Big data analysis-based real-time prediction system and method for degree of road compaction

Abstract

The present invention relates to the technical field of road construction, in particular to a big data analysis-based real-time prediction system and method for degree of road compaction. The system comprises a compaction region interference intervention analysis module, the compaction region interference intervention analysis module acquiring a road surface grid region passed by a compaction apparatus during the advancing process of the apparatus, which is denoted by a first grid region, acquiring a related affected grid region around the first grid region, which is denoted by a second grid region, and then analyzing the degree-of-compaction intervening interference coefficients of the first grid region respectively corresponding to different road surface grid regions in the second grid region during the execution process of the compaction apparatus. The present invention not only considers more diversified factors in the prediction process, but also takes into account the pressing effect of the road surface region passed by the compaction apparatus on the peripheral regions in the advancing process of the apparatus, thus achieving real-time calibration of the degree of compaction corresponding to the peripheral regions around the road surface region passed by the apparatus, and ensuring the accuracy of prediction results on the degree of road compaction.

Description

A real-time prediction system and method for road compaction based on big data analysis Technical Field

[0001] The present invention relates to the technical field of road construction, and in particular to a real-time prediction system and method for road surface compaction based on big data analysis. Background Art

[0002] The rapid development of highway construction in my country is driving increasingly stringent requirements for asphalt pavement construction technology and maintenance. The increasing volume of traffic and speeds are also driving higher and higher demands on pavement quality. To extend highway life and enhance drivability, it's crucial to simultaneously improve both highway construction efficiency and pavement quality. Combining advanced construction technology with compaction quality control is crucial during asphalt pavement construction.

[0003] Traditional compaction testing primarily involves sand filling, knife rings, and nuclear density methods. Most are post-tests. While accurate, the small sample size makes it difficult to represent the overall pavement compaction quality, and damages the pavement structure, failing to meet on-site testing requirements. The existing Superpaye pavement compaction system automatically adjusts the roller's operating parameters to control the roller's output characteristics, thereby obtaining real-time pavement compaction. The existing YZC12 tandem intelligent roller monitors pavement compaction by adaptively adjusting its amplitude in real time based on the density of the compacted material during the compaction process. However, existing technologies have significant drawbacks. On the one hand, the parameters used to predict pavement compaction are relatively simple. On the other hand, they fail to consider the impact of the compaction equipment on the surrounding areas of the pavement it passes through during its travel, causing changes in the compaction of surrounding areas. Consequently, existing real-time pavement compaction prediction systems based on big data analysis exhibit significant deviations in their predictions.

[0004] Summary of the Invention

[0005] The purpose of the present invention is to provide a real-time prediction system and method for road compaction based on big data analysis to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solution: a real-time prediction method for road surface compaction based on big data analysis, the method comprising the following steps:

[0007] S1. Obtaining the location of the road surface to be compacted, constructing a visual road surface model of the road surface to be compacted, rasterizing the constructed visual road surface model to obtain road surface grid areas of the same specifications, and numbering each road surface grid area;

[0008] S2. Obtaining characteristic information of the compacted pavement state of the road to be compacted before the compaction operation is performed; training various coefficient parameters in the road surface compaction degree prediction function model based on the characteristic information of the compacted pavement state during the compaction operation and the road surface compaction degree after the operation recorded in the historical data, to obtain a road surface compaction degree prediction function corresponding to the road surface to be compacted;

[0009] S3. While the compacting equipment is performing a compacting operation on the road surface to be compacted, the travel trajectory of the compacting equipment is obtained in real time, and the road surface grid area that the compacting equipment passes through each time is marked; in combination with the road surface compaction degree prediction function corresponding to the road surface to be compacted, the compaction degree corresponding to each road surface grid area in the visual road surface model of the road surface to be compacted is predicted in real time, and the corresponding compaction degree prediction value is bound to the corresponding road surface grid area;

[0010] S4. Obtaining a road surface grid area passed by the compaction equipment during its movement, which is recorded as a first grid area; obtaining associated affected grid areas surrounding the first grid area, which are recorded as second grid areas; and analyzing the compaction degree intervention interference coefficients of the first grid area on different road surface grid areas within the second grid area during the compaction equipment's execution;

