Preparation method, device and equipment of salt corrosion resistant asphalt material for coast expressway and storage medium

Abstract

According to the preparation method, device and equipment of the salt corrosion-resistant asphalt material for the coast expressway and the storage medium, environmental data of the coast expressway are obtained, the prices of matrix asphalt, an SBS modifier, a salt-resistant agent and filler are obtained respectively, and the salt corrosion-resistant asphalt material for the coast expressway is obtained according to the preset proportion ranges and prices corresponding to the matrix asphalt, the SBS modifier, the salt-resistant agent and the filler respectively. Determining a cost model, constructing a fitness model according to the cost model and the environmental data, determining target proportions corresponding to the matrix asphalt, the SBS modifier, the salt-resistant agent and the filler according to the fitness model and a genetic algorithm, and determining the target proportions of the matrix asphalt, the SBS modifier, the salt-resistant agent and the filler according to the target proportions. In consideration of the preparation cost and environmental factors, the optimal target proportions corresponding to the matrix asphalt, the SBS modifier, the salt-resistant agent and the filler are determined based on the genetic algorithm to prepare the salt-corrosion-resistant asphalt material, so that the cost is favorably controlled, the quality of the salt-corrosion-resistant asphalt material is ensured, and the salt corrosion resistance is ensured.

Description

Technical Field

[0001] This application relates to the field of production, and in particular to a method, apparatus, equipment and storage medium for preparing salt-resistant asphalt material for coastal highways. Background Technology

[0002] With the rapid economic development of coastal areas, the demand for coastal highway construction is increasing. However, the special marine environment of coastal areas has brought severe challenges to highway construction, among which salt corrosion is particularly prominent. Seawater is rich in salt, such as sodium chloride and magnesium chloride. These salts continuously erode highway pavement through sea breezes, spray from waves, and rainwater erosion. Long-term salt corrosion will lead to the deterioration of asphalt material performance, reduce the adhesion between asphalt and aggregate, and cause pavement loosening, potholes, cracking and other diseases, seriously affecting the service life of the pavement and driving safety. Therefore, it is crucial to prepare salt corrosion resistant asphalt materials. Currently, conventional asphalt materials have significant shortcomings in terms of salt corrosion resistance. In a salt-corrosion environment, the chemical structure of ordinary asphalt is easily damaged, leading to accelerated asphalt aging and reduced viscosity. As a result, it cannot effectively coat the aggregate, threatening the stability of the pavement structure. If the proportion of some salt-resistant agents is not appropriate, it may have a negative impact on other properties of asphalt, such as affecting its high-temperature stability or low-temperature crack resistance. Furthermore, some complex modification processes are not only costly but also difficult to promote and apply in actual production and construction. Summary of the Invention

[0003] This application provides a method, apparatus, equipment, and storage medium for preparing salt-erosion resistant asphalt material for coastal highways, to solve at least one problem existing in related technologies. The technical solution is as follows: In a first aspect, embodiments of this application provide a method for preparing salt-erosion resistant asphalt material for coastal highways, comprising: Obtain environmental data for the coastal highway, as well as the prices of base asphalt, SBS modifier, salt-resistant agent, and filler, respectively; Based on the preset proportion ranges and prices of the base asphalt, SBS modifier, salt-resistant agent, and filler, a cost model is determined, and an fitness model is constructed based on the cost model and the environmental data. Based on the fitness model and genetic algorithm, the target proportions of base asphalt, SBS modifier, salt-resistant agent, and filler are determined respectively. Salt-resistant asphalt materials are prepared according to the target proportions of base asphalt, SBS modifier, salt-resistant agent, and filler.

[0004] In one implementation, constructing the fitness model based on the cost model and the environmental data includes: Based on the environmental data, the quantitative range corresponding to each environmental parameter is determined; the environmental parameters include chloride concentration, temperature, humidity, ultraviolet intensity, and number of freeze-thaw cycles; Based on the quantification range and the preset proportion range, the weights of the base asphalt, SBS modifier, salt-resistant agent, filler, and each of the environmental parameters are determined respectively. A penetration retention rate model is constructed based on the base asphalt, SBS modifier, salt-resistant agent, filler, various environmental parameters and their corresponding weights. Based on the penetration retention rate model and the cost model, a fitness model is constructed.

[0005] In one embodiment, determining the weights of the base asphalt, SBS modifier, salt-resistant agent, filler, and each of the environmental parameters according to the quantification range and the preset proportion range includes: Within the preset proportion range corresponding to the base asphalt, SBS modifier, salt-resistant agent, and filler, several proportions are determined respectively, and the proportions are combined to obtain several sets of first test data; Within the quantization range corresponding to each environmental parameter, several parameter values ​​corresponding to each environmental parameter are determined, and the parameter values ​​are combined to obtain several sets of second experimental data. Under the conditions of the first test data and the second test data, the corresponding needle penetration retention rate is determined, and orthogonal test data is determined based on the first test data, the second test data and the needle penetration retention rate. Multiple regression analysis is performed based on the orthogonal experimental data and the formula of the preset penetration retention rate model to determine the weights of the base asphalt, SBS modifier, salt-resistant agent, filler, and each of the environmental parameters. Alternatively, the weights of each of the environmental parameters are determined by the analytic hierarchy process (AHP), and multiple regression analysis is performed based on the orthogonal experimental data, the formula of the preset penetration retention rate model, and the weights of each of the environmental parameters to determine the weights of the base asphalt, SBS modifier, salt-resistant agent, and filler.

[0006] In one implementation, constructing the fitness model based on the penetration retention rate model and the cost model includes: Based on the penetration retention rate model and the preset maximum retention rate, a performance normalization value is determined, and a first product of the performance normalization value and the first preset weight is determined. Based on the cost model and the maximum cost, a normalized cost value is determined, and a second product of the normalized cost value and the second preset weight is determined. A fitness model is constructed based on the sum of the first product and the second product.

[0007] In one embodiment, determining the target proportions of the base asphalt, SBS modifier, salt-resistant agent, and filler based on the fitness model and genetic algorithm includes: Based on the quantization range and each of the preset proportion ranges, several sets of simulation data corresponding to the number of individuals in the population are determined. Using a genetic algorithm, the fitness of each individual and the sum of fitness values ​​are determined based on the simulated data and the fitness model, respectively. Then, based on the fitness values ​​and the sum of fitness values, the fitness percentage of each individual is determined to form a roulette wheel probability distribution. Based on the random number and the probability distribution of the roulette wheel, the population is iterated until the change in the maximum fitness in a preset number of consecutive iterations is less than or equal to a preset threshold; wherein, in each iteration, individuals whose fitness ranks in the top preset percentage are retained. The proportions of base asphalt, SBS modifier, salt-resistant agent, and filler in the simulation data corresponding to the individual with the highest fitness are determined as the target proportions of base asphalt, SBS modifier, salt-resistant agent, and filler, respectively.

