Acoustic Emission Signal Characteristics Research Articles

Performance evaluation of deep learning approaches for fault diagnosis of rotational mechanical systems using vibration, sound, and acoustic emission signals

The present study emphasizes an optimized deep learning algorithm for gearbox fault detection using vibration, sound, and acoustic emission signals. Statistical and acoustic features are extracted from these signals, and various neural network algorithms are explored. The supervised deep feed forward neural network (DFFNN) demonstrates excellent performance with vibration signals but limited accuracy with sound and acoustic emission signals. To address this, unsupervised algorithms are optimized and compared with vibration-based classification. The findings show that unsupervised neural networks, particularly the auto-encoder and stacked auto-encoder architectures, achieve improved classification accuracy by leveraging the unique characteristics of acoustic emission signals. The unsupervised models also effectively overcome the vanishing gradient problem via regularization, enhancing their training efficiency. The stacked auto-encoder, with multiple layers of encoders and decoders, reduces computation time by 40% and memory consumption. These optimized algorithms hold promise for automated fault detection systems. The auto-encoder and stacked auto-encoder, utilizing vibration, sound, and acoustic emission signals, offer enhanced classification accuracy and can facilitate real-time monitoring of rotating mechanical systems. However, further optimization is needed to maximize their performance. In a nutshell, the supervised DFFNN excels in utilizing vibration signals for fault detection, while the unsupervised models exploit the distinctive characteristics of acoustic emission signals. Future research will focus on refining these algorithms to enhance their effectiveness. Implementing these optimized deep learning approaches can lead to autonomous fault detection systems, eliminating the need for continuous human supervision.

Applicability of a new composite amusement ride safety device based on acoustic emission monitoring technology

Under the premise of ensuring safety, it is of great significance to realize the lightweight of the non-main load-bearing parts of amusement facilities. The purpose of this study is to study the failure process of a newly designed carbon fiber bumper by using acoustic emission technology. First of all, the design of carbon fiber anti-collision bar can effectively restrain passengers, and its weight is reduced by nearly two-thirds compared to traditional metal materials. Subsequently, the load-bearing capacity of the bumper was tested and acoustic emission monitoring was carried out. The test results show that this new type of combined structure of amusement facility has high reliability, which exceeds the safety factor of 3.5 required by the steel structure of amusement facility. In addition, Renyi entropy was used to select the best window function of short-time Fourier transform, and the frequency domain characteristics of acoustic emission signals of typical damage modes were discussed through appropriately selected windows function. A classifier based on supervised machine learning is established by combining frequency features and acoustic emission feature parameters. Furthermore, the use of classifiers helps to understand the damage behaviour of composite structures.

Effect of Acoustic Emission Sensor Location on the Detection of Grinding Wheel Deterioration in Cylindrical Grinding

The acoustic emission (AE) technique is an effective method for monitoring grinding wheels, and numerous studies have been published on applying an AE to monitor grinding wheels. However, there are few studies on the effect of the location of the AE sensor in stably acquiring the AE signals generated during deterioration in cylindrical grinding wheels. In this study, we propose a stable method for detecting the deterioration of a cubic boron nitride (cBN) grinding wheel during cylindrical grinding using AE. We compared the AE signals acquired during grinding from an AE sensor located on the hydrostatic bearing, which supports the grinding wheel shaft, with those from the tailstock spindle. Although positioning the AE sensor on the hydrostatic bearing was found to reduce the AE signal intensity, the AE signal variations were smaller at the same grinding position, and the effect of the grinding position was less than that for the tailstock spindle. Moreover, positioning an AE sensor on the hydrostatic bearing is considered to provide the characteristics of AE signals specifically focused on the changes in cBN on the grinding wheel surface allowing the surface roughness of the workpiece to be estimated during grinding.