[0011] S5. In combination with the compaction equipment obtained in S4, during the execution process, the first grid area corresponds to the different pavement grid areas in the second grid area, respectively, and the compaction intervention interference coefficients corresponding to the different pavement grid areas in the second grid area in the visual pavement model of the pavement to be compacted are obtained. The compaction intervention interference amounts corresponding to the different pavement grid areas in the second grid area in the visual pavement model of the pavement to be compacted are obtained, and the compaction degrees of each pavement grid area in the second grid area are updated according to the obtained compaction intervention interference amounts, so as to obtain a real-time distribution map of the compaction degree of the visual pavement model of the pavement to be compacted, so as to assist the administrator in making decisions on the compaction plan in the area to which the pavement to be compacted belongs.

[0012] Furthermore, the visualized road surface model of the road surface to be compacted in S1 includes a corresponding area of ​​the road surface to be compacted, and the visualized road surface model of the road surface to be compacted and the corresponding area of ​​the road surface to be compacted are in a proportional scaling relationship;

[0013] In the process of rasterizing the constructed visual road surface model, the specifications of the grid are preset in the database, and the number of the i-th road surface grid area in the constructed visual road surface model is recorded as Ai;

[0014] The compacted road surface state characteristic information in S2 includes equipment characteristic information and road surface characteristic information.

[0015] The equipment characteristic information includes the number of compaction passes in each road surface grid area, the effective rolling time of the compaction equipment, and the compaction vibration frequency value;

[0016] The road surface characteristic information includes the asphalt paving thickness, initial paving temperature, and ambient temperature within each road surface grid area. Furthermore, the method for obtaining the road surface compaction degree prediction function corresponding to the road surface to be compacted in S2 includes the following steps:

[0017] S21. Constructing a first feature data pair corresponding to each pavement compaction item, denoted as ({B1, B2 / M, B3, B4, B5-B6}, Y), based on the compaction status feature information of each pavement compaction item during the compaction operation and the pavement compaction degree after the operation recorded in the historical data.

[0018] Among them, B1 represents the number of compaction passes of the corresponding pavement before the execution of the corresponding pavement compaction project; B2 represents the rolling time of the compaction equipment in the corresponding pavement area during the execution of the corresponding pavement compaction project; M represents the area of ​​the pavement area rolled by the compaction equipment during the execution of the corresponding pavement compaction project; B3 represents the compaction vibration frequency value of the compaction equipment during the execution of the corresponding pavement compaction project; B4 represents the average paving thickness of the asphalt in the pavement during the execution of the corresponding pavement compaction project; B5 represents the initial paving temperature when the corresponding pavement compaction project is executing the compaction operation of the corresponding pavement area; B6 represents the average ambient temperature when the corresponding pavement compaction project is executing the compaction operation of the corresponding pavement area; Y represents the average pavement compaction degree of the corresponding pavement area after the corresponding pavement compaction project is executing the compaction operation;

[0019] S22. Fit the obtained first characteristic data pair according to the multivariate linear regression equation y = c1·x1 + c2·x2 + c3·x3 + c4·x4 + c5·x5 + c6, where y represents the degree of compaction, x1 represents the number of compaction passes, x2 represents the ratio of rolling time to rolled road surface area, x3 represents the compaction vibration frequency of the compaction equipment, x4 represents the asphalt paving thickness, x5 represents the difference between the initial paving temperature and the ambient temperature, and c1, c2, c3, c4, c5, and c6 are compaction fitting coefficients;

[0020] The coefficients c1, c2, c3, c4, c5 and c6 in the fitting results are used as the training results of the corresponding coefficient parameters in the road surface compaction prediction function model to obtain the road surface compaction prediction function corresponding to the road surface to be compacted, which is recorded as F.

[0021] In the process of fitting the parameter pairs within multiple first feature data pairs using a multivariate linear regression equation, the present invention realizes the fitting process of each coefficient parameter within the corresponding multivariate linear regression equation. Different numbers of first feature data pairs or different parameter data within the corresponding first feature data pairs will lead to different coefficients in the final fitted multivariate linear regression equation. This method can effectively improve the accuracy and prediction precision of the pavement compaction prediction function F corresponding to the pavement to be compacted.

