Development and optimization of object detection technology in pavement engineering: A literature review

Due to the rapid advancement of the transportation industry and the continual increase in pavement infrastructure,it is difficult to keep up with the huge road maintenance task by relying only on the traditional manual detection method.Intelligent pavement detection technology with deep learning techniques is available for the research and industry areas by the gradual development of computer vision technology.Due to the different characteristics of pavement distress and the uncertainty of the external environment,this kind of object detection technology for distress classification and location still faces great challenges.This paper discusses the development of object detection technology and analyzes classical convolutional neural network(CNN)architecture.In addition to the one-stage and two-stage object detection frameworks,object detection without anchor frames is introduced,which is divided according to whether the anchor box is used or not.This paper also introduces attention mechanisms based on convolutional neural networks and emphasizes the performance of these mechanisms to further enhance the accuracy of object recognition.Lightweight network architecture is introduced for mobile and industrial deployment.Since stereo cameras and sensors are rapidly developed,a detailed summary of three-dimensional object detection algorithms is also provided.While reviewing the history of the development of object detection,the scope of this review is not only limited to the area of pavement crack detection but also guidance for researchers in related fields is shared.

Dynamic simulation insights into friction weakening effect on rapid long-runout landslides:A case study of the Yigong landslide in the Tibetan Plateau,China

This study proposed a novel friction law dependent on velocity,displacement and normal stress for kinematic analysis of runout process of rapid landslides.The well-known Yigong landslide occurring in the Tibetan Plateau of China was employed as the case,and the derived dynamic friction formula was included into the numerical simulation based on Particle Flow Code.Results showed that the friction decreased quickly from 0.64(the peak)to 0.1(the stead value)during the 5s-period after the sliding initiation,which explained the behavior of rapid movement of the landslide.The monitored balls set at different sections of the mass showed similar variation characteritics regarding the velocity,namely evident increase at the initial phase of the movement,followed by a fluctuation phase and then a stopping one.The peak velocity was more than 100 m/s and most particles had low velocities at 300s after the landslide initiation.The spreading distance of the landslide was calculated at the two-dimension(profile)and three-dimension scale,respectively.Compared with the simulation result without considering friction weakening effect,our results indicated a max distance of about 10 km from the initial unstable position,which fit better with the actual situation.

Intelligent extraction of road cracks based on vehicle laser point cloud and panoramic sequence images

In light of the limited efficacy of conventional methods for identifying pavement cracks and the absence of comprehensive depth and location data in two-dimensional photographs,this study presents an intelligent strategy for extracting road cracks.This methodology involves the integration of laser point cloud data obtained from a vehicle-mounted system and a panoramic sequence of images.The study employs a vehicle-mounted LiDAR measurement system to acquire laser point cloud and panoramic sequence image data simultaneously.A convolutional neural network is utilized to extract cracks from the panoramic sequence image.The extracted sequence image is then aligned with the laser point cloud,enabling the assignment of RGB information to the vehicle-mounted three dimensional(3D)point cloud and location information to the two dimensional(2D)panoramic image.Additionally,a threshold value is set based on the crack elevation change to extract the aligned roadway point cloud.The three-dimensional data pertaining to the cracks can be acquired.The experimental findings demonstrate that the use of convolutional neural networks has yielded noteworthy outcomes in the extraction of road cracks.The utilization of point cloud and image alignment techniques enables the extraction of precise location data pertaining to road cracks.This approach exhibits superior accuracy when compared to conventional methods.Moreover,it facilitates rapid and accurate identification and localization of road cracks,thereby playing a crucial role in ensuring road maintenance and traffic safety.Consequently,this technique finds extensive application in the domains of intelligent transportation and urbanization development.The technology exhibits significant promise for use in the domains of intelligent transportation and city development.

