Road performance index optimization method and system for low temperature modified asphalt

Abstract

The present invention discloses a road index optimization method and system for low-temperature modified asphalt, which relates to the technical field of big data analysis, including: obtaining an optimization training database; retrieving an optimization training data set corresponding to the current asphalt state; determining the road index requirements of asphalt; screening out optimization training data from the optimization training data set corresponding to the current asphalt state according to the road index requirements of the current asphalt; calculating and obtaining asphalt optimization data according to the optimization training data; optimizing asphalt according to the asphalt optimization data; updating the optimization training data under the current asphalt state; calculating and obtaining asphalt optimization data according to the updated optimization training data, and obtaining updated asphalt optimization data. The advantages of the present invention are: it can effectively ensure the quality of asphalt optimization, improve the asphalt optimization performance, and comprehensively improve the quality and service life of asphalt pavement.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis, and in particular to a method and system for optimizing road performance indicators of low-temperature modified asphalt. Background Art

[0002] Asphalt is a dark brown complex mixture of hydrocarbons of different molecular weights and their non-metallic derivatives. It is a kind of high-viscosity organic liquid. It is in liquid state, black on the surface, and soluble in carbon disulfide. Asphalt can be divided into coal tar asphalt, petroleum asphalt and natural asphalt. Among them, coal tar asphalt is a by-product of coking, petroleum asphalt is the residue after crude oil distillation, and natural asphalt is stored underground, some of which form mineral layers or accumulate on the surface of the earth's crust.

[0003] Asphalt is a common material for paving roads. The road use index of asphalt is an important data to measure the performance and use effect of asphalt pavement, covering multiple aspects such as bearing capacity, flatness, temperature stability, anti-skid ability, water permeability and noise. These indicators together constitute a comprehensive system for evaluating the performance and use effect of asphalt pavement. In order to improve the route index of asphalt, it is usually necessary to start from optimizing the construction process, strengthening maintenance management, adopting advanced technology and improving the flatness of asphalt concrete pavement, so as to improve the bearing capacity, flatness, temperature stability, anti-skid ability and other indicators of asphalt pavement, so as to ensure the quality and service life of the road. In the existing technology, the determination of asphalt optimization means is usually determined manually based on experience. Once the optimization means is determined, it will not be updated and learned according to the actual state. In the actual asphalt optimization process, it is often impossible to achieve the ideal asphalt optimization effect, resulting in a waste of resources. Summary of the invention

[0004] In order to solve the above-mentioned technical problems, a method and system for optimizing road indicators of low-temperature modified asphalt are provided. This technical solution solves the problem that the above-mentioned asphalt optimization means are usually determined manually based on experience. Once the optimization means are determined, they will not be updated and learned according to the actual status. In the actual asphalt optimization process, the ideal asphalt optimization effect cannot be achieved, resulting in a waste of resources.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A method for optimizing road performance indicators of low-temperature modified asphalt, comprising:

[0007] Obtaining an optimized training database;

[0008] Obtain the current asphalt state, and retrieve the optimized training data set corresponding to the current asphalt state from the optimized training database according to the current asphalt state;

[0009] Obtain environmental data of asphalt application sections, and determine the road use index requirements of asphalt based on the environmental data of asphalt application sections;

[0010] According to the current road use index requirements of asphalt, the optimized training data is selected from the optimized training data set corresponding to the current asphalt state;

[0011] Calculate and obtain asphalt optimization data based on the optimization training data;

[0012] Optimize asphalt according to asphalt optimization data;

[0013] Obtain asphalt optimization data to determine asphalt road performance indicators after asphalt optimization, and update the optimization training data under the current asphalt state through the optimization training model;

[0014] Calculate and obtain asphalt optimization data according to the updated optimization training data, and obtain updated asphalt optimization data;

[0015] When performing new asphalt optimization, the updated asphalt optimization data is used.

