Search

Partial Discharges (PDs) are a significant factor in reducing the insulation life of traction transformers. In recent years, the Acoustic Emission (AE) method has become the most advanced method for detecting PD signals in transformers. The AE method utilizes AE sensors placed on the transformer tank to detect ultrasonic signals emitted by PD and determine the Time Of Arrival (TOA) of the head wave. The windings and cores of a traction transformer consist mainly of metal, which greatly affects the propagation of PD ultrasonic waves. This paper establishes a 110 kV "pressure acoustic, transient" physical field model of the traction transformer with dimensions of 4.63 × 1.48 × 2.84 m3. The model is used to carry out the PD pressure acoustic physical field simulation study of the traction transformer, to clarify the physical characteristics of the ultrasound of the PD defects, and to establish observation points on the transformer tanks to receive ultrasonic time-domain waveforms for PD detection. The simulation results indicate that PD ultrasonic waves exhibit complex propagation characteristics, including reflection, refraction, and reverberation, as they pass through the windings and cores to the observation points. The TOA of the head wave in the ultrasound time-domain waveform is indicated by the first maximum value of the wave crest line. Finally, this paper proposes a multi-level localization method based on the AE method to determine which winding generates the PD in the large-scale traction transformer using only four dynamically moving observation points. [ABSTRACT FROM AUTHOR]

Softness is one of the essential properties of hygiene tissue products. Reliably measuring it is of utmost importance to ensure the balance between customer expectations and cost-effective tissue production. This study presents a method for assessing softness by analyzing acoustic emissions produced while tearing a tissue specimen. The aim was to train neural network models using the corrected results of human panel tests as the ground truth labels and to predict the tissue softness in two- and three-class recognition tasks. We also investigate the possibility of predicting some production parameters related to the softness property. The results proved that tissue softness and production parameters could be reliably estimated only by the tearing noise.

The paper reports the results of a comparative assessment concerned with the effectiveness of identifying the basic forms of partial discharges (PD) measured by the acoustic emission technique (AE), carried out by application of selected machine learning methods. As part of the re-search, the identification involved AE signals registered in laboratory conditions for eight basic classes of PDs that occur in paper-oil insulation systems of high-voltage power equipment. On the basis of acoustic signals emitted by PDs and by application of the frequency descriptor that took the form of a signal power density spectrum (PSD), the assessment involved the possibility of identifying individual types of PD by the analyzed classification algorithms. As part of the research, the results obtained with the use of five independent classification mechanisms were analyzed, namely: k-Nearest Neighbors method (kNN), Naive Bayes Classification, Support Vector Machine (SVM), Random Forests and Probabilistic Neural Network (PNN). The best results were achieved using the SVM classification tuned with polynomial core, which obtained 100% accuracy. Similar results were achieved with the kNN classifier. Random Forests and Naïve Bayes obtained high accuracy over 97%. Throughout the study, identification algorithms with the highest effectiveness in identifying specific forms of PD were established. [ABSTRACT FROM AUTHOR]

Identifying precursor information to rock failure is key to rock dynamic disaster warning. To solve the problem that a single in-situ monitoring method cannot accurately identify the precursors to rock failure, this paper combined a digital image correlation method, thermal infrared radiation and acoustic emission technology to conduct a multi-physical field joint monitoring experiment of granite under three-point bending. The information about strain, thermal infrared and acoustic emission of the rock brittle failure process could be obtained, and the variations in multi-physical field indices of the rock brittle failure process were analysed. Based on the theory of critical slowing-down, the study of the multi-physical field effects of critical slowing-down characteristics in the rock failure process, and further exploration of the precursor characteristics of the brittle failure of rock were undertaken. The results indicate that the strain, infrared, and acoustic emission parameters show sudden changes during brittle failure of granite. The lag step size has little effect on the variance of changes in multi-physical field parameters and exerts a similar influence on the changes in the autocorrelation coefficient curve. The degree of influence of the window length on the variance and autocorrelation coefficient curves of multi-physical field parameters is as follows: infrared field > strain field > acoustic emission field. Compared with the autocorrelation coefficient, the variance parameter is more universal and is better when the critical slowing-down theory is used to investigate the characteristics of multi-physical fields. The four parameters of the strain field variance, infrared field variance, the variance and autocorrelation coefficient for acoustic emission field increase sharply before fracture, representing precursor information to the brittle failure of granite. The four parameters can be used as disaster warning indicators in rock. Multi-mode joint monitoring and a comprehensive analysis of multi-physical information are beneficial to accurately determine the precursor points of rock failure disaster. [ABSTRACT FROM AUTHOR]

Softness is one of the essential properties of hygiene tissue products. Reliably measuring it is of utmost importance to ensure the balance between customer expectations and cost-effective tissue production. This study presents a method for assessing softness by analyzing acoustic emissions produced while tearing a tissue specimen. The aim was to train neural network models using the corrected results of human panel tests as the ground truth labels and to predict the tissue softness in two- and three-class recognition tasks. We also investigate the possibility of predicting some production parameters related to the softness property. The results proved that tissue softness and production parameters could be reliably estimated only by the tearing noise. [ABSTRACT FROM AUTHOR]

Crack inclination and material heterogeneity have important effects on the meso-mechanical mechanism and macroscopic mechanical behavior of rock-like materials. In order to study the failure characteristics of shotcrete body during the process of using shotcrete bolt mesh support in the deep fractured rock mass of Lannigou Gold Mine, this paper combined the Digital Image Processing Technique (DIP) and RFPA2D (Rock Failure Process Analysis System) to establish a real meso-structure numerical model of concrete with different inclination angle cracks, simulating its crack propagation law and failure process, and studied the influence of crack geometry distribution and meso-heterogeneity on the effect of concrete structure. The findings reveal that the crack inclination angle has a substantial impact on concrete materials' compressive strength and elastic modulus, and both of them all show a nonlinear increase with the increase of crack angle; Because of the inhomogeneity of the materials, the inclination and propagation pathways of wing cracks are random, and the aggregate inhibits crack initiation and propagation. The wing crack's initiation position moves closer to the tip as the crack inclination angle increases, and the length gets shorter; Acoustic emission(AE) evolution characteristics are similar in samples with varying dip angles. In the early stages of loading, the AE energy is minimal, and increases rapidly when approaching the peak stress. The fractal dimension was used to describe the damage evolution process inside the material, and a damage variable index (ω) based on the fractal theory was proposed. The more the ω, the greater the material's degree of degradation. The proposed index provided a new method for quantitative study of the damage evolution characteristics of rock-like materials. It has guiding significance for the research on the stability of wet shotcrete in the deep fractured rock mass of Lannigou Gold Mine. [ABSTRACT FROM AUTHOR]

The article presents the discussion on Insight's current awareness service covering British and international publications, conference proceedings, and multimedia products.

