A high-efficiency preparation and construction optimization system and method for cold patch asphalt mixture

Abstract

The application discloses a kind of cold patch asphalt mixture high-efficiency preparation and construction optimization system and method, belong to construction optimization technical field, by collecting the environmental parameter of construction site, including altitude, air pressure correction coefficient and light volatile factor, construct the multiscale mixture model of coupling air pressure response, combine discrete element and fluid mechanics simulation analysis mixture volatile path, structural stability and initial bonding strength, and then extract structure retention threshold and deduce the matching adjustment amount of medium-high boiling point solvent component;While using microcapsule controlled-release technology to delay light component release, and based on simulation platform and machine learning model output adaptive construction parameters, dynamically optimize paving temperature and compaction frequency, realize the efficient cooperation and intelligent regulation and control of cold patch material performance and on-site construction process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of construction optimization, in particular to a cold patch asphalt mixture efficient preparation and construction optimization system and method. BACKGROUND

[0002] With the continuous improvement of the use intensity of urban roads and highways, pavement diseases (such as potholes, cracks, etc.) frequently occur, which seriously affect driving safety and road life. Cold patch asphalt mixture has become one of the important materials in road maintenance due to its characteristics of normal temperature construction, simple operation and rapid repair. Traditional cold patch mixture is usually prepared by adding solvent oil or emulsifier to petroleum asphalt, although it can meet the basic repair needs, but there are still many deficiencies in material storage stability, low temperature construction adaptability and long-term bonding performance, etc. For example, when constructing in high altitude and low pressure environment, the light solvent component in the cold patch asphalt mixture volatilizes prematurely due to too low air pressure, resulting in significant decrease in the adhesion of the mixture, and the phenomenon of peeling and breaking within a short time after paving. Such problems are not easy to detect in plain areas, but are very prominent in plateau, mountainous and other special terrain areas, directly affecting the application range and on-site construction reliability of the cold patch material, and becoming an important technical obstacle restricting its promotion. SUMMARY

[0003] The purpose of the present application is to provide a cold patch asphalt mixture efficient preparation and construction optimization system and method to solve the problems in the background art.

[0004] In order to achieve the above purpose, the present application provides the following technical scheme: a cold patch asphalt mixture efficient preparation and construction optimization method, comprising:

[0005] Collecting construction environment parameters, including the altitude of the target construction point, the local air pressure correction coefficient, and the light volatile factor;

[0006] Constructing a constitutive model coupled with air pressure response, based on the coupling simulation of discrete element method and computational fluid dynamics, simulating the light component volatilization path, internal structure stability and initial bonding strength change of the mixture under the construction environment;

[0007] According to the coupling simulation output, identifying the key structure retention threshold of the cold patch mixture, that is, the minimum bonding strength value required to maintain the structural integrity within 30 minutes after paving;

[0008] Combining the light volatile factor and the structure retention threshold, calculating the bonding performance gap value, and back calculating the proportioning adjustment amount of the medium and high boiling point solvent component to fill the bonding gap;

[0009] The light component is subjected to microcapsule controlled release treatment, and the response temperature is set according to the altitude and typical temperature conditions of the construction point, and the delayed release time is controlled within 5-10 minutes after paving;

[0010] Output construction recommendation parameter set based on simulation platform, including recommended paving temperature, compaction frequency and construction window period;

[0011] Real-time collection of environmental change data during construction, combined with machine learning prediction model to dynamically adjust and optimize paving temperature and compaction frequency, achieving intelligent adaptive control of the construction process.

[0012] Preferably, the collection of construction environment parameters includes:

[0013] Real-time acquisition of the altitude of the target construction point through environmental sensing devices;

[0014] Based on the ratio of measured air pressure to standard atmospheric pressure, calculate the local air pressure correction coefficient;

[0015] Conduct constant-pressure volatilization experiments on selected light component samples, record the mass change under different air pressures and temperatures, and use piecewise linear interpolation method to construct the response surface of air pressure-temperature-time and volatilization rate; Real-time matching of current air pressure and temperature at the construction site, reading the corresponding unit time volatilization mass in the response surface, determining the light volatilization factor.

[0016] Preferably, the construction of the constitutive model coupled with air pressure response includes the following steps:

[0017] Establish the contact model between aggregate particles using the discrete element method, including particle size distribution, friction coefficient and contact elastic modulus;

[0018] Treat light asphalt components as continuous fluids, and describe their evaporation, diffusion and motion behavior under low air pressure conditions through computational fluid dynamics method;

[0019] Introduce air pressure response factor as control parameter, embed local air pressure correction coefficient into flow field boundary condition, dynamically adjust evaporation rate and asphalt-aggregate interfacial wetting behavior;

[0020] Real-time calculation of the change trend of initial bond strength in the coupled model, output of structure integrity maintenance time and initial peeling risk index.

[0021] Preferably, the simulation of light component volatilization path, internal structure stability and initial bond strength change of the mixture under construction environment includes:

[0022] Based on the scanning results of the microstructure of the mixture, construct an initial particle distribution model, and import this model into the discrete element simulation framework;

[0023] Introduce the light volatilization factor collected in the environmental parameters to drive the CFD module to simulate the non-steady-state diffusion-volatilization process of asphalt components;

[0024] The decay rate of the thickness of the inter-particle bonding bridges is calculated in real time, and the initial bonding strength decay curve is calculated according to the value change;

[0025] When the bonding strength decreases to a preset threshold value, the model automatically marks a potential peeling area.

[0026] Preferably, the adjustment amount of the proportion of the medium and high boiling point solvent component is calculated by:

[0027] According to the light volatile factors collected under the construction environment, the total expected volatile mass of the light component in the cold patch mixture within 30 minutes after paving is estimated;

[0028] By comparing the key structure retention threshold, the bonding performance gap value, that is, the difference between the minimum effective bonding strength required for the mixture to maintain structural integrity and the actual maintainable strength, is determined;

[0029] Based on the residual rate of the medium and high boiling point solvent under the current air pressure and temperature and the unit mass bonding strength contribution value, the replacement component mass required to fill the bonding performance gap value is calculated;

[0030] The adjustment amount of the proportion of the high boiling point solvent component is output as a partial replacement proportion of the original light component.

[0031] Preferably, the microcapsule controlled release treatment of the light component includes:

[0032] A polymer material with a heat-sensitive response characteristic is selected as the microcapsule wall material, which undergoes phase change or structure rupture at a set temperature to release the coating;

[0033] According to the altitude of the target construction point, the typical daytime temperature and heat conduction rate of the area where the target construction point is located are calculated, and the adaptive wall material response temperature interval is determined through an empirical correlation model;

[0034] The light component is coated in the form of liquid in the microcapsule core, and the wall material thickness and structure are controlled so that it reaches the response temperature and releases the content within 5-10 minutes after paving;

[0035] The microcapsules are uniformly mixed into the cold patch mixture to achieve controlled release of the light component, thereby reducing the premature volatilization loss before paving and during the initial compaction stage.