[0016] Preferably, the step of obtaining environmental data of the asphalt application section and determining the road use index requirement of asphalt in combination with the environmental data of the asphalt application section specifically includes:

[0017] Based on the pavement maintenance database, determining at least one known asphalt pavement working environment closest to the environmental data of the asphalt application section as a sample working environment;

[0018] The index attenuation rate of asphalt pavement under each sample working environment is retrieved from the pavement maintenance database;

[0019] The average value of the index attenuation rate of the asphalt pavement under all sample working environments is taken as the standard index attenuation rate of the asphalt application section;

[0020] Based on the design life of the asphalt pavement, the lower limit of the asphalt pavement index, and the standard index attenuation rate of the asphalt application section, the road use index requirements of asphalt are determined;

[0021] The road use index requirements of the asphalt are: In the formula, is the i-th road use index requirement of asphalt, is the lower limit of the i-th road use index of asphalt, is the standard index attenuation rate of the i-th road use index of asphalt, is the design life of the asphalt pavement. Preferably, the step of selecting the optimized training data from the optimized training data set corresponding to the current asphalt state according to the current asphalt road use index requirements specifically includes:

[0022] A data training index is set, recorded as n; all elements whose road use indexes are greater than the road use index requirements of the current asphalt are selected from the optimized training data set, recorded as target training data;

[0023] Determine whether the total number of target training data is greater than n. If so, calculate the index optimization value of the target training data based on the road use index of asphalt optimized based on the target training data and the road use index requirement of asphalt, and select the target training data whose index optimization value is ranked in the top n places in descending order as the optimized training data. If not, use all the target training data as the optimized training data.

[0024] Preferably, the calculation formula of the index optimization value is: In the formula, F is the optimized value of the index, is the optimization weight of the i-th road use index, is the i-th road performance index of the optimized asphalt, and m is the total number of road performance indexes of the asphalt. Preferably, the step of calculating and obtaining the asphalt optimization data according to the optimized training data specifically includes:

[0025] Calculate the average of all optimized training data as the asphalt optimized data.

[0026] Preferably, the optimization training model specifically includes:

[0027] Asphalt road use index after asphalt optimization based on asphalt optimization data, and calculate the index optimization value of the asphalt optimization data;

[0028] Determine the optimization consumption of all optimization training data and asphalt optimization data;

[0029] Determine data update indicators for all optimized training data and asphalt optimization data based on indicator optimization values ​​and optimization consumption of all optimized training data and asphalt optimization data;

[0030] Determine whether the difference between the data update index of this asphalt optimization data and the data update index of the last asphalt optimization data is greater than the update threshold. If so, the optimization training data is updated based on the data update index of all optimization training data and asphalt optimization data. If not, the optimization training data is not updated.

[0031] Preferably, the calculation formula of the data update index is: In the formula, Update the data index for the jth optimized training data, Optimize the indicator value for the jth optimized training data, is the optimization consumption of the jth optimization training data, Data update indicators for asphalt optimization data, Optimized values ​​for asphalt optimization data, Optimized consumption of data for asphalt optimization, To optimize the total number of training data.

[0032] Preferably, the updating of the optimized training data based on the data updating index of all the optimized training data and the asphalt optimized data specifically includes:

[0033] Traverse and determine whether the data update index of each optimized training data is less than the asphalt optimized data. If so, the optimized training data is eliminated; if not, the optimized training data is retained;

[0034] Determine whether the number of retained optimized training data plus asphalt optimized data is greater than n. If so, eliminate the data with the smallest index optimization value in the optimized training data and asphalt optimized data to obtain updated optimized training data. If not, use the retained optimized training data and asphalt optimized data as updated optimized training data.