Mechanical response and microscopic damage mechanism of pre-flawed sandstone subjected to monotonic and multilevel cyclic loading:A laboratory-scale investigation

This study aims to investigate the mechanical response and acoustic emission(AE)characteristic of pre-flawed sandstone under both monotonic and multilevel constant-amplitude cyclic loads.Specifically,we explored how coplanar flaw angle and load type impact the strength and deformation behavior and microscopic damage mechanism.Results indicated that being fluctuated before rising with increasing fissure angle under monotonic loading,the peak strength of the specimen first increased slowly and then steeply under cyclic loading.The effect of multilevel cyclic loading on the mechanical parameters was more significant.For a single fatigue stage,the specimen underwent greater deformation in early cycles,which subsequently stabilized.Similar variation pattern was also reflected by AE count/energy/b-value.Crack behaviors were dominated by the fissure angle and load type and medium-scale crack accounted for 74.83%–86.44%of total crack.Compared with monotonic loading,crack distribution of specimen under cyclic loading was more complicated.Meanwhile,a simple model was proposed to describe the damage evolution of sandstone under cyclic loading.Finally,SEM images revealed that the microstructures at the fracture were mainly composed of intergranular fracture,and percentage of transgranular fracture jumped under cyclic loading due to the rapid release of elastic energy caused by high loading rate.

How do the landslide and non-landslide sampling strategies impact landslide susceptibility assessment? d A catchment-scale case study from China

The aim of this study is to investigate the impacts of the sampling strategy of landslide and non-landslide on the performance of landslide susceptibility assessment(LSA).The study area is the Feiyun catchment in Wenzhou City,Southeast China.Two types of landslides samples,combined with seven non-landslide sampling strategies,resulted in a total of 14 scenarios.The corresponding landslide susceptibility map(LSM)for each scenario was generated using the random forest model.The receiver operating characteristic(ROC)curve and statistical indicators were calculated and used to assess the impact of the dataset sampling strategy.The results showed that higher accuracies were achieved when using the landslide core as positive samples,combined with non-landslide sampling from the very low zone or buffer zone.The results reveal the influence of landslide and non-landslide sampling strategies on the accuracy of LSA,which provides a reference for subsequent researchers aiming to obtain a more reasonable LSM.

Inner damage identification and residual strength assessment of a 3D printed tunnel with marble-like cementitious materials using piezoelectric transducers

Quantitative damage identification of surrounding rock is important to assess the current condition and residual strength of underground tunnels.In this work,an underground tunnel model with marble-like cementitious materials was first fabricated using the three-dimensional(3D)printing technique and then loaded to simulate its failure mode in the laboratory.Lead zirconate titanate piezoelectric(PZT)transducers were embedded in the surrounding rock around the tunnel in the process of 3D printing.A 3D monitoring network was formed to locate damage areas and evaluate damage extent during loading.Results show that as the load increased,main cracks firstly appeared above the tunnel roof and below the floor,and then they coalesced into the tunnel boundary.Finally,the tunnel model was broken into several parts.The resonant frequency and the peak of the conductance signature firstly shifted rightwards with loading due to the sealing of microcracks,and then shifted backwards after new cracks appeared.An overall increase in the root-mean-square deviation(RMSD)calculated from conductance signatures of all the PZT transducers was observed as the load(damage)increased.Damage-dependent equivalent stiffness parameters(ESPs)were calculated from the real and imaginary signatures of each PZT at different damage states.Satisfactory agreement between equivalent and experimental ESP values was achieved.Also,the relationship between the change of the ESP and the residual strength was obtained.The method paves the way for damage identification and residual strength estimation of other 3D printed structures in civil engineering.

Selection and modification of ground motion records using Newmark-Hall spectrum as target spectrum for long-period structures

Input ground motions have significant impacts on the uncertainty of structural responses in time-history analysis.In this study,records were selected and scaled for the evaluation of mean structural responses according to the target spectrum.The Newmark-Hall spectrum is closely related to seismic response of short,medium and long-period structures,so it was taken as the target spectrum here.The nonlinear time-history analyses of 9-story and 20-story steel moment-resisting frame structures were carried out as examples.They represent medium and long-period buildings,respectively.Three target spectra with risk of 50%,10%and 2%probabilities for exceedance in 50 years were calculated by the average Newmark-Hall spectrum method for three ground motion sets developed in the SAC Steel Project.The predicted structural mean responses of these Newmark-Hall spectra were compared with those calculated by the average spectral acceleration method for the same record set.It is found that both methods have similar accuracy for estimating the structural mean response.However,the method proposed herein is more effective in reducing the variability of the structural responses.Also,the proposed method is more advantageous for the time-history analysis of long-period structures or structures with more severe nonlinear responses under strong seismic excitations.

