber bundle tensile test were firstly performed to achieve the characteristics of AE signal of fiber fracture. Parameter analysis and waveform analysis were added to extract the different features of each class of signals in the In-situ tensile test of C/SiC mini-composite. The change of strain field on the sample surface analyzed by DIC (Digital Image Correlation) revealed the corresponding relationship between matrix cracking and AE signals. Microscopic examinationwas used to correlate the clusters to the damage mode. By analyzing the evolution process of signal activation for each class against the load, it also provided a reliable basis for the correlation between the obtained classes of the AE signals and the damage mechanism of the material.

The research on propagation characteristics of acoustic emission signals in stiffened plates based on the multipath propagation model

Mechanical equipment with the stiffener has a strong interference with the propagation of acoustic emission (AE) signals from faults, reducing the accuracy of fault detection. This paper conducts an in-depth study of the interaction between AE signals and the stiffener. The installation constraints, that can separate the direct signal, signals scattered from the stiffener and signals reflected from the boundary in the time domain, for sensors are deduced based on the multipath propagation model of AE signals in the stiffened plate. On this basis, the scattering characteristics of AE signals with different frequencies in different height stiffened plates are predicted by simulations. Moreover, the reflection and transmission coefficients are calculated to quantify the scattering characteristics. The results show that the signal, undergoing a “T-shaped” transformation at the stiffener, generates various modes, among which the transmission signal accounted for the largest proportion. In addition, experiments are performed to verify the numerical simulations, and the results are in good agreement with the numerical simulations. This work clarifies the propagation characteristics of AE signals in stiffened plates, and the research can optimize the spatial arrangement for sensors.

Thermodynamic Approach for the Identification of Instability in the Wood Using Acoustic Emission Technology

In order to monitor the crack growth of the wood material better and reduce failure risks, this paper studied the attenuation characteristics of acoustic emission signals in wood through pencil lead breaking (PLB) tests, in the aim of estimating the true amplitude value of the acoustic emission source signal. The tensile test of the double cantilever beam (DCB) specimens was used to simulate the crack tip growth within wood material, monitoring acoustic activity and location of crack tips within wood material using acoustic emission technology and digital image correlation (DIC). Results showed that the attenuation degree of acoustic emission signals increased exponentially as the propagation distance increased, and the relationship between relative amplitude attenuation rate and the propagation distance of the acoustic emission signal was established by the regression method, which provides the input parameters for the establishment of the crack instability prediction model in the next step. Based on a thermodynamic approach, a theoretical model for predicting crack instability was established, and the model was verified by DCB tests. The model uses acoustic emission parameters as the basis for judging whether the crack is instable. It provides theoretical support for the application of acoustic emission technology in wood health monitoring.

Damage monitoring of carbon fiber reinforced silicon carbide composites under random vibration environment by acoustic emission technology

Carbon fiber-reinforced silicon carbide (C/SiC) composites are widely used in high-temperature thermo-structural applications. They are subjected to extreme loading conditions, such as random vibrations, which are likely to damage the structure. Structural micro-damage identification during vibration is very difficult, owing to the randomness of the environmental vibration and the complicated response it causes in structures. This study aims to determine a method for monitoring the damage properties of a C/SiC structure under a random vibration environment using acoustic emission (AE) technology. First, a pencil break experiment is conducted to verify the feasibility of the AE technology. Then, an AE monitoring experiment of the structural damage in a vibration environment is systematically conducted. Two types of experiments are designed for simulating the damage formation process inside the structure. In addition, the parameter characteristics of typical AE signals in the random vibration test are analyzed, and the relationships between the AE signal parameters and vibration loading are obtained. Lastly, the different stages of material damage development and damage types in each stage are provided to reveal the damage evolution processes of C/SiC composites. The results indicate that AE technology can be effectively applied to investigate the damage behaviors of C/SiC composites in random vibration environments.

Investigation on the effect of EDM process variables and environments on acoustic emission signals

The performance of electrical discharge machining (EDM) primarily depends on the spark quality generated in the inter-electrode gap (IEG) between the tool and workpiece. A method for obtaining accurate information about the spark gap is required to effectively monitor the EDM process. The rise and fall of thermal energy in the discharge zone at a rapid rate during the dielectric breakdown produces high-pressure shock waves. This work explores the suitability of using acoustic emission (AE) generated from these shock waves and the elastic AE waves released on the workpiece due to the induced stress to monitor the performance and spark gap in EDM. The information content of the AE signals acquired at various machining conditions was extracted using AE RMS, spectral energy and peak amplitude. These features were able to well discriminate the machining condition, tool material, workpiece material, flushing pressure, current density, the initial surface roughness of the tool. Additionally, the AE signal features had a good and consistent correlation with the performance parameters, including material removal rate, surface roughness (Ra and Rq) and tool wear. The findings lay the groundwork to develop an effective, non-intrusive in-situ AE-monitoring system for performance and IEG condition in EDM.