Small Cracks Research Articles

Corrosion and mechanical characterisation of Al/TiO2/Y2O3 hybrid nanocomposites produced by squeeze casting

ABSTRACT In this study, the corrosion and mechanical performance of hybrid aluminium matrix nanocomposites (HAMNCs) reinforced with titanium oxide (TiO2) and yttrium oxide (Y2O3) nanoparticles were investigated. A squeeze-casting process was used to develop five HAMNCs with wt.% of nanoparticles of 2.5, 5, 7.5, and 10. The corrosion resistance of HAMNCs was investigated during a 168-h salt spray test. XRD examined the crystallographic and elemental properties of the HAMNCs. FESEM was used to examine nanoparticle distribution and interaction in the matrix. The microhardness, compression strength and yield strength properties of the fabricated samples were examined. The introduction of nanoparticles at 5 wt.% TiO2 +5 wt.% Y2O3 (HAMNC6) in the Al matrix had the most outstanding properties (corrosion resistance, microhardness, compression strength, yield strength). The properties were shown to be inversely proportional with an increase in the wt.% of the nanoparticles. The SEM analysis of corroded surfaces revealed that TiO2 and Y2O3 nanoparticles were found near the grain boundaries of HAMNC6, causing small pits and minor cracks.

Accurate acoustic classification research of visually similar monochrome porcelain fragments

AbstractExploring a non-destructive and rapid evaluation method for precious ancient ceramic relics is of significant importance. Currently, there are countless monochrome porcelain fragments awaiting measurement and categorization. Various instruments such as XRF, XRD, SEM, OM, and thermoluminescence dating have been extensively utilized by numerous researchers to study ancient ceramics. However, these techniques pose challenges in reliably identifying monochrome porcelain fragments from the same kiln with similar appearance, content, and microstructure due to their limitations. To address this issue, this study presents an acoustic measurement system that utilizes audible frequencies to non-destructively evaluate monochrome porcelain fragments. The proposed method enables the extraction of parameters related to time domain analysis (e.g., group delay), frequency domain analysis (e.g., resonance), and sound loss characteristics of these fragments. This non-destructive and efficient technology for detecting acoustic characteristics of monochrome porcelain fragments presented in this work clarifies the fundamental principles governing the interaction between sound waves and ancient ceramic fragments while providing a completely non-destructive and highly efficient method for classifying and restoring valuable solid cultural heritages like stone, jade, bronze etc. Moreover, this approach can also be applied for non-destructive testing of elastic modulus in advanced ceramic devices including detecting small cracks, deterioration effects due to aging as well as other defects.

The mechanism of silent steam pop during radiofrequency catheter ablation: an ex-vivo porcine heart study