This research aimed to investigate the accuracy of picking of P-wave arrival times in rock fracture acoustic emission signals. In order to simulate the mining scenario, Gaussian white noise and pulse noise were added to the data collected in the laboratory. Complete ensemble empirical mode decomposition with adaptive noise + Wavelet (CEEMDAN + Wavelet) was improved in this paper, where the Spearman rank correlation coefficient was adopted to effectively select intrinsic mode functions for denoising which retained the inherent characteristics of the rock fracture signal. The absolute amplitude and energy change rate of the envelope signal, calculated based on the Hilbert transform, were used as the input of the short term average/long term average (STA/LTA) normalization algorithm to pickup the P-wave arrival time. The reliability of this method was tested on 30 groups of recorded rock fracture laboratory data and 60 groups of added noise data. Taking the manual pickup results as the standard, the errors of CEEMDAN + Wavelet + STA/LTA + AIC (Akaike information criterion) method with the absolute amplitude of the signal as the input are all within 10 ms, and 86.67% of the results are within 5 ms. The method proposed in this paper effectively addressing the issue of false pickup caused by the sensitivity of AIC and traditional STA/LTA method for strong noise, and achieving relatively high accuracy and stability in processing low signal-to-noise ratio signals. This work contributes to monitor microscopic changes in rock bodies and is of great significance for the prediction and monitoring of geological disasters. [ABSTRACT FROM AUTHOR]

In the petroleum and coal industries, digital image technology and acoustic emission technology are employed to study rock properties, but both exhibit flaws during data processing. Digital image technology is vulnerable to interference from fractures and scaling, leading to potential loss of image data; while acoustic emission technology is not hindered by these issues, noise from rock destruction can interfere with the electrical signals, causing errors. The monitoring errors of these techniques can undermine the effectiveness of rock damage analysis. To address this issue, this paper focuses on the restoration of image data acquired through digital image technology, leveraging deep learning techniques, and using soft and hard rocks made of similar materials as research subjects, an improved Incremental Transformer image algorithm is employed to repair distorted or missing strain nephograms during uniaxial compression experiments. The concrete implementation entails using a comprehensive training set of strain nephograms derived from digital image technology, fabricating masks for absent image segments, and predicting strain nephograms with full strain detail. Additionally, we adopt deep separable convolutional networks to optimize the algorithm's operational efficiency. Based on this, the analysis of rock damage is conducted using the repaired strain nephograms, achieving a closer correlation with the actual physical processes of rock damage compared to conventional digital image technology and acoustic emission techniques. The improved incremental Transformer algorithm presented in this paper will contribute to enhancing the efficiency of digital image technology in the realm of rock damage, saving time and money, and offering an innovative approach to traditional rock damage analysis. [ABSTRACT FROM AUTHOR]

Monitoring the condition of the grinding wheel in real-time during the grinding process is crucial as it directly impacts the precision and quality of the workpiece. Deep learning technology plays a vital role in analyzing the changes in sensor signals and identifying grinding wheel wear during the grinding process. Therefore, this paper innovatively proposes a grinding wheel wear recognition method based on Variational Mode Decomposition (VMD) denoising and Aquila Optimizer—Convolutional Neural Network—Long Short-Term Memory (AO-CNN-LSTM). The paper utilizes Acoustic Emission (AE) signals generated during grinding to identify the condition of the grinding wheel. To address noise interference, the study introduces the VMD algorithm for denoising the sample dataset, enhancing the effectiveness of neural network training. Subsequently, the dataset is fed into the designed Convolutional Neural Network—Long Short-Term Memory (CNN-LSTM) structure with AO-optimized parameters. Experimental results demonstrate that this method achieves high accuracy and performance. [ABSTRACT FROM AUTHOR]

This paper is dedicated to the memory of Dr. Miklós Iványi, who instilled in the authors an appreciation for experimental investigations, which are foundational to understanding material and structural behavior. Timber-concrete composite structures are increasingly adopted for new buildings due to their favorable sustainability parameters and the increased availability of cross laminated timber. For larger spans, however, solid timber floors lead to higher timber volumes and the use of glulam beams may become necessary for a more efficient use of wood. This paper presents laboratory tests of glulam-concrete composite beams and is the first in a series of two papers on investigating the associated failure mechanisms. Three full-scale glulam-concrete beam specimens were studied. The glulam and concrete are monolithically interconnected using a continuous layer of adhesive. Shear reinforcement was added to the glulam beams to allow for failure mode control. Static load tests to failure were conducted along with acoustic emission monitoring to track the progression of the failure. The results indicate that the shear reinforcement of the glulam layer affects the load capacity of the composite beam through shifting the failure from a shear to a tension failure mode. Similar glulam-concrete beams can enable larger span applications for buildings and bridges while maintaining an attractive sustainability performance. [ABSTRACT FROM AUTHOR]

Bolted joints are widely used in various engineering structures. The bolted joint may become loosening under long-term oscillating load, and cause reciprocating friction between the contact interfaces. Acoustic emission (AE) is a phenomenon of rapid release of transient elastic waves, which will be generated continuously during the reciprocating friction. The friction conditions will affect the characteristics of the contact interface and the related AE signals. Therefore, analyzing the quantitative relationship between friction conditions and AE signal is significant for applying AE technique in bolt loosening monitoring. However, researches on the relationship between AE Vrms and friction operating parameters are mostly focused on rotating machineries currently, whether the obtained conclusions are suitable for bolted joints is not clear. This paper finds that the commonly used quantitative relationship between the AE Vrms and friction operating parameters is not suitable for bolted joint structures by comparing the theoretical and experimental AE Vrms. The relationship is then modified through exponential parameter fitting and verified using the same experiments in this paper. The results show that the modified equation can accurately describe the quantitative relationship between the AE Vrms and the friction operating parameters, thus revealing the mechanism of acoustic emission signals generated during the gross-slip. [ABSTRACT FROM AUTHOR]

Deep rock are often in a true triaxial stress state. Studying the impacts of varying unloading speeds on their strain energy (SE) density is highly significant for predicting rock stability. Through true triaxial unloading principal stress experiments and true triaxial stress equilibrium unloading experiments on sandstone, this paper proposes a method to compute the SE density in a true triaxial compressive unloading principal stress test. This method aims to analyze the SE variation in rocks under the action of true triaxial unloading principal stresses. Acoustic emission is used to verify the correctness of the SE density calculation method in this paper. This study found that: (1) Unloading in one principal stress direction causes the SE density to rise in the other principal stress directions. This rise in SE, depending on its reversibility, can be categorized into elastic and dissipated SE. (2)When unloading principal stresses, the released elastic SE density in the unloading direction is influence by the stress path and rate. (3) The higher the unloading speed will leads to greater increases in the input SE density, elastic SE density, and dissipative SE density in the other principal stress directions. (4) The dissipated SE generated under true triaxial compression by unloading the principal stress is positively correlated with the damage to the rock; with an increase in unloading rate, there is a corresponding increase in the formation of cracks after unloading. (5) Utilizing the stress balance unloading test, we propose a calculation method for SE density in true triaxial unloading principal stress tests. [ABSTRACT FROM AUTHOR]