[0035] Furthermore, a road performance index optimization system for low-temperature modified asphalt is proposed, which is used to implement the road performance index optimization method for low-temperature modified asphalt as described above, and includes: a data storage module, the data storage module is used to store an optimization training database;

[0036] An environmental analysis module, which is used to obtain environmental data of asphalt application sections and determine the road use index requirements of asphalt based on the environmental data of asphalt application sections;

[0037] A training data acquisition module, the training data acquisition module is electrically connected to the data storage module and the environment analysis module, the training data acquisition module is used to obtain the current asphalt state, retrieve the optimized training data set corresponding to the current asphalt state from the optimized training database according to the current asphalt state, and filter out the optimized training data from the optimized training data set corresponding to the current asphalt state according to the road use index requirements of the current asphalt;

[0038] An optimization analysis module, the optimization analysis module is electrically connected to the training data acquisition module, and the optimization analysis module is used to calculate and acquire asphalt optimization data according to the optimization training data;

[0039] A real-time optimization data acquisition module, wherein the real-time optimization data acquisition module is used to optimize asphalt according to the asphalt optimization data and obtain asphalt road use indicators after the asphalt optimization data is used to optimize the asphalt;

[0040] A data update module, which is electrically connected to the training data acquisition module, the real-time optimization data acquisition module and the optimization analysis module. The data update module is used to update the optimization training data under the current asphalt state through the optimization training model, and feed back the updated optimization training data to the optimization analysis module.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] The present invention proposes a road index optimization scheme for low-temperature modified asphalt. According to the performance index obtained by real-time optimization processing, the feedback value is calculated by a feedback training model and compared with the optimization training data. The optimization training data is updated according to the comparison results, and then the mapping model between the optimization performance and the optimization data is calculated using the updated data. Through learning, a mapping model in a more optimized state is obtained, and a more optimized asphalt optimization process strategy is output. The calculation is gradually updated during the processing, and the asphalt optimization process data is gradually iterated and optimized according to the actual processing state. Using these data for asphalt optimization can effectively ensure the quality of asphalt optimization, improve the asphalt optimization performance, and comprehensively improve the quality and service life of asphalt pavement. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a flow chart of the road performance index optimization method of low-temperature modified asphalt proposed by the present invention;

[0044] Figure 2 A flow chart of the method for determining the road use index requirements of asphalt proposed by the present invention;

[0045] Figure 3 A flow chart of the method for screening out optimized training data proposed by the present invention;

[0046] Figure 4 A flow chart of the method for optimizing the training model proposed by the present invention;

[0047] Figure 5 A flow chart of the method for optimizing training data updating proposed by the present invention;

[0048] Figure 6 This is a schematic diagram of the computer-readable storage medium structure proposed by the present invention. DETAILED DESCRIPTION

[0049] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0050] Reference Figure 1 As shown, a method for optimizing road performance indicators of low-temperature modified asphalt comprises:

[0051] Obtaining an optimization training database, the optimization training database consisting of all known historical asphalt optimization data and asphalt road use indicators after the historical asphalt optimization data;

[0052] Obtain the current asphalt state, and retrieve the optimized training data set corresponding to the current asphalt state from the optimized training database according to the current asphalt state;

[0053] Obtain environmental data of asphalt application sections, and determine the road use index requirements of asphalt based on the environmental data of asphalt application sections;

[0054] According to the current road use index requirements of asphalt, the optimized training data is selected from the optimized training data set corresponding to the current asphalt state;

[0055] Calculate and obtain asphalt optimization data based on the optimization training data;

[0056] Optimize asphalt according to asphalt optimization data;

[0057] Obtain asphalt optimization data to obtain asphalt road use indicators after asphalt optimization, and update the optimization training data under the current asphalt state through the optimization training model; calculate and obtain asphalt optimization data based on the updated optimization training data, and obtain updated asphalt optimization data;

[0058] When performing new asphalt optimization, the updated asphalt optimization data is used.