[0036] Preferably, the construction recommendation parameter set output by the simulation platform includes:

[0037] Based on the coupling air pressure response model and the mixture performance simulation platform, the environmental parameters of the construction site and the target mixture proportion are input, and the temperature response, bonding strength evolution and structural stability data of the material during the paving stage are obtained by running the simulation;

[0038] The change trend of the bonding strength in the simulation result is analyzed, a time period with the highest bonding performance retention rate in the optimal temperature range is extracted, and a recommended paving temperature corresponding to the time period is output;

[0039] According to the convergence speed of the void ratio in the simulation and the distribution of the compaction energy consumption, the compaction frequency and the vibration mode required to achieve the optimal compaction density are determined;

[0040] Combined with the temperature sensitive interval and the bonding formation window, the appropriate construction window period length is set, and a complete construction parameter recommendation set is output.

[0041] Preferably, the machine learning prediction model is combined to dynamically adjust and optimize the paving temperature and the compaction frequency, including:

[0042] An environment perception module is arranged on the construction site to collect dynamic environmental parameters such as air temperature, ground temperature, wind speed and air pressure in real time;

[0043] The collected environmental data are input into a machine learning model based on supervised learning, and the model has been trained by historical construction data to obtain the correlation between the paving effect and the environmental variables;

[0044] The model predicts the optimal paving temperature and compaction frequency range of the cold patch material under the current environmental condition according to the real-time input;

[0045] The prediction result is used as a control reference to output a dynamic adjustment suggestion to guide the on-site fine adjustment of the paving and compaction parameters of the construction equipment.

[0046] Preferably, the dynamic adjustment and optimization further includes:

[0047] A model based on reinforcement learning is established, and the model continuously learns the long-term influence of environmental changes on the adjustment effect of construction parameters through historical construction feedback;

[0048] The model continuously obtains environmental state input during the construction process and outputs a prediction of the influence of the current operation on the future structure stability;

[0049] According to the prediction result, a temperature-frequency-stability multi-objective trade-off function is set, and the current optimal strategy is calculated;

[0050] The paving temperature and the compaction frequency are dynamically adjusted according to the optimal strategy.

[0051] The application also provides a cold patch asphalt mixture efficient preparation and construction optimization system, which comprises:

[0052] An environmental parameter acquisition module acquires construction environmental parameters, including the altitude of the target construction point, the local air pressure correction coefficient, and the light volatile factor;

[0053] A multi-scale simulation analysis module is configured to build a constitutive model coupled with air pressure response, simulate the light component volatilization path, internal structure stability, and initial bond strength change of the mixture under construction environment based on the coupling simulation of the discrete element method and computational fluid dynamics;

[0054] A structure threshold identification module is configured to identify the key structure retention threshold of the cold patch mixture, i.e., the minimum bond strength value required to maintain the structural integrity within 30 minutes after paving, according to the coupling simulation output;

[0055] A proportioning backstepping module is configured to calculate the bond performance gap value in combination with the light volatile factor and the structure retention threshold, and backstep the proportioning adjustment amount of the medium and high boiling point solvent component to fill the bond gap.

[0056] A microcapsule controlled release module is configured to perform microcapsule controlled release processing on the light component, the response temperature of which is set according to the altitude and typical temperature conditions of the construction site, and the delayed release time is controlled within 5-10 minutes after paving.

[0057] A simulation-driven construction suggestion module is configured to output a construction suggestion parameter set based on the simulation platform, including the recommended paving temperature, compaction frequency, and construction window period.

[0058] A construction intelligent adjustment module is configured to collect environmental change data in real time during the construction process, and dynamically adjust and optimize the paving temperature and compaction frequency in combination with a machine learning prediction model, to realize intelligent adaptive control of the construction process.

[0059] In the above technical solution, the present application provides technical effects and advantages as follows:

[0060] 1. The present application introduces air pressure response factors and multi-scale simulation technology to accurately simulate the light component volatilization behavior and structure stability evolution process of cold patch asphalt mixture in a plateau low-pressure environment, solving the problems of insufficient bond strength and initial structure instability of traditional cold patch materials in plateau construction. By extracting the key structure retention threshold, backstepping the reasonable proportioning of medium and high boiling point solvents, and combining with the microcapsule controlled release technology, the bond retention time of the mixture is effectively prolonged, and the repair quality and material utilization rate are improved.

[0061] 2. The present application combines real-time environmental perception and machine learning algorithms to intelligently predict optimal construction parameters (such as paving temperature and compaction frequency), and dynamically adjusts them during the construction process, establishing an integrated closed-loop system of “material performance-simulation feedback-construction control”. Compared with the prior art, this method has the advantages of strong adaptability, fast response speed, high quality control precision, and is especially suitable for road rapid repair engineering in complex and variable climate conditions in plateau or remote areas. BRIEF DESCRIPTION OF DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings described below are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art based on these drawings.

[0063] Figure 1 The method flowchart of the present application.

[0064] Figure 2 The system module flowchart of the present application. DETAILED DESCRIPTION

[0065] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the present application.

[0066] Embodiment 1, please refer to Figure 1 As shown in the figure, the high-efficiency preparation and construction optimization method of the cold patch asphalt mixture described in this embodiment comprises:

[0067] Collecting construction environment parameters, including the altitude of the target construction point, the local air pressure correction coefficient, and the light volatile factor;

[0068] Constructing a constitutive model coupled with air pressure response, based on the coupling simulation of the discrete element method and computational fluid dynamics, simulating the light component volatilization path, internal structure stability and initial bond strength change of the mixture under the construction environment;

[0069] According to the coupling simulation output, identifying the key structure retention threshold of the cold patch mixture, that is, the minimum bond strength value required to maintain structural integrity within 30 minutes after paving;

[0070] Combining the light volatile factor and the structure retention threshold, calculating the bond performance gap value, and back calculating the proportioning adjustment amount of the medium and high boiling point solvent component to fill the bond gap;

[0071] The light component is subjected to microcapsule controlled release treatment, and the response temperature is set according to the altitude and typical temperature conditions of the construction point, and the delayed release time is controlled within 5-10 minutes after paving;

[0072] Based on the simulation platform output, the construction suggestion parameter set is output, including the recommended paving temperature, compaction frequency and construction window period;

[0073] Real-time environmental change data is collected during construction, and a machine learning prediction model is used to dynamically adjust and optimize paving temperature and compaction frequency, achieving intelligent adaptive control of the construction process.

[0074] First, the altitude of the construction site is collected during the construction preparation phase, which is 3500 meters. The GNSS module is used to cross-verify with the digital elevation map. Subsequently, the real-time air pressure is measured by a high-precision atmospheric pressure sensor, which is 67.5 kPa. The ratio is calculated with the standard atmospheric pressure (101.325 kPa), and the local air pressure correction coefficient is about 0.666.

[0075] At the same time, typical light solvents (such as petroleum ether, aromatic hydrocarbon mixture) are selected as the analysis object, and a portable dynamic thermal gravimetric-gas chromatography equipment is used to conduct a short-term volatilization experiment under the current air pressure and temperature conditions. The loss mass of each cubic meter of cold patch material in 5 minutes is about 8.1 grams, and the light volatile factor (LVF) is calculated as 8.1 g / m³·5min, which is an important input parameter for the subsequent model.