Purpose: Based on the micro-electro-mechanical system (MEMS) technology, acoustic emission sensors have gained popularity owing to their small size, consistency, affordability and easy integration. This study aims to provide direction for the advancement of MEMS acoustic emission sensors and predict their future potential for structural health detection of microprecision instruments. Design/methodology/approach: This paper summarizes the recent research progress of three MEMS acoustic emission sensors, compares their individual strengths and weaknesses, analyzes their research focus and predicts their development trend in the future. Findings: Piezoresistive, piezoelectric and capacitive MEMS acoustic emission sensors are the three main streams of MEMS acoustic emission sensors, which have their own advantages and disadvantages. The existing research has not been applied in practice, and MEMS acoustic emission sensor still needs further research in the aspects of wide frequency/high sensitivity, good robustness and integration with complementary metal oxide semiconductor. MEMS acoustic emission sensor has great development potential. Originality/value: In this paper, the existing research achievements of MEMS acoustic emission sensors are described systematically, and the further development direction of MEMS acoustic emission sensors in the future research field is pointed out. It provides an important reference value for the actual weak acoustic emission signal detection in narrow structures. [ABSTRACT FROM AUTHOR]

Aiming at the problem of fault diagnosis and classification of rolling bearing and gear of gearboxes, a novel method based on matrix distance features of Gramian angular field (GAF) image is proposed based on sliding window compressible GAF transformation. The method converts the one-dimensional fault signal into a two-dimensional feature matrix and constructs the discrimination matrix of each fault category by establishing the mean value of the feature matrix of a priori samples. For the new sampled signal, after converting it into a two-dimensional feature matrix, the feature matrix is obtained. The fault classification is carried out by using the matrix distance between feature matrix and the discrimination matrix of each category. The method is validated by the test data of Case Western Reserve University and the acoustic emission data from a gearbox test bench. The classification accuracy is 99.17% and 95.71%, which presented the feasibility and effectiveness of the novel method proposed in this paper. [ABSTRACT FROM AUTHOR]

Ignition advance angle is one of the important factors affecting the performance of the engine, when it occurs abnormally will make the engine power and economy worse, and even cause serious damage to the engine. Therefore, it is very necessary to recognize the abnormal ignition advance angle of the engine. However, the engine system is closed and has a complex structure, which makes traditional diagnostic methods difficult. This paper proposes an intelligent identification method based on acoustic emission (AE) signals, which collects the AE signals from the engine surface and divides their spectra into equal parts, and selects the frequency bands with high contribution to the classification based on the minimum distance method to construct feature maps, which is used as the input to the convolutional neural network (CNN). The extracted frequency band features of this method can better characterize the AE signals, and the constructed feature maps make the fault information more obvious. Experiments show that the accuracy of this method for abnormal ignition advance angle under normal operating conditions of piston aero-engine is 100%, which is better than the traditional methods. In addition, the recognition accuracies under the other two operating conditions are 99.75% and 98.5%, respectively, indicating that the method has a certain universality. [ABSTRACT FROM AUTHOR]

In this paper, preliminary studies on the failure analysis of hybrid composite materials utilizing acoustic emission and machine learning are presented. The main purpose of this study was to analyze the possibilities of using machine learning techniques as a way to better cluster the data obtained from acoustic emission. In this paper, we focus on data preparation, feature extraction (Laplacian score), determination of cluster number (Caliński–Harabasz, Silhouette, and Davies–Bouldin), and testing three clustering techniques, namely K-means, fuzzy C-means, and spectral clustering. The dataset was obtained by testing fiber metal laminates—composites consisting of metal and composite layers. Two experimental tests were realized on pre-cracked rectangular specimens—one with loading in mode I and one with loading in mode II (DCB—double cantilever beam and ENF—end-notch flexural test). Elastic waves were recorded during these tests via an acoustic emission system. Preliminary studies show that the proposed method can be used successfully to cluster data obtained in this way. The obtained dataset was split into 3 clusters (for the ENF test) and 5 clusters (DCB test). In the next stages of the research campaign, based on the presented results, we intend to change the approach to semi-supervised by running additional single-cause damage tests to enhance the achieved results and enable easier damage recognition. [ABSTRACT FROM AUTHOR]

Wind power is growing rapidly as a green and clean energy source. As the core part of a wind turbine, the blades are subjected to enormous stress in harsh environments over a long period of time and are therefore extremely susceptible to damage, while at the same time, they are costly, so it is important to monitor their damage in a timely manner. This paper is based on the detection of blade damage using acoustic emission signals, which can detect early minor damage and internal damage to the blades. Instead of conventional piezoelectric sensors, we use fiber optic gratings as sensing units, which have the advantage of small size and corrosion resistance. Furthermore, the sensitivity of the system is doubled by replacing the conventional FBG (fiber Bragg grating) with a π-phase-shifted FBG. For the noise problem existing in the system, this paper combines the traditional WPD (wavelet packet decomposition) denoising method with EMD (empirical mode decomposition) to achieve a better noise reduction effect. Finally, small wind turbine blades are used in the experiment and their acoustic emission signals with different damage are collected for feature analysis, which sets the stage for the subsequent detection of different damage degrees and types. [ABSTRACT FROM AUTHOR]

Due to the extremely low permeability of shale reservoirs, large-scale reservoir fracturing is required. Hydraulic fracturing is one of the most important technologies in shale gas exploration and development. In this paper, the acoustic emission energy and the number of location and fracture surface morphology of specimens before and after fracture are studied through hydraulic sand fracturing test. The test results show that: (1) the energy ratio obtained during hydraulic fracturing without proppant is the smallest, and increasing the confining pressure, as well as reducing the displacement and viscosity of the fracturing fluid will cause the energy ratio to decrease. From the perspective of acoustic emission energy, the proppant play an important role in the generation of fractures during hydraulic sand fracturing; (2) when the confining pressure increases, the number of shale specimens before and after rupture is the largest, but the total number of locating events is smaller than the sanding ratio increased; there is no proppant hydraulic fracturing, the number of specimens before and after the rupture is the largest. And the total number reached the minimum, indicating that the proppant can play an important role in the hydraulic sand fracturing test; (3) the sand is relatively large, the specific surface and standard deviation both reach the maximum, indicating that the fracture surface roughness is the largest under the test condition, and the fracturing effect is the best, but the specific surface and standard deviation are the minimum when fracturing without proppant, so indicating that the fracture surface fracturing effect is the worst at this time. [ABSTRACT FROM AUTHOR]

