Intelligent Small Sample Defect Detection of Concrete Surface Using Novel Deep Learning Integrating Improved YOLOv5

Dear Editor,This letter presents an intelligent small sample defect detection of concrete surface using novel deep learning integrating the improved YOLOv5 based on the Wasserstein GAN(WGAN)enhancement algorithm.The proposed method is capable of producing top-notch data sets to address the issues of insufficient samples and substandard quality.

Utilization of Basalt Saw Mud as a Spherical Porous Functional Aggregate for the Preparation of Ordinary Structure Concrete

To promote the production and application of artificial aggregates,save natural sand resources and protect the ecological environment,we evaluated the feasibility of using spherical porous functional aggregates(SPFAs) formed by basalt saw mud under autoclave curing in ordinary structural concrete.In our work,two types of prewetted functional aggregates were taken as replacements for natural aggregates with different volume substitution rates(0%,5%,10%,15%,20%,25%,and 30%) in the preparation of ordinary structural concrete with water-to-binder ratios(W/B) of 0.48 and 0.33.The effects of the functional aggregate properties and content,W/B,and curing age on the fluidity,density,mechanical properties and autogenous shrinkage of ordinary concrete were analyzed.The experimental results showed that the density of concrete declined at a rate of not more than 5%,and the 28 d compressive strength could reach 31.0-68.2 MPa.Low W/B,long curing age and high-quality functional aggregates were conducive to enhancing the mechanical properties of SPFAs concrete.Through the rolling effects,SPFAs can optimize the particle gradation of aggregate systems and improve the fluidity of concrete,and the water stored inside SPFAs provides an internal curing effect,which prolongs the cement hydration process and considerably reduces the autogenous shrinkage of concrete.SPFAs exhibits high strength and high density,as well as being more cost-effective and ecological,and is expected to be widely employed in ordinary structural concrete.

High-speed penetration of ogive-nose projectiles into thick concrete targets:Tests and a projectile nose evolution model

The majority of the projectiles used in the hypersonic penetration study are solid flat-nosed cylindrical projectiles with a diameter of less than 20 mm.This study aims to fill the gap in the experimental and analytical study of the evolution of the nose shape of larger hollow projectiles under hypersonic penetration.In the hypersonic penetration test,eight ogive-nose AerMet100 steel projectiles with a diameter of 40 mm were launched to hit concrete targets with impact velocities that ranged from 1351 to 1877 m/s.Severe erosion of the projectiles was observed during high-speed penetration of heterogeneous targets,and apparent localized mushrooming occurred in the front nose of recovered projectiles.By examining the damage to projectiles,a linear relationship was found between the relative length reduction rate and the initial kinetic energy of projectiles in different penetration tests.Furthermore,microscopic analysis revealed the forming mechanism of the localized mushrooming phenomenon for eroding penetration,i.e.,material spall erosion abrasion mechanism,material flow and redistribution abrasion mechanism and localized radial upsetting deformation mechanism.Finally,a model of highspeed penetration that included erosion was established on the basis of a model of the evolution of the projectile nose that considers radial upsetting;the model was validated by test data from the literature and the present study.Depending upon the impact velocity,v0,the projectile nose may behave as undistorted,radially distorted or hemispherical.Due to the effects of abrasion of the projectile and enhancement of radial upsetting on the duration and amplitude of the secondary rising segment in the pulse shape of projectile deceleration,the predicted DOP had an upper limit.

Fractal Study on the Evolution of Micro-Pores in Concrete Under Freeze-Thaw

After exposure to freeze-thaw cycles, scanning electron microscopy(SEM) and nuclear magnetic resonance(NMR) were used to test the four mixtures. The microstructure is qualitatively analyzed from the 2D SEM image and the 3D pore distribution curve before and after freezing and thawing. The fractal dimension is utilized to characterize the two-dimensional topography image and the three-dimensional pore distribution, quantitatively. The results reveal that the surface porosity and volume porosity increase as the freeze-thaw action increases. Self-similarity characteristics exist in micro-damage inside the concrete. In the fractal dimension, it is possible to characterize pore evolution quantitatively. The fractal dimension correlates with pore damage evolution. The fractal dimension effectively quantitatively characterizes micro-damage features at various scales from the local to the global level.