Abstract Background A steam pop (SP) during radiofrequency catheter ablation(RFCA) is usually assumed as an audible one and shows obvious changes of impedance, temperature or bipolar/unipolar potential of ablation catheter. Moreover, a SP generates a void which sometime penetrate the tissue and cardiac perforation. In clinical setting, we have sometimes experienced gas explosion from an ablating site detected only by intracardiac echography (ICE) without any sound or remarkable parameter changes, so called as a ‘silent’ SP (S-SP). However, the mechanism of this phenomenon is not yet to be clarified. Methods We performed RFCA of porcine ventricle using Tactiflex until a SP or 120s. In the first step, the output and the contact force (CF) of RFCA were fixed for 50W and 1g, 5g, 10g or 20g. Second, an ablation catheter was moved by every second with 50W. A SP was defined as suddenly gas explosion during RFCA detected by ICE and in case of non-audible SP by 2 persons standing 50cm away from ablation site, it was provided as a S-SP. Otherwise, we defined as audible one (A-SP). We analyzed the occurrence of S-SP and ablation parameters between S-SP and A-SP. Results In the first stage (n=24), 4 S-SPs and 17 A-SP were observed(S-SP; 3 in 1g and 1 in 20g, A-SP; 2 in 1g, 5 in 5g, 6 in 10g and 4 in 20g, p=0.0454). The ICE images of S-SP and A-SP seemed to be similar. S-SP significantly occurred in the setting of lower CF as compared with A-SP {3.0(2.25-16.5) vs. 8.0(5.0-21.5); p=0.0290}. There were no statistical differences concerning duration of RFCA, initial/final impedance, impedance drop, initial/maximum temperature. At the timing of SP, changes of potentials were relatively smaller in S-SP {bipolar: 0.975(0.565-6.410) vs. 5.700(3.680-8.915); p=0.0648, unipolar: 1.265(0.208-3.793) vs. 8.070(5.820-8.815); p=0.0003}. Voids formation after SPs were detected in 2(50%) of S-SP and 16(94%) of A-SP(p=0.0797). In the second beating stage (n=46), 14 S-SPs and 20 A-SPs were observed (Figure 1). Although there were no differences of average/maximum CF throughout RFCA, S-SP dominantly occurred when a catheter was pulling back against the tissue, or at the bottom of CF curve (Figure2). Whereas A-SP did when a catheter was pushing toward tissue, or at the end of ascending limb of CF curve. For ablated lesion, S-SP exhibited less void or smaller crack (Figure1). Conclusions S-SP was difficult to detect without ICE and occurred in the combined condition of high power (50W) and lower CF. For the setting of beating mode, just like clinical environment, S-SP was involved while an ablation catheter was moved away from the tissue. Although S-SP seemed to be safer than A-SP due to less or smaller voids, continuous RFCA after S-SP might involve a big void or perforation. Therefore, it might be better to use ICE for the detection of S-SP, especially for a site accompanied by unstable CF, like papillary muscles.Figure 1.Ablation parameters in a cathetFigure 2.The timing of steam pop

Cumulative damage characteristics of rock samples under cyclic low energy inclined plane impact

The ore pass wall in underground mines is often damaged by the impact and wear caused by unloaded ores. Studying the mechanisms of rock damage and failure under different impact angles can provide technical insights for the design and maintenance of the ore passes. This study employed an inclined impact experimental device along with a drop hammer loading test machine to perform cyclic low-energy impact tests on sandstone samples at five different inclined plane angles. The porosity of the rock samples was measured using a nuclear magnetic resonance (NMR) detection system, which provided data on porosity, T2 spectrum distribution, and NMR images of the samples after different numbers of impacts at different slope angles. The results indicate that: (1) Under cyclic inclined plane impact loading, an increase in the inclination angle, leads to reduced damage to the rock sample. The rock sample impacted at a 45° inclined plane exhibited the most severe damage. Rock samples with large inclination angles are more prone to experience rupture fractures at the tip of the inclined plane, primarily due to shear-tensile failure. The porosity changes dramatically at initially slope angles, resulting in greater damage. (2) As the number of impacts increases, the porosity of the samples first decreases, then increases, and subsequently decreases again. This progression corresponds to the closure of large pores following the first impact, followed by the expansion of micropores into macropores after 5 impacts, ultimately leading to gradual degradation of the samples until failure. (3) As the number of impacts increases, new cracks form within the rock sample and small cracks expand. Despite an increase in the number of micropores, the macropores still exert a significant influence on the rock samples, with the macropore spectrum area accounting for over 95%.

Experimental study on recycling rubber to increase the impact resistance of cement mortar

The COVID-19 pandemic has led to a surge in medical waste generation, posing hazards to both the environment and global health. The impacts of the COVID-19 pandemic’s medical waste hazard may persist long after the pandemic itself subsides. Improper disposal of medical waste can contaminate environment, posing risks to ecosystems and public health. Discarded medical rubber gloves, for example, can become a source of infection, improper disposal of these gloves can escalate the spread of infectious diseases and increase the risk of transmission of the virus to the general public. This study proposes an innovative and sustainable method to reinforce cement mortar by adding recycled glove rubber as an additive to cement mortar to increase its resistance to impact loads. This study conducted uniaxial compression tests, separating hopkinson pressure bar (SHPB) experiments and SEM observations to evaluate the quasi-static compressive strength and dynamic stress of recycled rubber fiber mortar (RRFM) with varying recycled rubber fiber (RRF) contents (0, 1%, 2%, 3%). Strain curves, dynamic increase factor (DIF), energy absorption rules, failure modes, and microstructure of RRFM mixtures. The experimental results demonstrate that with the addition of RRF, the dynamic stress-strain curve flattens and the peak strain gradually increases. The RRFM sample shows stronger toughness. In comparison to regular cement mortar (NM), RRFM has a higher DIF and specific absorbed energy, a faster increase in dynamic compressive strength, and the ability to absorb more energy per unit volume. Under the same impact load, RRFM has fewer and smaller cracks than NM. Scanning electron microscopy (SEM) testing also observed that RRF formed a strong connection pattern with the cement mortar matrix.