Wound rotor induction machine (WRIM) has been extensively used in different applications such as medium-power wind turbines and traction systems. Since these machines work under harsh and difficult conditions, condition monitoring of such systems is crucial. Different electrical and mechanical signatures of machines were used for electrical and mechanical fault detection in electrical machines such as vibration, acoustic emission, stray flux, and stator current signature. In recent years, stator current signature analysis due to simplicity, cost-effectiveness, and availability has been considered for fault detection process in comparison with previous conventional methods such as acoustic and vibration. In this paper, a high-resolution technique based on the chirp-Z transform is used for rotor asymmetry fault (RAF) detection in induction machines through stator current signature analysis. In this regard, the Teager-Kaiser energy operator (TKEO) technique for demodulation fault characteristic frequency is used as a pre-processing stage to avoid leakage of the supply frequency. The method has better accuracy due to better spectral resolution and resolvability. Furthermore, computational complexity in the proposed method will be reduced in comparison to the previous conventional ones which have used the Fast Fourier transform (FFT). The proposed technique is tested through synthetic and experimental stator current of WRIM in healthy and faulty conditions with different rotational speeds and fault severities. The results show the validity of the proposed method in rotor asymmetry fault detection through the stator current signature of WRIM. [ABSTRACT FROM AUTHOR]

Investigating the correlation between acoustic emission (AE) parameters and damage mechanisms in rock mechanics can help understand rock damage evolution under loading and provide a theoretical basis for engineering support and safety detection. Therefore, this paper presents experimental works on the correlation between AE and failure mechanisms of rock mass under uniaxial compression stress, with the aim of capturing the damage evolution leading to a new damage constitutive model. The experimental results indicate that the uniaxial compression process of shale can be divided into four stages according to AE characteristics. AE signals are minimal during the crack compaction and elastic stages. The crack initiation strength σci, which is approximately 55% of the uniaxial compressive strength, is identified when the cumulative AE counts and damage factor begin to increase slowly. When axial stress reaches the damage strength σcd, which is approximately 80% of the uniaxial compressive strength, a significant number of AE signals are generated. AE phenomena can be observed during the unstable crack development and post-crack stages. Considering the initial damage to the rock, the damage factor D initially decreases and then increases with increasing cumulative ring-down counts rather than exhibiting a monotonic increase. The damage factor D is proportional to the cumulative AE counts N in the stage before rock failure. [ABSTRACT FROM AUTHOR]

Rock cores retrieved from deep rock masses may be permanently damaged on account of the stress release occurring during the drilling process. The quantification of core damage is important for accurate evaluation of the rock strength at depth. This paper presents a laboratory simulation of the core drilling process under high in situ stress conditions. The study aims to quantitatively evaluate sampling damage from both macro and micro perspectives using mechanics tests and microscopic observations. The observed decrease in core specimen integrity with increasing sampling confining pressure is in line with practical engineering findings, thus validating the experimental method utilized in this paper. The test results show that the porosity of the core increases and P-wave velocity decreases as the sampling confining pressure increases, which indicates that the structure of the core is significantly changed by the sampling damage. The stress–strain curve exhibited increased nonlinearity and acoustic emission events at the initial stage of loading, indicating an increase in sampling damage with rising sampling pressure. The uniaxial compressive strength and Brazilian tensile strength of the cores drilled at 40 MPa are reduced by about 21% and 28%, respectively, compared to the undamaged rock, indicating that the effect of core damage on the rock strength cannot be ignored. Microstructural observations further reveal that the crack density of the cores drilled at 40 MPa is four times higher than that of the intact rock. Additionally, the development of microcracks shows obvious directionality, with microcracks preferentially developing perpendicular to the drilling direction. Stress path analysis of the cores indicates that the sampling damage may be primarily caused by tensile stresses. This study provides a better understanding of the mechanisms underlying sampling damage and core disking. [ABSTRACT FROM AUTHOR]

Cavitation is a detrimental phenomenon in hydraulic machinery, adversely impacting its performance, inducing vibration and noise, and leading to corrosion damage of overflow components. Centrifugal pump internal cavitation will lead to severe vibration and noise, and not only will the performance of hydraulic machinery be adversely affected but the impact generated by the collapse of the vacuole will also cause damage to the impeller wall structure, seriously affecting the safety of the equipment's operation. To prevent the generation and development of internal cavitation in centrifugal pumps, to prevent the hydraulic machinery from being in a state of cavitation for a long time, to avoid the failure of the unit, and to realize the predictive maintenance of centrifugal pumps, therefore, it is of great significance to research the methods for monitoring the cavitation of hydraulic machinery and the methods for suppressing the cavitation. This paper comprehensively describes the centrifugal pump cavitation mechanism and associated hazards. It also discusses the current state of centrifugal pump cavitation monitoring methods, including commonly used approaches such as the flow-head method, high-speed photography, pressure pulsation method, acoustic emission method, and vibration method. A comparative analysis of these methods is presented. Additionally, the paper explores signal characterization methods for centrifugal pump cavitation, including time-domain feature extraction, frequency-domain feature extraction, and time–frequency-domain feature extraction. The current research status is elaborated upon. Moreover, the paper presents methods to mitigate cavitation and prevent its occurrence. Finally, it summarizes the ongoing research on identifying and determining the cavitation state in centrifugal pumps and offers insights into future research directions. [ABSTRACT FROM AUTHOR]

Recent optical time-resolved experiments on single supported nano-objects (gold nanodisks with various diameter over thickness ratios) have demonstrated a marked enhancement of their vibrational quality factors for specific nano-object morphologies, resulting from the near-suppression of radiative vibrational damping associated with the emission of acoustic waves in the nano-object environment. This paper clarifies the origin of this phenomenon, which is ascribed to the creation of a "quasi-bound state in the continuum" vibrational mode by radiative coupling between two nano-object modes whose frequencies become close for specific nano-object shapes. The symmetry breaking induced by the presence of a substrate, which limits nanodisk acoustic emission to a half-space, is shown to play an essential role in enabling such radiative coupling. The impact of the acoustic mismatch between the nano-object and the substrate is explored, and it is shown that a moderate acoustic mismatch can still enable the creation of near-localized vibrational modes with high radiative quality factors, while allowing radiative coupling effects to occur over a broad range of nano-object geometries. Although this paper focuses on the situation of a substrate-supported gold nanodisk, which has already been the object of experimental investigations, the effects that it describes are general and constitute a promising approach to enhance the vibrational quality factors of nano-objects. [ABSTRACT FROM AUTHOR]

