Pavement Repair Research Articles

Introducing the mineral powder to strengthen polyurethane grouting materials for crack repair of asphalt pavements

Cracking in asphalt pavement may lead to structural distress while existing crack repair materials have significant shortcomings in terms of cost and construction efficiency. This study incorporates mineral powder into the polyurethane grouting materials to provide a more economical and durable solution for repairing cracks in asphalt pavement. The results of bonding and tensile tests show that excessive mineral powder may deteriorate the mechanical properties of polyurethane grouting materials, which is caused by the agglomeration of mineral powder observed by the microscale characterization. Characterization tests indicate that ultraviolet exposure results in the evolution of the chemical components and thermal stability of polyurethane grouting materials, subsequently causing the degeneration in the mechanical properties. The addition of mineral powders was found to increase the tensile strength of polyurethane grouting materials after Ultraviolet aging by 12 %, while the elongation at break measured in tensile tests remained essentially unchanged. The results of the splitting test, bending test, and immersion Marshall test prove the enhanced low-temperature property and moisture resistance of mineral powder-modified polyurethane grouting materials as compared to the styrene-butadiene-styrene emulsified asphalt. The economic analysis shows that this study presents a practical approach to cost-effective asphalt pavement crack repair, offering insights for enhancing the durability of asphalt pavements.

Research on Pavement Defect Detection Algorithm Based on SEM-YOLOv8n

Automated detection and identification of pavement distresses is essential for timely pavement repair. Subtle pavement defects and multiple defects detection is a challenging task under complex background. With the deepening of the deep learning network, some subtle features tend to disappear and are more difficult to detect under the influence of the complex background. To solve the above problems, this paper proposes the SEM-YOLOv8n pavement defect detection algorithm. Firstly, SPD-Conv is used to replace the traditional convolution, which is conducive to retaining more defect detail information in the image and improving the detection ability of subtle defects; then an efficient multi-scale attention mechanism is added to the fusion network, so that the network suppresses the background information and focuses more on the defect information. Finally, MPDIoU is introduced as a loss function, which optimizes the minimum perpendicular distance between the predicted bounding box and the real bounding box and improves the localization ability, thus improving the accuracy of the network. Finally, the effectiveness of the proposed network is verified on the IRRDD dataset, and the results show that the method achieves 91.9% (Precision), 91.3% (Recall), and 71.3% (mAP) for the classification and detection of road multi-scale minor defects, which meets the demand of real-time road defect detection.

Investigating the interfacial vertical shear behavior of BFPMPC mortar and cement concrete with pothole repair

Magnesium phosphate cement (MPC) has both traditional cement properties and ceramic properties with fast setting and hardening characteristics. To rapidly reopen traffic and extend its service life, MPC has been widely used in the rapid repair of highway and airport cement concrete pavement. This study utilizes basalt fiber-reinforced polymer-modified magnesium phosphate cement (BFPMPC) developed in previous research to rapid repair the typical potholes on cement concrete pavement, aims to reveal the interface properties between BFPMPC mortar and cement concrete and further investigate the underlying mechanisms for such properties. Firstly, the optimal mixture ratio was determined by orthogonal test design. Then, the shear strength of the repair interface was measured by composite BFPMPC mortar and cement concrete specimens. The mechanical characteristics of the repair interface and the microscopic mechanism were characterized by nano-indentation technology and SEM/EDS. Finally, the interface constitutive model was established by DIGIMAT and finite element model was developed to simulate the interface failure. Results showed that the no new hydration products were produced by the addition of polymer in BFPMPC. BFPMPC matrix became denser with the increase of age, resulting in the better bonding between fiber and paste. The interface vertical shear strength at 6 h and 3 d were 3.1 MPa and 3.9 MPa, respectively. SEM/EDS results showed that polymer has a certain self-healing ability to decrease the crack width with increase of curing age, and a variety of inclusions in the repair interface were observed. The elastic modulus of each inclusion phase can be effectively analyzed by nanoindentation. The simulation results showed that the pressure on upper surface of BFPMPC mortar transfers to the bottom through the repair interface. As the tensile stress on the bottom over the maximum interface tensile stress, the cracks were extend from the bottom to upper, then the structure was failed. Interface vertical shear strength of numerical simulation was, respectively, 3.149 MPa and 3.957 MPa. It is close to the plain shear strength experimental value, validating the proposed interface constitutive relationship.