Failure Characterization of Al-Zn-Mg Alloy and Its Weld Using Integrated Acoustic Emission and Digital Image Techniques

The three-point bending damage process of an A7N01 aluminum alloy body material and weld seam in an electric multiple unit train was monitored using acoustic emission (AE) and digital image technology. The AE signal characteristics of static load damage to the aluminum alloy and weld seam were studied using the AE signal parameter and time–frequency analysis. Based on the observation of the microstructure and fracture morphology, the source mechanism of AE signals was analyzed. The experimental results indicate that AE energy, centroid frequency, and peak frequency are effective indices for predicting the initiation of cracks in A7N01 aluminum alloy and weld seams. The digital image monitoring results of the notch tip damage evolution of aluminum alloy samples confirmed the predictions based on AE energy, centroid frequency, and peak frequency for crack initiation. The AE signal source mechanism revealed that the differences in AE characteristics between the base material and weld seam can be attributed to microstructure variations and fracture modes. In summary, the AE technique is more sensitive to changes in the fracture mode and can be utilized to monitor the damage evolution of welded structures.

Detection of defects during laser-powder interaction by acoustic emission sensors and signal characteristics

Acoustic Emission (AE) sensing is an in-situ real-time nondestructive monitoring method proposed for Additive Manufacturing (AM) to detect defects such as cracks. Previous AE research in AM mainly focused on developing algorithms to automatically detect the defects from AE signals without understanding the physical mechanisms or the signal characteristics that could be used as identifiers. We study AE signals during a laser spot welding on a powder bed to clearly distinguish between different physical mechanisms using their signal characteristics. We identified specific signals associated with 1) tensile cracks from cooling, 2) a powder effect on the substrate, and 3) sudden thermal expansion of the substrate. We used the spectral ratio between high frequency (70–150 kHz) and low frequency (10–40 kHz) spectral amplitudes in the frequency domain to classify and differentiate the source types. We found that porosity due to insufficient energy density did not produce detectable AE signals. Using a ball drop calibration technique, we used AE signals to estimate the absolute sizes of the tensile cracks. Crack sizes ranged from 40 μm to 1 mm and were in general agreement with scanning electron microscope images of the fractures. We performed a line scanning test and successfully validated its potential for the application. Our findings provide a basic understanding of AE signal characteristics in AM, as well as the practical parameters used to separate the signal types.

Experimental study on multiple characteristics of multi-source AE signals during cavitation process of waterjet propulsion pump

In order to investigate the cavitation-induce acoustic emission (AE) characteristics of a waterjet propulsion pump, a synchronous experimental system consisting of a test pump, a high-speed camera, and acoustic emission sensors has been established. The characteristic parameters of AE signals are extracted to established the quantitative relationships between cavitation status and AE signals. These characteristic parameters mainly consist of the ringing count rate Rc , energy release rate Er , and Hurst index Hi . The cavitation status of the test pump is reflected in the characteristic parameters of the AE signals obtained by the sensors installed at different locations. The incipient blade suction side (SS) cavitation as well as the blade tip gap cavitation can be detected through the change of characteristic parameters of AE signals at impeller inlet. The start of head drop can be reflected by the variety of characteristic parameters of AE signals at impeller middle. Large-scale cavitation will lead to the breakdown of pump performance and dramatically characteristic parameters’ change of AE signals can be measured by the sensors located at impeller outlet.

Acoustic emission characteristic of sandstone and sandstone like material under multi-path loading.

Using spline interpolation to select proportions of similar materials, a comparative analysis of the fracturing behavior of sandstone specimens and similar material specimens was conducted through Brazilian splitting tests under multi-path loading. The study revealed that during stepwise loading, both sandstone and similar materials exhibited memory effects and plastic deformation. However, under constant velocity loading, the relationship between force and displacement in sandstone showed linearity after compaction. Employing MATLAB optimization algorithms for the inversion of acoustic emission event information, the distribution of fracture points, and the evolution of cracks were analyzed. The findings indicated that under stepwise loading, both sandstone and similar materials exhibited banded distribution of peak frequencies, with sandstone concentrated in the mid-low-frequency range and similar materials leaning towards the low-frequency range. The amplitude-frequency characteristics of acoustic emission signals suggested that initially, sandstone produced low-frequency, low-amplitude signals. As cracks developed, these signals gradually transformed into high-frequency, high-amplitude signals, ultimately leading to macroscopic failure. The ringing counts and b-values of sandstone displayed an approximate "W" shape distribution, with a subsequent decrease in b-values during final failure. In contrast, the acoustic emission counts were inversely related to b-values. Similar materials exhibited slightly more acoustic emission counts than sandstone, with relatively lower b-values. The crack development process of both sandstone and similar materials was confirmed through these observations. From the perspective of section initiation and local damage, sandstone and similar materials exhibited similar failure characteristics. The proportions of quartz sand: cement: water = 9:1:0.9 in similar materials demonstrated the most similar characteristics to sandstone in terms of mechanical loading, acoustic emission features, and failure morphology. This suggests that these similar materials can be used as substitutes for sandstone in analogous simulation experiments. The study provides theoretical support for understanding rock fracture mechanisms, offers guidance for the selection and proportioning of similar materials, and holds significance for predicting and controlling rock fracture behavior in engineering applications.