A U-Shaped Network-Based Grid Tagging Model for Chinese Named Entity Recognition

Chinese named entity recognition(CNER)has received widespread attention as an important task of Chinese information extraction.Most previous research has focused on individually studying flat CNER,overlapped CNER,or discontinuous CNER.However,a unified CNER is often needed in real-world scenarios.Recent studies have shown that grid tagging-based methods based on character-pair relationship classification hold great potential for achieving unified NER.Nevertheless,how to enrich Chinese character-pair grid representations and capture deeper dependencies between character pairs to improve entity recognition performance remains an unresolved challenge.In this study,we enhance the character-pair grid representation by incorporating both local and global information.Significantly,we introduce a new approach by considering the character-pair grid representation matrix as a specialized image,converting the classification of character-pair relationships into a pixel-level semantic segmentation task.We devise a U-shaped network to extract multi-scale and deeper semantic information from the grid image,allowing for a more comprehensive understanding of associative features between character pairs.This approach leads to improved accuracy in predicting their relationships,ultimately enhancing entity recognition performance.We conducted experiments on two public CNER datasets in the biomedical domain,namely CMeEE-V2 and Diakg.The results demonstrate the effectiveness of our approach,which achieves F1-score improvements of 7.29 percentage points and 1.64 percentage points compared to the current state-of-the-art(SOTA)models,respectively.

Mesoscale Mechanical Properties and Influencing Factors of Concrete under Uniaxial Tension

Monte Carlo simulations were carried out to generate a mesoscale model of concrete with randomly packed aggregates with different shapes and sizes.The mechanical properties of concrete specimens under uniaxial tensile loads were studied using statistical results.The results indicated that the entire process of damage and failure of specimens exhibited mainly two failure types:fracture patternsⅠandⅡ.Furthermore,the influences of the aggregate content ratio,aggregate shape,aggregate size,interfacial transition zone(ITZ)strength,and porosity ratio on the concrete specimens were analyzed.The numerical simulation results showed that the elastic modulus of the concrete specimens increased approximately linearly with the aggregate volume ratio but decreased linearly with the porosity and was not affected by the ITZ strength.The tensile strength decreased with the increases in the aggregate content and porosity of the sample,but increased linearly with the ITZ strength.In addition,the aggregate shape led to a difference in the tensile strength of the concrete.

Mechanical Behavior Based on Aggregates Microstructure of Ultra-high Performance Concrete

We developed ultra-high performance concrete(UHPC)incorporating mullite sand and brown corundum sand(BCS),and the quartz sand UHPC was utilized to prepare for comparison.The properties of compressive strength,elastic modulus,ultrasonic pulse velocity,flexural strength,and toughness were investigated.Scanning electron microscopy and nanoindentation were also conducted to reveal the underlying mechanisms affecting macroscopic performance.Due to the superior interface bonding properties between mullite sand and matrix,the compressive strength and flexural toughness of UHPC have been significantly improved.Mullite sand and BCS aggregates have higher stiffness than quartz sand,contributing to the excellent elastic modulus exhibited by UHPC.The stiffness and volume of aggregates have a more significant impact on the elastic modulus of UHPC than interface performance,and the latter contributes more to the strength of UHPC.This study will provide a reference for developing UHPC with superior elastic modulus for structural engineering.

Non-dimensional analysis on blast wave propagation in foam concrete:Minimum thickness to avoid stress enhancement

Foam concrete is a prospective material in defense engineering to protect structures due to its high energy absorption capability resulted from the long plateau stage.However,stress enhancement rather than stress mitigation may happen when foam concrete is used as sacrificial claddings placed in the path of an incoming blast load.To investigate this interesting phenomenon,a one-dimensional difference model for blast wave propagation in foam concrete is firstly proposed and numerically solved by improving the second-order Godunov method.The difference model and numerical algorithm are validated against experimental results including both the stress mitigation and the stress enhancement.The difference model is then used to numerically analyze the blast wave propagation and deformation of material in which the effects of blast loads,stress-strain relation and length of foam concrete are considered.In particular,the concept of minimum thickness of foam concrete to avoid stress enhancement is proposed.Finally,non-dimensional analysis on the minimum thickness is conducted and an empirical formula is proposed by curve-fitting the numerical data,which can provide a reference for the application of foam concrete in defense engineering.