[0059] This solution calculates the feedback value through the feedback training model based on the optimization performance index obtained from the real-time optimization processing, and compares it with the data in the optimization training data. The optimization training data is updated according to the comparison results, and then the mapping model between the optimization performance and the optimization data is calculated based on the updated optimization training data. After the updated learning, the mapping model between the optimization performance and the optimization data in a more optimized state is obtained, and a more optimized asphalt optimization process strategy is output. By gradually updating the calculation during the processing, the asphalt optimization process data can be gradually iterated and optimized according to the actual processing status. Using this data for asphalt optimization can effectively ensure the asphalt optimization quality and improve the asphalt optimization performance.

[0060] Reference Figure 2 As shown, the environmental data of the asphalt application section is obtained, and the road use index requirements of asphalt are determined based on the environmental data of the asphalt application section, including:

[0061] Based on the pavement maintenance database, determining at least one known asphalt pavement working environment closest to the environmental data of the asphalt application section as a sample working environment;

[0062] The index attenuation rate of asphalt pavement under each sample working environment is retrieved from the pavement maintenance database;

[0063] The average value of the index attenuation rate of the asphalt pavement under all sample working environments is taken as the standard index attenuation rate of the asphalt application section;

[0064] Based on the design life of the asphalt pavement, the lower limit of the asphalt pavement index, and the standard index attenuation rate of the asphalt application section, the road use index requirements of asphalt are determined;

[0065] The road use index requirements for asphalt are: In the formula, is the i-th road use index requirement of asphalt, is the lower limit of the i-th road use index of asphalt, is the standard index attenuation rate of the i-th road use index of asphalt, The design life of the asphalt pavement. In order to ensure the compatibility of the asphalt optimization scheme with the actual environment, local climate characteristics, traffic conditions, soil conditions and other factors must be fully considered in the design stage. For example, in hot and rainy areas, asphalt pavements need to have better resistance to high temperatures and water damage; and in sections with frequent heavy traffic, it is necessary to consider improving the bearing capacity and fatigue resistance of asphalt. This scheme combines actual environmental factors and selects several known asphalt pavement working environments that are close to asphalt application sections as sample working environments to evaluate the performance attenuation of asphalt pavements in actual applications. Combined with actual conditions, the asphalt optimization method is designed to effectively ensure the compatibility of asphalt optimization with the actual environment, and then effectively ensure the quality of asphalt optimization, thereby extending the service life of the asphalt pavement and ensuring the long-term safety and stability of the road.

[0066] Reference Figure 3 As shown, according to the current asphalt road use index requirements, the optimized training data set corresponding to the current asphalt state is screened to select the optimized training data, which specifically includes:

[0067] A data training index is set, recorded as n; all elements whose road use indexes are greater than the road use index requirements of the current asphalt are selected from the optimized training data set, recorded as target training data;

[0068] Determine whether the total number of target training data is greater than n. If so, calculate the index optimization value of the target training data based on the road use index of asphalt optimized based on the target training data and the road use index requirement of asphalt, and select the target training data whose index optimization value is ranked in the top n places in descending order as the optimized training data. If not, use all the target training data as the optimized training data.

[0069] The formula for calculating the indicator optimization value is: In the formula, F is the optimized value of the index, is the optimization weight of the i-th road use index, is the i-th road index of the optimized asphalt, and m is the total number of road indexes of asphalt. By selecting a number of optimized training data that meet the road index requirements from the optimized training data set corresponding to the current asphalt state, as the optimized training data in the initial state, the optimized training data in the initial state represents the known asphalt optimization means that can meet the requirements of asphalt road indexes. By conducting comprehensive learning and analysis on these asphalt optimization means, the asphalt optimization effect can be effectively guaranteed;

[0070] If there is no optimization training data in the existing optimization training data set that is greater than the current asphalt road use index requirement, it means that the currently known optimization methods cannot meet the actual application requirements of asphalt pavement. At this time, it is necessary to feedback data to the background management terminal to make optimization decisions for asphalt.

[0071] In some embodiments, obtaining the asphalt optimization data by calculation based on the optimized training data specifically includes: calculating the average value of all the optimized training data as the asphalt optimization data.