[0022] Furthermore, when predicting the compaction degree corresponding to each road surface grid area in the visualized road surface model of the road surface to be compacted in real time in S3, the equipment characteristic information and road surface characteristic information corresponding to each road surface grid area in the compacted road surface state characteristic information are collected, and a first characteristic data pair corresponding to each road surface grid area is constructed. The first characteristic data pair corresponding to each road surface grid area is respectively substituted into the road surface compaction degree prediction function F corresponding to the road surface to be compacted, and the compaction degree prediction value corresponding to each road surface grid area is obtained;

[0023] During the compaction operation of the compaction equipment on the road surface to be compacted, the movement trajectory of the compaction equipment is obtained in real time, and each time the compaction equipment marks the road surface grid area passed by the movement trajectory, each time the marking number corresponding to the road surface grid area increases, the first feature data pair corresponding to the corresponding road surface grid area needs to be updated once.

[0024] Furthermore, when obtaining the second grid area in S4, the second grid area is a grid area outside the outline of the first grid area and whose distance from different position points on the outline of the first grid area is less than or equal to the corresponding radiation radius of the corresponding position points; the radiation radius corresponding to different position points on the outline of the first grid area is different,

[0025] When obtaining the wave radiation radius corresponding to different position points on the first grid area contour, the wave radiation radius corresponding to a certain position point on the first grid area contour is recorded as R, and R is smaller than the width of the road surface to be compacted;

[0026] Assuming that the radiation radius is R1, if R1-β·e YS2-YS0 / e YS3-YS1 ∈U, then R1 is used as an alternative value of the wave and radiation radius R corresponding to the corresponding position point on the first grid area outline, and R is the minimum value among the corresponding alternative values ​​R1;

[0027] Among them, U represents the tolerance range of the radiation radius deviation preset in the database; YS2 represents the average compaction degree of each road surface grid area in the first grid area after the compaction equipment passes through; YS0 represents the average compaction degree of each road surface grid area in the first grid area before the compaction equipment passes through; YS1 represents the average compaction degree of all road surface grid areas outside the outline of the first grid area and whose distance from the corresponding position on the edge of the outline of the first grid area is less than or equal to R1; YS3 represents the compaction degree requirement reference value corresponding to the area to be compacted in the database, which is preset.

[0028] The present invention takes into account the squeezing effect of the first grid area on the second grid area when the compaction equipment passes through the first grid area, and at the same time realizes the screening of the affected radiation radius R, which can effectively lock the second grid area corresponding to the first grid area, and provides data support for the subsequent steps of analyzing the compaction intervention interference coefficient corresponding to the first grid area to different pavement grid areas in the second grid area during the execution of the compaction equipment.

[0029] Furthermore, the method for analyzing the compaction degree intervention interference coefficient corresponding to the first grid area and different road surface grid areas in the second grid area during the execution of the compaction equipment in S4 includes the following steps:

[0030] S41, obtaining the difference between the average value of the predicted compaction degree of each road surface grid area in the first grid area after the compaction equipment passes through and the average value of the predicted compaction degree of each road surface grid area in the second grid area before the compaction equipment passes through, and recording it as a first deviation;

[0031] S42: Recording the difference between the reference compaction requirement value corresponding to the area of ​​the road surface to be compacted in the database and the average of the predicted compaction values ​​corresponding to each road surface grid area within the second grid area before the compaction equipment passes as a second deviation; the reference compaction requirement value corresponding to the area of ​​the road surface to be compacted in the database is preset;

[0032] S43. Obtain the compaction degree intervention interference coefficients corresponding to the first grid area and different road surface grid areas in the second grid area during the compaction process. The compaction degree intervention interference coefficient corresponding to the first grid area and the kth road surface grid area in the second grid area is recorded as Gk. Gk = [β1·e YP2-YP0 +β2·e YP2-YP1k ]·(1-rk / Rk),

[0033] Wherein, β1 represents the first interference conversion coefficient; β2 represents the second interference conversion coefficient; both β1 and β2 are constants preset in the database;

[0034] YP0 represents the average compaction degree of each road surface grid area in the first grid area before the compaction equipment passes through; YP1k represents the compaction degree of the kth road surface grid area in the second grid area; YP2 represents the average compaction degree of each road surface grid area in the first grid area after the compaction equipment passes through;

[0035] rk represents the shortest distance between the kth road surface grid area in the second grid area and the first grid area;

[0036] Rk represents the maximum radiation radius corresponding to each intersection point with the contour edge of the first grid area in each line segment corresponding to the shortest distance from the kth road surface grid area to the contour edge of the first grid area in the second grid area.