Calculation of Mass Concrete Temperature and Creep Stress under the Influence of Local Air Heat Transfer

Temperature-induced cracking during the construction of mass concrete is a significant concern.Numerical simulations of concrete temperature have primarily assumed that the concrete is placed in an open environment.The problem of heat transfer between the air and concrete has been simplified to the concrete’s heat dissipation boundary.However,in the case of tubular concrete structures,where air inlet and outlet are relatively limited,the internal air temperature does not dissipate promptly to the external environment as it rises.To accurately simulate the temperature and creep stress in tubular concrete structures with enclosed air spaces during construction,we establish an air–concrete coupled heat transfer model according to the principles of conjugate heat transfer,and the accuracy of the model is verified through experiments.Furthermore,we conduct a case study to analyze the impact of airflow within the ship lock corridor on concrete temperature and creep stress.The results demonstrate that enhancing airflow within the corridor can significantly reduce the maximum concrete temperature.Compared with cases in which airflow within the corridor is neglected,the maximum concrete temperature and maximum tensile stress can be reduced by 12.5℃ and 0.7 MPa,respectively,under a wind speed of 4 m/s.The results of the traditional calculation method are relatively close to those obtained at a wind speed of 1 m/s.However,the temperature reduction process in the traditional method is faster,and the method yields greater tensile stress values for the corridor location.

Electrochemical Study of the Corrosion Inhibitory Capacity of Calcined Attapulgite in Reinforced Concrete Medium

The durability of reinforced concrete structures is greatly influenced by the corrosion of the reinforcement. In addition to air pollution related to the repair of corroded structures, chloride ions are the main factors of corrosion of reinforced concrete structures. This study aims to valorize a clay inhibitor against reinforcement corrosion in reinforced concrete. This clay (Attapulgite) was incorporated into reinforced concretes at different percentages of substitution of calcined attapulgite (0%, 5% and 10%) to cement in the formulation. The corrosion inhibitory power of attapulgite is evaluated in reinforced concretes subjected to the action of chloride ions at different intervals in the NaCl solution (1 day, 21 days and 45 days) by electrochemical methods (zero current chronopotentiometry, polarization curves and electrochemical impedance spectroscopy). This study showed that in the presence of chloride ions, the composition based on 10% attapulgite has an appreciable inhibitory effect with an average inhibitory efficiency of 82%.

Effect of Modification Treatment on Chloride Ions Permeability and Microstructure of Recycled Brick-mixed Aggregate Concrete

The modification methods of pozzolan slurry combined with sodium silicate and silicon-based additive were respectively adopted to treat recycled coarse brick-mixed aggregate(RCBA)in this study.The compressive strength and chloride permeability resistance of recycled aggregate concrete(RAC)before and after modification treatment were tested,and the microstructure of RAC was analyzed by mercury intrusion porosimetry(MIP)and scanning electron microscopy(SEM).The results show that the physical properties of RCBA strengthened by modification treatment are improved,and the compressive strength and chloride permeability resistance of treated RAC are also significantly improved.The modification treatment optimizes the pore size distribution of RAC,which increases the number of gel pores and transition pores,and decreases the number of capillary pores and macro pores.The surface fractal dimension shows a significant correlation with chloride diffusion coefficient,indicating that the variation of chloride permeability of treated RAC is consistent with the microstructure evolution.

Evaluation of internal void related defects in reinforced concrete slab using electromagnetic wave properties

This study aims to develop a damage-detection algorithm based on the electromagnetic wave properties inside a reinforced concrete structure.The proposed method involves employing two algorithms based on data measured using ground-penetrating radar—a common electromagnetic wave method in civil engineering.The possible defect area was identified based on the energy dissipated by the damage in the frequency-wavenumber domain,with the damage localized using the calculated relative permittivity of the measurements.The proposed method was verified through a finite difference time-domain-based numerical analysis and a testing slab with artificial damage.As a result of verification,the proposed method quickly identified the presence of damage inside the concrete,especially for honeycomb-like defects located at the top of the rebar.This study has practical significance in scanning structures over a large area more quickly than other non-destructive testing methods,such as ultrasonic methods.

Calculation of Mass Concrete Temperature Containing Cooling Water Pipe Based on Substructure and Iteration Algorithm

Mathematical physics equations are often utilized to describe physical phenomena in various fields of science and engineering.One such equation is the Fourier equation,which is a commonly used and effective method for evaluating the effectiveness of temperature control measures for mass concrete.One important measure for temperature control in mass concrete is the use of cooling water pipes.However,the mismatch of grids between large-scale concrete models and small-scale cooling pipe models can result in a significant waste of calculation time when using the finite element method.Moreover,the temperature of the water in the cooling pipe needs to be iteratively calculated during the thermal transfer process.The substructure method can effectively solve this problem,and it has been validated by scholars.The Abaqus/Python secondary development technology provides engineers with enough flexibility to combine the substructure method with an iteration algorithm,which enables the creation of a parametric modeling calculation for cooling water pipes.This paper proposes such a method,which involves iterating the water pipe boundary and establishing the water pipe unit substructure to numerically simulate the concrete temperature field that contains a cooling water pipe.To verify the feasibility and accuracy of the proposed method,two classic numerical examples were analyzed.The results showed that this method has good applicability in cooling pipe calculations.When the value of the iteration parameterαis 0.4,the boundary temperature of the cooling water pipes can meet the accuracy requirements after 4∼5 iterations,effectively improving the computational efficiency.Overall,this approach provides a useful tool for engineers to analyze the temperature control measures accurately and efficiently for mass concrete,such as cooling water pipes,using Abaqus/Python secondary development.