[0072] After screening and iteration, the data existing in the optimized training data is the optimized asphalt optimization data set under the current training progress. The average value of the optimized data in the optimized training data is taken as the asphalt optimization data output, which can effectively ensure that the output asphalt optimization data is the optimized data under the current training state, and effectively ensure the quality of asphalt optimization.

[0073] Reference Figure 4 As shown, the optimization training model specifically includes:

[0074] Asphalt road use index after asphalt optimization based on asphalt optimization data, and calculate the index optimization value of the asphalt optimization data;

[0075] Determine the optimization consumption of all optimization training data and asphalt optimization data;

[0076] Determine data update indicators for all optimized training data and asphalt optimization data based on indicator optimization values ​​and optimization consumption of all optimized training data and asphalt optimization data;

[0077] Determine whether the difference between the data update index of this asphalt optimization data and the data update index of the last asphalt optimization data is greater than the update threshold. If so, the optimization training data is updated based on the data update index of all optimization training data and asphalt optimization data. If not, the optimization training data is not updated. The update threshold is the training termination condition. In some embodiments, the update threshold is set to 1% of the last asphalt optimization data.

[0078] The calculation formula of the data update index is: In the formula, Update the data index for the jth optimized training data, Optimize the indicator value for the jth optimized training data, is the optimization consumption of the jth optimization training data, Data update indicators for asphalt optimization data, Optimized values ​​for asphalt optimization data, Optimized consumption of data for asphalt optimization, To optimize the total number of training data. In practical applications, the optimization strategy of asphalt road indicators needs to consider not only the performance of asphalt, but also the resource consumption corresponding to the optimization strategy. Based on this, this solution uses data update indicators to comprehensively evaluate the optimization strategy in terms of performance and consumption. In this way, a balance can be achieved in terms of optimization performance and resource consumption, and the maximum utilization of resources can be achieved.

[0079] Reference Figure 5 As shown, based on the data update indicators of all optimized training data and asphalt optimized data, the optimized training data update specifically includes:

[0080] Traverse and determine whether the data update index of each optimized training data is less than the asphalt optimized data. If so, the optimized training data is eliminated; if not, the optimized training data is retained;

[0081] Determine whether the number of retained optimized training data plus asphalt optimized data is greater than n. If so, eliminate the data with the smallest index optimization value in the optimized training data and asphalt optimized data to obtain updated optimized training data. If not, use the retained optimized training data and asphalt optimized data as updated optimized training data.

[0082] By updating and learning the optimization data through the actual asphalt optimization situation, the optimization effect of asphalt can be effectively improved in the actual asphalt optimization process, making the asphalt optimization strategy more in line with the actual environmental conditions. The asphalt optimization data design method using real-time training and learning can effectively reduce the dependence of asphalt optimization data design on the experience of staff. The asphalt optimization data design using an automated training system can automatically calculate the asphalt optimization data.

[0083] Further, based on the same inventive concept as the above-mentioned method for optimizing the road performance index of low-temperature modified asphalt, this solution proposes a road performance index optimization system for low-temperature modified asphalt, comprising:

[0084] A data storage module, the data storage module is used to store the optimization training database;

[0085] Environmental analysis module, which is used to obtain environmental data of asphalt application sections and determine the road use index requirements of asphalt based on the environmental data of asphalt application sections;

[0086] A training data acquisition module, the training data acquisition module is electrically connected to the data storage module and the environment analysis module, and the training data acquisition module is used to obtain the current asphalt state, retrieve the optimized training data set corresponding to the current asphalt state from the optimized training database according to the current asphalt state, and filter out the optimized training data from the optimized training data set corresponding to the current asphalt state according to the road use index requirements of the current asphalt;

[0087] An optimization analysis module, the optimization analysis module is electrically connected to the training data acquisition module, and the optimization analysis module is used to calculate and acquire asphalt optimization data according to the optimization training data;

[0088] A real-time optimization data acquisition module is used to optimize asphalt according to asphalt optimization data, and obtain asphalt optimization data to obtain asphalt road use indicators after asphalt optimization;

[0089] The data update module is electrically connected to the training data acquisition module, the real-time optimization data acquisition module and the optimization analysis module. The data update module is used to update the optimization training data under the current asphalt state through the optimization training model, and feed back the updated optimization training data to the optimization analysis module.