[0076] In the multi-scale material behavior modeling phase, the discrete element method (DEM) is used to establish the aggregate contact model to simulate the contact force transmission and distribution characteristics of the 5-25 mm gravel under external load. The contact friction coefficient is set to 0.45, and the elastic modulus is set to 3.2 GPa.

[0077] At the same time, in the computational fluid dynamics (CFD) framework, the asphalt phase is regarded as a non-Newtonian fluid, and the "air pressure response factor" variable is introduced, with the air pressure correction coefficient of 0.666 as one of the flow field boundary conditions, to dynamically reflect the volatility intensity and speed of light components.

[0078] Through the coupling operation of DEM and CFD, the internal temperature field, gas diffusion field and bonding force field changes within the first 30 minutes after paving are simulated. The results show that within 15 minutes after paving, 30% of the aggregate interface in the material shows a trend of reduced bonding due to light component evaporation.

[0079] According to the coupling simulation output data, the bonding strength change curve of the key nodes is extracted, and it is calculated that as the light component volatilizes, the bonding bridge thickness decreases from the initial 0.52 mm to 0.18 mm, and the continuity of the mixture structure significantly decreases.

[0080] By setting the structure integrity standard (i.e. when the interface bonding force attenuation exceeds 60%, it is considered to be unstable), the critical time for structure instability is determined to be the 23rd minute after paving, and the corresponding bonding strength is 0.135 MPa. Therefore, this value is defined as the key structure retention threshold (SR_thresh) under the current construction environment.

[0081] The threshold value will serve as a performance benchmark target for subsequent proportioning adjustment, to determine whether the amount of medium-high boiling point solvent component added is sufficient to extend the structural stability time to more than 30 minutes.

[0082] Based on the aforementioned calculated light volatile factor and structural retention threshold, a target bond strength gap model is established. Assuming that the existing proportioning reduces the bond strength to 0.135 MPa after 23 minutes, and the bond strength required to maintain 30 minutes should not be less than 0.150 MPa, the bond strength difference is calculated to be 0.015 MPa.

[0083] By consulting the material database, two medium-high boiling point solvents (A agent and B agent) are selected, wherein the initial boiling point of A agent is 185°C, and the unit mass bonding contribution is 0.007 MPa / g; the initial boiling point of B agent is 210°C, and the unit bonding contribution is 0.010 MPa / g. Under the current air pressure, the 30-minute residual rate of the two is 65% and 78% respectively.

[0084] The above parameters are substituted into the constructed backstepping function, and according to the expected bond strength compensation value, it is determined that the total mass of A agent and B agent required to be introduced is 6.5 grams per cubic meter of cold patch material, and the final proportioning is A:B = 2:3, as part of the replacement of light components.

[0085] The adjusted test batch enters the coupled simulation process again, and the simulation shows that the mixed material still maintains a bond strength of 0.152 MPa within 30 minutes after paving, meeting the structural integrity requirements, verifying the effectiveness of the proportioning strategy.

[0086] Through the above verification examples, after collecting and quantifying the highland environment parameters, combined with multi-scale simulation, the performance weaknesses of the mixture under specific working conditions can be accurately identified; and through the simulation results, the material proportioning optimization can be guided in reverse, so that the adaptive design of the cold patch mixture can be completed in a data-driven manner, greatly improving its construction adaptability and early structural stability in the plateau low-pressure environment. The method has high precision, systematicness and practicality, and provides a feasible path for efficient customization and on-site regulation of cold patch asphalt mixture.

[0087] In the coupled simulation model constructed in the present application, the air pressure response factor is not only used to correct the light component vapor pressure value, but also further adjusts the adhesion parameters of the wet boundary condition by controlling the wetting angle and diffusion speed of the asphalt-aggregate interface area, to realize the response adjustment of the micro wetting behavior. This mechanism ensures that the wetting state simulated under low air pressure can still reflect the actual flow boundary changes, and enhances the adaptability and prediction accuracy of the simulation model under complex climate.

[0088] A typical plateau construction environment (about 3700 meters above sea level, about 65 kPa of air pressure, and 15-28℃ fluctuation of ground temperature) was selected as the simulation boundary condition. In terms of material parameters, the cold patch mainly includes basalt gravel (particle size 5-20 mm), light mineral oil (low boiling point section), high molecular viscosity agent, and part of the emulsifier. The target void ratio of the cold patch is 15%-18%.

[0089] In the discrete element modeling, the PFC3D platform was used to simulate the contact behavior of aggregate particles, the contact stiffness between particles was set to Pa, the friction coefficient was 0.5, and the particle size distribution conformed to the actual screening result. The contact points between the particles were set as a bonded contact model, which can simulate the degradation characteristics of the bonded bridge after heat-force coupling.

[0090] A multi-parameter response surface of light component volatilization was established in the simulation platform. The piecewise linear interpolation and multivariate fitting method were used to associate the air pressure, temperature, time, and volatilization rate three-dimensional data, and a dynamic mapping table of light volatilization factor (LVF) was constructed. The response surface as the basic input of the air pressure response factor can be queried in real time by the system in different construction environments, and drive the linkage calculation of the evaporation sub-model and the bond prediction module. In addition, the machine learning model is used to extract the features of the response surface data, and a prediction function between the paving parameters and the bond performance is established, so as to realize the adaptive adjustment of the construction temperature and the compaction frequency.

[0091] In the present application, Fluent or OpenFOAM is used to simulate the light component volatilization path, the initial oil content of the material is set to 3.8%, which is regarded as a multi-component volatile liquid, and the evaporation behavior depends on the local air pressure, temperature and molecular diffusion coefficient.

[0092] In order to enhance the simulation accuracy, the air pressure response factor is set as an independent variable and participates in the calculation of the volatilization rate in real time. The air pressure of the light component is converted by the Antoine equation, and the diffusion coefficient is dynamically updated with the change of temperature and pore shape.

[0093] Among them, the air pressure response factor refers to the control parameter used to reflect the influence of the change of air pressure on the volatilization rate of light components in asphalt, the adhesion behavior of gas-solid interface and the pore diffusion mechanism. As a dynamic input variable in the coupled simulation model, it is used to adjust the diffusion coefficient, wetting boundary condition and vapor pressure boundary setting under the condition of air pressure-temperature in simulation.

[0094] The specific determination method is as follows:

[0095] Standardized pressure-volatilization rate curve acquisition: by pressure-controlled volatilization experiment device, the volatilization rate of the same light component (such as alkane or aromatic hydrocarbon) is measured at different pressures (such as 80 kPa, 100 kPa, 120 kPa), the mass loss rate is recorded and the empirical relationship curve between the mass loss rate and the pressure is fitted =f(P), wherein is the volatilization rate, and P is the ambient pressure;

[0096] Vapor pressure basic calculation using the Antoine equation: according to the Antoine equation the saturated vapor pressure at the reference pressure is obtained , wherein A, B, C are empirical coefficients of the light component, and T is the temperature;

[0097] Pressure correction coefficient extraction: combined with experimental data and Antoine equation calculation value, a correction function is constructed ; wherein is the standard atmospheric pressure, and F(P) represents the pressure response factor;

[0098] In the CFD (Computational Fluid Dynamics) or multi-field coupling simulation platform (such as COMSOL, Fluent), the "pressure response factor" is set as a boundary condition control parameter, which is coupled with the temperature field and the pore evolution field in real time;

[0099] The pressure response factor is numerically fitted and functionally derived by MATLAB program, and the input value is updated in real time in the simulation in the form of a lookup table, which is used to adjust the interface volatilization boundary and the diffusion sub-model.