Wind-Thermal Environmental Characteristic of Multi-Variable Passive Enhanced Natural Ventilation System for High and Large Space Building

Natural ventilation effects in high and large space buildings of tropical areas greatlya ffect the air conditioning energy consumption.Aiming at nearly zero energy building design,thisp aper mainly contributes to provide theoretical basis and reference for thermal comfortable air conditioning system design of high and large space buildings.Taking a theatre in Hainan as study object,a newly composite enhanced natural ventilation system is proposed by integrating theu nderground tunnel-based earth to air heat exchange system and the solar chimney.Ventilationq uantity,air velocity and air temperature field,human vertical temperature gradient differenceu nder24simulation working conditions are considered and analyzed by using ANSYS Fluent.Fort he underground tunnel,results show that Group Two with double underground tunnels and side airs upply location shows its advantages in cooling effects and air supply uniformity.Then for the solar chimney,results show that the solar radiation intensity contributes to larger difference int ransmission power and leads to different cooling effects.On the whole,the system under workingc ondition No.7with120m long,side air supply,double underground tunnel and20m high,1mw ide,0.6°absorber plate angle solar chimney shows its priority in better comprehensive performance.

Analytical model for predicting time-dependent lateral deformation of geosynthetics-reinforced soil walls with modular block facing

To date,few models are available in the literature to consider the creep behavior of geosynthetics when predicting the lateral deformation(d)of geosynthetics-reinforced soil(GRS)retaining walls.In this study,a general hyperbolic creep model was first introduced to describe the long-term deformation of geosynthetics,which is a function of elapsed time and two empirical parameters a and b.The conventional creep tests with three different tensile loads(Pr)were conducted on two uniaxial geogrids to determine their creep behavior,as well as the a-Pr and b-Pr relationships.The test results show that increasing Pr accelerates the development of creep deformation for both geogrids.Meanwhile,a and b respectively show exponential and negatively linear relationships with Pr,which were confirmed by abundant experimental data available in other studies.Based on the above creep model and relationships,an accurate and reliable analytical model was then proposed for predicting the time-dependent d of GRS walls with modular block facing,which was further validated using a relevant numerical investigation from the previous literature.Performance evaluation and comparison of the proposed model with six available prediction models were performed.Then a parametric study was carried out to evaluate the effects of wall height,vertical spacing of geogrids,unit weight and internal friction angle of backfills,and factor of safety against pullout on d at the end of construction and 5 years afterwards.The findings show that the creep effect not only promotes d but also raises the elevation of the maximum d along the wall height.Finally,the limitations and application prospects of the proposed model were discussed and analyzed.

Restraint effect of partition wall on the tunnel floor heave in layered rock mass

The presence of horizontal layered rocks in tunnel engineering significantly impacts the stability and strength of the surrounding rock mass,leading to floor heave in the tunnel.This study focused on preparing layered specimens of rock-like material with varying thickness to investigate the failure behaviors of tunnel floors.The results indicate that thin-layered rock mass exhibits weak interlayer bonding,causing rock layers near the surface to buckle and break upwards when subjected to horizontal squeezing.With an increase in the layer thickness,a transition in failure mode occurs from upward buckling to shear failure along the plane,leading to a noticeable reduction in floor heave deformation.The primary cause of significant deformation in floor heave is upward buckling failure.To address this issue,the study proposes the installation of a partition wall in the middle of the floor to mitigate heave deformation of the rock layers.The results demonstrate that the partition wall has a considerable stabilizing effect on the floor,reducing the zone of buckling failure and minimizing floor heave deformation.It is crucial for the partition wall to be sufficiently high to prevent buckling failure and ensure stability.Through simulation calculations on an engineering example,it is confirmed that implementing a partition wall can effectively reduce floor heave and enhance the stability of tunnel floor.