[0008] In one embodiment, the preparation of the salt-resistant asphalt material according to the target proportions of the base asphalt, SBS modifier, salt-resistant agent, and filler includes: According to the target proportions of the base asphalt, SBS modifier, salt-resistant agent, and filler, the salt-resistant asphalt material to be prepared is mixed. Based on the target proportions of SBS modifier, salt-resistant agent, and filler, the dynamic viscosity of the salt-resistant asphalt material at the target processing temperature is determined. Based on the preset uniformity, determine the stirring rate and stirring time corresponding to the mixing of the salt corrosion resistant asphalt material to be prepared; When the dynamic viscosity is within the preset viscosity range, the salt-resistant asphalt material to be prepared is prepared according to the target processing temperature, the stirring rate and the stirring time to obtain the final salt-resistant asphalt material. When the dynamic viscosity is outside the preset viscosity range, at least one of the target proportion of SBS modifier, the target proportion of filler and the target processing temperature is adjusted until the newly determined dynamic viscosity is within the preset viscosity range.

[0009] In one embodiment, the method further includes: The actual penetration retention rate, actual dynamic viscosity, and actual uniformity of the final salt-resistant asphalt material are detected, and the actual penetration retention rate is compared with the penetration retention rate threshold, the actual dynamic viscosity is compared with a preset viscosity range, and the actual uniformity is compared with a preset uniformity. If the actual penetration retention rate is greater than or equal to the penetration retention rate threshold, the actual dynamic viscosity is within the preset viscosity range, and the actual uniformity is greater than or equal to the preset uniformity, the final salt corrosion resistant asphalt material is determined to be of qualified quality. If the actual penetration retention rate is less than the penetration retention rate threshold or the actual dynamic viscosity is outside the preset viscosity range, adjust the target proportion of at least one of the SBS modifier and filler. If the actual uniformity is less than the preset uniformity, increase the stirring rate or stirring time.

[0010] Secondly, embodiments of this application provide an apparatus for preparing salt-resistant asphalt material for coastal highways, comprising: The acquisition module is used to acquire environmental data of the coastal highway, as well as the prices of the base asphalt, SBS modifier, salt-resistant agent, and filler, respectively. The construction module is used to determine the cost model based on the preset proportion range and price of the base asphalt, SBS modifier, salt-resistant agent, and filler, and to construct the fitness model based on the cost model and the environmental data. The determination module is used to determine the target proportions of base asphalt, SBS modifier, salt-resistant agent, and filler, respectively, based on the fitness model and the genetic algorithm. The preparation module is used to prepare salt-resistant asphalt materials according to the target proportions of base asphalt, SBS modifier, salt-resistant agent, and filler.

[0011] In one embodiment, the coastal highway salt-resistant asphalt material preparation device further includes a detection module, which is used for: The actual penetration retention rate, actual dynamic viscosity, and actual uniformity of the final salt-resistant asphalt material are detected, and the actual penetration retention rate is compared with the penetration retention rate threshold, the actual dynamic viscosity is compared with a preset viscosity range, and the actual uniformity is compared with a preset uniformity. If the actual penetration retention rate is greater than or equal to the penetration retention rate threshold, the actual dynamic viscosity is within the preset viscosity range, and the actual uniformity is greater than or equal to the preset uniformity, the final salt corrosion resistant asphalt material is determined to be of qualified quality. If the actual penetration retention rate is less than the penetration retention rate threshold or the actual dynamic viscosity is outside the preset viscosity range, adjust the target proportion of at least one of the SBS modifier and filler. If the actual uniformity is less than the preset uniformity, increase the stirring rate or stirring time.

[0012] Thirdly, embodiments of this application provide an electronic device, including: a processor and a memory, wherein the memory stores instructions that are loaded and executed by the processor to implement the methods in any of the above-described embodiments.

[0013] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed, implements the methods in any of the above-described embodiments.

[0014] The beneficial effects of the above technical solution include at least the following: By acquiring environmental data of the coastal highway and obtaining the prices of base asphalt, SBS modifier, salt-resistant agent, and filler, a cost model is determined based on the preset proportion ranges and prices of each component. A fitness model is then constructed based on the cost model and environmental data. Using the fitness model and a genetic algorithm, the target proportions of each component are determined. Considering preparation costs and environmental factors, the optimal target proportions of these components are determined using a genetic algorithm for the preparation of salt-resistant asphalt materials. This approach helps control costs and ensures the quality and salt-resistant performance of the asphalt materials.

[0015] The above overview is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, these aspects, embodiments, and features will become readily apparent from the accompanying drawings and the following detailed description. Attached Figure Description

[0016] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments disclosed in this application and should not be construed as limiting the scope of this application.

[0017] Figure 1 This is a schematic flowchart illustrating the steps of a method for preparing salt-resistant asphalt material for coastal highways according to an embodiment of this application; Figure 2This is a structural block diagram of a coastal highway salt-erosion resistant asphalt material preparation apparatus according to an embodiment of this application; Figure 3 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0018] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of this application. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0019] Reference Figure 1 The flowchart illustrates a method for preparing salt-erosion resistant asphalt material for coastal highways according to an embodiment of this application. This method may include at least steps S100-S400: S100, obtain environmental data for the coastal highway, and obtain prices for base asphalt, SBS modifier, salt-resistant agent, and filler respectively.

[0020] S200: Based on the preset proportion ranges and prices of base asphalt, SBS modifier, salt-resistant agent, and filler, a cost model is determined, and an fitness model is constructed based on the cost model and environmental data.

[0021] S300. Based on the fitness model and genetic algorithm, determine the target proportions of base asphalt, SBS modifier, salt-resistant agent, and filler.

[0022] S400: Prepare salt-resistant asphalt materials according to the target proportions of base asphalt, SBS modifier, salt-resistant agent, and filler.