[0100] In the simulation platform, the paving start is taken as the time starting point, and the internal structure and bonding performance within the first 30 minutes are continuously simulated.

[0101] The light components of the cold patch mainly evaporate and diffuse through the capillary channels and pore gaps on the surface of the aggregate. Simulation data shows that within the first 5 minutes after paving, the light component content in the top 20 mm thick area decreases by 43%; within 15 minutes, the overall average content decreases to 58% of the original, and the voids at the top layer approach the critical dry state.

[0102] As the light component decreases, the residual oil film thickness gradually thins in the CFD module. The interfacial shear force of the corresponding contact points in the DEM module decreases, and some particles lose effective bonding bridges. The structural integrity is quantified by the Connectivity Index, and it is found that the bonding network shows an exponential breaking trend after the 20th minute, and some areas form isolated particle clusters.

[0103] To solve the problem of adhesion performance decline caused by the volatilization of light components, the adhesion performance gap value is used as the basis for back calculation in this embodiment. The minimum addition mass of medium and high boiling point solvents is derived from this value, and the programmable logic unit is used in the implementation system to automatically set and adjust the component addition amount. At the same time, to solve the problem of early release of light components in the initial compaction stage, microcapsule coating is used for controlled release treatment to ensure gradual release during the formation of the bonding bridge, making up for the structural instability risk caused by early failure.

[0104] Set 100 contact points to track the change of their normal bonding force, output the initial bonding strength change curve, and find that the strength decreases significantly faster after the 10th minute. The bonding strength decreases from the initial value of 0.21 MPa to 0.14 MPa at the 25th minute.

[0105] At the same time, record the temperature and pressure field data, and find that the cooling effect caused by the volatilization of light components at the contact points can reduce the elastic recovery performance of the constitutive model, further accelerating the structural instability process.

[0106] To achieve the extraction of the structure retention threshold and the forward identification of the initial peeling risk index, further establish the judgment mechanism of structural instability.

[0107] The initial peeling risk index refers to the possibility of structural instability caused by the rapid volatilization of light components within the first 30 minutes after the mixture is spread, which is quantified by the bonding strength time change curve, interface breakage ratio, and particle detachment rate obtained from simulation calculation.

[0108] According to the DEM model data, the normal force change of all contact points is counted on the time axis, and the time when more than 5% of the contact points fail for the first time (t = 22.5 min) is recorded as the critical time of the structure.

[0109] At this time, the average bonding strength of the system is about 0.132 MPa, which is defined as the structure retention threshold (SR_thresh) of the cold patch mixture in this environment.

[0110] By establishing the interface breakage ratio (IBR) index, which is defined as the percentage of failed contact points per unit time, when IBR increases from 3% to more than 9% within 5 minutes, it is determined that the initial peeling risk index has increased sharply.

[0111] Based on the above criteria, the simulation system can predict that the structure will deteriorate significantly at the 25th minute when it is spread at the 20th minute, thus providing a 5-minute early warning signal for construction personnel to adjust the construction window or supplement the solvent.

[0112] Finally, the "bond strength-time-air pressure three-dimensional response surface" is generated, which can be used for subsequent construction adaptation model fast call to improve data reuse rate.

[0113] This embodiment details the reconstruction of the bond decay process of cold patch mixture at the initial stage of paving by coupling simulation of discrete elements and fluid mechanics, combining environmental pressure response factors and multi-physical field simulation, and quantitatively outputting the key structure retention threshold. This scheme not only solves the problem that traditional empirical methods cannot predict bond failure, but also establishes an initial particle distribution model between light component volatilization and structure retention for the first time, providing a reliable theoretical basis and reusable simulation platform for mixture environmental adaptive control and intelligent construction recommendation.

[0114] Among them, the initial particle distribution model scans the microstructure of the cold patch mixture sample through three-dimensional laser scanning and image reconstruction technology, and then based on the particle size distribution data, shape parameters (such as aspect ratio, corner angle) to construct a simulation particle cloud, and map it to the DEM software as the initial state of simulation.

[0115] Combined with the multi-physical field coupling model constructed earlier, run the DEM-CFD joint simulation to record the change trend of the normal bond force of representative contact points in the cold patch mixture with time, with a sampling interval of 10 seconds and a total duration of 0-30 minutes after paving.

[0116] 100 representative particle contact points are extracted from the simulation to construct the average curve of the change of bond strength with time, and it is found that the bond strength remains in the range of 0.18-0.21 MPa for the first 10 minutes, and then gradually decreases, dropping to 0.138 MPa at the 25th minute.

[0117] The structure instability criterion is set as "the effective bond force between aggregates decays to less than 30% of the initial strength", and 0.135 MPa is set as the preliminary reference lower limit.

[0118] All contact points are segmented by time period for statistical analysis, and the structure stability index of each segment is normalized. Finally, it is determined that when the bond strength is 0.135 MPa, the internal structure of the mixture appears a significant loose trend, so this value is defined as the structure retention threshold SR_thresh.

[0119] To improve the sensitivity and universality of simulation prediction, the "strength gradient backtracking method" is used, that is, a set of different initial bond strength conditions are set before simulation, and the minimum bond strength required to maintain structural integrity for 30 minutes is backtracked through multiple simulation results.

[0120] The initial bond strength was set to four levels: 0.12, 0.14, 0.16, and 0.18 MPa. The simulation was run for 30 minutes to observe the structural retention performance, and the inter-particle structural retention rate, crack propagation trend, and void network damage ratio were recorded.

[0121] It was found that when the initial strength was 0.12 MPa, the structure lost its continuity in about 20 minutes; 0.14 MPa could be maintained for 26 minutes; and 0.16 MPa and above successfully maintained a stable state for 30 minutes.

[0122] The minimum initial bond strength of 0.16 MPa, which could maintain structural stability for 30 minutes, was used as the back-propagation result. Combined with the average output value of other models, the final structural retention threshold was set to between 0.150-0.160 MPa, with 0.155 MPa used in subsequent proportioning optimization design.

[0123] This value directly participates in the back-propagation process of the bonding performance contribution of high-boiling-point solvent components and is a key basic parameter for determining the replacement ratio of components.

[0124] Considering that the material structure may experience local interface failure due to lightweight volatilization during actual operation, the "interface breakage ratio" (IBR) was introduced as a new indicator to identify the starting point of structural degradation from a microscopic perspective.

[0125] In the simulation, the shear failure criterion was set, and the ratio of inter-particle shear force to normal force (τ / σ) was collected. When this ratio exceeded the material shear failure ratio of 0.7, it was considered as interface failure.

[0126] With a 1-minute sliding window, the number of interface failure points was counted, and the evolution curve of the proportion of failure points over time was drawn.

[0127] When the proportion of interface failure points to the total number of contact points first exceeded 5%, it was determined to be the critical point of structural instability. The system bond strength at this moment was 0.138 MPa, which was highly consistent with the results of the time series segmentation method.