Bonding Performance and Microstructural Mechanism between Rapid Repair Materials and Old Concrete Pavement

In China, airports predominantly utilize airport cement concrete pavement, which inevitably undergoes deterioration in service. To uphold pavement durability and functionality, and ensure aircraft operational safety, prompt repairs of affected areas are imperative. Therefore, ordinary Portland cement mortars were used as the control group to compare and analyze the bonding performances of two common airport pavement repair materials: modified Portland cement mortars and phosphate cement mortars. Meanwhile, through microscopic experiments, the microscopic characteristics of the interfacial transition zone (ITZ) were studied, and the interface bonding mechanism was analyzed. The research results indicate that the interface bonding strength between phosphate cement mortar and old concrete pavement is the highest. This was because the elements in phosphate cement penetrated the old concrete pavement through hydration reactions, forming van der Waals forces and chemical bonding forces. In addition, the research results indicated that the presence of old concrete pavement made the three repair materials produce similar sidewall effects with the old concrete pavement, leading to a low hydration degree of the repair materials. However, the chemical bonding and penetrating structure of phosphate cement compensated for the weakening effect of the ITZ in the repair materials.

Pavement Crack Detection and Solution with Artificial Intelligence

Detecting and repairing pavement cracks is essential to ensure road safety and longevity. Traditional inspection and maintenance methods are time-consuming, expensive and often inaccurate. In recent years, there has been a growing trend to use artificial intelligence (AI) to automate the process of pavement crack detection and repair. The article focuses on using AI techniques to detect pavement cracks and provide solutions to repair them. The proposed solution is based on using deep learning algorithms to analyze high-resolution images of the road surface. Photos are taken with a vehicle camera or a drone. The deep learning algorithm is trained using a large data set of tagged sidewalk crack images. Once trained, the algorithm can accurately detect and classify the type of cracks on the pavement surface, including longitudinal, transverse, block and crocodile cracks. The algorithm can also determine the severity of each crack and help prioritize repairs. When cracks are detected, the AI system can make recommendations for repair solutions. This includes identifying the appropriate caulk or filler material to use depending on the type and severity of the crack. The AI system can also recommend the most efficient and cost-effective repair method, such as B. Crack sealing, crack filling or deep repair. Overall, using AI to detect and repair cracks in sidewalks offers a more accurate, efficient, and cost-effective solution to keep roads safe and sustainable. By automating the inspection and repair process, this technology can help prevent accidents, reduce maintenance costs, and improve overall road safety.

An eco-friendly crack sealant approach for asphalt pavement by using laboratory tests and molecular dynamic simulation

Waste engine oil (WEO) is detrimental to the environment and challenging to recycle on a large scale. Fortunately, the utilization of WEO as an additive in asphalt pavement crack sealant offers both economic benefits and engineering feasibility. In this study, an eco-friendly crack sealant was prepared using WEO and crumb rubber (CR) modified asphalt (WCRA). The viscoelasticity, storage stability, adhesion, and water resistance properties of the sealant were tested to evaluate its suitability for crack repair. In addition, molecular dynamic (MD) simulation was employed to elucidate the interface adhesion mechanism of the sealant-crack wall interface. The test results demonstrated that the viscosity of the sealant is primarily proportional to the content of CR and inversely proportional to WEO. Furthermore, the storage stability is satisfactory after the addition of moderate WEO. The medium and high temperature flexibility of the sealant is between base asphalt and SBS-modified asphalt. Based on the laboratory tests, 35% (by weight of base asphalt) microwave-treated CR and 25% (by weight of CR) WEO are the optimal proportions for preparing the sealant. MD simulation demonstrated that CR inhibits the diffusion of asphalt components and aggregates asphaltenes in close proximity to the crack wall surface. WEO not only stimulates molecular activity but also maintains the equilibrium of the asphalt colloid system, which is conducive to the penetration and water resistance of the sealant. The study will provide a reference for the utilization of waste materials and the cost-effective repair of asphalt pavements.