[0090] The process of using the above system is as follows:

[0091] Step 1: The environmental analysis module obtains environmental data of the asphalt application section, and determines the road use index requirements of asphalt based on the environmental data of the asphalt application section;

[0092] Step 2: The training data acquisition module acquires the current asphalt state, retrieves the optimized training data set corresponding to the current asphalt state from the optimized training database according to the current asphalt state, and selects the optimized training data from the optimized training data set corresponding to the current asphalt state according to the road use index requirements of the current asphalt;

[0093] Step 3: The optimization analysis module calculates and obtains asphalt optimization data based on the optimization training data;

[0094] Step 4: The real-time optimization data acquisition module optimizes asphalt according to the asphalt optimization data, and obtains the asphalt optimization data to calculate the asphalt road use index after the asphalt optimization;

[0095] Step 5: The data update module updates the optimization training data under the current asphalt state through the optimization training model, and feeds the updated optimization training data back to the optimization analysis module.

[0096] Figure 6 Schematic diagram of a computer-readable storage medium structure provided by an embodiment of the present application. Figure 6 As shown, a computer-readable storage medium 600 according to an embodiment of the present application is shown. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are executed by the processor, a road use index optimization method for low-temperature modified asphalt according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0097] In summary, the advantages of the present invention are: it can effectively ensure the optimized quality of asphalt, improve the optimized performance of asphalt, and comprehensively improve the quality and service life of asphalt pavement.

[0098] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for optimizing road performance indicators of low-temperature modified asphalt, characterized in that: include: Obtaining an optimized training database; Obtain the current asphalt state, and retrieve the optimized training data set corresponding to the current asphalt state from the optimized training database according to the current asphalt state; Obtain environmental data of asphalt application sections, and determine the road use index requirements of asphalt based on the environmental data of asphalt application sections; According to the current road use index requirements of asphalt, the optimized training data is selected from the optimized training data set corresponding to the current asphalt state; Calculate and obtain asphalt optimization data based on the optimization training data; Optimize asphalt according to asphalt optimization data; Obtain asphalt optimization data to determine asphalt road performance indicators after asphalt optimization, and update the optimization training data under the current asphalt state through the optimization training model; Calculate and obtain asphalt optimization data according to the updated optimization training data, and obtain updated asphalt optimization data; When performing new asphalt optimization, use updated asphalt optimization data; The optimization training model specifically includes: Asphalt road use index after asphalt optimization based on asphalt optimization data, and calculate the index optimization value of the asphalt optimization data; Determine the optimization consumption of all optimization training data and asphalt optimization data; Determine data update indicators for all optimized training data and asphalt optimization data based on indicator optimization values ​​and optimization consumption of all optimized training data and asphalt optimization data; Determine whether the difference between the data update index of the current asphalt optimization data and the data update index of the previous asphalt optimization data is greater than the update threshold. If so, update the optimization training data based on the data update index of all the optimization training data and the asphalt optimization data. If not, do not update the optimization training data. The calculation formula of the data update index is: In the formula, Update the data index for the jth optimized training data, Optimize the indicator value for the jth optimized training data, is the optimization consumption of the jth optimization training data, Data update indicators for asphalt optimization data, Optimized values ​​for asphalt optimization data, Optimized consumption of data for asphalt optimization, To optimize the total number of training data; The updating of the optimized training data based on the data updating indexes of all the optimized training data and the asphalt optimized data specifically includes: traversing and determining whether the data updating index of each optimized training data is less than the data updating index of the asphalt optimized data, if so, removing the optimized training data, if not, retaining the optimized training data; Determine whether the number of the retained optimized training data plus the asphalt optimized data is greater than n. If so, remove the data with the smallest index optimization value in the optimized training data and the asphalt optimized data to obtain the updated optimized training data. If not, use the retained optimized training data and the asphalt optimized data as the updated optimized training data. The step of selecting the optimized training data from the optimized training data set corresponding to the current asphalt state according to the current asphalt road use index requirement specifically includes: Set a data training index, denoted as n; Filter out all elements whose road use indexes are greater than the road use index requirements of the current asphalt from the optimized training data set, and record them as target training data; Determine whether the total number of target training data is greater than n. If so, calculate the index optimization value of the target training data based on the road use index of asphalt optimized by the target training data and the road use index requirement of asphalt, and select the target training data whose index optimization value is ranked in the top n positions in descending order as the optimized training data. If not, use all the target training data as the optimized training data; The calculation formula of the optimized value of the indicator is: In the formula, F is the optimized value of the index, is the optimization weight of the i-th road use index, is the i-th road use index of the optimized asphalt, and m is the total number of road use indexes of asphalt.