[0037] Furthermore, when obtaining the compaction degree intervention interference amounts corresponding to different road surface grid areas in the second grid area of ​​the visualized road surface model of the road surface to be compacted in S5, the compaction degree intervention interference amount corresponding to the k-th road surface grid area in the second grid area of ​​the visualized road surface model of the road surface to be compacted is recorded as Hk, and the value of HK is equal to the product of the compaction degree corresponding to the k-th road surface grid area in the second grid area and the compaction degree intervention interference coefficient corresponding to the k-th road surface grid area in the second grid area;

[0038] When the compaction degree of each pavement grid area within the second grid area is updated according to the obtained compaction intervention interference amount in S5, the updated compaction degree result of the kth pavement grid area within the second grid area in the visualized pavement model of the pavement to be compacted is recorded as Dk, and Dk is equal to the difference between the compaction degree of the kth pavement grid area within the second grid area before the update and HK in the visualized pavement model of the pavement to be compacted.

[0039] A real-time road compaction prediction system based on big data analysis, comprising the following modules:

[0040] A model rasterization analysis module, which obtains the location of the road surface to be compacted, constructs a visual road surface model of the road surface to be compacted, rasterizes the constructed visual road surface model to obtain road surface grid areas of the same specifications, and numbers each road surface grid area;

[0041] a pavement compaction prediction module, which obtains characteristic information about the compacted pavement state of the pavement to be compacted before the compaction operation is performed; and trains various coefficient parameters in a pavement compaction prediction function model based on the characteristic information about the compacted pavement state of each pavement compaction item during the compaction operation and the pavement compaction degree after the operation recorded in historical data, thereby obtaining a pavement compaction prediction function corresponding to the pavement to be compacted;

[0042] A compaction trajectory marking module, which obtains the travel trajectory of the compaction equipment in real time during the compaction operation of the compaction equipment on the road surface to be compacted, and marks the road surface grid area passed by the compaction equipment each time; combines the road surface compaction degree prediction function corresponding to the road surface to be compacted, and predicts the compaction degree corresponding to each road surface grid area in the visual road surface model of the road surface to be compacted in real time, and binds the corresponding compaction degree prediction value to the corresponding road surface grid area;

[0043] A compaction area interference intervention analysis module, which obtains the road surface grid area passed by the compaction equipment during its movement, recorded as the first grid area; obtains the associated affected grid area surrounding the first grid area, recorded as the second grid area; and analyzes the compaction degree interference coefficient corresponding to the first grid area on different road surface grid areas within the second grid area during the execution of the compaction equipment;

[0044] A compaction degree update and auxiliary management module, in combination with the obtained compaction equipment execution process, the compaction degree intervention interference coefficient corresponding to the first grid area to different pavement grid areas in the second grid area is obtained, and the compaction degree intervention interference amount corresponding to the different pavement grid areas in the second grid area in the visual pavement model of the pavement to be compacted is obtained. The compaction degree of each pavement grid area in the second grid area is updated according to the obtained compaction degree intervention interference amount, and a real-time distribution map of the compaction degree of the visual pavement model of the pavement to be compacted is obtained to assist the administrator in making decisions on the compaction plan in the area to which the pavement to be compacted belongs.

[0045] Furthermore, the compaction area interference intervention analysis module includes a first grid area acquisition unit, a second grid area acquisition unit and an intervention interference analysis unit.

[0046] The first grid area acquisition unit acquires a road surface grid area passed by the compaction equipment during its movement, and records it as a first grid area;

[0047] The second grid area acquisition unit acquires the associated wave-affected grid area around the first grid area, which is recorded as the second grid area;

[0048] The intervention interference analysis unit analyzes the compaction degree intervention interference coefficients corresponding to different road surface grid areas in the second grid area and the first grid area during the execution of the compaction equipment.