Supporting and controlling rockburst hazards is a great challenge for deep rock engineering. A new cable, the negative Poisson's ratio (NPR) cable, exhibits excellent mechanical properties, including high energy absorption and resilience to impacts. To investigate its control effect on rockburst, a series of true triaxial strainburst experiments were conducted on sandstone specimens under different anchoring conditions (no support, ordinary support, NPR cable support). The model NPR cables were developed based on similar principles. In addition, the acoustic emission response and fragmentation characteristics were analysed. The experimental results indicate that the NPR cables are capable of co-deforming with the rock and absorbing energy, increasing rock strength and promoting internal rock tensile fracture. The rapid response of the NPR cables during rockbursts provided effective support, exerted better impact resistance and significantly reduced the mass and fractal dimension of the ejected fragments. Thus, NPR cables can reduce kinetic energy release and effectively control rockburst hazards compared to ordinary cables. The aim of this paper is to provide a reference for the design of rockburst support in engineering. [ABSTRACT FROM AUTHOR]

A novel machine learning-based model is introduced in this research paper to forecast tool wear using acoustic emission (AE) signals. Adaptive boosting (AdaBoost) and a sophisticated feature engineering strategy are employed by the model to enhance the precision of its predictions. The proposed model, Machine Learning Tool Wear Prediction (MLTWP), analyzes AE signals generated during machining operations to distinguish between healthy and worn-out tool conditions with remarkable accuracy. The crux of our approach consists of meticulously eliminating and enhancing the temporal and spectral characteristics of the AE signals. We employ the Kolmogorov-Smirnov test to identify the most valuable classification features. We implemented AdaBoost with the objective of progressively enhancing a set of weak classifiers' ability to identify instances that were incorrectly classified in previous iterations. Utilizing this method increases the model's sensitivity to minute variations in tool wear conditions and its overall classification precision. The MLTWP model underwent extensive testing on a benchmark data set comprising 25,304 AE signal records from cutting mill tools, using a training tool split of 9,989 worn (positive) and 8,990 benign (negative) instances. The results of our experiments, validated through four-fold cross-validation, indicate that the MLTWP model exhibits superior performance compared to the existing Tool Wear Prediction using Acoustic Emission Signals (TWPAE) model. To provide greater specificity, the MLTWP exhibited the following metrics on average: precision (92.2%), specificity (91.38%), sensitivity (90.42%), accuracy (90.9%), and MCC (81.72%). The fact that these metrics exhibit significant improvement over those of the TWPAE model demonstrates that our method of feature engineering and adaptive boosting is effective at precisely predicting tool wear. This research not only advances the existing understanding of tool wear prediction but also establishes a robust framework for the implementation of machine learning in manufacturing predictive maintenance. [ABSTRACT FROM AUTHOR]

The wear state of mechanical seal friction pair directly determines the reliability of mechanical seal. In this paper, the mapping mechanism between contact wear response and acoustic emission (AE) signals of friction pair is indicatively proposed, and the relationship between wear frequency and time-averaged wear is explored. First of all, AE sensors were arranged on the Multi-function tribometer Rtec MFT-5000, static and dynamic friction tests were carried out on the contact form of M106K-WC (graphite-cemented carbide) and WC–WC, the AE signals are collected, and the wear amounts of the two groups of friction pairs were measured; then, the friction and wear signals are separated and reprocessed by time–frequency analysis. The results show that the static wear response frequency (SWRF) of M106K-WC is about 70 ± 10 kHz, the SWRF of WC–WC is about 90 ± 10 kHz, and the dynamic wear response frequency (DWRF) of WC–WC is about 175 ± 10 kHz; the root mean square (RMS) values of DWRF amplitudes is positively correlated with the wear amounts. According to the research results, it is inferred that there is a difference between the signal frequency in the quasi-static wear process and the dynamic wear process, there is a great correlation between the wear frequency and the material pair, and the working condition has little influence on the wear frequency. The mapping relationship between AE signal and time-averaged wear of friction pair is revealed. [ABSTRACT FROM AUTHOR]

Acoustic emission (AE) is a non-destructive technique that relies on monitoring naturally occurring sources of high frequency ultrasound in components and structures. Ultrasonic waves propagate in the form of different wave modes—for instance Lamb waves in thin plates, or Rayleigh and P- and S- waves in bulk structures. Those wave modes have different properties, but also contain information regarding the source of the naturally occurring wave. Manually, the wave modes can be recognized by comparing a time–frequency representation of the signal to the dispersion curves expected in the tested object. For analyzing a large number of signals, this manual mode recognition becomes a tedious process. This paper proposes a method to automate the wave mode recognition based on some minimal knowledge of the occurring wave modes. As inputs, only the propagation speed of the possible wave modes and the source position need to be provided along with a limited set of reference wavelets for each wave mode. Cross-correlation of a signal with a reference wavelet of a mode reduces the signal to a limited number of peaks that may delineate the start of the mode. Using other signals from the same event but from different sensors, velocities are calculated for each peak in order to select the peak that corresponds to the arrival of the mode under investigation. To validate the method, a dataset was recorded based on four types of out-of-plane sources: Hsu-Nielsen sources of 0.3 and 0.5 mm, sensor pulse signals and AEs from melting ice. Since the presented dataset was recorded on a plate, the aim of the validation was to recognize the zero-order symmetrical and anti-symmetrical Lamb modes. The results of the proposed mode recognition method applied to this dataset are compared with results from manual mode recognition. For Hsu-Nielsen sources, the succes rate is found to be above 95%. For narrow-band pulsed signals or for AEs from melting ice with a low signal-to-noise ratio, succes rates between 75 and 80% relative to manual mode recognition are reported. [ABSTRACT FROM AUTHOR]