Small fatigue crack behavior of CP-Ti in thin-walled cruciform specimens under biaxial loading

This study investigates the small fatigue crack propagation behavior of commercially pure titanium (CP-Ti) using thin-walled cruciform specimens under in-plane biaxial loading, considering the effects of biaxial ratio and phase angle. Increasing phase angle results in more secondary cracks merging with main cracks perpendicular to the rolling direction (RD) and transverse direction (TD), a phenomenon attributed to the rise in shear stress that accelerates main crack growth. Higher loading biaxiality or a lower phase angle leads to decreased crack propagation rates and increased biaxial fatigue life. Electron backscatter diffraction (EBSD) analysis reveals that when the maximum normal stress aligns with the RD, prismatic slip primarily governs crack propagation, thereby accelerating crack propagation rates. Conversely, alignment with the TD reduces prismatic slip activity and crack propagation rates. Under equi-biaxial loading, prismatic slip activity decreases further, and crack propagation is dominated by multiple slip and twinning, consequently resulting in the slowest propagation rates. Additionally, a higher proportion of prismatic slip under high phase angle also accelerates crack propagation. Finally, incorporating Findley equivalent stress into the Chapetti model, which considers the crack length-dependent threshold effect, a highly accurate biaxial small fatigue crack propagation rate model is proposed.

A lightweight Mini-YOLOv5s algorithm for small target crack detection in tunnels

ABSTRACT The automatic detection and identification of tunnel cracks is very important for safe driving and tunnel maintenance. In order to accelerate the application of automated detection and reduce the deployment cost of target detection algorithm on edge devices, this paper adopts non-destructive testing and proposes a lightweight Mini-YOLOv5s algorithm for small target crack detection in tunnels, which mainly includes DP-C3 module, GDConv module, ECA-C3 module, CARAFE lightweight upsampling operator and loss function IGIoU. Among them, the DP-C3 module uses PConv to reduce the computational complexity of the model, and uses dilated convolution to enrich the receptive field to improve the information loss. The GDConv module improves the feature extraction capability of deep information. The feature fusion of small crack target information is realised by using ECA-C3 module and CARAFE lightweight up-sampling operator. A new loss function IGIoU is used to pay more attention to the contact degree of the boundary frame, so as to minimise the loss and improve the detection accuracy. Experiments show that the detection accuracy of Mini-YOLOv5s on self-made tunnel crack dataset reaches 91%, which compensates for the information loss, while the number of model parameters and GFLOPs are reduced by 35.4% and 30.4% respectively.

Fatigue life prediction of film-cooling Hole specimens with initial damage

This study investigates a Nickel-based single crystal (SX) superalloy with femtosecond laser-drilled film-cooling holes (FCHs) under varying temperatures (room temperature, 850 °C, and 980 °C), employing a novel framework for predicting fatigue life based on initial manufacturing damage quantification. For all tested anisotropic SX superalloy specimens (including smooth and FCH specimens), the initial damage state is characterized as an equivalent initial flaw size (EIFS), and an EIFS calculation model considering stress concentration is established. Subsequently, the fatigue crack paths and microstructural characteristics of the FCH specimens at different temperatures are analyzed, elucidating crack initiation mechanisms and propagation patterns. A novel incremental plasticity J-integral driving force for fatigue crack propagation is introduced. By incorporating the closure effect of small crack propagation and employing Markov Chain Monte Carlo simulations for determining crack growth rate probabilities, a more accurate expression for the crack growth rate in relation to ΔJfat − ΔJth is derived. This expression comprehensively captures crack patterns on crystallographic planes and Type I mixed mode behavior. Finally, the total fatigue life of the FCH structures, featuring a threefold dispersion zone in both room and high-temperature environments, is predicted through experimental observations and description of crack growth rates. The predicted outcomes significantly outperform those of the conventional life prediction models reliant on crystal plasticity theory.