Experimental study on the size effect on the equation of state of concretes under shock loading

Adopting the classical theory of hydrocodes,the constitutive relations of concretes are separated into an equation of state(EoS)which describes the volumetric behavior of concrete material and a strength model which depicts the shear properties of concrete.The experiments on the EoS of concrete is always challenging due to the technical difficulties and equipment limitations,especially for the specimen size effect on the EoS.Although some researchers investigate the shock properties of concretes by fly-plate impact tests,the specimens used in their tests are usually in one size.In this paper,the fly-plate impact tests on concrete specimens with different sizes are performed to investigate the size effect on the shock properties of concrete materials.The mechanical background of the size effect on the shock properties are revealed,which is related to the lateral rarefaction effect and the deviatoric stress produced in the specimen.According to the tests results,the modified EoS considering the size effect on the shock properties of concrete are proposed,which the bulk modulus of concrete is unpredicted by up to 20% if size effects are not accounted for.

On the Preparation of Low-Temperature-Rise and Low-Shrinkage Concrete Based on Phosphorus Slag

The effects of different contents of a MgO expansive agent and phosphorus slag on the mechanical properties,shrinkage behavior,and the heat of hydration of concrete were studied.The slump flow,setting time,dry shrinkage,and hydration heat were used as sensitive parameters to assess the response of the considered specimens.As shown by the results,in general,with an increase in the phosphorus slag content,the hydration heat of concrete decreases for all ages,but the early strength displays a downward trend and the dry shrinkage rate increases.The 90-d strength and dry shrinkage of concrete could be improved with a phosphorus residue content between 0%-20%,with the best performances in terms of mechanical properties and shrinkage characteristics being achieved for a content of 20 kg/m^(3).On the basis of these results,it can be concluded that appropriate amounts of phosphorus slag and MgO expansive agent can be used to improve the compressive strength of concrete in the later stage by reducing the hydration heat and dry shrinkage rate,respectively.

Resilience-incorporated seismic risk assessment of precast concrete frames with“dry”connections

A resilience-incorporated risk assessment framework is proposed and demonstrated in this study to manifest the advantageous seismic resilience of precast concrete frame(PCF)structures with“dry”connections in terms of their low damage and rapid recovery.The framework integrates various uncertainties in the seismic hazard,fragility,capacity,demand,loss functions,and post-earthquake recovery.In this study,the PCF structures are distinguished from ordinary reinforced concrete frame(RCF)structures by characterizing multiple limit states for the PCF based on its unique damage mechanisms.Accordingly,probabilistic story-wise pushover analyses are performed to yield story-wise capacities for the predefined limit states.In the seismic resilience analysis,a step-wise recovery model is proposed to idealize the functionality recovery process,with separate considerations of the repair and non-repair events.The recovery model leverages the economic loss and downtime to delineate the stochastic post-earthquake recovery curves for the resilience loss estimation.As such,contingencies in the probabilistic post-earthquake repairs are incorporated and the empirical judgments on the recovery parameters are largely circumvented.The proposed framework is demonstrated through a comparative study between two“dry”connected PCFs and one RCF designed as alternative structural systems for a prototype building.The results from the risk quantification indicate that the PCFs show reduced loss hazards and lower expected losses relative to the RCF.Particularly,the PCF equipped with energy dissipation devices at the“dry”connections largely reduces the expected economic loss,downtime,and resilience loss by 29%,56%,and 60%,respectively,compared to the RCF.

