Acoustic emission signal identification of different rocks based on SE-1DCNN-BLSTM network model

In order to study fracture mechanism of rocks in different brittle mineral contents,this study pro-poses a method to identify the acoustic emission signal released by rock fracture under different brittle miner-al content(BMC),and then determine the content of brittle matter in rock.To understand related interference such as the noises in the acoustic emission signals released by the rock mass rupture,a 1DCNN-BLSTM network model with SE module is constructed in this study.The signal data is processed through the 1DCNN and BLSTM networks to fully extract the time-series correlation features of the signals,the non-correlated features of the local space and the weak periodicity law.Furthermore,the processed signals data is input into the fully connected layers.Finally,softmax function is used to accurately identify the acoustic emission signals released by different rocks,and then determine the content of brittle minerals contained in rocks.Through experimental comparison and analysis,1DCNN-BLSTM model embedded with SE module has good anti-noise performance,and the recognition accuracy can reach more than 90 percent,which is better than the traditional deep network models and provides a new way of thinking for rock acoustic emission re-search.

Identifying the real fracture hidden in rock microcrack zone by acoustic emission energy

Identifying the real fracture of rock hidden in acoustic emission(AE)source clusters(AE-depicted microcrack zone)remains challenging and crucial.Here we revealed the AE energy(representing dissipated energy)distribution rule in the rock microcrack zone and proposed an AE-energy-based method for identifying the real fracture.(1)A set of fracture experiments were performed on granite using wedgeloading,and the fracture process was detected and recorded by AE.The microcrack zone associated with the energy dissipation was characterized by AE sources and energy distribution,utilizing our selfdeveloped AE analysis program(RockAE).(2)The accumulated AE energy,an index representing energy dissipation,across the AE-depicted microcrack zone followed the normal distribution model(the mean and variance relate to the real fracture path and the microcrack zone width).This result implies that the nucleation and coalescence of massive cracks(i.e.,real fracture generation process)are supposed to follow a normal distribution.(3)Then,we obtained the real fracture extension path by joining the peak positions of the AE energy normal distribution curve at different cross-sections of the microcrack zone.Consequently,we distinguished between the microcrack zone and the concealed real fracture within it.The deviation was validated as slight as 1–3 mm.

Characteristic stress variation and microcrack evolution of granite subjected to uniaxial compression using acoustic emission methods

The size of mineral grain has a significant impact on the initiation and propagation of microcracks within rocks.In this study,fine-,medium-,and coarse-grained granites were used to investigate microcrack evolution and characteristic stress under uniaxial compression using the acoustic emission(AE),digital image correlation(DIC),and nuclear magnetic resonance(NMR)measurements.The experimental results show that the characteristic stress of each granite decreased considerably with increasing grain sizes.The inflection points of the b-value occurred earlier with an increase in grain sizes,indicating that the larger grains promote the generation and propagation of microcracks.The distribution characteristics of the average frequency(AF)and the ratio of rise time to amplitude(RA)indicate that the proportion of shear microcracks increases with increasing grain size.The NMR results indicate that the porosity and the proportion of large pores increased with increasing grain size,which may intensify the microcrack evolution.Moreover,analysis of the DIC and AE event rates suggests that the high-displacement regions could serve as a criterion for the degree of microcrack propagation.The study found that granites with larger grains had a higher proportion of high-displacement regions,which can lead to larger-scale cracking or even spalling.These findings are not only beneficial to understand the pattern of microcrack evolution with different grain sizes,but also provide guidance for rock monitoring and instability assessment.

Mechanical anisotropy associated with beddings in shale under Brazilian test conditions:Insights from acoustic emission statistics