Investigation of cracking behavior of fine-grained clays exposed to different humidity environments and engineering implications based on X-ray computed tomography

Due to the humidity difference between fine-grained clay and atmosphere environment, the complex crack network is formed, which is the main channel for water storage and migration and hence poses a potential threat to engineering construction. Therefore, the appropriate characterization of cracking behavior of fine-grained clay is of great significance for exploring its microphysical properties. To this end, this work took expansive soils as research object and a series of desiccation tests and X-ray computed tomography tests were conducted to investigate the shrinkage cracking behavior. The results indicate that a higher desiccation rate records a smaller shrinkage strain, but it aggravates the cracking on a much larger scale. Especially at high desiccation rates, two-dimensional crack ratio shows a significant fluctuation. Small cracks tend to turn into large ones during desiccation, and the increasing desiccation rate primarily exerts a significant effect on the cracks with equivalent radius more than 1000 µm. The expansive soil is dominated by horizontal cracks, and a low desiccation rate mainly promotes the connection between horizontal cracks, whereas high desiccation rates enhance the connectivity of oblique cracks, which exerts an adverse effect on soil slopes. Besides, the rise in desiccation rate leads to a wealth of micro-scale pores and throats occurring in the soil. The fine-grained clays at higher desiccation rates present larger pore and throat volume, more connected pores, and higher average coordination number, thus enhancing the connectivity between pore and pore. Permeability simulation results also confirm the positive correlation between connected crack ratio and hydraulic conductivity of the soil. In terms of engineering significance, narrowing down the difference in humidity between fine-grained clays and atmosphere is the most effective measure to constrain the extension of cracks.

Experimental investigation of FSW induced property changes in welded dissimilar Mg–Al–Zn alloys

Intense plastic deformation and intermixing during friction stir welding of dissimilar alloys may suppress the properties in welded zone. To suitably control these changes, careful study is required. Present research investigates microstructure, mechanical performance and corrosion behaviour at different rotational speeds in friction stir welded dissimilar AZ31–AZ91 Mg alloys. Very small cracks were present in welded zone due to formation of magnesium oxide (MgO). The EBSD analysis suggest more concentrated fibre texture at 1000 rpm tool rotational speed as compared to 700 rpm tool rotational speed in welded zone and the texture maximum intensity was 39.447 times of random distribution at tool rotational speed of 1000 rpm. The obtained maximum microhardness was 82 Hv at tool rotational speed of 700 rpm. The maximum values of tensile strength (234.86 ± 7.77 MPa) and flexural strength (350.89 ± 17.67 MPa) of welded samples were decreased as compared to base materials. The corrosion rate of welded samples was increased and corroded surface have some pits and corroded rings. The highest corrosion rate (2.1596 mm / year ) was obtained at 700 rpm. This experimental work suggests that in overall, sample welded at 1000 rpm tool rotational speed has better weld property.

On the Growth of Small Cracks in 2024‐T3 and Boeing Space, Intelligence and Weapon Systems AM LPBF Scalmalloy®

ABSTRACTThe desire to use additively manufactured (AM) parts to ensure the availability of military aircraft, and to build limited‐life unmanned aerial vehicles (drones), coupled with the United States Air Force (USAF) approach to the airworthiness certification of AM parts has focused attention on durability analysis/assessment, and hence on the growth of small cracks in AM parts. Previous studies have shown that laser powder fusion built (LPBF) Scalmalloy® has: i) A yield stress and an ultimate strength that are greater than that of AA2024‐T3 and comparable to that of AA7075‐T6; ii) A resistance to crack growth that is better than that of AA7075‐T6 and comparable to that of AA2024‐T3. However, since the ability to predict the durability of a part is essential for its airworthiness certification, the present paper illustrates how to perform a linear elastic fracture mechanics (LEFM)‐based durability assessment of Boeing Space, Intelligence and Weapon System (BSIWS) LPBF Scalmalloy®. The durability study includes specimens with both machined surfaces and surfaces left in the as‐built condition. As a result, it would appear that BISWS AM LPBF Scalmalloy® is an ideal candidate for building limited‐life AM replacement parts for fixed and rotary wing aircraft and drones.