Evolution characteristics of fracture volume and acoustic emission entropy of monzogranite under cyclic loading

The volume evolution behavior of rock fissures and the characteristics of acoustic emission under cyclic loading are critical for rock stability analysis. To study the volume change behavior of monzogranite fissures and the characteristics of acoustic emission signals under cyclic loading, we selected samples of monzogranite at − 1600 m from a gold mine located in the Jiaodong Peninsula at a depth of − 1600 m and investigated the samples using triaxial cyclic loading—unloading tests and acoustic emission monitoring. As the volume change behavior of the monzogranite fissures and acoustic emission signals were monitored and recorded, the calculated fracture volume strain ratio coefficient and acoustic emission entropy value were proposed to describe the evolution process of fissures inside the rock. The research results showed that the volume strain ratio curve of the rock fractures exhibited a logarithmic variation characteristic during the cyclic loading and unloading, and the fracture volume strain ratio better reflected the relative scale of the internal fracture strain in the rock to the total volume strain. The acoustic emission entropy value reflected the crack evolution behavior during the loading and failure processes, which was a rapid decline in the initial stage of loading and a rapid upward trend in the failure stage. The observed “V”-shaped change in the acoustic emission entropy can be used as an early warning for rock failure. The research results can provide theoretical guidance for rock stability analysis.

Spatial propagation characteristics of acoustic emission signals in parallel steel wire cables

Accurate spatial propagation characteristics facilitate damage spatial localization, which is crucial for assessing the condition of parallel steel wire cables (PSWC). Existing studies have focused on the longitudinal propagation of acoustic emission (AE) signals, limiting accurate spatial damage assessment. This study comprehensively explored the spatial propagation characteristics of AE signals in PSWC using finite elements and attenuation tests. AE signals propagate hexagonally on the transverse section, with different amplitude attenuation rates at different angles—8% at 0° and 60°, 5 % at 30° and 45°. Additionally, AE signals exhibit oscillatory propagation between different wires in the longitudinal direction. The longitudinal speed (5706 m/s) is approximately 4.2 times faster than the transverse speed (1371 m/s), and the propagation path can be simplified as longitudinal and then transverse, offering valuable guidance for damage localization. The optimum frequency is 150 kHz in the transverse direction and 30 kHz in the longitudinal direction.

Response characteristics of acoustic emission signal and judgment criteria for different fracture modes

Coal mining is going deeper into the ground, resulting in more intense and frequent mine dynamic disasters. To ensure the early warning of dynamic disasters, it is significant to accurately reveal the differences of acoustic emission (AE) signals generated by rock fractures. This paper focuses on studying how AEs average frequency (AF) and rise angle (RA) change in sandstone during loading, and examines the characteristics of waveform amplitude, energy, and frequency distribution of AE signals from different types of fractures. The findings reveal that the percentage of shear fracture gradually increases with increasing load, and the energy activity of the AE signal is significantly enhanced in the high stress stage. The occurrence of the main fracture was preceded by a large number of low-frequency tensile fracture AE signals, accompanied by a small decrease in RA and a small increase in AF. The spectra of different fracture signals were characterized as “low anomalous F” for shear fractures, “vertical F” for low-frequency tensile fractures, and “high anomalous F” for high-frequency tensile fractures. Their energy distribution in the frequency domain was respectively described as “peak-centered distribution”, “pillar-shaped distribution” and “peak-skewed distribution”. The outcomes of the decomposition and reconstruction from the P- and S-waves reveal that the P wave energy (Ep) dominates in the high-frequency tensile fracture AE signal, while the S wave energy (Es) is greater in the low-frequency tensile fracture and the shear fracture AE signals. The ES/EP threshold value for laboratory discrimination of tensile and shear fracture is 3, as the fracture extends and penetrates, the ES/EP value rises rapidly at the appearance of macroscopic fracture. The findings offer theoretical guidance for monitoring and early warning of coal and rock dynamic hazards as well as revealing the morphology of fracture source.