Key Technology and Complete-set Equipment for Intelligent Construction of HSR Simply-supported Girder Reinforcement Framework

In view of the problems such as backward production mode,poor quality stability,high safety risk and incomplete control system during erection of the reinforcement framework of simply-supported box girders for high-speed railway(HSR),and in combination with the key points and main challenges in the reinforcement framework construction of Guangzhou-Zhanjiang HSR,the overall technical route for the intelligent manufacturing of reinforcement framework of simply-supported box girders is put forward.The component design of reinforcement framework of simply supported box girder is carried out based on BIM,and the feasibility of the scheme is verified through segment assembly test.The assembly techniques are studied in combination with the mesh design scheme to achieve rapid forming of the reinforcement framework.R&D of automatic processing equipment for components,material transshipment equipment,automatic hoisting equipment and technological equipment for assembly clamping fixture are carried out to realize the overall design of equipment production line.An intelligent control system is developed for the whole-process intelligent construction of reinforcement framework to realize the full life-cycle applications for the workshop production and visual management including intelligent layout and quality traceability.The research results systematically optimize and innovate the assembly and forming technologies of reinforcement framework in the prefabrication beam yard of high-speed railway,realize the component processing,automatic assembly and information technology management,improve the construction quality,efficiency and information technology level of intelligent manufacturing of reinforcement framework of railway prefabricated beam as a whole,and reduce the construction cost of the project.The research has realized a major breakthrough in the construction technology of railway prefabricated box girders,which has the extensive technical and market promotion values.

Prediction of damage potential in mainshock–aftershock sequences using machine learning algorithms

Assessing the potential damage caused by earthquakes is crucial for a community’s emergency response.In this study,four machine learning(ML)methods—random forest,extremely randomized trees,AdaBoost(AB),and gradient boosting(GB)—were employed to develop prediction models for the damage potential of the mainshock(DIMS)and mainshock–aftershock sequences(DIMA).Building structures were modeled using eight single-degree-of-freedom(SDOF)systems with different hysteretic rules.A set of 662 recorded mainshock–aftershock(MS-AS)ground motions was selected from the PEER database.Seven intensity measures(IMs)were chosen to represent the characteristics of the mainshock and aftershock.The results revealed that the selected ML methods can well predict the structural damage potential of the SDOF systems,except for the AB method.The GB model exhibited the best performance,making it the recommended choice for predicting DIMS and DIMA among the four ML models.Additionally,the impact of input variables in the prediction was investigated using the shapley additive explanations(SHAP)method.The high-correlation variables were sensitive to the structural period(T).At T=1.0 s,the mainshock peak ground velocity(PGVM)and aftershock peak ground displacement(PGDA)significantly influenced the prediction of DIMA.When T increased to 5.0 s,the primary high-correlation factor of the mainshock IMs changed from PGVM to the mainshock peak ground displacement(PGDM);however,the highcorrelation variable of the aftershock IMs remained PGDA.The high-correlation factors for DIMS showed trends similar to those of DIMA.Finally,a table summarizing the first and second high-correlation variables for predicting DIMS and DIMA were provided,offering a valuable reference for parameter selection in seismic damage prediction for mainshock–aftershock sequences.

Numerical Analysis of Perforation during Hydraulic Fracture Initiation Based on Continuous-Discontinuous Element Method

Perforation is a pivotal technique employed to establish main flow channels within the reservoir formation at the outset of hydraulic fracturing operations.Optimizing perforation designs is critical for augmenting the efficacy of hydraulic fracturing and boosting oil or gas production.In this study,we employ a hybrid finite-discrete element method,known as the continuous–discontinuous element method(CDEM),to simulate the initiation of post-perforation hydraulic fractures and to derive enhanced design parameters.The model incorporates the four most prevalent perforation geometries,as delineated in an engineering technical report.Real-world perforations deviate from the ideal cylindrical shape,exhibiting variable cross-sectional profiles that typically manifest as an initial constriction followed by an expansion,a feature consistent across all four perforation types.Our simulations take into account variations in perforation hole geometries,cross-sectional diameters,and perforation lengths.The findings show that perforations generated by the 39g DP3 HMX perforating bullet yield the lowest breakdown pressure,which inversely correlates with increases in sectional diameter and perforation length.Moreover,this study reveals the relationship between breakdown pressure and fracture degree,providing valuable insights for engineers and designers to refine perforation strategies.