[0049] Compared with the existing technology, the beneficial effect achieved by the present invention is: in the process of real-time prediction of road surface compaction, the present invention not only considers more diversified factors in the prediction process (equipment characteristic information and road surface characteristic information), but also takes into account the squeezing effect of the road surface area passed by the equipment on the surrounding area during the movement of the compaction equipment, thereby realizing real-time calibration of the corresponding compaction degree of the surrounding area of ​​the road surface area passed by the equipment, and ensuring the accuracy of the road surface compaction prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0051] FIG1 is a flow chart of a method for real-time prediction of road surface compaction based on big data analysis according to the present invention;

[0052] FIG2 is a schematic structural diagram of a road surface compaction real-time prediction system based on big data analysis according to the present invention. DETAILED DESCRIPTION

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0054] Referring to FIG1 , the present invention provides a technical solution: a real-time prediction method for road surface compaction based on big data analysis, the method comprising the following steps:

[0055] S1. Obtaining the location of the road surface to be compacted, constructing a visual road surface model of the road surface to be compacted, rasterizing the constructed visual road surface model to obtain road surface grid areas of the same specifications, and numbering each road surface grid area;

[0056] The visualized road surface model of the road surface to be compacted in S1 includes a corresponding area of ​​the road surface to be compacted, and the visualized road surface model of the road surface to be compacted and the corresponding area of ​​the road surface to be compacted are in a proportional scaling relationship;

[0057] In the process of rasterizing the constructed visual road surface model, the specifications of the grid are preset in the database, and the number of the i-th road surface grid area in the constructed visual road surface model is recorded as Ai;

[0058] S2. Obtaining characteristic information of the compacted pavement state of the road to be compacted before the compaction operation is performed; training various coefficient parameters in the road surface compaction degree prediction function model based on the characteristic information of the compacted pavement state during the compaction operation and the road surface compaction degree after the operation recorded in the historical data, to obtain a road surface compaction degree prediction function corresponding to the road surface to be compacted;

[0059] The compacted road surface state characteristic information in S2 includes equipment characteristic information and road surface characteristic information.

[0060] The equipment characteristic information includes the number of compaction passes in each road surface grid area, the effective rolling time of the compaction equipment, and the compaction vibration frequency value;

[0061] The road surface characteristic information includes the asphalt paving thickness, initial paving temperature and ambient temperature in each road surface grid area.

[0062] The method for obtaining the road surface compaction degree prediction function corresponding to the road surface to be compacted in S2 comprises the following steps:

[0063] S21. Constructing a first feature data pair corresponding to each pavement compaction item, denoted as ({B1, B2 / M, B3, B4, B5-B6}, Y), based on the compaction status feature information of each pavement compaction item during the compaction operation and the pavement compaction degree after the operation recorded in the historical data.

[0064] Among them, B1 represents the number of compaction passes of the corresponding pavement before the execution of the corresponding pavement compaction project; B2 represents the rolling time of the compaction equipment in the corresponding pavement area during the execution of the corresponding pavement compaction project; M represents the area of ​​the pavement area rolled by the compaction equipment during the execution of the corresponding pavement compaction project; B3 represents the compaction vibration frequency value of the compaction equipment during the execution of the corresponding pavement compaction project; B4 represents the average paving thickness of the asphalt in the pavement during the execution of the corresponding pavement compaction project; B5 represents the initial paving temperature when the corresponding pavement compaction project is executing the compaction operation of the corresponding pavement area; B6 represents the average ambient temperature when the corresponding pavement compaction project is executing the compaction operation of the corresponding pavement area; Y represents the average pavement compaction degree of the corresponding pavement area after the corresponding pavement compaction project is executing the compaction operation;

[0065] S22. Fit the obtained first characteristic data pair according to the multivariate linear regression equation y = c1·x1 + c2·x2 + c3·x3 + c4·x4 + c5·x5 + c6, where y represents the degree of compaction, x1 represents the number of compaction passes, x2 represents the ratio of rolling time to rolled road surface area, x3 represents the compaction vibration frequency of the compaction equipment, x4 represents the asphalt paving thickness, x5 represents the difference between the initial paving temperature and the ambient temperature, and c1, c2, c3, c4, c5, and c6 are compaction fitting coefficients;

[0066] The coefficients c1, c2, c3, c4, c5 and c6 in the fitting results are used as the training results of the corresponding coefficient parameters in the road surface compaction prediction function model to obtain the road surface compaction prediction function corresponding to the road surface to be compacted, which is recorded as F.