Numerical study of phase space analysis for the development of subsurface crack detection method using pulsed eddy current

Root-deck cracks, a prominent form of subsurface damage observed in orthotropic steel decks (OSDs), pose significant challenges to maintaining structural integrity. Early detection of these cracks is crucial to prevent further deterioration. This paper introduces novel and robust techniques for processing response signals obtained from the Pulsed Eddy Current Technique (PECT) using phase space analysis. The proposed methods aim to improve sensitivity and noise handling capabilities by employing an appropriate damage index derived from comprehensive phase space analysis, enabling effective detection of subsurface cracks in OSDs. A numerical study demonstrates the effectiveness of the proposed methods in detecting crack length change as small as 1 mm from the bottom of a 12 mm steel plate, with the Change in Phase Space Topology (CPST) identified as a suitable damage index. Furthermore, the newly proposed signal processing techniques allow for a more comprehensive interpretation of response signals for subsurface damage detection, encapsulating the extent of damage within a single value, even in the presence of small crack lengths near the bottom of the steel plate and noise. As a result, the proposed methods overcome the limitations of conventional approaches and offer promising prospects for enhanced subsurface crack detection in OSDs.

Competitive Fracture Mechanism and Microstructure‐Related Life Assessment of GH4169 Superalloy in High and Very High Cycle Fatigue Regimes

ABSTRACTHigh and very high cycle fatigue tests were performed to examine the microstructure and fracture mechanism of GH4169 superalloy in combination with techniques including electron‐backscatter diffraction (EBSD). Fractographic analysis revealed that surface failures are induced by surface flaws, whereas internal failures are caused by pores, facets, and inclusions. The three‐dimensional observation shows that fracture surfaces exhibit an irregular texture due to crystallographic mismatch of grains and plastic deformation at the crack tip. Based on EBSD analysis, Euler angles exhibited a complex geometry of grain orientation at the crack tip area, hindering crack propagation as evidenced by lower values of the Schmid factor and misorientation at the crack tip. Furthermore, the threshold values of small and long cracks decrease, whereas the transformation sizes from small to long crack growth increase from surface to internal failure. Finally, a novel microstructure defect‐based life prediction model is established, and the predicted results demonstrate a close resemblance to experimental outcomes.

Laboratory Model Tests on the Deformation and Failure of Terraced Loess Slopes Induced by Extreme Rainfall

Heavy rainfall is the main factor inducing the failure of loess slopes. However, the failure mechanism and mode of terraced loess slopes under heavy rainfall have not been well investigated and understood. This paper presents the experimental study on the deformation and failure of terraced loess slopes with different gradients under extreme rainfall conditions. The deformation and failure processes of the slope and the migration of the wetting front within the slope during rainfall were captured by the digital cameras installed on the top and side of the test box. In addition, the mechanical and hydrological responses of the slope, including earth pressure, water content, pore water pressure, and matric suction, were monitored and analyzed under rainfall infiltration and erosion. The experimental study shows that the deformation and failure of terraced loess slopes under heavy rainfall conditions exhibit the characteristic of progressive erosion damage. In general, the steeper the slope, the more severe the deformation and failure, and the shorter the time required for erosion failure. The data obtained from sensors embedded in the slope can reflect the mechanical and hydraulic characteristics of the slope in response to rainfall. The earth pressure and pore water pressure in the slope exhibit a fluctuating pattern with continued rainfall. The failure mode of terraced loess slopes under extreme rainfall can be summarized into five stages: erosion of slope surface and formation of small gullies and cracks, expansion of gullies and cracks along the slope surface, widening and deepening of gullies, local collapse and flow-slip of the slope, and large-scale collapse of the slope. The findings can provide preliminary data references for researchers to better understand the failure characteristics of terraced loess slopes under extreme rainfall and to further validate the results of numerical simulations and analytical solutions.