A comprehensive understanding of shale’s bedding anisotropy is crucial for shale-related engineering activities,such as hydraulic fracturing,drilling and underground excavation.In this study,seven Brazilian tests were conducted on shale samples at different bedding orientations with respect to the loading direction(0°,45°and 90°)and the disc end face(0°,45°and 90°).An acoustic emission(AE)system was employed to capture the evolution of damage and the temporal-spatial distribution of microcracks under splitting-tensile stress.The results show that the Brazilian tensile strength decreases with increasing bedding inclination with respect to the disc end face,while it increases with the angle between bedding and loading directions.Increasing the bedding inclination with respect to the end face facilitates the reduction in b value and enhances the shale’s resistance to microcrack growth during the loading process.Misalignment between the bedding orientation and the end face suppresses the growth of mixed tensile-shear microcracks,while reducing the bedding angle relative to the loading direction is beneficial for creating mixed tensile-shear and tensile cracks.The observed microscopic failure characteristics are attributed to the competing effects of bedding activation and breakage of shale matrix at different bedding inclinations.The temporal-spatial distribution of microcracks,characterized by AE statistics including the correlation dimension and spatial correlation length,illustrates that the fractal evolution of microcracks is independent of bedding anisotropy,whereas the spatial distribution shows a stronger correlation.The evolution features of correlation dimension and spatial correlation length could be potentially used as precursors for shale splitting failure.These findings may be useful for predicting rock mass instability and analyzing the causes of catastrophic rupture.

Shear band evolution and acoustic emission characteristics of sandstone containing non-persistent flaws

Direct shear tests were conducted on sandstone specimens under different constant normal stresses to study the coalescence of cracks between non-persistent flaws and the shear sliding characteristics of the shear-formed fault.Digital image correlation and acoustic emission(AE)techniques were used to monitor the evolution of shear bands at the rock bridge area and microcracking behaviors.The experimental results revealed that the shear stresses corresponding to the peak and sub-peak in the stressdisplacement curve are significantly affected by the normal stress.Strain localization bands emerged at both the tip of joints and the rock bridge,and their extension and interaction near the peak stress caused a surge in the AE hit rate and a significant decrease in the AE b value.Short and curvilinear strain bands were detected at low normal stress,while high normal stress generally led to more microcracking events and longer coplanar cracks at the rock bridge area.Furthermore,an increase in normal stress resulted in a higher AE count rate and more energetic AE events during friction sliding along the shearformed fault.It was observed that the elastic energy released during the crack coalescence at the prepeak stage was much greater than that released during friction sliding at the post-peak stage.More than 75%of AE events were located in the low-frequency band(0e100 kHz),and this proportion continued to rise with increasing normal stress.Moreover,more AE events of low AF value and high RA value were observed in specimens subjected to high normal stress,indicating that greater normal stress led to more microcracks of shear nature.

Enhancing microseismic/acoustic emission source localization accuracy with an outlier-robust kernel density estimation approach

Monitoring sensors in complex engineering environments often record abnormal data,leading to significant positioning errors.To reduce the influence of abnormal arrival times,we introduce an innovative,outlier-robust localization method that integrates kernel density estimation(KDE)with damping linear correction to enhance the precision of microseismic/acoustic emission(MS/AE)source positioning.Our approach systematically addresses abnormal arrival times through a three-step process:initial location by 4-arrival combinations,elimination of outliers based on three-dimensional KDE,and refinement using a linear correction with an adaptive damping factor.We validate our method through lead-breaking experiments,demonstrating over a 23%improvement in positioning accuracy with a maximum error of 9.12 mm(relative error of 15.80%)—outperforming 4 existing methods.Simulations under various system errors,outlier scales,and ratios substantiate our method’s superior performance.Field blasting experiments also confirm the practical applicability,with an average positioning error of 11.71 m(relative error of 7.59%),compared to 23.56,66.09,16.95,and 28.52 m for other methods.This research is significant as it enhances the robustness of MS/AE source localization when confronted with data anomalies.It also provides a practical solution for real-world engineering and safety monitoring applications.

Implications for identification of principal stress directions from acoustic emission characteristics of granite under biaxial compression experiments

The rock fracture characteristics and principal stress directions are crucial for prevention of geological disasters.In this study,we carried out biaxial compression tests on cubic granite samples of 100 mm in side length with different intermediate principal stress gradients in combination with acoustic emission(AE)technique.Results show that the fracture characteristics of granite samples change from‘sudden and aggregated’to‘continuous and dispersed’with the increase of the intermediate principal stress.The effect of increasing intermediate principal stress on AE amplitude is not significant,but it increases the proportions of high-frequency AE signals and shear cracks,which in turn increases the possibility of unstable rock failure.The difference of stress in different directions causes the anisotropy of rock fracture and thus leads to the obvious anisotropic characteristics of wave velocity variations.The anisotropy of wave velocity variations with stress difference is probable to identify the principal stress directions.The AE characteristics and the anisotropy of wave velocity variations of granite under two-dimensional stress are not only beneficial complements for rock fracture characteristic and principal stress direction identification,but also can provide a new analysis method for stability monitoring in practical rock engineering.