[0067] S3. While the compacting equipment is performing a compacting operation on the road surface to be compacted, the travel trajectory of the compacting equipment is obtained in real time, and the road surface grid area that the compacting equipment passes through each time is marked; in combination with the road surface compaction degree prediction function corresponding to the road surface to be compacted, the compaction degree corresponding to each road surface grid area in the visual road surface model of the road surface to be compacted is predicted in real time, and the corresponding compaction degree prediction value is bound to the corresponding road surface grid area;

[0068] When predicting the compaction degree corresponding to each road surface grid area in the visualized road surface model of the road surface to be compacted in real time in S3, the equipment characteristic information and road surface characteristic information corresponding to each road surface grid area in the compacted road surface state characteristic information are collected, and a first characteristic data pair corresponding to each road surface grid area is constructed. The first characteristic data pair corresponding to each road surface grid area is respectively substituted into the road surface compaction degree prediction function F corresponding to the road surface to be compacted to obtain the compaction degree prediction value corresponding to each road surface grid area;

[0069] During the compaction operation of the compaction equipment on the road surface to be compacted, the movement trajectory of the compaction equipment is obtained in real time, and each time the compaction equipment marks the road surface grid area passed by the movement trajectory, each time the marking number corresponding to the road surface grid area increases, the first feature data pair corresponding to the corresponding road surface grid area needs to be updated once.

[0070] S4. Obtaining a road surface grid area passed by the compaction equipment during its movement, which is recorded as a first grid area; obtaining associated affected grid areas surrounding the first grid area, which are recorded as second grid areas; and analyzing the compaction degree intervention interference coefficients of the first grid area on different road surface grid areas within the second grid area during the compaction equipment's execution;

[0071] When obtaining the second grid area in S4, the second grid area is a grid area outside the first grid area outline and whose distance from different position points on the first grid area outline is less than or equal to the corresponding wave and radiation radius of the corresponding position points; the wave and radiation radius corresponding to different position points on the first grid area outline is different,

[0072] When obtaining the wave radiation radius corresponding to different position points on the first grid area contour, the wave radiation radius corresponding to a certain position point on the first grid area contour is recorded as R, and R is smaller than the width of the road surface to be compacted;

[0073] Assuming that the radiation radius is R1, if R1-β·e YS2-YS0 / e YS3-YS1 ∈U, then R1 is used as an alternative value of the wave and radiation radius R corresponding to the corresponding position point on the first grid area outline, and R is the minimum value among the corresponding alternative values ​​R1;

[0074] Among them, U represents the tolerance range of the radiation radius deviation preset in the database; YS2 represents the average compaction degree of each road surface grid area in the first grid area after the compaction equipment passes through; YS0 represents the average compaction degree of each road surface grid area in the first grid area before the compaction equipment passes through; YS1 represents the average compaction degree of all road surface grid areas outside the outline of the first grid area and whose distance from the corresponding position on the edge of the outline of the first grid area is less than or equal to R1; YS3 represents the compaction degree requirement reference value corresponding to the area to be compacted in the database, which is preset.

[0075] In this embodiment, R1-β·e YS2-YS0 / e YS3-YS1 ∈U is a judgment condition, and the judgment condition for R1 is a two-way selection process. First, the size of R1 directly affects the value of YS1, and then affects β·e YS2-YS0 / e YS3-YS1 The value of R1-β·e YS2-YS0 / e YS3-YS1 The value of will affect the choice of R1.