2. The method for optimizing the road performance index of low-temperature modified asphalt according to claim 1, characterized in that: The step of obtaining environmental data of the asphalt application section and determining the road use index requirement of asphalt in combination with the environmental data of the asphalt application section specifically includes: determining, based on a pavement maintenance database, at least one known asphalt pavement working environment closest to the environmental data of the asphalt application section as a sample working environment; The index attenuation rate of asphalt pavement under each sample working environment is retrieved from the pavement maintenance database; The average value of the index attenuation rate of the asphalt pavement under all sample working environments is taken as the standard index attenuation rate of the asphalt application section; Based on the design life of the asphalt pavement, the lower limit of the asphalt pavement index, and the standard index attenuation rate of the asphalt application section, the road use index requirements of asphalt are determined; The road use index requirements of the asphalt are: In the formula, is the i-th road use index requirement of asphalt, is the lower limit of the i-th road use index of asphalt, is the standard index attenuation rate of the i-th road use index of asphalt, Design life of asphalt pavement.

3. The method for optimizing road performance of low-temperature modified asphalt according to claim 2, characterized in that: The calculation to obtain asphalt optimization data according to the optimized training data specifically includes: Calculate the average of all optimized training data as the asphalt optimized data.

4. A road performance index optimization system for low-temperature modified asphalt, characterized in that: A method for optimizing the road performance of low-temperature modified asphalt according to any one of claims 1 to 3, comprising: A data storage module, wherein the data storage module is used to store an optimization training database; An environmental analysis module, which is used to obtain environmental data of asphalt application sections and determine the road use index requirements of asphalt based on the environmental data of asphalt application sections; A training data acquisition module, the training data acquisition module is electrically connected to the data storage module and the environmental analysis module, the training data acquisition module is used to acquire the current asphalt state, retrieve the optimized training data set corresponding to the current asphalt state from the optimized training database according to the current asphalt state, and filter out the optimized training data from the optimized training data set corresponding to the current asphalt state according to the road use index requirements of the current asphalt; an optimization analysis module, the optimization analysis module is electrically connected to the training data acquisition module, the optimization analysis module is used to calculate and acquire asphalt optimization data according to the optimized training data; A real-time optimization data acquisition module, wherein the real-time optimization data acquisition module is used to optimize asphalt according to the asphalt optimization data and obtain asphalt road use indicators after the asphalt optimization data is used to optimize the asphalt; A data update module, which is electrically connected to the training data acquisition module, the real-time optimization data acquisition module and the optimization analysis module. The data update module is used to update the optimization training data under the current asphalt state through the optimization training model, and feed back the updated optimization training data to the optimization analysis module.

5. A computer-readable storage medium having computer-readable instructions stored thereon, characterized in that: When the computer-readable instructions are called, the road performance index optimization method of low-temperature modified asphalt as described in any one of claims 1-3 is executed.

Images