[0128] Based on this model, a "bond strength-interface breakage rate" mapping diagram can be constructed to quickly predict the stability risk in the later stage at the beginning of the simulation, improving the simulation efficiency.

[0129] The three methods systematically identified and evaluated the structural integrity and bonding performance of the mixture at different levels (macro, parameter gradient, and microstructure). The results showed that:

[0130] The structural retention thresholds obtained by each method were highly consistent, with a fluctuation range of 0.135-0.160 MPa.

[0131] The appropriate method can be selected according to the construction environment and simulation accuracy requirements for rapid analysis.

[0132] The extracted threshold value will be directly used in solvent component optimization, microcapsule controlled release design and construction parameter recommendation.

[0133] The research results of this embodiment can be integrated in the form of intelligent modeling module in the simulation platform in the actual plateau construction environment, supporting the structure performance prediction and bonding force regulation strategy formulation of the front-line construction personnel, and providing key data support and method foundation for the adaptability and efficient construction of cold patch material in extreme environment.

[0134] This embodiment aims at the problem of rapid evaporation of light components and decline of initial bonding performance of cold patch asphalt mixture in plateau low pressure environment. The simulated output light volatile factor (LVF) and structure retention threshold (SR_thresh) are used as input variables, and through multi-path parameter backstepping, component physical property screening and bonding performance matching, the ratio adjustment amount of medium and high boiling point solvent components is determined to optimize the bonding system performance of cold patch material and realize the structure integrity maintenance within 30 minutes after paving.

[0135] Among them, through the bonding strength gap ΔS (the difference between the target bonding strength and the current simulation value), combined with the residual rate (R) and the unit bonding contribution value (C) of each solvent component, the required added mass is backstepped using the following formula: M=ΔS / (C×R); to determine the added amount of each medium and high boiling point solvent, and to optimize the proportion.

[0136] This scheme is based on the field collection and simulation prediction data, combined with the light volatile factor (LVF) and the structure retention threshold, to calculate the bonding strength gap caused by the loss of light components in the key period, and then backstep the minimum added mass of medium and high boiling point solvent components.

[0137] Among them, the measured light volatile factor (volatile mass per unit volume per unit time) is combined with the paving layer thickness, construction time period (30 minutes) and temperature-pressure conditions to calculate the total volatile mass through an empirical model, for example: the total volatile mass is predicted = LVF x layer thickness x time window / correction factor; wherein the correction factor is used to calibrate the difference between the laboratory and the field.

[0138] Take a high-altitude work site (elevation 3650 meters, air pressure about 68 kPa) as an example, the environmental temperature fluctuates between 17-26℃, and the measured light volatile factor is LVF = 9.6 g / m³ / 5min. The CFD simulation results show that within 30 minutes after paving, the total volatile amount of light components under the original formula is up to 45 g / m³, resulting in a decrease in bonding strength to 0.128 MPa, which is lower than the structural retention threshold of 0.150 MPa. The difference in bonding strength is calculated as: ΔS = 0.150 - 0.128 = 0.022 MPa.

[0139] In this embodiment, three organic solvent components with medium-high boiling point characteristics are selected as candidate compensation materials, labeled as Component A, Component B and Component C. Component A has an initial boiling point of 180℃, a 30-minute residual rate of 62%, and a bonding contribution value per unit mass of 0.0045 MPa / g; Component B has an initial boiling point of 200℃, a 30-minute residual rate of 71%, and a bonding contribution of 0.0059 MPa / g; and Component C has the highest initial boiling point of 215℃, a residual rate of 78%, and the largest bonding contribution of 0.0064 MPa / g.

[0140] In the simulation analysis, the bonding strength of the cold patch mixture decreases to 0.128 MPa within 30 minutes after paving, which is lower than the target structural retention threshold of 0.150 MPa, and the bonding performance gap is 0.022 MPa. Taking Component C as an example, if it is used as the only compensation material, it can provide a bonding improvement of 0.0064 MPa per unit mass. To fill the strength gap of 0.022 MPa, the effective mass required is about 3.44 grams per cubic meter of mixture.

[0141] Considering that the 30-minute residual rate of Component C in the target construction environment is 78%, the actual amount to be added should be: 3.44 grams / 0.78 ≈ 4.41 grams per cubic meter. This calculation result provides a clear solvent usage suggestion for actual production and mixing, and lays a foundation for subsequent recompounding optimization and on-site adjustment.

[0142] Through multiple experimental simulation groups in high-altitude environments, 20 groups of (LVF, SR_thresh, ΔM) samples are collected, and an empirical relationship is fitted: ; where: a = 0.92, b = 1.15, c = 0.87 (empirical fitting parameters); combined with the database residual rate and contribution rate, the recommended components are A (30%) + C (70%) combination to improve the early bonding force coverage rate and the late residual efficiency. This method has been encapsulated in the construction simulation platform interface, and construction personnel can quickly obtain component recommendations and mixing suggestions by inputting the measured LVF and project target bonding threshold, realizing semi-automatic decision-making.

[0143] This method tests multiple combinations of medium-high boiling point solvents in a simulation platform, dynamically simulating the impact of their residual properties on structural bonding responses, achieving direct coupling between structural behavior and additive schemes.

[0144] Four groups of solvent system ratios (different boiling point recombination) are constructed, and CFD-DEM coupling simulation is run, recording the following indicators:

[0145] Bonding strength retention time, interfacial growth rate, void ratio evolution trend, and bonding bridge residual proportion.

[0146] Simulation data shows that the component combination (A10%, B30%, C60%) has an average bonding strength of 0.157 MPa within 0-30 minutes after paving, with a bonding bridge fracture rate of only 12%, far superior to other ratios. This result shows that under low air pressure conditions, the proportion of high residual rate solvents should be appropriately increased to delay structural instability.

[0147] Based on multiple simulation data, the "component ratio-structural stability response surface graph" is output, providing simulation assistance for optimization in subsequent projects and serving as a training basis for AI parameter tuning algorithms.

[0148] The above three methods can be used for the optimization of medium-high boiling point component ratios, adapting to different construction environments and data availability requirements: Method one is suitable for fine control of ratios; Method two is suitable for rapid on-site application; Method three is suitable for large-scale simulation platforms or AI-assisted design systems. Actual project paving shows that after using the recommended scheme, the cold patch has a bonding strength of 0.158 MPa or higher at 30 minutes, the repair area peeling rate is reduced by 67%, and the structure retention time is increased to 42 minutes, significantly better than traditional formulations.

[0149] In a high-altitude construction site (altitude 3750 meters, air pressure about 66 kPa), the on-site measurement of light volatile factors is 10.2 g / m³ / 5min. According to the aforementioned simulation model, the total volatile loss of light components within 30 minutes after paving is estimated to be 46.3 g / m³, and the bonding strength decreases to 0.129 MPa due to rapid oil loss, which is lower than the set structural retention threshold of 0.150 MPa, with a bonding performance gap of 0.021 MPa.