This paper attempts to evaluate the change in the behavior of the acoustic waves associated with flexure cracks developed in rubberized concretes in a subfreezing environment. Seven normal and rubberized concrete mixtures were developed with different compositions. Prism samples from each mixture were tested at two temperatures (25°C and −20°C) under a four-point monotonic flexure test while being monitored via two attached acoustic emission (AE) sensors to collect the emitted AEs till failure. The AE signal characteristics such as signal amplitudes, number of hits, and cumulative signal strength (CSS) were collected and used for three AE parameter-based analyses: b-value, intensity, and rise time–amplitude (RA) analysis. Analyzing the acoustic activity revealed micro- and macrocracks nucleation, which were found to be associated with a noticeable spike in CSS, historic index [H(t)], severity (Sr) values, and a significant dip in the b-values. In addition, cold temperature was found to increase the micro- and macrocracking onset load and time regardless of mixture composition. Besides, mixtures with a lower C/F, less crumb rubber (CR) content, and/or smaller rubber particle size witnessed higher micro- and macrocrack load and time thresholds. Noticeably, the AE signal attenuation effect caused by the high CR content (up to 30%) at 25°C was significantly relieved when samples were tested at −20°C. Three charts were developed to classify the cracking level based on the values of the intensity analysis parameters [H(t) and S] and RA analysis. Practical Applications: Infrastructure failures can cause severe economic losses and fatalities, but luckily they can be avoided through regular inspections with the aid of nondestructive testing and subsequent repairs. Aging structures need more inspections to detect potential deficiencies, whereas newly constructed ones can safely undergo fewer inspections and preserve resources. Data from nondestructive testing programs can optimize inspection schedules. When it comes to hard-to-reach structures in extreme weather, acoustic emission (AE) has the potential to be a more suitable nondestructive testing technique over other conventional methods. Some concerns were raised regarding the effectiveness of the AE technique for applications involving novel construction materials such as rubberized concrete, because rubber particles have noticeable acoustic absorption capacities that may affect the parameters of the AE waves and impact the posttesting analysis. Another concern was the influence of cold temperature on the AE wave characteristics due to the change in concrete microstructure at low temperatures. This study aimed at addressing these concerns by utilizing AE analysis to highlight the onset of micro- or macrocracks in rubberized concrete mixtures exposed to cold temperatures. Three user-friendly charts are presented that can advise on inspection decisions based on whether deterioration has reached a certain level. [ABSTRACT FROM AUTHOR]

Structural elements undergo multiple levels of damage at various locations due to environments and critical loading conditions. The level of damage and its location can be predicted using acoustic emission (AE) waveforms that are captured from the generation of inherent microcracks. Existing AE methods are reliant on the feature selection of the captured waveforms and may be subjective in nature. To automate this process, this paper proposes a deep-learning model to predict the damage severity and its expected location using AE waveforms. The model is based on a densely connected convolutional neural network (CNN) that offers superior feature extraction and minimal training data requirements. Time-domain AE waveforms are used as inputs of the proposed model to automate the process of predicting the severity of damage and identifying the expected location of the damage in structural elements. The proposed approach is validated using AE data collected from a concrete beam and a wooden beam and plate. The results show the capability of the proposed method for predicting the level of damage with an accuracy range of 92-95% and identifying the approximate location of damage with 90-100% accuracy. Thus, the proposed method serves as a robust technique for damage severity prediction and localization in civil structures. [ABSTRACT FROM AUTHOR]

Depleted gas reservoirs are important natural gas storage media, thus research on the mechanical properties and damage evolution of reservoir rocks under alternating load conditions has significant practical implications for seal integrity studies. This paper conducted multi-level cyclic loading triaxial compression experiments on medium-porosity medium-permeability sandstone under different confining pressures and used acoustic emission (AE) instruments to detect the AE characteristics during the experiment, analyzing the mechanical characteristics, AE, and damage evolution characteristics. The experimental results show that after cyclic loading, the peak strength of sandstone increased by 14–17%. With the increase in the upper limit stress of cyclic loading, the elastic modulus showed a trend of first increasing and then gradually decreasing. The damage variable of rock samples rose with a rise in the upper limit stress of cyclic loading and confining pressure, and the rock damage was mostly localized at the peak stress. The AE b-value increased generally as confining pressure increased, showing that fractures occurred quicker and more unevenly at lower confining pressures. The distribution of RA-AF values shows that a sudden increase in stress causes the initiation and expansion of cracks in medium-permeability sandstone, and that tensile and shear cracks form continuously during the cyclic loading process, with shear cracks developing more pronounced. This research can provide some theoretical guidance for the long-term stable operation and pressure enhancement expansion of depleted gas reservoir storage facilities. [ABSTRACT FROM AUTHOR]

Drones are a promising technology performing various functions, ranging from aerial photography to emergency response, requiring swift fault diagnosis methods to sustain operational continuity and minimise downtime. This optimises resources, reduces maintenance costs, and boosts mission success rates. Among these methods, traditional approaches such as visual inspection or manual testing have long been utilised. However, in recent years, data representation methods, such as deep learning systems, have achieved significant success. These methods learn patterns and relationships, enhancing fault diagnosis, but also face challenges with data complexity, uncertainties, and modelling complexities. This paper tackles these specific challenges by introducing an efficient representation learning method denoted Multiverse Augmented Recurrent Expansion (MVA-REX), allowing for an iterative understanding of both learning representations and model behaviours and gaining a better understanding of data dependencies. Additionally, this approach involves Uncertainty Bayesian Optimisation (UBO) under Extreme Learning Machine (ELM), a lighter neural network training tool, to tackle both uncertainties in data and reduce modelling complexities. Three main realistic datasets recorded based on acoustic emissions are involved in tackling propeller and motor failures in drones under realistic conditions. The UBO-MVA Extreme REX (UBO-MVA-EREX) is evaluated under many, error metrics, confusion matrix metrics, computational cost metrics, and uncertainty quantification based on both confidence and prediction interval features. Application compared to the well-known long-short term memory (LSTM), under Bayesian optimisation of the approximation error, demonstrates performances, certainty, and cost efficiency of the proposed scheme. More specifically, the accuracy obtained by UBO-MVA-EREX, ~0.9960, exceeds the accuracy of LSTM, ~0.9158, by ~8.75%. Besides, the search time for UBO-MVA-EREX is ~0.0912 s, which is ~98.15% faster than LSTM, ~4.9287 s, making it highly applicable for such challenging tasks of fault diagnosis-based acoustic emission signals of drones. [ABSTRACT FROM AUTHOR]

This paper applied the prevalent acoustic emission (AE) technology to identify the damage modes and critical conditions for FRP/steel-concrete composite beams during the failure process. AE signals generated by the structural damages were classified efficiently by using a novel self-adaptive real-time clustering (SARTC) method; damage modes corresponding to each clustering category were recognized and analyzed, and the dominant damage type at different stages was obtained by comparing the AE activities and feature values. By conducting the AE intensity analysis, the dynamic evolutionary mechanisms and critical conditions of composite beams were identified; the increase in intensity value from 0.2 to 0.3 reflects the process from critical yielding to major fracture. By establishing the non-linear fitting model between local response and cumulative AE energy, the instantaneous status at arbitrary local position of the composite beam can be inverted and predicted quantitatively by independent AE testing. [ABSTRACT FROM AUTHOR]