Characteristics of acoustic emission signals in damp cracking coal rocks

A uniaxial load experiment on coal rocks at different stress rates was carried out, based on the characteristics of acoustic emission (AE) signals in cracking coal rocks, decomposition, de-noising and reconstruction for the AE signals through wavelet packet transform for solving the current problems created by the presence of noise in AE signals and the existing problems in AE signal processing. The results show that the various characteristics of AE signals in coal rocks cracking under different situations can be clearly reflected, after the AE signals are de-noised by the wavelet packet. Compared to dry coal rocks, the number of AE occurrences in damp coal rocks was significantly reduced, as well as the average amplitude. The number of AE occurrences in damp and dry coal rocks clearly increased with increases in the loading rate, but the largest amplitude of the AE signals in damp coal rocks has been reduced. There is no clear evidence of change in dry coal rocks.

基于单通道AE盲源分离的结构损伤定位

声发射(acoustic emission,简称AE)能够实现复杂板状结构损伤定位,但多数AE检测定位方法仅针对单AE源的情况,而实际中复杂板状结构产生损伤时会伴随多个AE卷积混合信号。为了解决工程中多AE源定位的问题,提出一种单通道AE盲分离-模态提取定位方法。首先,对采集的AE信号进行信号降噪,使用单通道盲源分离算法分离出无回波成分的AE信号,将多源定位转为多个单源定位问题;其次,通过提取单频模态,求取声波传播速度,估计到达时间差来进行疲劳裂纹损伤定位;最后,经过计算机仿真实验和钢箱梁桥断铅半实物仿真实验,验证了方法的准确性和有效性,并通过载荷破坏AE检测实验验证了方法的实用性。结果表明,所提方法能够应用于复杂板状结构多AE源定位问题,为实际工程应用提供了可靠的依据及参考价值。

PARAMETERS OPTIMIZATION OF CONTINUOUS WAVELET TRANSFORM AND ITS APPLICATION IN ACOUSTIC EMISSION SIGNAL ANALYSIS OF ROLLING BEARING

Morlet wavelet is suitable to extract the impulse components of mechanical fault signals. And thus its continuous wavelet transform （CWT） has been successfully used in the field of fault diagnosis. The principle of scale selection in CWT is discussed. Based on genetic algorithm, an optimization strategy for the waveform parameters of the mother wavelet is proposed with wavelet entropy as the optimization target. Based on the optimized waveform parameters, the wavelet scalogram is used to analyze the simulated acoustic emission （AE） signal and real AE signal of rolling bearing. The results indicate that the proposed method is useful and efficient to improve the quality of CWT.

Mechanical responses and acoustic emission behaviors of coal under compressive differential cyclic loading(DCL):a numerical study via 3D heterogeneous particle model

The stability of coal walls(pillars)can be seriously undermined by diverse in-situ dynamic disturbances.Based on a 3D par-ticle model,this work strives to numerically replicate the major mechanical responses and acoustic emission(AE)behaviors of coal samples under multi-stage compressive cyclic loading with different loading and unloading rates,which is termed differential cyclic loading(DCL).A Weibull-distribution-based model with heterogeneous bond strengths is constructed by both considering the stress-strain relations and AE parameters.Six previously loaded samples were respectively grouped to indicate two DCL regimes,the damage mechanisms for the two groups are explicitly characterized via the time-stress-dependent variation of bond size multiplier,and it is found the two regimes correlate with distinct damage patterns,which involves the competition between stiffness hardening and softening.The numerical b-value is calculated based on the mag-nitudes of AE energy,the results show that both stress level and bond radius multiplier can impact the numerical b-value.The proposed numerical model succeeds in replicating the stress-strain relations of lab data as well as the elastic-after effect in DCL tests.The effect of damping on energy dissipation and phase shift in numerical model is summarized.