[0023] The technical solution of this application embodiment obtains environmental data of the coastal highway and the prices of the base asphalt, SBS modifier, salt-resistant agent, and filler, respectively. Based on the preset proportion range and price of the base asphalt, SBS modifier, salt-resistant agent, and filler, a cost model is determined. Based on the cost model and environmental data, a fitness model is constructed. Based on the fitness model and genetic algorithm, the target proportions of the base asphalt, SBS modifier, salt-resistant agent, and filler are determined. Considering the preparation cost and environmental factors, the optimal target proportions of the base asphalt, SBS modifier, salt-resistant agent, and filler are determined based on the genetic algorithm for the preparation of salt-resistant asphalt materials. This helps to control costs and ensure the quality of salt-resistant asphalt materials, thus guaranteeing their salt-resistant performance.

[0024] In one embodiment, in step S100, the prices of the base asphalt, SBS modifier, salt-resistant agent, and filler can be obtained by searching the internet or relevant books. Optionally, the prices are 3200, 18000, 25000, and 600 yuan / ton, respectively.

[0025] Optionally, the collected environmental data for coastal highways includes chloride concentration data, temperature data, humidity data, ultraviolet (UV) intensity data, and freeze-thaw cycle count data. For example, chloride concentration data is obtained by measuring the chloride concentration of coastal atmospheric deposition and road surface water using ion chromatography, and a dynamic database is established by monitoring chloride concentration data quarterly; temperature data is determined based on meteorological data from the past 5 years; humidity data of the road surface is collected in real time using humidity sensors, which can distinguish between rainy season, wet season, and dry season, with different humidity ranges corresponding to different salinity permeability coefficients; UV intensity data in the 300-400nm band is measured using a UV radiometer, taking into account the aggravating effect of the summer midday UV peak on asphalt photo-oxidation; and freeze-thaw cycle count data is calculated based on the number of days with a minimum temperature ≤0℃ and a maximum temperature ≥5℃.

[0026] In one embodiment, step S200 determines the cost model based on the preset proportion ranges and prices of the base asphalt, SBS modifier, salt-resistant agent, and filler, respectively. For example: 1. Base asphalt: Use 70# or 90# road petroleum asphalt, with a preset proportion range of 82%-88%. That is, the proportion of base asphalt 'a' needs to be determined from 82% to 88%. Too low a proportion will result in insufficient low-temperature crack resistance, while too high a proportion will affect the dispersion effect of the modifier.

[0027] 2. SBS Modifier: Star-shaped SBS with a molecular weight of 200,000-300,000 is used. The preset proportion range is 3.5%-4.5%. That is, the proportion of SBS modifier b needs to be determined from 3.5%-4.5% and needs to be precisely controlled. The modification effect is not significant if it is below 3%, and it is easy to cause a sharp increase in cost and a decrease in high temperature stability if it is above 5%.

[0028] 3. Salt-resistant agent: The composite salt-resistant agent organic amine + nano SiO2 is selected, with a preset proportion range of 1.5%-2.5%. That is, the proportion c of the salt-resistant agent needs to be determined from 1.5% to 2.5%. The salt-resistant effect is weak when it is below 1%, and it will reduce the adhesion between asphalt and aggregate when it is above 3%.

[0029] 4. Filler: Limestone mineral powder (fineness 0.075mm sieve residue ≤10%) is used, with a preset proportion range of 6%-9% (below 5% it is difficult to form a skeleton structure, and above 10% it is easy to cause the mixture to be dry). That is, the proportion d of filler needs to be determined from 6%-9%, and the sum of a, b, c and d must be 100%.

[0030] It should be noted that the above-mentioned preset proportion ranges can determine the effective action ranges of each component through orthogonal experiments in advance as the preset proportion ranges; taking the above price example, taking 1 ton as an example, the cost model can be determined at this time :

[0031] It can be understood that a, b, c, and d are respectively restricted by their own corresponding preset proportion ranges.

[0032] In one implementation, in step S200, according to the cost model and environmental data, a fitness model is constructed, including steps S210 - S240: S210. According to the environmental data, determine the quantization ranges corresponding to each environmental parameter.

[0033] It can be understood that the environmental parameters include chloride salt concentration (C), temperature (T), humidity (H), ultraviolet intensity (U), and number of freeze-thaw cycles (N); by analyzing the obtained environmental data, the quantization ranges corresponding to each environmental parameter are determined. For example: The quantization range of chloride salt concentration (C) is 0.5% - 6.0% (covering different regional characteristics such as tidal zones and splash zones); the quantization range of temperature (T) is divided into a temperature range from -15°C (extreme low temperature) to 45°C (extreme high temperature), and at the same time, the day-night temperature difference coefficient , that is, the difference between the maximum temperature and the minimum temperature, is introduced to quantify the acceleration effect of temperature fluctuation on salt corrosion; humidity (H): If in the rainy season, the quantization range is H≥85%, if in the humid season (60% < H < 85%), if in the dry season (H≤60%); the quantization range of ultraviolet intensity (U) is 5 - 30 W / m², considering the exacerbating effect of the ultraviolet peak at noon in summer on the photooxidation of asphalt; the quantization range of the number of freeze-thaw cycles (N) is set to 0 - 80 times, which can cover different coastal areas at different latitudes, and each cycle corresponds to a growth coefficient of 1.2% in the internal porosity of the material.

[0034] S220. According to the quantization range and the preset proportion range, respectively determine the weights corresponding to the matrix asphalt, SBS modifier, anti-salt agent, filler, and each environmental parameter.

[0035] Optionally, S220 includes S2201 - S2204: S2201. Within the preset proportion ranges corresponding to the matrix asphalt, SBS modifier, anti-salt agent, and filler, respectively determine several proportions, and combine the proportions to obtain several groups of first test data.

[0036] Optionally, within a preset range of proportions for the base asphalt, SBS modifier, salt-resistant agent, and filler, several proportions are determined respectively. For example, A proportions are determined for the base asphalt, SBS modifier, salt-resistant agent, and filler. These proportions are then combined to form a set of first experimental data, thus obtaining several sets of first experimental data. It is understood that in each set of first experimental data, the sum of all proportions is 100%.

[0037] S2202. Within the quantification range corresponding to each environmental parameter, determine several parameter values ​​corresponding to each environmental parameter, and combine the parameter values ​​to obtain several sets of second experimental data.

[0038] Optionally, within the quantification range corresponding to each environmental parameter, several parameter values ​​corresponding to each environmental parameter are determined. Similarly, chloride concentration, temperature, humidity, ultraviolet intensity, and number of freeze-thaw cycles can all be determined with A parameter values. A parameter value of chloride concentration, a parameter value of temperature, a parameter value of humidity, a parameter value of ultraviolet intensity, and a parameter value of number of freeze-thaw cycles are combined to form a set of second experimental data, thereby obtaining several sets of second experimental data.