Machine learning coupled with acoustic emission signal features for tool wear estimation during ultrasonic machining of Inconel 718

The material removal in the ultrasonic machining process is due to the fracture of the workpiece material. The fracture is due to energy transfer by vibrating abrasive particles. The vibration energy is induced by a tool oscillating at a frequency of more than 20 kHz. The vibrating particles not only impact the workpiece surface but also impact the oscillating tool, and it leads to the fracture of the tool, which is of interest to understand to guarantee efficient machining with accuracy and precision. In the current investigation, the tool wear during the ultrasonic machining of Inconel 718 super alloy is attempted. An acoustic emission sensor is integrated with the machining setup, and signal information is extracted in the time and time-frequency domains. The features and process parameters are input to a support vector regression model to estimate tool wear. The model developed for tool wear prediction yields an accuracy of 96.13% compared to the model developed with only process parameters, which delivers an accuracy of 84.89%. The developed model can be beneficial for the real-time monitoring of tool wear during the ultrasonic machining process for industrial and remote applications.

Study on the mechanical properties and acoustic emission signal characteristics of freezing pipe

The increase in freezing depth requires thicker, stronger, and colder freezing walls, and various complex factors in deep strata greatly increase the risk of freezing pipe fracture. To address the phenomenon of freezing pipe fracture, this paper designs freezing pipe and joint mechanical performance experiments based on acoustic emission (AE) technology, mainly testing the deformation of freezing steel pipes and composite joints at normal and low temperatures, changes in load bearing capacity, and corresponding AE characteristics of the process. Additionally, the associated AE characteristics throughout the process will be analyzed. The ultimate goal is to establish a discriminative pattern for identifying the critical fracture of freezing pipes based on the analysis of AE signal characteristics in conjunction with mechanical properties. The sensitivity of the AE system under low-temperature conditions and the reliability of the test were tested through pencil lead break experiments, and saltwater noise detection experiments were conducted to prevent noise interference from low-temperature saltwater flow and pipe wall friction in the identification of crucial signals for freezing pipe fracture. This study provides a basis for identifying the deformation mechanics and fracture warning of freezing pipes through dynamic analysis of AE monitoring information.

A hybrid deep learning method for AE source localization for heterostructure of wind turbine blades

An acoustic emission (AE) and hybrid deep learning networks based damage source localization method for heterostructure of wind turbine blades is proposed in this paper. Firstly, comprehensive data preprocessing is performed, including AE signal denoising, feature extraction, feature selection and normalization. New training features including AE descriptors, features of time, frequency domains and spectral features are extracted. A feature selection method based on Light-GBM and correlation analysis is employed to identify relevant features for AE source localization. Subsequently, two deep learning networks, AM-BiLNN and AM-LCNN, are developed to locate the damage source in two steps. Then, numerical tests are implemented on localized structure of a wind turbine blade to verify the performance of the proposed method and the performance of the selected features and the robustness of the proposed method under noise are investigated. Furthermore, a comparative investigation between the proposed method with long short-term memory neural networks (LSTM), convolutional neural networks (CNN) and the cluster-based method is carried out to demonstrate the superiority of the proposed method. The results highlight the superiority and robustness of the proposed method. Feature selection is shown to effectively enhance coordinate localization performance.