Cooling characteristics of thermochromic powder modified sand fog seal on asphalt pavement in summer high-temperature environment

Reversible optical response can occur in thermochromic materials with temperature changes, which has great potential in the field of pavement temperature regulation. The thermochromic sand fog seal (TP-SFS) was proposed in this study, which has the functions of pavement repair and temperature control. In this study, different types (red, blue, black) and contents (0 %, 2 %, 4 %, 6 %, and 8 %) of thermochromic powders (TP) were used to prepare TP-SFS. Secondly, the cooling characteristics of different TP-SFS was explored from the perspectives of temperature change rate, cooling temperature, and temperature gradient, based on the designed indoor and outdoor multi-cycle illumination test. Then, the prediction model of the outdoor cooling effect was proposed. In addition, the conservation and environmental benefits of different TP-SFS were calculated according to the empirical formula. It is found that after spraying TP-SFS, the heating rate of pavement decreases and the cooling rate increases. The cooling effect at 2 cm depth of the pavement sprayed with TP-SFS is the most significant, and the temperature gradient of the pavement is reduced. The cooling temperature of the pavement increases with the increase of TP content. In the outdoor environment, the more obvious cooling effect occurs as the process of pavement temperature increases and decreases. Additionally, the reliability of the designed indoor test is high, and the cooling effect of TP-SFS in outdoor environment can be well predicted according to the proposed model. The results of empirical formula calculation show that TP-SFS has a significant effect on delaying rutting development and alleviating urban heat island effect.

A novel polyurethane-based mortar for pavement crack repair: Development, characterization, and performance evaluation

In light of the severe hazards posed by pavement cracks on traffic safety and infrastructure longevity, the development of a convenient and effective pavement repair material has become essential. The excellent cohesive strength and resilience of PU offer significant potential as a crack repair material, ensuring enhanced durability and reliability in pavement crack repairs. This study systematically explored the workability, mechanical properties, interface bonding performance, and fracture behavior of PUM as a pavement repair material through mechanical strength tests, interfacial tensile tests, and three-point bending tests based on DIC. The results indicate that the fluidity of PUM can be adjusted through the binder-sand ratio and PD content, enabling customization for various repair scenarios. PUM demonstrates exceptional one-day compressive and flexural strengths, achieving 18.8 MPa and 7.1 MPa, respectively. Furthermore, the bond tensile strength of PUM reaches 4.3 MPa, exhibiting accelerated strength development that meets the requirements for vehicle traffic after repairs. The lower elastic modulus of PUM, ranging from 0.28 to 0.63, indicates improved deformation adaptability. SEM analysis reveals a complex interfacial bonding network between PU and aggregates, considerably enhancing the energy dissipation capacity of PUM with a peak GF value of 205.05 N/m. DIC technology robustly captured the crack progression, revealing significantly reduced stress concentration at the crack tip of PUM, with no through-thickness cracks detected during the three-point bending fracture process. It is recommended that PUM be prepared with an 80 % binder-sand ratio and 5 % PD to achieve an optimal balance of workability, mechanical, and fracture properties.

Preparation and Performance Study of Rapid Repair Epoxy Concrete for Bridge Deck Pavement.

With the rapid development of bridge construction, the service life of bridges and traffic volume continue to increase, leading to the gradual appearance of diseases such as potholes and cracks in bridge deck pavements under repeated external loads. These issues severely impact the safety and service life of bridges. The repair of bridge deck potholes and cracks is crucial for ensuring the integrity and safety of bridge structures. Rapid repair materials designed for this purpose play a critical role in effectively and efficiently addressing these issues. In order to address the issues of pavement diseases, this study focuses on the rapid repair of epoxy concrete for bridge deck pavements and its performance is studied using experimental methods. Firstly, carbon black, rubber powder, and other materials were used to improve the elastic modulus and aging resistance of the epoxy concrete. Secondly, the addition of solid asphalt particles provided thermal sensitivity to the repair material. Finally, various properties of the rapid repair epoxy concrete for bridge deck pavements were tested through experiments including compressive strength testing, elastic modulus measurement, thermal sensitivity testing, and anti-UV aging testing. The experimental results show that adding carbon black and rubber powder reduces the elastic modulus of epoxy concrete by 25% compared to normal epoxy concrete, while increasing its aging resistance by 1.8%. The inclusion of solid asphalt particles provided thermal sensitivity to the repair material, contributing to better stress coordination between the repair material and the original pavement material under different temperature conditions. The epoxy concrete has early strength, toughness, and anti-aging properties, making it suitable for rapid repair of bridge deck pavement.