[0150] To back-calculate the required medium-high boiling point solvent ratio for compensation, the following analysis process is established:

[0151] Introduce candidate solvent components (denoted as A, B, C), each with the following attributes:

[0152] Component A: initial boiling point 180℃, bonding contribution 0.0045 MPa / g, 30-minute residual rate 62%;

[0153] Component B: Initial boiling point 200℃, cohesive contribution 0.0059 MPa / g, 30-minute residual rate 71%;

[0154] Component C: Initial boiling point 215℃, cohesive contribution 0.0064 MPa / g, 30-minute residual rate 78%;

[0155] Taking Component C as an example, the mass required to fill in the strength gap of 0.021 MPa is: 0.021 ÷ 0.0064 ≈ 3.28 g / m³; the actual mass required is 3.28 ÷ 0.78 ≈ 4.21 g / m³.

[0156] To optimize the cost and reaction rate, the final choice is a mixed strategy of B:C = 1:2, with a total addition mass controlled at 6.5 g / m³, in which Component B contributes to the starting cohesive force and Component C prolongs the cohesive retention time.

[0157] Among them, through CFD-DEM simulation comparison of cohesive retention time and structural integrity of different proportions, it is found that the combination of B:C = 1:2 can achieve a cohesive strength ≥0.150 MPa within 30 minutes and the lowest stripping rate (such as 12%) under the premise of controllable cost, so this combination is selected.

[0158] In order to verify the influence of different medium-high boiling point solvent component proportions on the cohesive properties of cold patch materials, a CFD-DEM coupled simulation model is constructed to simulate and evaluate multiple combination schemes. Three representative components are considered: Component A (initial boiling point 180℃), Component B (200℃) and Component C (215℃), and the following four groups of proportion schemes are tested:

[0159] A:B:C = 1:1:1;

[0160] A:B:C = 0:1:2;

[0161] A:B:C = 1:2:1;

[0162] A:B:C = 0:1:2 (i.e. B:C = 1:2);

[0163] The simulation evaluation indexes include:

[0164] Average cohesive strength within 30 minutes after paving (MPa);

[0165] Stripping rate (percentage of interface damage points after 30 minutes);

[0166] Simulation stabilization time (the duration of the structure network to remain stable, min);

[0167] Single cost (yuan / m³, estimated according to materials).

[0168] Table 1 data results show

[0169] Matching scheme 30-minute average bonding strength (MPa) Peeling rate (%) Stabilization time (min) Material cost (yuan / m³) A:B:C=1:1:1 0.145 17.6 27 9.8 A:B:C=0:1:2 0.158 12.1 31 10.2 A:B:C=1:2:1 0.151 14.3 29 10.5 B:C=1:2 0.157 12.0 30 9.6

[0170] As can be seen from Table 1, the combination of B:C = 1:2 achieves the lowest stripping rate and the optimal material cost balance while ensuring that the bonding strength meets the standard (≥0.150 MPa). The structural stability retention time reaches more than 30 minutes, meeting the design requirements. Therefore, the combination is finally selected as the recommended ratio scheme.

[0171] In addition, in the actual test section verification, the ratio combination shows good structural retention ability, and the structural integrity score reaches the "A" level after 30 minutes, which is better than the conventional formula, further verifying the accuracy and practicality of the simulation results.

[0172] This scheme performs well in simulation tests: the mixture bonding strength is maintained at more than 0.154 MPa 30 minutes after paving, and the structural connection integrity is improved by about 35%, meeting the design requirements.

[0173] To reduce the pre-paving and early-stage evaporation of cold patch materials and improve the effective participation of lightweight components in the key stage, microencapsulation coating technology is used for controlled release treatment.

[0174] According to the construction point altitude of 3750 meters and the local surface temperature distribution (daytime normal temperature about 25℃, local area instantaneous temperature can reach 40℃ after paving), poly-lactide-co- poly(ethylene glycol) (PLGA-PEG) is selected as the wall material, and the thermal response temperature threshold is set to 42℃, which can trigger phase change rupture within 5-10 minutes after paving.

[0175] The average particle size of the microcapsule is controlled between 150-300 μm, and the coating rate is more than 80%, effectively delaying the evaporation time window.

[0176] Through thermal analysis test, the core temperature of the microcapsule reaches the trigger point at the 6th minute under the influence of heat conduction during the paving process, and the release of the main components is completed; the release rate conforms to the single-peak lag mode, which can provide stable light component supply within 5-10 minutes.

[0177] In the field mixing test, compared with the conventional light component mixture, the initial bonding strength between asphalt and aggregate of the microcapsule system increases by 19%, the air void rate decreases by 4.3%, and the surface uniformity is significantly enhanced.

[0178] This controlled release strategy cooperates with the aforementioned high-boiling point component backstepping results to build a dynamic balance system of "fast evaporation - slow release - long-term residual", which significantly improves the adaptability of the mixture in the plateau environment.

[0179] With the help of the multi-physical simulation platform constructed in the early stage, the cold patch material after optimization and microencapsulation treatment is simulated in a virtual construction environment, and a set of construction parameter suggestions is automatically generated, covering paving temperature, compaction frequency and construction window period.

[0180] Simulation of the initial bond strength response at different paving temperatures (25℃, 30℃, 35℃, 40℃) found that the optimal working temperature range was 32–36℃. Based on the temperature response rate and bond strength retention ability, the recommended paving temperature was 34±2℃.

[0181] Based on the simulation results of void ratio change trend and mechanical density, the initial compaction frequency was recommended to be 50 Hz, and the compaction time was controlled in the range of 40–60 seconds / ㎡ to avoid asphalt film rupture and early vibration delamination.

[0182] Through temperature-strength coupling curve analysis, the best compaction window is within the first 15 minutes after paving is completed, combined with the overlap of the microcapsule release peak, which can ensure the stable establishment of the bond bridge.

[0183] This set of construction parameters has been integrated into the intelligent terminal construction guidance system. Field construction personnel can directly call the recommended values based on real-time sensing data to improve construction response efficiency and quality consistency.

[0184] The above three technical solutions are applied to the field test section, and the field feedback is as follows:

[0185] The initial strength of the material is improved by 23%, the 30-minute structure retention rate is increased by 41%, the average time for construction compaction operation is reduced by 18%, and the peeling rate within 3 months after road repair is reduced to 30% of the traditional formula.

[0186] The above data fully verify that the system optimization strategy of "bond gap identification → controlled release regulation → parameter-driven construction" can effectively solve the early failure problem of cold patch material on the plateau, and improve its construction adaptability and service life.

[0187] In the rapid repair project of the plateau highway (construction site: altitude 3850 meters, daily temperature difference up to 18℃, sudden wind speed up to 7 m / s), the project deployed a multi-source environmental data acquisition module, including:

[0188] Temperature sensor (monitoring ground temperature and environmental temperature);

[0189] Atmospheric pressure sensor (monitoring real-time air pressure at the construction site);

[0190] Humidity and wind speed sensor (auxiliary judgment of evaporation rate and heat dissipation trend);

[0191] GPS and timestamp module (correlation with historical construction data to match the current time period and location).

[0192] These sensors are integrated on the side end of the paving equipment, pre-processed locally by the edge computing unit, and data is packaged and sent to the central intelligent control platform every 10 seconds as input variables for machine learning prediction models.