[0039] S2203. Under the conditions of the first test data and the second test data, determine the corresponding penetration retention rate, and determine the orthogonal test data based on the first test data, the second test data and the penetration retention rate.

[0040] For example, a set of first experimental data and a set of second experimental data are used as experimental conditions. Then, the penetration retention rate under these experimental conditions is determined by traditional testing methods. Therefore, a set of first experimental data, a set of second experimental data, and a measured penetration retention rate constitute a complete set of experimental data. Several sets of complete experimental data constitute orthogonal experimental data. For example, it can be determined that 500 sets of complete experimental data constitute orthogonal experimental data.

[0041] S2204. Based on the orthogonal experimental data and the formula of the preset penetration retention rate model, perform multiple regression analysis to determine the weights of the base asphalt, SBS modifier, salt-resistant agent, filler, and each environmental parameter. Alternatively, determine the weights of each environmental parameter through the analytic hierarchy process (AHP). Based on the orthogonal experimental data, the formula of the preset penetration retention rate model, and the weights of each environmental parameter, perform multiple regression analysis to determine the weights of the base asphalt, SBS modifier, salt-resistant agent, and filler.

[0042] In this embodiment of the application, the preset penetration retention rate model is:

[0043] Where R is the penetration retention rate, and 52.3 is the baseline value. The weights corresponding to the base bitumen. The weight corresponding to the SBS modifier. The weights corresponding to salt-resistant agents, The weight corresponding to the filler. The weights corresponding to the chloride concentration C are: The weights corresponding to temperature T. The weights corresponding to humidity H are: The weight corresponding to the number of freeze-thaw cycles N. This is the random error term.

[0044] In one implementation, a multiple regression analysis is performed based on orthogonal experimental data and a pre-defined formula for the penetration retention rate model. This minimizes the overall error between the calculated penetration retention rate of the 500 penetration retention rate models and the measured penetration retention rate, thereby determining the specific values ​​of the weights corresponding to the base asphalt, SBS modifier, salt-resistant agent, filler, and various environmental parameters. For example, after determining the specific values ​​of each weight, the final penetration retention rate model is as follows:

[0045] The weighting significance is as follows: 3.22 indicates that for every 1% increase in the proportion of anti-salt agent, the penetration retention rate increases by an average of 3.22%, significantly higher than other components, reflecting its core anti-salt effect; -1.76 indicates that for every 1% increase in chloride concentration, the penetration retention rate decreases by an average of 1.76%, accurately quantifying the damage caused by salt corrosion; the error term εvarepsilon is controlled within ±1.5% by increasing the experimental sample size and repeating the experiment three times for each parameter and taking the average value to reduce random error.

[0046] Optionally, model validation: Three typical coastal sections were selected, and on-site sampling was conducted in the northern freeze-thaw zone, the southern high-temperature and high-humidity zone, and the salt spray frequent zone. The actual environmental parameters were substituted into the formula to calculate the predicted values, and compared with the 28-day salt spray test results of the on-site core samples. The error was ≤3.2%, which proved the practical applicability of the model.

[0047] In another implementation, the weights of each environmental parameter can be determined using the Analytic Hierarchy Process (AHP). For example, AHP can be used to calculate the weights of each environmental factor, and then several road material experts can score the importance of chloride concentration (C), temperature (T), humidity (H), ultraviolet radiation intensity (U), and freeze-thaw cycle count (N). Finally, the weights of each environmental parameter can be determined, for example... =0.35、 =0.20、 =0.15、 =0.15、 =0.15 (number of freeze-thaw cycles). Then, these weights are directly substituted into the formula for the penetration retention rate model, or the weights can be further fine-tuned before being substituted into the formula. Based on the orthogonal experimental data, the preset formula for the penetration retention rate model, and the weights corresponding to each environmental parameter, a multiple regression analysis is performed. This means only the weights corresponding to the base asphalt, SBS modifier, salt-resistant agent, and filler need to be analyzed. In some implementations, the determined weights serve as quantitative coefficients for the influence of each environmental factor on the deterioration of asphalt materials. Through the formula coefficients, the differential quantification of the influence of different environmental factors on the penetration retention rate R is achieved. For example, chloride concentration has the highest weight; its negative impact on performance, after being amplified by the weight, accurately reflects the dominant role of salt corrosion in actual working conditions, solving the prediction bias problem caused by the neglect of the primary and secondary factors in traditional single-factor models. Fine-tuning can be: 1. Make a weighted adjustment of ±0.05 based on the specific environmental characteristics of the coastal area. The adjustment should be based on environmental monitoring data of the area over the past 3 years, such as the average chloride concentration determined by ion chromatography and the number of freeze-thaw cycles recorded by the meteorological station. 2. Tidal Zone / Splash Zone: The chloride concentration is significantly higher than in normal areas, which can... Increased to 0.40, while simultaneously decreasing the weighting of humidity or UV intensity (e.g.) (Decreased to 0.10). 3. Northern freeze-thaw zones: An average of ≥60 freeze-thaw cycles per year can... The weighting for chloride concentration has been adjusted upwards to 0.20 and downwards to 0.30. 4. Southern regions with high temperature and humidity: The synergistic effect of temperature and humidity is significant, which can... Increased to 0.25 Keep it at 0.15. Lowered to 0.30.

[0048] The model can be fine-tuned and verified using core samples from the field to ensure that the prediction error remains ≤3.2%, thus guaranteeing its adaptability to different coastal conditions.

[0049] S230. Based on the base asphalt, SBS modifier, salt-resistant agent, filler, various environmental parameters and their corresponding weights, a penetration retention rate model is constructed.

[0050] Optionally, all the determined weights are substituted into the formula of the penetration retention rate model above to finally construct the penetration retention rate model.

[0051] S240. Based on the penetration retention rate model and the cost model, construct the fitness model.

[0052] Optionally, S240 includes S2401-S2403: S2401. Based on the penetration retention rate model and the preset maximum retention rate, determine the performance normalization value, and determine the first product of the performance normalization value and the first preset weight.

[0053] Optionally, based on the penetration retention rate model and preset maximum retention rate (e.g., 95%), determine the performance normalization value. And determine the performance normalization value and First preset weight (e.g., 0.7, prioritizing performance) first product .

[0054] S2402. Based on the cost model and the highest cost, determine the normalized cost value, and determine the second product of the normalized cost value and the second preset weight.