Influence of surface roughness and interfacial agent on the interface bonding characteristics of polyurethane concrete and cement concrete

As a new type of concrete material, polyurethane concrete has excellent physical and mechanical properties which is widely used in the maintenance and reinforcement of damaged areas of concrete pavement. Because of the difference in the performance between polymer concrete and ordinary concrete, it is of great significance to accurately evaluate the bond performance between polymer concrete and ordinary concrete in order to avoid interface damage in the subsequent use of the repaired pavement. In this study, the bonding specimens were made by changing the roughness and interfacial agent of the bonding interface between polymer concrete and cement concrete, and splitting tensile test and direct shear test were carried out to explore the bond properties between them. Polymer concrete-cement concrete composite beam specimens were made to simulate the maintenance and reinforcement of cement concrete pavements with polymer concrete in the actual projects, and the flexural performance test was carried out to explore the common mechanical characteristics of bonding specimens. The test results showed that the bond performance of polymer concrete and cement concrete was closely related to the interface roughness and the interfacial agents, and the addition of polymer concrete improves the common stress characteristic of composite beam specimens. The test results provide a basis for polymer concrete as a rapid repair material for concrete pavement repair.

Predicting Rutting Development Using Machine Learning Methods Based on RIOCHTrack Data

As the main cause of asphalt pavement distress, rutting severely affects pavement safety. Establishing an accurate rutting prediction model is crucial for asphalt pavement maintenance, pavement structure design, and pavement repair. This study explores five machine learning methods, namely Support Vector Regression (SVR), Artificial Neural Network (ANN), Gradient Boosting Decision Tree (GBDT), Random Forest (RF), and Extra Trees, to predict the development of rutting depth using data from RIOHTRack. The model’s performance is measured by comparing the performance evaluation indicators of different models, such as the coefficient of determination, root mean square error, mean absolute error, and mean absolute percentage error. The results demonstrate that integrated learning techniques such as RF, GBDT, and Extra Trees works best with R2 = 0.9761, 0.9833, and 0.9747. Moreover, the GBFT model can capture the trend of the measured rutting progression curve better than the mechanistic-empirical (M-E) model. The analysis of feature importance reveals that, in addition to external factors such as temperature and axle load, the aggregate of the asphalt concrete layer and air void crucially affect rutting. The higher the base strength, the smaller the rutting depth. The proposed model is highly straightforward and serves as an accessible analysis tool for engineers in practice.

A Parametric Study Investigating the Dowel Bar Load Transfer Efficiency in Jointed Plain Concrete Pavement Using a Finite Element Model