Fatigue Life Assessment of Corroded AlSi10MgMn Specimens

This study investigates the influence of pre-corrosion damage on the fatigue behavior of AlSi10MgMn high-pressure die-cast specimens, using the statistical distribution of corrosion depths. The analysis is conducted on two different surface conditions: an unmachined rough surface (Ra=5.05μm) and a machined, polished surface (Ra=0.25μm). For the unmachined specimens, the corrosive damage manifests as homogeneously spread localized corrosion, whereas the polished specimens exhibit less uniform but deeper corrosion. The average corrosion depth of the polished specimens is found to be slightly higher (313 μm compared to 267 μm) with a broader depth distribution. Specimens are tested under a constant bending load amplitude in laboratory conditions at a stress ratio of R=0 until fracture. A fracture mechanics-based methodology is developed to assess the remaining fatigue life of corroded specimens, utilizing short and long crack fracture mechanical parameters derived from SENB specimens. This model incorporates a thickness reduction of the critical specimen cross-section based on the corrosion depth distribution and combines it with a small initial crack of the intrinsic defect size (aeff=14μm). Regardless of the surface condition, using the most frequent corrosion depth for thickness reduction provides a good estimate of the long-life fatigue strength, while using the 90th percentile depth allows for a conservative assessment.

A novel damage index for crack identification of a drilling riser during deployment based on the modal vibration energy flow

Early detection of structural damage especially small cracks in marine deepwater drilling risers is of paramount importance. Small cracks are always hard to detect because of weak vibration signals if using traditional damage indices, such as natural frequencies and mode shapes including modal displacements, cross-section slopes, and curvatures. Especially when the deepwater riser is during deployment, the variable suspension riser length and strong sea environment noise make the small crack identification more difficult. To address this problem, this study formulates a new concept of damage detection by integrating the vibration energy flow theory into the vibration-based damage detection (VDD) technique. A novel damage-sensitive feature (DSF) named modal vibration energy flow (MVEF) is established for detecting and locating the small cracks in deepwater drilling risers. The capability of the approach is verified by using the same riser model and the numerical results in the literature. The sensitivities versus crack positions and depths, variable suspension riser length, and sea noise are studied in detail. Results show that the proposed index MVEF is more sensitive than the classic traditional DSFs, i.e., modal slope, modal strain (or curvature), and modal strain energy. In total, the MVEF approach can accurately identify the small cracks and is robust against noise interference, suitable for detecting and locating small cracks in the deepwater drilling riser during deployment.

Study on the fatigue properties of SPR-bonded aluminum-steel sheet joints

This study deals mainly with the influence of adhesive layer on the fatigue behavior and fretting of self-piercing riveted (SPR) joint joining differing thicknesses of AlSi10MnMg aluminum and DP590 steel sheets in lap shear geometry. Fatigue life, failure modes, crack propagation and fretting behaviors of the SPR and SPR-bonded joints were investigated and compared. The results showed that the static strength and fatigue life of SPR-bonded joints were significantly enhanced than that of SPR joints, but the fatigue failure mode of SPR-bonded and SPR joints differed. The SPR-bonded joints all failed in a rivet tail pull-out mode at all tested loads, which accompanied with small cracking in the aluminum sheet in contact with the rivet tail at lower test load. However, the failure mode of the SPR joints shifted from the aluminum sheet cracking to rivet tail pull-out as the fatigue test load increased. And during the aluminum sheet cracking failure, the fatigue crack originated from the faying interface of aluminum and steel sheet at the vicinity of the rivet shank and propagated along the width direction of aluminum sheet. Fretting wear analysis showed that the overall extent of fretting decreased and the location of fretting areas varied due to the adhesive bonding. Fretting of SPR joints mostly existed at the faying interface between aluminum and steel about 1.5mm away from the rivet shank and resulted in fatigue crack initiation, while the fretting region of SPR-bonded joints shifted to the faying interface between rivet tail and aluminum sheet.