[0193] Real-time sensing data includes but is not limited to: current ground temperature (℃); atmospheric pressure (kPa); wind speed (m / s); humidity (%); asphalt temperature (measured by the paving layer); light component loss rate prediction value (provided by the CFD estimation model).

[0194] In the system platform, a multi-input multi-output (MIMO) machine learning model is deployed, which is trained based on regression algorithms (such as XGBoost, multi-layer perceptron MLP). The goal is to predict construction parameter outputs based on environmental inputs, including: optimal paving temperature; optimal compaction frequency; reasonable compaction time window; structure stability score.

[0195] Using construction data samples from 9 plateau projects, including temperature, air pressure, light component loss rate, and structure instability time after paving, a total of 2000+ samples, data preprocessing is used to train the model.

[0196] After the model inputs real-time environmental parameters, the output is as follows:

[0197] Under the current construction state, the recommended paving temperature is 33-35℃; the recommended initial compaction frequency is 48-52 Hz; the predicted optimal starting time for compaction is between 2-4 minutes after paving; the current bonding bridge formation trend is good, with a structure score of "B+ ". The platform presents the results on the construction control terminal interface through color codes and data charts to assist operators in making parameter adjustment decisions.

[0198] To further improve the system's response capability to complex environmental disturbances (such as sudden cooling, sudden wind, etc.), the system introduces a reinforcement learning (Reinforcement Learning, RL) strategy model, building autonomous learning capabilities so that it can optimize control strategies based on historical feedback without explicit rules.

[0199] State-Action-Reward mechanism setting:

[0200] State (S): including current environmental parameters, construction parameter settings, bonding strength prediction;

[0201] Action (A): adjust paving temperature, compaction frequency, and other control variables;

[0202] Reward (R): assign values based on structure retention rate after 30 minutes of simulation prediction (e.g. bonding strength greater than threshold reward +1, less than negative value).

[0203] The RL model uses the Q-learning algorithm to continuously update the Q-value table, and through the process of continuous "exploration-error-strengthening", the optimal parameter combination memory under different environments is formed. For example, under continuous high wind speed and low air pressure, the system gradually "learns" to increase the paving temperature and delay the compaction time to compensate for heat loss and early evaporation.

[0204] Once the policy output deviates from the current device setting parameters, the system will automatically generate adjustment instructions and send them to the construction equipment control port. The equipment automatically modifies the temperature control system (such as heating temperature) or vibration frequency controller according to the intelligent adjustment value, realizing dynamic optimization closed-loop control.

[0205] The system is integrated and applied to a certain municipal road rapid maintenance project on the plateau, and in 14 days, about 6300 m² of cold patch repair area is completed, and the monitoring and feedback data are as follows:

[0206] The average initial bonding strength is improved by 18.6%; the structural instability rate is reduced by 42% compared with the traditional parameter setting; the paving temperature fluctuation is controlled within ±1.8℃; the actual compaction frequency deviates from the recommended value by less than 3Hz; the overall construction time is shortened by 11%, and the material loss is reduced by 9%. The field operators feedback that the system interface is intuitive, and the parameter recommendation is close to the experience value, which greatly reduces the rework or quality hidden dangers caused by environmental mutations.

[0207] This embodiment shows the complete closed-loop process of cold patch asphalt mixture construction intelligent control: real-time environmental perception→ intelligent prediction model→ optimal strategy recommendation→ adaptive parameter adjustment. The system combines classical regression algorithm and reinforcement learning strategy, not only has historical experience memory, but also has environmental dynamic response ability, especially suitable for road maintenance engineering in complex and variable environments such as plateau, remote areas, etc., and has high popularization value.

[0208] Embodiment 2, please refer to Figure 2 The cold patch asphalt mixture efficient preparation and construction optimization system described in this embodiment comprises:

[0209] An environmental parameter acquisition module acquires construction environmental parameters, including the altitude of the target construction point, the local air pressure correction coefficient, and the light volatile factor;

[0210] A multi-scale simulation analysis module constructs a constitutive model coupled with air pressure response, based on the coupling simulation of discrete element method and computational fluid dynamics, simulates the light component volatilization path, internal structure stability and initial bonding strength change of the mixture in the construction environment;

[0211] a structure threshold identification module, which identifies a key structure retention threshold of the cold patch mixture according to the coupling simulation output, that is, a minimum bonding strength value required to maintain structural integrity within 30 minutes after paving;

[0212] a proportioning backstepping module, which calculates a bonding performance gap value in combination with the lightweight volatile factor and the structure retention threshold, and backsteps a proportioning adjustment amount of the medium-high boiling point solvent component to fill the bonding gap;

[0213] a microcapsule controlled release module, which performs microcapsule controlled release processing on the lightweight component, with a response temperature set according to the altitude and typical temperature conditions of the construction site, and a delayed release time controlled within 5-10 minutes after paving;

[0214] a simulation-driven construction suggestion module, which outputs a construction suggestion parameter set based on the simulation platform, including recommended paving temperature, compaction frequency, and construction window period;

[0215] a construction intelligent adjustment module, which collects environmental change data in real time during the construction process, and dynamically adjusts and optimizes the paving temperature and compaction frequency in combination with a machine learning prediction model, to realize intelligent adaptive control of the construction process.

[0216] The above formulas are all dimensionless numerical calculations, and the formulas are obtained by software simulation of a large amount of data to obtain a formula closest to the actual situation. The preset parameters in the formula are set by a person skilled in the art according to the actual situation.

[0217] It should be understood that the term "and / or" in this document is only a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the front and rear associated objects, but it can also represent an "and / or" relationship. The specific meaning can be understood in combination with the context before and after.

[0218] Those skilled in the art can appreciate that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0219] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A method for efficient preparation and optimized construction of cold-mix asphalt mixtures, characterized in that: include: Collect construction environment parameters, including the altitude of the target construction site, the local air pressure correction factor, and the light volatile factor; A constitutive model coupled with air pressure response was constructed, and a coupled simulation based on discrete element method and computational fluid dynamics was used to simulate the volatilization path of light components, internal structural stability and changes in initial bond strength of the mixture under construction environment. Based on the coupled simulation output, the structural retention threshold of the cold patch mixture is identified, which is the minimum bond strength required to maintain structural integrity within 30 minutes after paving. By combining the light volatility factor with the structure retention threshold, the bonding performance gap value is calculated, and the proportion adjustment amount of medium and high boiling point solvent components is deduced to fill the bonding gap. Lightweight components are subjected to microencapsulation controlled release treatment, and the response temperature is set according to the altitude and typical temperature conditions of the construction site, with the delayed release time controlled within 5 to 10 minutes after paving. Based on the simulation platform, a set of construction recommendation parameters is output, including recommended paving temperature, compaction frequency and construction window period; During construction, environmental change data is collected in real time, and machine learning prediction models are used to dynamically adjust and optimize paving temperature and compaction frequency, thereby achieving intelligent adaptive control of the construction process.

2. The method for efficient preparation and optimized construction of cold-mix asphalt mixture according to claim 1, characterized in that: The collected construction environment parameters include: The altitude of the target construction site is obtained in real time through environmental sensing devices. Calculate the local pressure correction factor based on the ratio of measured air pressure to standard atmospheric pressure; A constant-pressure volatilization experiment was conducted on a selected light component sample, and the changes in volatilized mass under different pressures and temperatures were recorded. A response surface of pressure-temperature-time and volatilization rate was constructed using a piecewise linear interpolation method. The current pressure and temperature were matched in real time at the construction site, and the corresponding volatilized mass per unit time in the response surface was read to determine the light volatile factor.