High-strength bolts play a crucial role in ultra-high-pressure equipment such as bridges and railway tracks. Effective monitoring of bolt conditions is of paramount importance for common fault repair and accident prevention. This paper aims to detect and classify bolt corrosion levels accurately. We design and implement a bolt corrosion classification system based on a Wireless Acoustic Emission Sensor Network (WASN). Initially, WASN nodes collect high-speed acoustic emission (AE) signals from bolts. Then, the ReliefF feature selection algorithm is applied to identify the optimal feature combination. Subsequently, the Extreme Learning Machine (ELM) model is utilized for bolt corrosion classification. Additionally, to achieve high prediction accuracy, an improved goose algorithm (GOOSE) is employed to ensure the most suitable parameter combination for the ELM model. Experimental measurements were conducted on five classes of bolt corrosion levels: 0%, 25%, 50%, 75%, and 100%. The classification accuracy obtained using the proposed method was at least 98.04%. Compared to state-of-the-art classification diagnostic models, our approach exhibits superior AE signal recognition performance and stronger generalization ability to adapt to variations in working conditions. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this study is to investigate the effect of coaxial swirlers on acoustic emission and reduction of potential core length in jet engines. Design/methodology/approach: The swirlers are introduced in the form of curved vanes with angles varied from 0° to 130°, corresponding to swirl numbers of 0–1.5. These swirlers are fixed in the annular chamber and tested at different nozzle pressure ratios of 2, 4 and 6. Findings: The study finds that transonic tones exist for the nonswirl jet, creating an unfavorable effect. However, these screech tones are eliminated by introducing a swirl jet at the nozzle exit. Weak swirl shows a greater reduction in noise than strong swirl at subsonic conditions. In addition, the introduction of swirl jets at all pressure ratios significantly reduces jet noise and core length in supersonic conditions, mitigating the noise created by shockwaves and leading to screech tone-free jet mixing. Originality/value: The paper provides valuable insights into the use of coaxial swirlers for noise reduction and core length reduction in jet engines, particularly in supersonic conditions. [ABSTRACT FROM AUTHOR]

The detection and identification of noise from moving parts inside a sealed cavity is crucial for ensuring the reliability of sealed equipment. However, traditional noise recognition methods struggle to meet the stringent demands for high detection accuracy. Inspired by the idea of ensemble learning, this paper proposes a noise recognition method that combines recognition results with high-dimensional mapping to enhance the recognition of noise. Firstly, a built noise identification experimental system is used to collect signals. Then, features are filtered and extracted based on acoustic emission principles and signal properties. Ultimately, a new fusion method is devised incorporating recognition results as new features into the original dataset and designing multiple layers of single algorithms based on their individual strengths to enhance the feature extraction capabilities of the algorithm. In the first layer of the fusion algorithm, CatBoost learns from the original dataset and incorporates its recognition results into the dataset. XGBoost then trains on the new dataset as the training set. Finally, the sparse output matrix generated by XGBoost is input into a logistic regression (LR) algorithm for training and prediction. The proposed method is verified by experiments on datasets and the results show that the accuracy of this method is higher than that of a single recogniser. It also performs better than current mature stacking fusion methods and mapping-based fusion methods. This fusion approach is of great significance for improving noise recognition accuracy and for innovating fusion methods. [ABSTRACT FROM AUTHOR]

Copyright of Atomic Energy Science & Technology is the property of Editorial Board of Atomic Energy Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Accurate estimation of the position of the fault source in the aircraft engine is the key to achieve engine structural health monitoring (SHM). In this paper, a convolutional neural network and graph convolutional network (CNN–GCN)-based dual-sensor acoustic emission (AE) localization method is proposed for locating the fault source in the engine casing with multi-part coupling features. Firstly, the time–frequency map data sets of AE signals at different locations are established by using continuous wavelet transform to analyze the effect of multi-part coupling features on AE signals. Secondly, combined with its reverberation mode, multi-modal and dispersion characteristics, the effectiveness of CNN–GCN model is trained, verified and tested. Finally, the sensitivity of the localization results to the sensor types is analyzed, and the sensor combination mode with high localization accuracy is obtained. These results show that the proposed method in this paper can be used as an effective means for locating the fault source of the engine casing with complex coupling interface features. [ABSTRACT FROM AUTHOR]

Steel-fibre-reinforced concrete (SFRC) has been increasingly used in the field of engineering structures in recent years. Hence, the accurate monitoring of the fracturing process of in-service SFRC has considerable significance in terms of structural safety. This paper investigates the acoustic emission (AE) and digital image correlation (DIC) features characterising the damage behaviour of SFRC samples in compression. For all the tests, cumulated AE, b-value, βt coefficient, average frequency, and rise angle are considered to describe the actual SFRC failure mechanisms. The results show that SFRC exhibits enhanced toughness compared to normal concrete (NC), with an indicated transition from a brittle to a ductile structural behaviour. This improved behaviour can be attributed to the bridging effect of steel fibres, which also drives the progressive tensile-to-shear crack transition, thus being the main cause of the final SFRC failure. As the loading rate increases, there is a corresponding increase in the number of shear cracks, leading to a decrease in the overall ductility and toughness of SFRC. Moreover, since the number of shear cracks notably increases right before SFRC fracture, this can serve as a safety warning of the impending failure. Furthermore, the cumulated AE curve displays a strong discontinuity in the occurrence of an unstable fracturing process in SFRC, which can also be forecasted by the AE time-scaling coefficient βt. The AE and DIC features can be used as failure precursors in the field of structural surveying, offering an accurate technical support for engineering failure warnings. [ABSTRACT FROM AUTHOR]

The present paper discusses the scientific and technical problem of optimizing the design and characteristics of a new type of solid-state sensors for motion parameters on bulk acoustic waves in order to increase the signal-to-noise ratio and the detectability of an informative signal against the background of its own noise and interference. Criteria for choosing materials for structural elements, including piezoelectric transducers of the sensitive element, were identified; a corresponding numerical simulation was performed using the developed program; and experimental studies according to the suggested method were carried out to validate the obtained analytical and calculated positions. The experimental results revealed the correctness of the chosen criteria for the optimization of design parameters and characteristics, demonstrated the high correlation between the results of modeling and field studies, and, thus, confirmed the prospects of using this new type of solid-state acoustic sensors of motion parameters in the navigation and control systems of highly dynamic objects. [ABSTRACT FROM AUTHOR]

In metal cutting processes, tool condition monitoring has a great importance to prevent surface damage and maintaining the quality of surface finishing. With the development of digitalisation and connection of industrial machines, it has become possible to collect real-time data from various types of sensors (e.g. vibration, acoustic or emission) during the process execution. However, information fusion from multiple sensor signals and tool health prediction still present a big challenge. The aim of this paper is to present a data-driven framework to estimate the tool wear status and predict its remaining useful life by using machine learning techniques. The first part of the framework is dedicated to sensor data preprocessing and feature engineering, while the second part deals with the development of prediction models. Different types of machine learning algorithms are used and compared to find the best result. A case study in a milling process is presented to illustrate the potentialities of the proposed framework for tool condition monitoring. [ABSTRACT FROM AUTHOR]