Acoustic Emission Measurements During a Four-Point Bending Test on a Reinforced Concrete Specimen

Acoustic emission (AE) measurements were carried out during a four-point bending test to in-vestigate the influence of the shear load-bearing capacity of reinforced concrete beams (so-called Leonhardt beam) with shear reinforcement. The results of AE measurements show that the AE activity begins immediately after starting loading. During the test approximately 3.500 AE events could be automatically located using longitudinal and transverse wave arrival times. Most AE events are in the central region of the specimen within the sensor network. Therefore, only the flexural tensile cracks are represented through AE locations. The transverse shear crack that occurred during the ultimate failure of the specimen is outside the sensor arrangement and has not been detected. Due to the localization error, the AE events are distributed in a cloud-like manner, and as a result, they do not sharply depict the macroscopic flexural tensile cracks. Ra-ther, acoustic emission indicates that a crack network of many small microscopic cracks formed in the tensile area, resulting in a very rough and fragmented crack morphology. Additional to the conventional source location, we applied the so-called collapsing method to highlight structures already inherent within the unfocused AE events clouds.

Predicting actual crack size through crack signal obtained by advanced Flexible Eddy Current Sensor using ResNet integrated with CBAM and Huber loss function

This study presents an advanced FEC sensor, engineered by arranging coils in a co-directional current configuration. Moreover, boasting a compact design, the FEC sensor showcases significantly enhanced spatial resolution, enabling robust detection of small cracks even at low excitation frequencies and mitigating issues of overlapping in adjacent crack detection. Results indicate successful crack detection through voltage and phase measurements, albeit with phase signals demonstrating variation at specific excitation frequencies, complicating the determination of actual crack sizes. Consequently, a novel model is proposed to forecast actual crack sizes, leveraging experimental data from the FEC sensor system. This model integrates a Residual Neural Network (ResNet) architecture with a Convolutional Block Attention Module (CBAM) and utilizes the Huber loss function to minimize errors during model training. Comparative analysis underscores the superior performance of the proposed model in predicting crack length and depth compared to the standalone ResNet, particularly when utilizing the Huber loss function with a δ value of 1.0. Evaluation metrics, encompassing Mean Squared Error (MSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE), illustrate an average accuracy surpassing 95 % for crack size predictions. Consequently, the proposed model demonstrates remarkable performance, significantly reducing the time required to ascertain actual crack sizes by leveraging voltage and phase measurements.

Design of coal mine drilling detection model combining improved YOLOv5 and Gaussian filtering

Coal is currently the most important energy source in most countries. With the advent of information intelligence, more and more intelligent technologies are being applied in coal mine detection. A new model for coal mine drilling detection, which combines improved YOLOv5 and Gaussian filtering, is proposed to address the low efficiency and poor accuracy in manual detection of coal mine drilling. This new model incorporates attention mechanism and multi-object detection model on the basis of traditional YOLOv5. Due to factors such as equipment vibration and electrical interference in drilling detection, random noise is often mixed into the image signal data obtained. In order to effectively reduce the impact of noise on data and improve signal-to-noise ratio, Gaussian filtering method is studied for data denoising. This new model’s border regression loss value was 0.004 lower than the YOLOv5 loss value. This new optimization method’s accuracy was improved from 0.966 to 0.982. This new model improved the detection accuracy of small cracks by about 0.05. The detection depth of the coal seam in this new model was 9.54 m, which was closer to the true value than other methods. Therefore, using the new model to detect coal mine boreholes can effectively improve the accuracy of borehole detection images, which has a good effect on the analysis of coal mine rock layers. This new model has a good guiding role in the detection images and rock analysis research of future coal mine boreholes. The research has good research value in oil drilling inspection, natural gas pipeline monitoring, and quality inspection of industrial automation systems. This provides important technical support for future coal mine drilling image detection and rock analysis research.