3. The method for efficient preparation and construction optimization of cold-mix asphalt mixture according to claim 1, characterized in that: The construction of the constitutive model coupled with the pressure response includes the following steps: A contact model between aggregate particles was established using the discrete element method, with parameters including particle size distribution, friction coefficient, and contact elastic modulus. The lightweight asphalt component is treated as a continuous fluid, and its evaporation, diffusion, and motion behavior under low pressure conditions are described using computational fluid dynamics methods. By introducing a pressure response factor as a control parameter and embedding the local pressure correction coefficient into the flow field boundary conditions, the evaporation rate and the wetting behavior between asphalt and aggregate are dynamically adjusted. The changing trend of initial bond strength is calculated in real time in the coupled model, and the structural integrity maintenance time and initial peeling risk index are output.

4. The method for efficient preparation and construction optimization of cold-mix asphalt mixture according to claim 3, characterized in that: The simulated mixture under construction conditions exhibits changes in the volatilization path of its lightweight components, internal structural stability, and initial bond strength, including: An initial particle distribution model was constructed based on the microstructure scanning results of the mixture, and the model was then imported into the discrete element simulation framework. Lightweight volatile factors collected from environmental parameters are introduced to drive the CFD module to simulate the unsteady diffusion-volatilization process of asphalt components; The decay rate of interparticle bonding bridge thickness is calculated in real time, and the initial bonding strength decay curve is deduced based on the change of this value. When the bond strength drops to a preset threshold, the model automatically marks potential peeling areas.

5. The method for efficient preparation and construction optimization of cold-mix asphalt mixture according to claim 1, characterized in that: The method for adjusting the proportions of medium- and high-boiling-point solvent components is derived by reversal, including: Based on the lightweight volatile factors collected under the construction environment, the total expected volatile mass of the lightweight components in the cold patch mixture within 30 minutes after paving is estimated. By comparing the structural retention threshold, the bonding performance gap value is determined, which is the difference between the minimum effective bond strength required for the mixture to maintain structural integrity and the actual retainable strength. Based on the residual rate of medium- and high-boiling-point solvents at the current pressure and temperature and their contribution to the bond strength per unit mass, calculate the mass of alternative components required to fill the bond performance gap. Output the adjustment amount of the high-boiling-point solvent component as a partial replacement ratio of the original light component.

6. The method for efficient preparation and construction optimization of cold-mix asphalt mixture according to claim 1, characterized in that: The microencapsulation controlled-release treatment of the light components includes: A polymer material with thermosensitive response characteristics is selected as the microcapsule wall material. The material undergoes a phase change or structural rupture at a set temperature to release the encapsulated material. Based on the altitude of the target construction site, the typical daytime air temperature and heat conduction rate of the area where the target construction site is located are calculated, and the appropriate wall material response temperature range is determined through an empirical correlation model. Light components are encapsulated in liquid form in the core of microcapsules, and the wall thickness and structure are controlled so that the microcapsule reaches the response temperature and releases its contents within 5 to 10 minutes after paving. Microcapsules are uniformly incorporated into cold patch mixes to achieve controlled release of lightweight components, thereby reducing premature volatilization losses before paving and during the initial compaction stage.

7. The method for efficient preparation and construction optimization of cold-mix asphalt mixture according to claim 1, characterized in that: The set of construction suggestion parameters output based on the simulation platform includes: Based on the coupled air pressure response model and the mixture performance simulation platform, the environmental parameters of the construction site and the target mixture ratio are input, and the simulation is run to obtain the temperature response, bond strength evolution and structural stability data of the material during the paving stage. Analyze the trend of bond strength variation in the simulation results, extract the time period with the highest bond performance retention rate within the optimal temperature range, and output the recommended paving temperature corresponding to the optimal temperature range. Based on the convergence rate of porosity and the distribution of compaction energy consumption in the simulation, the compaction frequency and vibration mode required to achieve the optimal compaction density are determined. By combining the temperature-sensitive range and the bonding window, a suitable construction window duration is set, and a set of construction suggestion parameters is output.

8. The method for efficient preparation and construction optimization of cold-mix asphalt mixture according to claim 1, characterized in that: The dynamic adjustment and optimization of paving temperature and compaction frequency, combined with machine learning prediction models, includes: Environmental sensing modules are deployed at the construction site to collect dynamic environmental parameters such as air temperature, surface temperature, wind speed, and air pressure in real time. The collected environmental data is input into a machine learning model built on supervised learning. The model has been trained with historical construction data to obtain the correlation between paving effect and environmental variables. The model predicts the optimal paving temperature and compaction frequency range of cold patch material under current environmental conditions based on real-time input. The prediction results are used as a control reference to output dynamic adjustment suggestions and guide the construction equipment to make on-site fine adjustments to the paving and compaction parameters.

9. The method for efficient preparation and construction optimization of cold-mix asphalt mixture according to claim 8, characterized in that: The dynamic adjustment and optimization further includes: Establish a reinforcement learning-based model that continuously learns the long-term impact of environmental changes on the adjustment of construction parameters through historical construction feedback; The model continuously acquires environmental state inputs during construction and outputs a prediction of the impact of the current operation on the future structural stability. Based on the prediction results, a multi-objective trade-off function for temperature, frequency, and stability is set, and the current optimal strategy is calculated. The paving temperature and compaction frequency are dynamically adjusted based on the optimal strategy.

10. A system for efficient preparation and construction optimization of cold-patch asphalt mixtures, used to implement the method for efficient preparation and construction optimization of cold-patch asphalt mixtures as described in any one of claims 1-9, characterized in that: include: The environmental parameter acquisition module collects construction environmental parameters, including the altitude of the target construction site, the local air pressure correction coefficient, and the light volatile factor. The multi-scale simulation analysis module constructs a constitutive model coupled with air pressure response. Based on the coupled simulation of discrete element method and computational fluid dynamics, it simulates the volatilization path of light components, internal structural stability and changes in initial bond strength of the mixture under construction environment. The structural threshold identification module identifies the structural retention threshold of cold-mixed materials based on the coupled simulation output, which is the minimum bond strength required to maintain structural integrity within 30 minutes after paving. The ratio deduction module, combining the light volatility factor and the structure retention threshold, calculates the bonding performance gap value and deduces the ratio adjustment amount of the medium and high boiling point solvent components to fill the bonding gap. The microcapsule controlled release module performs microcapsule controlled release treatment on lightweight components. Its response temperature is set according to the altitude and typical temperature conditions of the construction site, and the delayed release time is controlled within 5 to 10 minutes after paving. The simulation-driven construction suggestion module outputs a set of construction suggestion parameters based on the simulation platform, including recommended paving temperature, compaction frequency and construction window period; The intelligent construction adjustment module collects environmental change data in real time during construction and combines it with machine learning prediction models to dynamically adjust and optimize paving temperature and compaction frequency, thereby achieving intelligent adaptive control of the construction process.

Images