[0076] The method for analyzing the compaction degree intervention interference coefficient corresponding to different road surface grid areas in the second grid area in the first grid area during the execution of the compaction equipment in S4 includes the following steps:

[0077] S41, obtaining the difference between the average value of the predicted compaction degree of each road surface grid area in the first grid area after the compaction equipment passes through and the average value of the predicted compaction degree of each road surface grid area in the second grid area before the compaction equipment passes through, and recording it as a first deviation;

[0078] S42: Recording the difference between the reference compaction requirement value corresponding to the area of ​​the road surface to be compacted in the database and the average of the predicted compaction values ​​corresponding to each road surface grid area within the second grid area before the compaction equipment passes as a second deviation; the reference compaction requirement value corresponding to the area of ​​the road surface to be compacted in the database is preset;

[0079] S43. Obtain the compaction degree intervention interference coefficients corresponding to the first grid area and different road surface grid areas in the second grid area during the compaction process. The compaction degree intervention interference coefficient corresponding to the first grid area and the kth road surface grid area in the second grid area is recorded as Gk. Gk = [β1·e YP2-YP0 +β2·e YP2-YP1k ]·(1-rk / Rk),

[0080] Wherein, β1 represents the first interference conversion coefficient; β2 represents the second interference conversion coefficient; both β1 and β2 are constants preset in the database;

[0081] YP0 represents the average compaction degree of each road surface grid area in the first grid area before the compaction equipment passes through it; YP1k represents the compaction degree of the kth road surface grid area in the second grid area; YP2 represents the average compaction degree of each road surface grid area in the first grid area after the compaction equipment passes through it;

[0082] rk represents the shortest distance between the kth road surface grid area in the second grid area and the first grid area;

[0083] Rk represents the maximum radiation radius corresponding to each intersection point with the contour edge of the first grid area in each line segment corresponding to the shortest distance from the kth road surface grid area to the contour edge of the first grid area in the second grid area.

[0084] S5. In combination with the compaction equipment obtained in S4, during the execution process, the first grid area corresponds to the different pavement grid areas in the second grid area, respectively, and the compaction intervention interference coefficients corresponding to the different pavement grid areas in the second grid area in the visual pavement model of the pavement to be compacted are obtained. The compaction intervention interference amounts corresponding to the different pavement grid areas in the second grid area in the visual pavement model of the pavement to be compacted are obtained, and the compaction degrees of each pavement grid area in the second grid area are updated according to the obtained compaction intervention interference amounts, so as to obtain a real-time distribution map of the compaction degree of the visual pavement model of the pavement to be compacted, so as to assist the administrator in making decisions on the compaction plan in the area to which the pavement to be compacted belongs.

[0085] In this embodiment, the real-time distribution diagram of the compaction degree of the visual pavement model of the pavement to be compacted will, in the process of assisting the administrator in making decisions on the compaction plan within the area to which the pavement to be compacted belongs, count the average value of the compaction degree corresponding to each pavement grid area in the visual pavement model of the pavement to be compacted, recorded as ξ, and construct a normal fluctuation range of the compaction degree, recorded as [ξ-Ψ, ξ+Ψ], where Ψ is the fluctuation deviation threshold preset in the database, and the pavement grid area with a compaction degree less than ξ-Ψ in the real-time distribution diagram of the compaction degree of the visual pavement model of the pavement to be compacted will be recorded as an under-pressure area, and the pavement grid area with a compaction degree less than ξ+Ψ in the real-time distribution diagram of the compaction degree of the visual pavement model of the pavement to be compacted will be recorded as an over-pressure area, thereby assisting the administrator in making decisions on the execution of subsequent compaction plans.

[0086] When obtaining the compaction degree intervention interference amounts corresponding to different road surface grid areas in the second grid area of ​​the visualized road surface model of the road surface to be compacted in S5, the compaction degree intervention interference amount corresponding to the k-th road surface grid area in the second grid area of ​​the visualized road surface model of the road surface to be compacted is recorded as Hk, and the value of HK is equal to the product of the compaction degree corresponding to the k-th road surface grid area in the second grid area and the compaction degree intervention interference coefficient corresponding to the k-th road surface grid area in the second grid area;

[0087] When the compaction degree of each pavement grid area within the second grid area is updated according to the obtained compaction intervention interference amount in S5, the updated compaction degree result of the kth pavement grid area within the second grid area in the visualized pavement model of the pavement to be compacted is recorded as Dk, and Dk is equal to the difference between the compaction degree of the kth pavement grid area within the second grid area before the update and HK in the visualized pavement model of the pavement to be compacted.