Multi-feature fusion has been widely used to enhance recognition accuracy for different health stages of rails, which may lead to high dimensionality and information redundancy of signals. In addition, conventional supervised methods require plenty of labeled samples with class information, which can take significant time and involve high economic costs. In order to improve the effectiveness of the electromagnetic acoustic emission technique in rail crack defect recognition, a novel method including multi-feature fusion based on weakly supervised learning and recognition threshold construction is proposed in this paper. First, a mechanism consisting of multi-feature extraction and feature selection is developed to fully reflect the information of different health stages of the rail and avoid interference caused by the ineffective features. Then, the effective features and a novel weakly unsupervised label are input into the self-normalizing convolutional neural network and long short-term memory model to construct the rail health indicator (RHI). Finally, the recognition threshold is calculated based on the characteristics of the RHI to achieve crack recognition automatically. Furthermore, the experimental results under different working conditions demonstrate that the proposed method achieves a higher recognition performance than other existing methods in rail crack defect recognition. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this paper is to describe various aspects of the visco-elastoplastic (VEP) behavior of porous-hardened concrete samples in relation to standard tests. Design/methodology/approach: The problem is formulated on the basis of the rheological-dynamic analogy (RDA). In this study, changes in creep coefficient, Poisson's ratio, damage variables, modulus of elasticity, strength and angle of internal friction as a function of porosity are defined by P and S wave velocities. The RDA model provides a description of the degradation process of material properties from their peak state to their ultimate values using void volume fraction (VVF). Findings: Compared to numerous versions of acoustic emission tracking developed to analyze the behavior of total wave propagation in inhomogeneous media with density variations, the proposed model is comprehensive in interpretation and consistent with physical understanding. The comparison of the damage variables with the theoretical variables under the assumption of spherical voids in the spherical representative volume element (RVE) shows a satisfactory agreement of the results for all analyzed samples if the maximum porosities are used for comparison. Originality/value: The paper presents a new mathematical-physical method for examining the effect of porosity on the characteristics of hardened concrete. Porosity is essentially related to density variations. Therefore, it was logical to define the limit values of porosity using the strain energy density. [ABSTRACT FROM AUTHOR]

The autonomous fault diagnosis of mechanical systems is crucial to addressing smart manufacturing product issues. In this article, we propose intelligent diagnosis and prediction technologies based on acoustic emission (AE) for mechanical motors. The integration of practical technologies, such as acoustic analysis, artificial intelligence (AI), edge computing (EC), electromagnetics, communication, and other theory-based subjects, is convenient for achieving flexible changes made in response to the edge operation trend. The proposed model, developed using acoustic information links with machine learning (ML) platforms to collect acoustic information via feature extraction (FE), is novel in that it can detect system health and prevent system failures. It can inspire innovative design concepts once the above model is combined with the EC migration module. In addition, in this paper, we discuss the embedded system in smart manufacturing applications, including AE, to establish an ML framework that is trained using audio emission data. The valuable results from the proposed algorithm experiments show that the audio judgment accuracy rate can be above 90%. At the current stage, the metric accuracy and precision of mechanical motor discrimination can reach 93.5% and 0.97, respectively. In this paper, we present an analytical method for performing motor axis misalignment judgment based on tiny machine learning (TinyML) techniques, which will enable the IoT field to move toward smart energy savings. [ABSTRACT FROM AUTHOR]

The characteristics of acoustic emission signals generated in the process of rock deformation and fission contain rich information on internal rock damage. The use of acoustic emissions monitoring technology can analyze and identify the precursor information of rock failure. At present, in the field of acoustic emissions monitoring and the early warning of rock fracture disasters, there is no real-time identification method for a disaster precursor characteristic signal. It is easy to lose information by analyzing the characteristic parameters of traditional acoustic emissions to find signals that serve as precursors to disasters, and analysis has mostly been based on post-analysis, which leads to poor real-time recognition of disaster precursor characteristics and low application levels in the engineering field. Based on this, this paper regards the acoustic emissions signal of rock fracture as a kind of speech signal generated by rock fracture uses this idea of speech recognition for reference alongside spectral analysis (STFT) and Mel frequency analysis to realize the feature extraction of acoustic emissions from rock fracture. In deep learning, based on the VGG16 convolutional neural network and AlexNet convolutional neural network, six intelligent real-time recognition models of rock fracture and key acoustic emission signals were constructed, and the network structure and loss function of traditional VGG16 were optimized. The experimental results show that these six deep-learning models can achieve the real-time intelligent recognition of key signals, and Mel, combined with the improved VGG16, achieved the best performance with 87.68% accuracy and 81.05% recall. Then, by comparing multiple groups of signal recognition models, Mel+VGG-FL proposed in this paper was verified as having a high recognition accuracy and certain recognition efficiency, performing the intelligent real-time recognition of key acoustic emission signals in the process of rock fracture more accurately, which can provide new ideas and methods for related research and the real-time intelligent recognition of rock fracture precursor characteristics. [ABSTRACT FROM AUTHOR]

Chemical pressure storage tanks are containers designed to store fluids at high pressures, i.e., their internal pressure is higher than the atmospheric pressure. They can come in various shapes and sizes, and may be fabricated from a variety of materials. As aggressive chemical agents stored under elevated pressures can cause significant damage to both people and the environment, it is essential to develop systems for the early damage detection and the monitoring of structural integrity of such vessels. The development of early damage detection and condition monitoring systems could also help to reduce the maintenance costs associated with periodic inspections of the structure and unforeseen operational breaks due to unmonitored damage development. It could also reduce the related environmental burden. In this paper, we consider a hybrid material composed of glass-fiber-reinforced polymers (GFRPs) and a polyethylene (PE) layer that is suitable for pressurized chemical storage tank manufacturing. GFRPs are used for the outer layer of the tank structure and provides the dominant part of the construction stiffness, while the PE layer is used for protection against the stored chemical medium. The considered damage scenarios include simulated cracks and an erosion of the inner PE layer, as these can be early signs of structural damage leading to the leakage of hazardous liquids, which could compromise safety and, possibly, harm the environment. For damage detection, PZT sensors were selected due to their widely recognized applicability for the purpose of structural health monitoring. For sensor installation, it was assumed that only the outer GFRP layer was available as otherwise sensors could be affected by the stored chemical agent. The main focus of this paper is to verify whether elastic waves excited by PZT sensors, which are installed on the outer GFRP layer, can penetrate the GFRP and PE interface and can be used to detect damage occurring in the inner PE layer. The efficiency of different signal characteristics used for structure evaluation is compared for various frequencies and durations of the excitation signal as well as feasibility of PZT sensor application for passive acquisition of acoustic emission signals is verified. [ABSTRACT FROM AUTHOR]

The article presents a list of relevant papers compiled from publications received, which include Numerical modelling of stochastic fatigue damage accumulation in thick composites; and Optimal finite difference schemes for multiple damage identification in beams.