Three-Dimensional Multi-Phase Microscopic Simulation of Service Life of Recycled Large Aggregate Self-Compacting Concrete

Recycled large aggregate self-compacting concrete (RLA-SCC) within multiple weak areas. These weak areas have poor resistance to chloride ion erosion, which affects the service life of RLA-SCC in the marine environment. A three-dimensional multi-phase mesoscopic numerical model of RLA-SCC was established to simulate the chloride ions transportation in concrete. Experiments of RLA-SCC immersing in chloride solution were carried out to verify the simulation results. The effects of recycled large aggregate (RLA) content and RLA particle size on the service life of concrete were explored. The results indicate that the mesoscopic numerical simulation results are in good agreement with the experimental results. At the same depth, the closer to the surface of the RLA, the greater the chloride ion concentration. The service life of RLA-SCC in marine environment decreases with the increase of RLA content. Compared with the service life of 20% content, the service life of 25% and 30% content decreased by 20% and 42% respectively. Increasing the particle size of RLA can effectively improve the service life of RLA-SCC in chloride environment. Compared with the service life of 50 mm particle size, the service life of 70 mm and 90 mm increased by 61% and 163%, respectively. .

Reactivation of a huge ancient landslide by surface water infiltration

An ancient landslide, situated in Deqin County, Yunnan Province, China, was used to investigate the reactivation by water infiltration. This study considers the infiltration process and landslide stability using finite-element method(FEM)-based models. The results show that the reactivation of old landslide deposit was triggered by the long-term leakage of diversion ditch before October 2012, and the reactivation was triggered again by the intense rainfall on 7-9 October 2012. The old cracks, which formed in the earlier reactivation of landslide, played a key role for the rainfall infiltration. They offered a preferential path for much more rainfall to infiltrate fast into deep soil, and caused wetting front to move down faster in landslide. The old slip zone with lower permeability was another important factor to cause the infiltrated water to accumulate and form a high pore water pressure above slip zone. Then the high pore water pressure decreased the shear strength of slip zone and triggered the reactivation of the old landslide deposit again.

Fabrication, property characterization and thermal performance of composite phase change material plates based on tetradecanol-myristic acid binary eutectic mixture/expanded perlite and expanded vermiculite for building application

A binary eutectic mixture composed of tetradecanol(TD)and myristic acid(MA)was maximally absorbed into the microstructures of expanded perlite(EP)and expanded vermiculite(EVMT),respectively,through a self-made vacuum adsorption roller to prepare phase change material(PCM)particle(PCP).Then EP and EVMT-based composite PCM plates were respectively fabricated through a mold pressing method.The thermal property,chemical stability,microstructure and durability were characterized by differential scanning calorimeter(DSC),Fourier transform infrared spectroscope(FT-IR),scanning electron microscope(SEM)and thermal cycling tests,respectively.The results show that both PCPs have high latent heats with 110 J/g for EP-based PCP and more than 130 J/g for EVMT-based PCP,compact microstructure without PCM leakage,stable chemical property and good durability.The research results have proved the feasibility for the vacuum adsorption roller used in the composite PCM fabrication.Results of thermal storage performance experiment indicate that the fabricated PCM plates have better thermal inertia than common building materials,and the thermal storage performance of PCM plates has nonlinearly changed with outside air velocity and temperature increase.Therefore,PCM plates show a significant potential for the practical application of building thermal storage.

Experimental investigation on the failure mechanism of a rock landslide controlled by a steep-gentle discontinuity pair

A type of rock landslide is very common in practical engineering, whose stability is mainly controlled by the rock bridge between the steep tensile crack at the crest and the low-inclination weak discontinuities at the toe(namely, ligament is the term for the locking section in the slope). To obtain a deeper understanding into the failure process of this kind of landslide, twenty-four physical slope models containing a steep-gentle discontinuity pair(a steep crack in the upper part and a low-inclination discontinuity in the lower part) were tested by applying vertical loads at the crests. The results indicate that the inclination angle of the ligament(θ) has great influence on the failure and stability of this type of rock slope. With the change of θ, three failure patterns(five subtypes) concerning the tested slopes can be observed, i.e., tensile failure of the ligament(Type 1), tension-shear failure of the ligament(Type 2) and two-stage failure of the main body(Type 3). The failure process of each failure mode presents five stages in terms of crack development, vertical load, horizontal/vertical displacements and strains in the ligaments. The specific range of the ligament angle between different failure patterns is summarized. The discussion on the failure resistances and ductility of different failure patterns, and the guiding significances of the experimental findings to the stability evaluation and the reinforcement were conducted.