[0055] Optionally, according to the cost model and highest cost (That is, the largest result that can be calculated by selecting the corresponding percentage within the constraints of various preset percentage ranges) Determine the normalized cost value. And determine the normalized cost value. With the second preset weight The second product .

[0056] S2403. Construct a fitness model based on the sum of the first product and the second product.

[0057] Specifically, the fitness model is as follows:

[0058] in, For fitness, subsequent iterations use max For the goal.

[0059] In one implementation, step S300 includes steps S310-S340: S310. Based on the quantization range and each preset proportion range, determine several sets of simulation data corresponding to the number of individuals in the population.

[0060] Optionally, similar to the complete experimental data, the corresponding environmental parameter values, base asphalt, SBS modifier, salt-resistant agent, and filler proportions are selected within the quantification range and various preset proportion ranges. Then, several sets of simulation data are determined by combining them. That is, the determination is still limited by the preset proportion range. To ensure the dominant position of the base asphalt, Each set of simulation data includes the parameter values ​​of various environmental parameters (these parameter values ​​are fixed), the proportions of base asphalt, SBS modifier, salt-resistant agent, and filler (the proportions are varied). The difference from complete test data is that it does not include the measured penetration retention rate. The penetration retention rate can be obtained by substituting the simulation data into the penetration retention rate model, which is equivalent to a predicted penetration retention rate.

[0061] S320. Using a genetic algorithm, based on the simulation data and the fitness model, determine the fitness of each individual and the sum of the fitness of all individuals. Then, based on the fitness and the sum of the fitness, determine the fitness percentage of each individual to form a roulette wheel probability distribution.

[0062] It should be noted that a set of simulated data is considered as an individual (i.e., corresponding to a specific set of a, b, c, d). The population size, i.e. the number of individuals, is 100, so there are 100 sets of simulated data. Experiments have verified that a population size of 100 can balance computational efficiency and solution diversity. If the size is too small, it is easy to get trapped in local optima, while if it is too large, it will increase the computation time.

[0063] Optionally, a genetic algorithm can be used to calculate fitness based on both the simulated data and the fitness model, i.e., by substituting the simulated data into the fitness model. This allows us to determine the fitness of each individual. and all fitness Total fitness Then, based on fitness and the sum of fitness respectively. The ratio is used to determine the fitness percentage of each individual. Forming a roulette wheel probability distribution, That is, the fitness of the i-th individual. That is, the fitness percentage of the i-th individual.

[0064] S330. Based on the random number and the probability distribution of the roulette wheel, iterate the population until the change in the largest fitness in a series of preset iterations is less than or equal to a preset threshold; wherein, in each iteration, retain the individuals whose fitness ranks in the top preset percentage according to size.

[0065] Optionally, in the genetic algorithm, 100 random numbers between 0 and 1 are generated. Traverse the probability distribution of the roulette wheel and find the one that satisfies The individual m (i.e., the ID of the selected individual, when the random number is...) Individual m is selected when it falls within the cumulative probability interval of individual m, and is then added to the offspring population. Here, j is the index of a random number. This refers to the probability of the k-th individual, where k is a cyclic index variable used to accumulate the probabilities from the 1st individual to the m / m-1th individual. In each iteration: 1. Retain individuals whose fitness ranks in the top 5% (e.g., the top percentage) of the current population, i.e., the "elite retention strategy," to avoid losing high-quality solutions due to random selection, ensuring algorithm convergence, and ultimately ensuring the offspring population still has 100 pairs of individuals; 2. Crossover operation: Perform single-point crossover on selected individuals, with a crossover probability set to 0.7, meaning 70% of pairings will undergo crossover, avoiding excessive crossover that could destroy high-quality genes; 3. Mutation operation: Randomly mutate a preset percentage (e.g., 5%) of individuals (adjusted by ±0.5% of the component percentage), ensuring a low mutation rate, maintaining diversity, and preventing the algorithm from getting stuck in random search.

[0066] In this embodiment of the application, to ensure that the optimal target proportion obtained by the optimization algorithm not only meets the core salt corrosion resistance performance index (penetration retention rate R), but also fully meets other key road performance requirements of road asphalt materials, performance-derived constraints are introduced: Based on the optimized asphalt formulation components (a, b, c, d), the following performance-derived constraints are introduced: 1. High-temperature stability: Asphalt mixtures prepared based on formulation components (a, b, c, d) are verified through rutting tests (e.g., by substituting relevant formulas). The dynamic stability (DS) must be ≥3000 cycles / mm to ensure that the asphalt material meets the high-temperature stability requirements and avoids deformation under high-temperature conditions. 2. Low-temperature crack resistance: Asphalt samples were prepared based on the formulation components (a, b, c, d) and analyzed to see if they met the requirements of JTGF40-2004 specification, so that the ductility at -10℃ is ≥25cm, and the asphalt material is prevented from cracking in the low-temperature marine environment; 3. Water stability: Based on the formulation components (a, b, c, d) to prepare asphalt mixtures, and in conjunction with salt resistance performance verification (e.g., by substituting into relevant formulas), the asphalt mixtures must meet the freeze-thaw splitting strength ratio (TSR) ≥ 85%.

[0067] S340. Determine the proportions of base asphalt, SBS modifier, salt-resistant agent, and filler in the simulation data corresponding to the individual with the highest fitness as the target proportions of base asphalt, SBS modifier, salt-resistant agent, and filler, respectively.

[0068] It should be noted that when the change in the maximum fitness is less than or equal to a preset threshold (e.g., 0.1%) during iterations up to a preset number of consecutive iterations (e.g., 10 times), the iteration ends. The proportions of base asphalt, SBS modifier, salt-resistant agent, and filler in the simulation data corresponding to the individual with the current maximum fitness (i.e., the proportion of base asphalt a, the proportion of SBS modifier b, the proportion of salt-resistant agent c, and the proportion of filler d in the individual with the maximum fitness) are determined as the final target proportions of base asphalt, SBS modifier, salt-resistant agent, and filler, respectively.

[0069] In one embodiment, step S400 includes steps S410-S440: S410. Mix the salt-resistant asphalt material to be prepared according to the target proportions of the base asphalt, SBS modifier, salt-resistant agent, and filler.

[0070] Optionally, after determining the target proportions of the base asphalt, SBS modifier, salt-resistant agent, and filler, the salt-resistant asphalt material to be prepared is mixed based on these target proportions, and then the salt-resistant asphalt material is processed and prepared.