Transverse joints are introduced in jointed plain concrete pavement systems to mitigate the risk of cracks that can develop due to shrinkage and temperature variations. However, the structural behaviour of jointed plain concrete pavement (JPCP) is significantly affected by the transverse joint, as it creates a discontinuity between adjacent slabs. The performance of JPCP at the transverse joints is enhanced by providing steel dowel bars in the traffic direction. The dowel bar provides reliable transfer of traffic loads from the loaded side of the joint to the unloaded side, known as load transfer efficiency (LTE) or joint efficiency (JE). Furthermore, dowel bars contribute to the slab’s alignment in the JPCP. Joints are the critical component of concrete pavements that can lead to various distresses, necessitating rehabilitation. The Swedish Transport Administration (Trafikverket) is concerned with the repair of concrete pavement. Precast concrete slabs are efficient for repairing concrete pavement, but their performance relies on well-functioning dowel bars. In this study, a three-dimensional finite element model (3D-FEM) was developed using the ABAQUS software to evaluate the structural response of JPCP and analyse the flexural stress concentration in the concrete slab by considering the dowel bar at three different locations (i.e., at the concrete slabs’ top, bottom, and mid-height). Furthermore, the structural response of JPCP was also investigated for several important parameters, such as the joint opening between adjacent slabs, mispositioning of dowel bars (horizontal, vertical, and longitudinal translations), size (diameter) of the dowel bar, and bond between the slab and the dowel bar. The study found that the maximum LTE occurred when the dowel bar was positioned at the mid-depth of the concrete slab. An increase in the dowel bar diameter yielded a 3% increase in LTE. Conversely, the increase in the joint opening between slabs led to a 2.1% decrease in LTE. Additionally, the mispositioning of dowel bars in the horizontal and longitudinal directions showed a 2.1% difference in the LTE. However, a 0.5% reduction in the LTE was observed for a vertical translation. Moreover, an approximately 0.5% increase in LTE was observed when there was improved bonding between the concrete slab and dowel bar. These findings can be valuable in designing and evaluating dowel-jointed plain concrete pavements.

Role of Fly Ash in the Repair Interface between Magnesium Phosphate Cement and Cement Concrete

This paper examines a rapid repair material for cement concrete pavement based on magnesium phosphate cement (MPC) blended with fly ash (FA). Three kinds of stress forms for rapid repair of Portland cement concrete pavement (PCCP) were evaluated and the role of FA in the repair interface was studied. The optimal mixture ratio of FA-MPC mortar was determined, and the compressive and flexural strength tested. The composite specimens were then designed to test the interfacial bonding, tensile, and plain shear strength. Finally, the multi-scale mechanism of FA in the interface was analyzed by a pull-off adhesion test, nanoindentation test, scanning electron microscope (SEM)/energy dispersive spectrometer (EDS), Raman spectrum, and molecular dynamics simulation. The optimal content of FA in MPC mortar was 20%. The laminated beam structure had the maximum strength, and the interface load bearing capacity was the lowest. For further multi-scale analysis, the results of the pull-off adhesion test showed the adhesion strength of interface was increased by the curing age and loading rate. Adhesion capacity of basalt aggregate and FA-MPC was stronger than that of Portland cement mortar and FA-MPC. The elastic modulus of MPC-aggregate interface was more than that of MPC-OPC mortar. SEM/EDS and Raman spectrum results showed that the MPC blended with FA had cracks and defects at the interface formed with cement mortar. Less FA formed near the interface. The good adhesion ability of FA and basalt aggregate was verified by molecular dynamics simulation. By contrast, poor adhesion strength with cement mortar was confirmed.

Bond strength and interface characteristics between magnesium phosphate cement mortar and ordinary Portland cement concrete in a frigid environment

ABSTRACT The rapid repair of airport runways and concrete pavements using magnesium phosphate cement mortar (MPCM) in frigid environments requires the MPCM to have high bond strength with ordinary Portland cement (OPC). In this study, the effects of the pouring temperature of MPCM, surface roughness, water content, and strength grade of concrete on the interfacial bond strength and characteristics between MPCM and OPC were investigated in a frigid environment (−20°C ± 2°C). The results indicated that the 3-h compressive strength of MPCM reached 30 MPa, whereas the 3-h flexural bond strength between MPCM and OPC (BS MPCM-OPC) exceeded 2.5 MPa when the pouring temperature for the MPCM mixture is 0-5°C in a frigid environment. The moisture content of concrete before freezing had a more significant impact on BS MPCM-OPC than the influence of concrete roughness in a frigid environment; however, the influence of the concrete strength grade can be disregarded. The hydration heat of MPCM can quickly release with an increase in the pouring temperature, which accelerates phosphate dissolution and promotes the generation of struvite and the development of the BS MPCM-OPC. Furthermore, the interface bonding between MPCM and OPC involves physical bonding, mechanical anchoring, and weak chemical bonding in a frigid environment.