Moment tensor and stress inversion solutions of acoustic emissions during compression and tensile fracturing in crystalline rocks

We investigate the accuracy and robustness of moment tensor(MT)and stress inversion solutions derived from acoustic emissions(AEs)during the laboratory fracturing of prismatic Barre granite specimens.Pre-cut flaws in the specimens introduce a complex stress field,resulting in a spatial and temporal variation of focal mechanisms.Specifically,we consider two experimental setups:(1)where the rock is loaded in compression to generate primarily shear-type fractures and(2)where the material is loaded in indirect tension to generate predominantly tensile-type fractures.In each test,we first decompose AE moment tensors into double-couple(DC)and non-DC terms and then derive unambiguous normal and slip vectors using k-means clustering and an unstructured damped stress inversion algorithm.We explore temporal and spatial distributions of DC and non-DC events at different loading levels.The majority of the DC and the tensile non-DC events cluster around the pre-cut flaws,where macro-cracks later develop.Results of stress inversion are verified against the stress field from finite element(FE)modeling.A good agreement is found between the experimentally derived and numerically simulated stress orientations.To the best of the authors’knowledge,this work presents the first case where stress inversion methodologies are validated by numerical simulations at laboratory scale and under highly heterogeneous stress distributions.

Identification of acoustic emission signal in aluminum alloys spot welding based on fractal theory

The acoustic emission signal of aluminum alloys spot welding includes the information of forming nugget and is one of the important parameters in the quality control. Due to the nonlinearity of the signals, classic Euclidean geometry can not be applied to depict exactly. The fractal theory is implemented to quantitatively describe the characteristics of the acoustic emission signals. The experiment and calculation results show that the box counting dimension of acoustic emission signal, between 1 and 2, are distinctive from different nugget areas in AC spot welding. It is proved that box counting dimension is an effective characteristic parameter to evaluate spot welding quality. In addition, fractal theory can also be applied in other spot welding parameters, such as voltage, current, electrode force and so on, for the purpose of recognizing the spot welding quality.

一种ALMAE-SWSupAE裂纹声发射信号识别算法研究

针对裂纹声发射信号的识别问题,基于大边缘自编码器(LMAE)和堆叠融合监督自编码器(SFSupAE)设计了自适应大边缘堆叠权重监督自编码(ALMAE-SWSupAE)算法。针对LMAE中的固定k值问题,引入自适应k值算法,修改h(s)运算方法解决数据溢出问题;在SFSupAE中引入子分类器的性能权重优化分配策略,并设计新的权重函数;使用铝合金试件进行拉伸裂纹实验,识别采集到的声发射信号。研究结果表明:所提出的ALMAE-SWSupAE算法法识别准确率达到98.89%,相较于SSAE、SDAE、CAE、StAE和SAE方法性能具有明显提升,并在消融实验中证明了其改进有效性。

A robust triaxial localization method of AE source using refraction path

Acoustic emission(AE)localization algorithms based on homogeneous media or single-velocity are less accurate when applied to the triaxial localization experiments.To the end,a robust triaxial localization method of AE source using refraction path is proposed.Firstly,the control equation of the refraction path is established according to the sensor coordinates and arrival times.Secondly,considering the influence of time-difference-of-arrival(TDOA)errors,the residual of the governing equation is calculated to estimate the equation weight.Thirdly,the refraction points in different directions are solved using Snell’s law and orthogonal constraints.Finally,the source coordinates are iteratively solved by weighted correction terms.The feasibility and accuracy of the proposed method are verified by pencil-lead breaking experiments.The simulation results show that the new method is almost unaffected by the refraction ratio,and always holds more stable and accurate positioning performance than the traditional method under different ratios and scales of TDOA outliers.

Chaos analysis of acoustic emission signals in spot welding process

Based on chaos time series and fractal theory, acoustic emission signals were studied in the process of spot welding. According to calculating 8 welding parameters using phase space reconstruction method, the largest Lyapunov exponents were positive values and chaos characteristics were firstly discovered from acoustic emission signals in spot welding. In order to evaluate acoustic emission signal, Hausdorff dimension is put forward to analyze and estimate chaos characteristics. The experiment and calculation results indicate that the Hausdorff dimension of acoustic emission signal is significantly distinguishable in the nuggets with different welding parameters. This research provides a new method for measuring the resistance spot welding quality.