[0071] S420. Determine the dynamic viscosity of the salt-resistant asphalt material at the target processing temperature based on the target proportions of SBS modifier, salt-resistant agent, and filler.

[0072] Optionally, the dynamic viscosity of the salt-resistant asphalt material at the target processing temperature (e.g., 135°C) is determined based on the target proportions of SBS modifier, salt-resistant agent, and filler, i.e., b, c, and d, respectively. The formula is based on data from a Brinell viscometer test:

[0073] Understandably, when the target processing temperature is outside 135°C, the parameters in the formula determined based on the Brinell viscometer test data will change.

[0074] S430. Based on the preset uniformity, determine the mixing rate and mixing time corresponding to the mixing of the salt-resistant asphalt material to be prepared.

[0075] Optionally, assuming the preset uniformity U of the material is ≥95%, the mixing rate and mixing time corresponding to the mixing of the salt-resistant asphalt material to be prepared are determined based on the following formula:

[0076] Among them, 30 sets of different stirring rates were used. Stirring time The empirical constants are obtained by fitting the uniformity test under the given conditions. stirring rate Unit (r / min), stirring time The unit is (min), therefore a preset uniformity should be required. When, substituting into the formula, we get ,like ,but For example, to allow for a safety margin, a stirring time can be set. The time limit is 35 minutes, subject to adjustment based on actual conditions.

[0077] S440. When the dynamic viscosity is within the preset viscosity range, the salt-resistant asphalt material to be prepared is prepared according to the target processing temperature, stirring rate and stirring time to obtain the final salt-resistant asphalt material. When the dynamic viscosity is outside the preset viscosity range, at least one of the target proportion of SBS modifier, the target proportion of filler and the target processing temperature is adjusted until the newly determined dynamic viscosity is within the preset viscosity range.

[0078] Optionally, the preset viscosity range is, for example, 1.5-3.0 Pa·s; when the calculated dynamic viscosity... Within the preset viscosity range, based on the target processing temperature (135°C) and stirring rate and mixing time =35min was used as the process parameter to prepare the salt-erosion resistant asphalt material to be prepared, and the final salt-erosion resistant asphalt material was obtained.

[0079] In addition, temperature gradient control can be implemented during the preparation process. For example, the temperature fluctuation during the preparation stage is ≤ ±2℃, and a PID temperature control system is used to achieve closed-loop control. A dual-shaft stirrer (blade diameter to container diameter ratio of 0.6-0.7) is used to ensure that there are no dead zones in the stirring.

[0080] When the dynamic viscosity is outside the preset viscosity range, it is necessary to adjust at least one of the following: the target proportion of SBS modifier (b), the target proportion of filler (d), and the target processing temperature (135°C), until the newly determined dynamic viscosity falls within the preset viscosity range. Subsequent processing is then based on these adjustments. For example, if the degree to which the dynamic viscosity exceeds the preset viscosity range (e.g., the difference from the midpoint of the preset viscosity range) is less than or equal to a threshold value, at least one of the target proportion (b) and the target proportion of filler (d) can be fine-tuned. If it exceeds the threshold value, the target processing temperature can be adjusted.

[0081] In one embodiment, the method for preparing salt-resistant asphalt material for coastal highways according to this application may further include steps S510-S540: S510. Detect the actual penetration retention rate, actual dynamic viscosity, and actual uniformity of the final salt-resistant asphalt material, and compare the actual penetration retention rate with the penetration retention rate threshold, the actual dynamic viscosity with the preset viscosity range, and the actual uniformity with the preset uniformity.

[0082] Optionally, after preparing the final salt-resistant asphalt material, actual measurements are performed to detect the actual penetration retention rate, actual dynamic viscosity, and actual uniformity of the final salt-resistant asphalt material. In some embodiments, in addition to directly using a single test result as the judgment basis, multiple tests can be performed, and the average value is calculated for each test. This average value is used as the actual penetration retention rate, actual dynamic viscosity, and actual uniformity. Then, the actual penetration retention rate is compared with a penetration retention rate threshold (e.g., 85%), the actual dynamic viscosity is compared with a preset viscosity range, and the actual uniformity is compared with a preset uniformity (e.g., 95%) to ensure the viscosity range suitable for construction and road performance.

[0083] S520. If the actual penetration retention rate is greater than or equal to the penetration retention rate threshold, the actual dynamic viscosity is within the preset viscosity range, and the actual uniformity is greater than or equal to the preset uniformity, the final salt corrosion resistant asphalt material is deemed to be of qualified quality.

[0084] Optionally, if the actual penetration retention rate is greater than or equal to the penetration retention rate threshold, the actual dynamic viscosity is within the preset viscosity range, and the actual uniformity is greater than or equal to the preset uniformity, then the final salt corrosion resistant asphalt material is determined to be of qualified quality.

[0085] S530. If the actual penetration retention rate is less than the penetration retention rate threshold or the actual dynamic viscosity is outside the preset viscosity range, adjust the target proportion of at least one of the SBS modifier and filler.

[0086] Optionally, if the actual penetration retention rate is less than the penetration retention rate threshold or the actual dynamic viscosity is outside the preset viscosity range, it indicates that the performance is substandard. In this case, the target proportion of at least one of the SBS modifier and filler can be adjusted, i.e., at least one of b and d can be adjusted. It is understood that after adjustment, the calculation will return to S510 until the conditions in S520 are met; otherwise, the cycle will continue indefinitely.

[0087] S540. If the actual uniformity is less than the preset uniformity, increase the stirring rate or stirring time.

[0088] Alternatively, if the actual uniformity is less than the preset uniformity, it indicates that the uniformity is not up to standard. In this case, the stirring rate can be increased. Or stirring time It should be noted that the degree of increase is adjusted based on actual conditions, such as stirring time. Increase stirring speed by 5-10 minutes. Increase the speed by 100-200 r / min. Similarly, after adjustment, it will return to the calculation in S510 until the condition in S520 is met; otherwise, it will loop indefinitely.