Development and performance of a novel hybrid toughened unsaturated polyester resin (UPR) composite for crack repair of asphalt pavement

In order to effectively seal the cracks, a novel hybrid toughened unsaturated polyester resin (RMUP) crack repair material using liquid nitrile rubber (LNR) and nano-montmorillonite (nano-MMT) is developed in this study. The optimum RMUP formula is determined through mechanical performance tests, viscosity test, fluorescence microscopy, etc. The mechanical properties of the RMUP composite are compared individually with those of toughened UPR by LNR or nano-MMT, while the workability, mechanical performance, durability and cost are compared to other commonly used crack repair materials such as epoxy resin (EP), polyurethane (PU), silicone (SI) and SBS-modified emulsified asphalt (SEA) sealants. The hybrid toughening effect and potential of RMUP as a crack repair material is validated. Furthermore, the hybrid toughening mechanisms are analyzed using Fourier transform infrared spectroscopy (FT-IR). The test results show that the hybrid combination of LNR and nano-MMT effectively toughens UPR, not only improving its ductility but also maintaining its high mechanical strength. Additionally, as a repair material, RMUP exhibits excellent workability, being less temperature-dependent, with a moderate operating time and rapid strength increase following repair, and possesses high mechanical strength (the tensile strength up to 19 MPa) and favorable durability with only a 2%− 4% performance degradation exposing to water immersion environments and no weight loss in extremely hot weather, as well as cost-effectiveness, featuring similar properties to EP sealant but at half the cost of EP. The mechanism analysis reveals that the LNR chemically interacts with the UPR matrix, cross-linking to the UPR’s polymer chains. Simultaneously, the nano-MMT galleries are intercalated by the UPR polymer chains, resulting in an intercalated nanocomposite formation. Both interactions contribute to RMUP's improved toughness.

Effect of phenyl functional groups on the adsorption behaviour of dodecyl anionic emulsifiers on oxides on the aggregate surface

ABSTRACT Emulsified asphalt finds extensive application in pavement repair, addressing issues like road ruts and cracks. While the adsorption behaviour of emulsifiers on oxide surfaces (CaCO3 and SiO2) of aggregates is influenced by the presence of phenyl functional groups, the precise mechanism of this influence remains insufficiently understood. This study employs molecular dynamics models and macroscopic experiments to investigate the mechanism involving emulsifiers, sodium ions, and water at aggregate interfaces, quantifying the role of phenyl functional groups from a molecular perspective. The results reveal the following: strong electrostatic attraction between alkaline aggregates and Na+, leading to substantial Na+ adsorption. The phenyl functional groups reduce diffusion coefficient, adsorption energy, and amounts in alkaline aggregates (−34.6%, −16%, −12.5%), while increasing them in acidic aggregates (+15.9%, + 14.7%, + 27.7%). The phenyl functional groups impact hydrogen bond acceptors, TPSA, and emulsifier complexity, altering adsorption. They enhance emulsifier electrostatic potential, affecting adsorption on different surfaces. In summary, this ongoing research framework aims to fine-tune emulsifiers through the use of phenyl functional groups, enhancing adsorption strength, adsorption amount, and diffusion between emulsifiers and aggregates. This work holds great significance for optimizing emulsifier molecular structures.

Temperature Field Characterization of Iron Tailings Based on Microwave Maintenance Technology.