Dynamic process analysis of the Niumiangou landslide triggered by the Wenchuan earthquake using the finite difference method and a modified discontinuous deformation analysis

The Niumiangou landslide was the largest landslide triggered by the 2008 Wenchuan earthquake,which was significantly affected by the amplification effect of seismic acceleration.The ringshear experiments indicated that the materials in the source area of the Niumiangou landslide were subjected to friction degradation under a big shear displacement,which may result in rapid movement of the landslide.In order to better understand the landslide movement and study the effect of the friction degradation on movement mechanisms,the dynamic process of Niumiangou landslide was simulated with a new numerical method,which combines the finite difference method(FDM)and the discontinuous deformation analysis(DDA).First,the FDM was used to study the initiation time,amplification effect and velocity of the landslide.Afterwards,these initiation velocities were applied to the blocks in the DDA model by corresponding coordination in the FDM model.A displacementdependent friction model of the sliding surface was incorporated into DDA code to further understand the kinetic behavior of the landslide.The results show that the displacement-dependent friction strongly decreases the friction coefficient of sliding surface under a big displacement,which can obviously promote the run-out and velocity of landslide.The model output well matches the topographic map formed by the landslide.This implies that the proposed model can be applied to the simulation of earthquake-induced landslides with amplification effect,and the friction degradation model is important to clarify the movement mechanism of high-speed and long-distance landslides.

Experimental study of vertical and batter pile groups in saturated sand using a centrifuge shaking table

To study the dynamic response of vertical and batter pile groups in saturated sand,dynamic tests of these pile groups in saturated sand were carried out using the ZJU400 geotechnical centrifuge at Zhejiang University.The following results were obtained.(1)As the motion intensity increased,the peak acceleration in soil layers at different depths significantly decreased,indicating that the soil stiffness was significantly reduced.(2)During the motion process,the instantaneous bending moment of the vertical and batter pile groups at different depths changed continuously,which had a strong relationship with the saturated sand liquefaction.In the process of sand liquefaction,the residual bending moment generated by the batter pile was more obvious than that of the vertical pile.(3)With the liquefaction of the saturated sand,the distribution of the maximum bending moment of the vertical pile group changed,and the bending moment near the pile cap of the vertical and batter pile groups was always large.(4)In certain cases,the horizontal acceleration and dynamic displacement of the vertical pile cap were amplified.When the motion intensity was large,residual displacement of the batter pile cap occurred.

Experimental and numerical study on hysteretic performance of SMA spring-friction bearings

This paper presents an experimental and numerical study to investigate the hysteretic performance of a new type of isolator consisting of shape memory alloy springs and friction bearing called an SMA spring-friction bearing （SFB）. The SFB is a sliding-type isolator with SMA devices used for the seismic protection of engineering structures. The principle of operation of the isolation bearing is introduced. In order to explore the possibility of applying SMA elements in passive seismic control devices, large diameter superelastic tension/compression NiTi SMA helical springs used in the SFB isolator were developed. Mechanical experiments of the SMA helical spring were carried out to understand its superelastic characteristics. After that, a series of quasi-static tests on a single SFB isolator prototype were conducted to measure its force-displacement relationships for different loading conditions and study the corresponding variation law of its mechanical performance. The experimental results demonstrate that the SFB exhibits full hysteretic curves, excellent energy dissipation capacity, and moderate recentering ability. Finally, a theoretical model capable of emulating the hysteretic behavior of the SMA-based isolator was then established and implemented in MATLAB software. The comparison of the numerical results with the experimental results shows the efficacy of the proposed model for simulating the response of the SFB.