[0089] The method of this application embodiment: 1. It has achieved full-process quantitative management from environmental factor analysis and material composition optimization to preparation process control, effectively solving problems such as insufficient salt corrosion resistance and the disconnect between simulation and reality in existing technologies, and providing a systematic solution for the long-term service of asphalt pavement of coastal highways; 2. Technically: The multi-factor coupled predictive model for salt corrosion resistance comprehensively considers environmental factors such as chloride concentration, temperature, humidity, UV intensity, and freeze-thaw cycles, as well as the influence of material components such as base asphalt, SBS modifier, salt-resistant agent, and filler on the salt corrosion resistance of asphalt materials. Compared with traditional single-factor analysis models, it can more accurately simulate actual coastal environmental conditions and predict changes in material performance. Salt corrosion resistant asphalt materials developed based on this model have a penetration retention rate that is 5 percentage points higher than existing technologies, reaching over 85%, effectively enhancing the durability of asphalt materials in salt corrosion environments, significantly improving the salt corrosion resistance of asphalt pavements, and extending the service life of pavements. 3. Economically: The material composition optimization algorithm reduces costs while pursuing high performance. By optimizing the material composition, the amount of expensive modifiers and salt-resistant agents used is reduced while meeting the requirements for salt corrosion resistance, thus effectively controlling material costs. Compared with traditional salt-corrosion resistant asphalt materials, the cost of asphalt materials prepared by this method can be reduced by 10%-15%. In addition, due to the extended service life of the pavement, the frequency of road maintenance and reconstruction is reduced, lowering the total life cycle cost of the road, including expenses for material procurement, construction, and maintenance. It also reduces resource waste and improves resource utilization efficiency.

[0090] 3. In terms of social applications: Ensuring road safety and smooth traffic flow, the improved salt corrosion resistance effectively extends the service life of asphalt pavement on coastal expressways, reduces the number and time of road repairs caused by pavement damage, not only reduces the interference of road repairs on traffic, ensuring road safety and smooth traffic flow, improving transportation efficiency, reducing the time costs and energy consumption caused by vehicle congestion and delays, but also helps to improve public satisfaction and comfort when traveling.

[0091] Reference Figure 2 The diagram shows a structural block diagram of an apparatus for preparing salt-resistant asphalt material for coastal highways according to an embodiment of this application. The apparatus may include: The acquisition module is used to acquire environmental data of the coastal highway, as well as the prices of the base asphalt, SBS modifier, salt-resistant agent, and filler, respectively. The construction module is used to determine the cost model based on the preset proportion range and price of the base asphalt, SBS modifier, salt-resistant agent, and filler, and to construct the fitness model based on the cost model and environmental data. The determination module is used to determine the target proportions of base asphalt, SBS modifier, salt-resistant agent, and filler based on the fitness model and genetic algorithm. The preparation module is used to prepare salt-resistant asphalt materials according to the target proportions of base asphalt, SBS modifier, salt-resistant agent, and filler.

[0092] In one embodiment, the coastal highway salt-erosion resistant asphalt material preparation apparatus further includes a detection module, which is used for: The actual penetration retention rate, actual dynamic viscosity, and actual uniformity of the final salt-resistant asphalt material were tested. The actual penetration retention rate was compared with the penetration retention rate threshold, the actual dynamic viscosity was compared with the preset viscosity range, and the actual uniformity was compared with the preset uniformity. If the actual penetration retention rate is greater than or equal to the penetration retention rate threshold, the actual dynamic viscosity is within the preset viscosity range, and the actual uniformity is greater than or equal to the preset uniformity, the final salt corrosion resistant asphalt material is deemed to be of qualified quality. If the actual penetration retention rate is less than the penetration retention rate threshold or the actual dynamic viscosity is outside the preset viscosity range, adjust the target proportion of at least one of the SBS modifier and filler. If the actual uniformity is less than the preset uniformity, increase the stirring rate or stirring time.

[0093] The functions of each module in the device of this application embodiment can be found in the corresponding description in the above method, and will not be repeated here.

[0094] Reference Figure 3 The diagram illustrates a structural block diagram of an electronic device according to an embodiment of this application. The electronic device includes a memory 310 and a processor 320. The memory 310 stores instructions that can be executed on the processor 320. The processor 320 loads and executes these instructions to implement the method for preparing salt-resistant asphalt material for coastal highways described in the above embodiment. The number of memories 310 and processors 320 can be one or more.

[0095] In one embodiment, the electronic device further includes a communication interface 330 for communicating with external devices and exchanging data. If the memory 310, processor 320, and communication interface 330 are implemented independently, they can be interconnected via a bus to communicate with each other. This bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0096] Optionally, in a specific implementation, if the memory 310, processor 320 and communication interface 330 are integrated on a single chip, the memory 310, processor 320 and communication interface 330 can communicate with each other through an internal interface.

[0097] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method for preparing anti-salt corrosion asphalt material for coastal highways provided in the above embodiments.

[0098] This application also provides a chip, which includes a processor for calling and executing instructions stored in a memory, causing a communication device on which the chip is installed to perform the method provided in this application.

[0099] This application also provides a chip, including: an input interface, an output interface, a processor, and a memory. The input interface, output interface, processor, and memory are connected through an internal connection path. The processor is used to execute code in the memory. When the code is executed, the processor is used to execute the method provided in the application embodiment.

[0100] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors can be microprocessors or any conventional processor. It is worth noting that the processor can be a processor supporting the Advanced Reduced Instruction Set Computing (RISC) machine (ARM) architecture.

[0101] Further, optionally, the aforementioned memory may include read-only memory and random access memory, and may also include non-volatile random access memory. The memory may be volatile or non-volatile, or may include both. Non-volatile memory may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may include random access memory (RAM), which serves as an external cache. Many forms of RAM are available by way of example, but not limitation. Examples include static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0102] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another.

[0103] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0104] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0105] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process. Furthermore, the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functionality involved.

[0106] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus or device (such as a computer-based system, a processor-included system or other system that can fetch and execute instructions from, an instruction execution system, apparatus or device).

[0107] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. All or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware, the program being stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiments.

[0108] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. This storage medium can be a read-only memory, a disk, or an optical disk, etc.

[0109] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in this application, and these should all be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for preparing salt-erosion resistant asphalt material for coastal highways, characterized in that, include: Obtain environmental data for the coastal highway, as well as the prices of base asphalt, SBS modifier, salt-resistant agent, and filler, respectively; Based on the preset proportion ranges and prices of the base asphalt, SBS modifier, salt-resistant agent, and filler, a cost model is determined, and an fitness model is constructed based on the cost model and the environmental data. Based on the fitness model and genetic algorithm, the target proportions of base asphalt, SBS modifier, salt-resistant agent, and filler are determined respectively. Salt-resistant asphalt materials are prepared according to the target proportions of base asphalt, SBS modifier, salt-resistant agent, and filler.