Microwave maintenance technology, as a new development trend, can realize the environmentally noninvasive and rapid repair of asphalt pavement and gradually replace traditional maintenance methods. Iron tailings were used as a self-healing material in this study to investigate the temperature response matching of microwave maintenance technology. Firstly, the physical properties and the mechanism of iron tailings were elaborated through macroscopic physical index testing and microscopic X-ray diffraction (XRD) analysis. Secondly, the applicability of aggregates to microwave heating was demonstrated by analyzing the temperature rise characteristics of the granules using infrared imaging. Then, the temperature field variation rules of the iron tailing asphalt mixture were summarized by microwave heating Marshall specimens. Finally, the road performance was assessed by conducting high-temperature dynamic stability, low-temperature tensile, water immersion Marshall, and freeze-thaw splitting tests. The experimental results showed that the iron tailings can be used as an aggregate for high-grade asphalt pavement and as the preferred aggregate for microwave maintenance technology. The iron tailings temperature field was radial from the inside out to provide different temperature response states for different pavement diseases, so the asphalt was dissolved and precipitated in a short time. The particle size of iron tailings was inversely proportional to the wave-absorbing heating rate, and the heating efficiency of the small particle size (0-4.75 mm) was the highest. The specimens doped with 4.75-13.2 mm iron tailings showed the best heating performance and road performance, with the average surface temperature of the specimens reaching 126.0 °C within 2 min. In summary, according to different disease types and construction needs, iron tailings can be used as an aggregate for asphalt pavement, providing an appropriate temperature field and improving the efficiency of the microwave maintenance of asphalt pavements.

Rapid Repair of Road Surface with Magnesium Phosphate Cement: Case Study of Pavement Repair in Qingdao

Rapid Repair of Road Surface with Magnesium Phosphate Cement: Case Study of Pavement Repair in Qingdao

Study on the Mechanical Properties of Polyurethane-Cement Mortar Containing Nanosilica: RSM and Machine Learning Approach

Polymer-modified cement mortar has been increasingly used as a runway/road pavement repair material due to its improved bending strength, bonding strength, and wear resistance. The flexural strength of polyurethane–cement mortar (PUCM) is critical in achieving a desirable maintenance effect. This study aims to evaluate and optimize the flexural strength of PUCM involving nano silica (NS) using a central composite design/response surface methodology (CCD/RSM) to design and establish statistical models. The PU binder and NS were utilized as input parameters to evaluate the responses, such as compressive and flexural strength. Moreover, machine learning (ML) algorithms including artificial neural networks (ANN) and Gaussian regression process (GPR) were used. The PUCM mixtures were prepared by adding a PU binder at 0%, 10%, 15%, and 25% by weight of cement. At the same time, NS was incorporated into the mortar mixes at 0 to 3% (interval of 1%) by cement weight. The results showed that the simultaneous effect of PU binder at the optimal content and NS improved the performance of PUCM. Adding NS to the mortar mixture mitigated some of the strength lost due to the PU binder, which remarkably reduces the strength properties at a high content. The optimized PUCM can be obtained by partly adding 3.5% PU binder and 2.93% NS particles by the weight of cement. The performance of the machine learning algorithms was tested using performance indicators such as the determination of coefficient (R2), mean absolute error (MAE), mean-square error (MSE), and root-mean-square error (RMSE). The GPR algorithm outperformed the ANN with higher R2 and lower MAE values in the training and testing phases. The GPR can predict flexural strength with 90% accuracy, while ANN can predict it with 75% accuracy.

ОСОБЛИВОСТІ ОБСТЕЖЕННЯ НЕЖОРСТКОГО ДОРОЖНЬОГО ОДЯГУ ПРИ ПРОЄКТУВАННІ ЗАХОДІВ РЕМОНТУ ІЗ ЗАСТОСУВАННЯМ ТЕХНОЛОГІЇ ХОЛОДНОГО РЕСАЙКЛІНГУ

Problem Statement. Observation of the performance of objects restored by cold recycling technology shows that more attention should be paid to diagnosing the condition of existing pavement and predicting the processes that cause premature deterioration. Purpose. To find solutions to clarify the condition of the existing pavement and to determine in more detail the factors of deterioration. Research methods. Analytical and experimental with the use of computer modeling. Conclusions. Based on the results of the research, an algorithm for conducting the survey was developed, which consists of two consecutive stages. This algorithm is based on the results of the first stage of the survey that provides that not only data are collected, but also envisages that a program for the second stage of the survey is drawn up. Based on the results of the second stage of the survey, a plan diagram of the same type of road sections is formed, the need for additional preparatory work to eliminate local areas with deterioration is determined, and constructive and technological solutions for the repair of pavement using cold recycling technology are developed with the determination of the depth of milling, the amount and composition of stone materials that are additionally added to the mixture, the composition of the binder, etc.