Prediction of fracture and dilatancy in granite using acoustic emission signal cloud

The invisibility of fracture network evolution in the rock under triaxial compression seriously restricts the correlation modeling between dilatancy behavior and fracture interconnectivity.The key to solving such a challenge is strongly dependent on the accurate modeling of the spatial correlation in fracture network,which could be indirectly re-constructed by the acoustic emission(AE)signal cloud.Considering the interaction of local fractures,a cube cluster approach is established to describe the spatial correlation.The evolutional cube clusters effectively present the geometric characteristics induced by the increasing dilatancy of fracture.Two descriptors(i.e.three-axis length sum and pore fraction)are introduced to correlate cluster model with dilatancy behavior.Most fitting results support the linear correlation between two descriptors and volumetric strain,which verifies the sensitiveness of the cube cluster model to dilatancy.More importantly,by the statistical analysis of cluster structure,the cluster model shows the potential of calculating fracture angle.Moreover,a comparison between dilatancybased damage and porosity-based damage is made not to prove the best but provide an AE-based prediction of local damage evolution.Finally,four classical models for calculating fracture angle are compared.The deviations prove the huge difficulty of describing the development of the fracture network uniquely dependent on a fracture angle.The proximity of measured angle and cluster-based angle supports the effectiveness of predication by the cube cluster approach.

Study of hydraulic fracture growth behavior in heterogeneous tight sandstone formations using CT scanning and acoustic emission monitoring

Tortuous hydraulic fractures(HFs) are likely to be created in heterogeneous formations such as conglomerates, which may cause sand plugging, ultimately resulting in poor stimulation efficiency. This study aims to explore HF growth behavior in conglomerate through laboratory fracturing experiments under true tri-axial stresses combined with computed tomography scanning and acoustic emission(AE) monitoring. The effects of gravel size, horizontal differential stress, and AE focal mechanisms were examined. Especially, the injection pressure and the AE response features during HF initiation and propagation in conglomerate were analyzed. Simple HFs with narrow microfractures are created in conglomerate when the gravels are considerably smaller than the specimen, whereas complex fractures are created when the gravels are similar in size to the specimen, even under high horizontal differential stresses. Breakdown pressure and AE rates are high when a HF is initiated from the high-strength gravel. A large pressure decline after the breakdown may indicate the creation of a planar and wide HF. Analyzing the focal mechanism indicates that the shear mechanism generally dominates with an increase in the HF complexity. Tensile events are likely to occur during HF initiation and are located around the wellbore. Shear events occur mainly around the nonplanar and complex matrix/gravel interfaces.

Laboratory acoustic emission study for earthquake generation process

Since the similarity in size distribution of earthquakes and acoustic emissions （AE） was found in the 1960s, many laboratory studies have been motivated by the need to provide tools for the prediction of mining failures and natural earthquakes. This paper aims, on the one hand, to draw an outline of laboratory AE studies in the last 50 years, which have addressed seismological problems. Topics include the power laws in which the similarity between AEs and earthquakes is involved and progress that has been made in AE technology and laboratory AE study. On the other hand, this study will highlight some key issues intensively discussed, especially in the last three decades, such as aspects related to the pre-failure damage evolution, fault nucleation and growth in brittle rocks and discuss factors governing these processes.

Mechanical properties and acoustic emission characteristics of thick hard roof sandstone in Shendong coal field

The mechanical properties and acoustic emission characteristics of thick hard roof sandstone were investigated. Samples were taken from the 30.87-m thick sandstone roof in a mine in the Shengdong coal field, China. Firstly, the composition and microscopic characteristics were analyzed by XRD and FE-SEM, respectively. Moreover, the indirect tensile test, uniaxial compression test, three axis compression experiment and AE test are carried out by using RMT-150C mechanics experiment system with DSS-8B AE test system. The experiment results indicate that the main framework particles of sandstone are quartz and feldspar, and mainly quartz. Cements are mainly pyrite, kaolinite, chlorite and zeolite cross needle, clinochlore, and clay minerals. The microstructure of sandstone is very dense, with few pores and high cementation degree. The tensile strength, compressive strength and elastic modulus of sandstone are 4.825, 85.313 MPa, 13.814 GPa, respectively, so the sandstone belongs to hard rock. The AE cumulative counts of sandstone can be divided into three phases： relatively flat growth period, rapid growth period and spurt period. The signal strength of AE waveform can be used as a warning signal. In the tensile fracture zone, the warning value is 0.4 mV, and in the compression shear failure zone, it is 4 mV. The numbers of cumulative counts of AE under different stress conditions have obvious difference. Moreover, the growth of cumulative counts of acoustic emission is more obvious when the stress is more than 60% of the peak stress.