2. The method for preparing salt-resistant asphalt material for coastal highways according to claim 1, characterized in that: The step of constructing the fitness model based on the cost model and the environmental data includes: Based on the environmental data, the quantitative range corresponding to each environmental parameter is determined; the environmental parameters include chloride concentration, temperature, humidity, ultraviolet intensity, and number of freeze-thaw cycles; Based on the quantification range and the preset proportion range, the weights of the base asphalt, SBS modifier, salt-resistant agent, filler, and each of the environmental parameters are determined respectively. A penetration retention rate model is constructed based on the base asphalt, SBS modifier, salt-resistant agent, filler, various environmental parameters and their corresponding weights. Based on the penetration retention rate model and the cost model, a fitness model is constructed.

3. The method for preparing salt-resistant asphalt material for coastal highways according to claim 2, characterized in that: The step of determining the weights of the base asphalt, SBS modifier, salt-resistant agent, filler, and each of the environmental parameters according to the quantification range and the preset proportion range includes: Within the preset proportion range corresponding to the base asphalt, SBS modifier, salt-resistant agent, and filler, several proportions are determined respectively, and the proportions are combined to obtain several sets of first test data; Within the quantization range corresponding to each environmental parameter, several parameter values ​​corresponding to each environmental parameter are determined, and the parameter values ​​are combined to obtain several sets of second experimental data. Under the conditions of the first test data and the second test data, the corresponding needle penetration retention rate is determined, and orthogonal test data is determined based on the first test data, the second test data and the needle penetration retention rate. Multiple regression analysis is performed based on the orthogonal experimental data and the formula of the preset penetration retention rate model to determine the weights of the base asphalt, SBS modifier, salt-resistant agent, filler, and each of the environmental parameters. Alternatively, the weights of each of the environmental parameters are determined by the analytic hierarchy process (AHP), and multiple regression analysis is performed based on the orthogonal experimental data, the formula of the preset penetration retention rate model, and the weights of each of the environmental parameters to determine the weights of the base asphalt, SBS modifier, salt-resistant agent, and filler.

4. The method for preparing salt-erosion resistant asphalt material for coastal highways according to claim 2, characterized in that: The step of constructing the fitness model based on the penetration retention rate model and the cost model includes: Based on the penetration retention rate model and the preset maximum retention rate, a performance normalization value is determined, and a first product of the performance normalization value and the first preset weight is determined. Based on the cost model and the maximum cost, a normalized cost value is determined, and a second product of the normalized cost value and the second preset weight is determined. A fitness model is constructed based on the sum of the first product and the second product.

5. The method for preparing salt-resistant asphalt material for coastal highways according to any one of claims 2-4, characterized in that: The determination of the target proportions of base asphalt, SBS modifier, salt-resistant agent, and filler based on the fitness model and genetic algorithm includes: Based on the quantization range and each of the preset proportion ranges, several sets of simulation data corresponding to the number of individuals in the population are determined. Using a genetic algorithm, the fitness of each individual and the sum of fitness values ​​are determined based on the simulated data and the fitness model, respectively. Then, based on the fitness values ​​and the sum of fitness values, the fitness percentage of each individual is determined to form a roulette wheel probability distribution. Based on the random number and the probability distribution of the roulette wheel, the population is iterated until the change in the maximum fitness in a preset number of consecutive iterations is less than or equal to a preset threshold; wherein, in each iteration, individuals whose fitness ranks in the top preset percentage are retained. The proportions of base asphalt, SBS modifier, salt-resistant agent, and filler in the simulation data corresponding to the individual with the highest fitness are determined as the target proportions of base asphalt, SBS modifier, salt-resistant agent, and filler, respectively.

6. The method for preparing salt-resistant asphalt material for coastal highways according to any one of claims 2-4, characterized in that: The preparation of salt-resistant asphalt materials based on the target proportions of base asphalt, SBS modifier, salt-resistant agent, and filler includes: According to the target proportions of the base asphalt, SBS modifier, salt-resistant agent, and filler, the salt-resistant asphalt material to be prepared is mixed. Based on the target proportions of SBS modifier, salt-resistant agent, and filler, the dynamic viscosity of the salt-resistant asphalt material at the target processing temperature is determined. Based on the preset uniformity, determine the stirring rate and stirring time corresponding to the mixing of the salt corrosion resistant asphalt material to be prepared; When the dynamic viscosity is within the preset viscosity range, the salt-resistant asphalt material to be prepared is prepared according to the target processing temperature, the stirring rate and the stirring time to obtain the final salt-resistant asphalt material. When the dynamic viscosity is outside the preset viscosity range, at least one of the target proportion of SBS modifier, the target proportion of filler and the target processing temperature is adjusted until the newly determined dynamic viscosity is within the preset viscosity range.

7. The method for preparing salt-resistant asphalt material for coastal highways according to claim 6, characterized in that: The method further includes: The actual penetration retention rate, actual dynamic viscosity, and actual uniformity of the final salt-resistant asphalt material are detected, and the actual penetration retention rate is compared with the penetration retention rate threshold, the actual dynamic viscosity is compared with a preset viscosity range, and the actual uniformity is compared with a preset uniformity. If the actual penetration retention rate is greater than or equal to the penetration retention rate threshold, the actual dynamic viscosity is within the preset viscosity range, and the actual uniformity is greater than or equal to the preset uniformity, the final salt corrosion resistant asphalt material is determined to be of qualified quality. If the actual penetration retention rate is less than the penetration retention rate threshold or the actual dynamic viscosity is outside the preset viscosity range, adjust the target proportion of at least one of the SBS modifier and filler. If the actual uniformity is less than the preset uniformity, increase the stirring rate or stirring time.

8. A device for preparing salt-resistant asphalt material for coastal highways, characterized in that, include: The acquisition module is used to acquire environmental data of the coastal highway, as well as the prices of the base asphalt, SBS modifier, salt-resistant agent, and filler, respectively. The construction module is used to determine the cost model based on the preset proportion range and price of the base asphalt, SBS modifier, salt-resistant agent, and filler, and to construct the fitness model based on the cost model and the environmental data. The determination module is used to determine the target proportions of base asphalt, SBS modifier, salt-resistant agent, and filler, respectively, based on the fitness model and the genetic algorithm. The preparation module is used to prepare salt-resistant asphalt materials according to the target proportions of base asphalt, SBS modifier, salt-resistant agent, and filler.

9. An electronic device, characterized in that, include: A processor and a memory, wherein instructions are stored in the memory and loaded and executed by the processor to implement the method as claimed in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program therein, which, when executed, implements the method as described in any one of claims 1-7.

Images