Interpretable real-time monitoring of pipeline weld crack leakage based on wavelet multi-kernel network

The deep learning technology used for pipeline weld crack leakage monitoring lacks physical interpretability, which makes it difficult to provide theoretical support to decision-makers, reducing the practicality and applicability of the technology. To solve this problem, a deep learning framework that combines interpretability and feature fusion is proposed to solve the real-time monitoring problem of pipeline leaks. First, three different wavelet basis functions are used to analyze the leakage acoustic emission signal, and the resulting time-frequency features exhibit correlation and complementarity. Based on this, an interpretable neural network with different wavelet convolution kernels is designed to extract abstract feature details of wideband acoustic emission signals through multi-level dynamic receptive fields. Then, a feature fusion module based on channel importance weighting was designed to optimize the learning process of the network by highlighting the contribution of different channels. Finally, the effectiveness and superiority of the proposed method were verified through pipeline leakage acoustic emission monitoring experiments. The results show that the proposed method can effectively extract distinguishing features of leak acoustic emission signals, and the recognition accuracy of different leakage states can reach 98.32%, which is significantly higher than that of typical deep learning methods. In addition, feature map visualization proves that the proposed method has physical interpretability in abstract feature extraction, which will provide a reference basis for correct decision-making by industrial technicians.

Surface damage characteristics and identification based on acoustic emission in diamond point grinding carbon/carbon ceramic matrix composites

This study mainly investigated the effect of machining parameters on acoustic emission (AE) characteristics in grinding three-dimensional carbon/carbon ceramic matrix composites with superabrasive diamond grinding points. Signal processing techniques including fast Fourier transform (FFT) and short-time Fourier transform (SWFT) were applied to evaluate frequency features of AE signals. The RMS values were used as an indicator to detect grinding energy releasing characteristics. Results indicated that grinding speed and grinding depth were the main influencing factors on RMS values, while feed speed presented limited effects. The maximum undeformed chip thickness hmax and active grits number were two key factors affecting RMS variation of the AE signals, which corresponded to the intensity of single AE source and the number of total AE ones, respectively. The material removal mechanisms were studied via detailed SEM micrographs of machined surfaces, revealing that fiber fracture and debonding were the main material removal modes in point grinding carbon/carbon composites. The material removal mode can be possibly identified from the frequency of AE signal, as the band of 12–35 kHz mainly corresponded to fiber fracture, 35–70 kHz referred to debonding between the fiber and matrix, 70–90 kHz indicated the frictions, and the fourth band (90–120 kHz) was related to the matrix cracks.

Real-Time Recognition Method for Key Signals of Rock Fracture Acoustic Emissions Based on Deep Learning.

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.

Damage pattern recognition for corroded beams strengthened by CFRP anchorage system based on acoustic emission techniques

This study presents a damage pattern recognition approach for corroded steel beams strengthened by CFRP anchorage system based on acoustic emission clustering analysis. The proposed method includes four steps: acoustic emission signal acquisition, feature extraction, clustering analysis, and damage pattern recognition. Four corroded beams with different corrosion levels and strengthening schemes were tested under four-point bending loading. The acoustic emission signals were collected during the loading process and analyzed using Gaussian mixture model clustering method. The results showed that the collected AE data were analyzed using clustering analysis, successfully distinguishing the distinct damage patterns associated with each mode. The AE signals exhibited distinct characteristics for different damage modes: concrete matrix damage had high-frequency and low-energy characteristics, CFRP-matrix debonding showed intermediate values for all parameters, and CFRP tearing had longer durations, lower peak frequencies, and high-energy characteristics. Besides, the study identified three stages of the damage process: an initial stage with fewer low-intensity AE signals, a damage development stage characterized by an increase in concrete-matrix damage and CFRP – matrix debonding signals, and a continuous damage growth stage with significant AE signals associated with three damage modes. Furthermore, the degree of corrosion significantly influenced the cumulative AE energy of damage modes. Lower degrees of corrosion led to higher cumulative energy from concrete matrix damage and CFRP-matrix debonding. These findings provide valuable insights for understanding the damage evolution and failure mechanisms of CFRP-strengthened corroded beams. The use of AE techniques for damage pattern recognition can enhance the evaluation and design of CFRP anchorage systems, leading to more effective rehabilitation strategies for corroded structures.