Quantification of the concrete freeze–thaw environment across the Qinghai–Tibet Plateau based on machine learning algorithms

The reasonable quantification of the concrete freezing environment on the Qinghai–Tibet Plateau(QTP) is the primary issue in frost resistant concrete design, which is one of the challenges that the QTP engineering managers should take into account. In this paper, we propose a more realistic method to calculate the number of concrete freeze–thaw cycles(NFTCs) on the QTP. The calculated results show that the NFTCs increase as the altitude of the meteorological station increases with the average NFTCs being 208.7. Four machine learning methods, i.e., the random forest(RF) model, generalized boosting method(GBM), generalized linear model(GLM), and generalized additive model(GAM), are used to fit the NFTCs. The root mean square error(RMSE) values of the RF, GBM, GLM, and GAM are 32.3, 4.3, 247.9, and 161.3, respectively. The R^(2) values of the RF, GBM, GLM, and GAM are 0.93, 0.99, 0.48, and 0.66, respectively. The GBM method performs the best compared to the other three methods, which was shown by the results of RMSE and R^(2) values. The quantitative results from the GBM method indicate that the lowest, medium, and highest NFTC values are distributed in the northern, central, and southern parts of the QTP, respectively. The annual NFTCs in the QTP region are mainly concentrated at 160 and above, and the average NFTCs is 200 across the QTP. Our results can provide scientific guidance and a theoretical basis for the freezing resistance design of concrete in various projects on the QTP.

Influence of Recycled Concrete Fine Powder on Durability of Cement Mortar

In this paper,the durability of cement mortar prepared with a recycled-concrete fine powder(RFP)was examined;including the analysis of a variety of aspects,such as the carbonization,sulfate attack and chloride ion erosion resistance.The results indicate that the influence of RFP on these three aspects is different.The carbonization depth after 30 days and the chloride diffusion coefficient of mortar containing 10%RFP decreased by 13.3%and 28.19%.With a further increase in the RFP content,interconnected pores formed between the RFP particles,leading to an acceleration of the penetration rate of CO_(2)and Cl^(−).When the RFP content was less than 50%,the corrosion resistance coefficient of the compressive strength of the mortar was 0.84-1.05 after 90 days of sulfate attack.But the expansion and cracking of the mortar was effectively alleviated due to decrease of the gypsum production.Scanning electron microscope(SEM)analysis has confirmed that 10%RFP contributes to the formation of a dense microstructure in the cement mortar.

Impact of typical environments in China’s western mountainous areas on the durability of railway concrete:a review

Purpose–This study aims to analyze the impact mechanism of typical environments in China’s western mountainous areas on the durability of railway concrete and propose measures to improve durability.Design/methodology/approach–With the continuous promotion of infrastructure construction,the focus of China’s railway construction has gradually shifted to the western region.The four typical environments of large temperature differences,strong winds and dryness,high cold and low air pressure unique to the western mountainous areas of China have adverse effects on the durability of typical railway structure concrete(bridges,ballastless tracks and tunnels).This study identified the characteristics of four typical environments in the western mountainous areas of China through on-site research.The impact mechanism of the four typical environments on the durability of concrete in different structural parts of railways has been explored through theoretical analysis and experimental research;Finally,a strategy for improving the durability of railway concrete suitable for the western mountainous areas of China was proposed.Findings–The daily temperature difference in the western mountainous areas of China is more than twice that of the plain region,which will lead to significant temperature deformation and stress in the multi-layered structure of railway ballastless tracks.It will result in cracking.The wind speed in the western plateau region is about 2.5 to 3 times that of the plain region,and the average annual rainfall is only 1/5 of that in the plain region.The drying effect on the surface of casting concrete will significantly accelerate its cracking process,leading to serious durability problems.The environmental temperature in the western mountainous areas of China is generally low,and there are more freeze-thaw cycles,which will increase the risk of freeze-thaw damage to railway concrete.The environmental air pressure in the western plateau region is only 60%of that in the plain region.The moisture inside the concrete is more likely to diffuse into the surrounding environment under the pressure difference,resulting in greater water loss and shrinkage deformation of the concrete in the plateau region.The above four issues will collectively lead to the rapid deterioration of concrete durability in the western plateau region.The corresponding durability improvement suggestions from theoretical research,new technology development and standard system was proposed in this paper.Originality/value–The research can provide the mechanism of durability degradation of railway concrete in the western mountainous areas of China and corresponding improvement strategies.

Physics-data coupling-driven method to predict the penetration depth into concrete targets

The projectile penetration process into concrete target is a nonlinear complex problem.With the increase ofexperiment data,the data-driven paradigm has exhibited a new feasible method to solve such complex prob-lem.However,due to poor quality of experimental data,the traditional machine learning(ML)methods,whichare driven only by experimental data,have poor generalization capabilities and limited prediction accuracy.Therefore,this study intends to exhibit a ML method fusing the prior knowledge with experiment data.The newML method can constrain the fitting to experimental data,improve the generalization ability and the predic-tion accuracy.Experimental results show that integrating domain prior knowledge can effectively improve theperformance of the prediction model for penetration depth into concrete targets.