Experimental Study on the Damage Mechanism of Reinforced Concrete Beams Based on Acoustic Emission Technique

The purpose of this paper is to investigate the developmental process of internal damage in prestressed concrete beams under static loading conditions. We conducted static loading tests on two prestressed reinforced concrete beams and one ordinary reinforced concrete beam. Acoustic emission (AE) technology was employed to dynamically monitor the entire process of the test beams simultaneously. The energy and ring count AE characteristic parameters were studied, and the frequency domain characteristics of acoustic emission signals from three test beams were analyzed. The actual failure process of the test beams was compared with the AE characteristic parameters and the waveform frequency distribution. Furthermore, the corresponding relationships between the actual failure process and the AE characteristic parameters were analyzed. Additionally, the frequency distribution of waveforms was examined. The obtained data, including deflection, strain, and prestress variation within the beams, were combined with theoretical calculations to explore the damage development law of simply supported reinforced concrete beams during the entire failure process. Comparative studies revealed a strong correlation between the actual failure processes of the three test beams and the AE characteristic parameters as well as the waveform frequency distribution. The strain variation trend of the ordinary reinforced concrete beam closely matched the AE signal characteristics, with the critical load often occurring at around 40% of the ultimate load. The strain and deflection variations of the prestressed reinforced concrete beams exhibited a robust correspondence with the AE signal characteristics. The critical load typically manifested at approximately 80% of the ultimate load. The ultimate load of the prestressed reinforced concrete beams decreased by approximately 20% under cyclic loading conditions compared to hierarchical loading.

Prediction of remaining fatigue life of metal specimens using data-driven method based on acoustic emission signal

Aiming at the difficulty of predicting the remaining fatigue life of mechanical parts, a similar fatigue life prediction method based on acoustic emission signals is proposed considering the failure of vibration signals. Moreover, this paper innovatively introduces the temperature signal as a degradation feature to assist the acoustic emission signal feature for fatigue life prediction. The proposed fatigue life prediction method involves multiple processes such as feature extraction, feature smoothing, feature selection, feature compression and health index construction. A variational autoencoder structure combined with a long short-term memory neural network is used to achieve feature compression and retain feature trend. A tensile fatigue test bench was developed to collect the degradation signal from health to fatigue fracture to validate the proposed method. The validation results show that the proposed method can accurately predict the remaining fatigue life. In addition, the role of various data processing methods and the applicability of the proposed method in different working conditions are also discussed.

Cluster-based sensor selection framework for acoustic emission source localization in concrete

The acoustic emission (AE) method can determine the location of damage initiation and progression in large-scale structures using an array of sensors. As the location accuracy depends on proper identification of time of arrival and wave velocity, the method is more successful in homogeneous and isotropic materials than in heterogeneous materials such as concrete. The heterogeneity causes dispersive and attenuative properties such that the source-sensor distance and angle control the AE signal characteristics influencing the source location accuracy. Generally, using more than the minimum number of sensors in the location algorithm results in more accurate source localization. If the AE signal of a sensor is significantly different from the other sensors, its time of arrival may not contribute beneficially to the source localization algorithm. On the contrary, this may increase errors in determining arrival time due to signal distortion caused by dispersion, low signal-to-noise ratios resulting from attenuation, or sensors being occupied with detecting nearby noise signals. In this paper, a new cluster-based sensor selection framework is developed for selecting the best sensor combinations before applying the source localization algorithm. The framework involves selecting the best combination of sensors to input into the source localization algorithm based on the cross-correlation characteristics of signal features for single AE events or cluster analyses for large datasets. Both approaches identify the signal similarity of sensors to be used in the location sensor group. As two-dimensional source localization requires a minimum of three sensors, the number of sensor outputs extracted from the sensor selection framework is bounded by three. The source localization accuracy is evaluated using the data collected impact excitation with the known source location and structural tests of a Basalt Fiber-Reinforced Polymer (BFRP) reinforced concrete slab. The impact experiments show that the new framework to select the best three-sensor combination increases the localization accuracy to 93%, unlike the results obtained by using all six sensors (80%) and the first three sensors in the hit sequence (75%). The framework is applied to the AE data recorded from actual damage initiation and progression in a simply supported BFRP-reinforced concrete slab. The cluster of events accumulates more densely at the mid-span, where the crack initiation is validated with crack sensors and images. It is demonstrated that selecting the sensors for two-dimensional source localization using similarity analyses improves the accuracy of the source location in concrete.