[0088] As shown in Figure 2, a real-time road compaction prediction system based on big data analysis includes the following modules:

[0089] A model rasterization analysis module, which obtains the location of the road surface to be compacted, constructs a visual road surface model of the road surface to be compacted, rasterizes the constructed visual road surface model to obtain road surface grid areas of the same specifications, and numbers each road surface grid area;

[0090] a pavement compaction prediction module, which obtains characteristic information about the compacted pavement state of the pavement to be compacted before the compaction operation is performed; and trains various coefficient parameters in a pavement compaction prediction function model based on the characteristic information about the compacted pavement state of each pavement compaction item during the compaction operation and the pavement compaction degree after the operation recorded in historical data, thereby obtaining a pavement compaction prediction function corresponding to the pavement to be compacted;

[0091] A compaction trajectory marking module, which obtains the travel trajectory of the compaction equipment in real time during the compaction operation of the compaction equipment on the road surface to be compacted, and marks the road surface grid area passed by the compaction equipment each time; combines the road surface compaction degree prediction function corresponding to the road surface to be compacted, and predicts the compaction degree corresponding to each road surface grid area in the visual road surface model of the road surface to be compacted in real time, and binds the corresponding compaction degree prediction value to the corresponding road surface grid area;

[0092] A compaction area interference intervention analysis module, which obtains the road surface grid area passed by the compaction equipment during its movement, recorded as the first grid area; obtains the associated affected grid area surrounding the first grid area, recorded as the second grid area; and analyzes the compaction degree interference coefficient corresponding to the first grid area on different road surface grid areas within the second grid area during the execution of the compaction equipment;

[0093] A compaction degree update and auxiliary management module, in combination with the obtained compaction equipment execution process, the compaction degree intervention interference coefficient corresponding to the first grid area to different pavement grid areas in the second grid area is obtained, and the compaction degree intervention interference amount corresponding to the different pavement grid areas in the second grid area in the visual pavement model of the pavement to be compacted is obtained. The compaction degree of each pavement grid area in the second grid area is updated according to the obtained compaction degree intervention interference amount, and a real-time distribution map of the compaction degree of the visual pavement model of the pavement to be compacted is obtained to assist the administrator in making decisions on the compaction plan in the area to which the pavement to be compacted belongs.

[0094] The compaction area interference intervention analysis module includes a first grid area acquisition unit, a second grid area acquisition unit and an intervention interference analysis unit.

[0095] The first grid area acquisition unit acquires a road surface grid area passed by the compaction equipment during its movement, and records it as a first grid area;

[0096] The second grid area acquisition unit acquires the associated wave affected grid area around the first grid area, which is recorded as the second grid area;

[0097] The intervention interference analysis unit analyzes the compaction degree intervention interference coefficients corresponding to different road surface grid areas in the second grid area and the first grid area during the execution of the compaction equipment.

[0098] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0099] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A real-time prediction method for pavement compaction based on big data analysis, characterized in that: The method comprises the following steps: S1. Obtain the regional location of the road surface to be compacted, construct a visual road surface model of the road surface to be compacted, rasterize the constructed visual road surface model to obtain road surface grid areas with the same specifications, and number each road surface grid area; S2. Obtaining characteristic information of the compacted pavement state before the compaction operation is performed on the pavement to be compacted; training each coefficient parameter in the pavement compaction degree prediction function model according to the characteristic information of the compacted pavement state of each pavement compaction item during the compaction operation and the pavement compaction degree after the operation is performed, and obtaining a pavement compaction degree prediction function corresponding to the pavement to be compacted; S3. When the compaction equipment performs compaction operation on the road surface to be compacted, the travel trajectory of the compaction equipment is obtained in real time, and the road surface grid area that the compaction equipment passes through each time is marked; combined with the road surface compaction degree prediction function corresponding to the road surface to be compacted, the compaction degree corresponding to each road surface grid area in the visual road surface model of the road surface to be compacted is predicted in real time, and the corresponding compaction degree prediction value is bound to the corresponding road surface grid area; S4, obtaining the road surface grid area that the compaction equipment passes through during the movement, recorded as the first grid area; obtaining the associated affected grid area around the first grid area, recorded as the second grid area; analyzing the compaction degree intervention interference coefficient corresponding to the first grid area to different road surface grid areas in the second grid area during the execution of the compaction equipment; S5. In combination with the compaction equipment obtained in S4, during the execution process, the first grid area corresponds to different pavement grid areas in the second grid area, respectively, and the compaction intervention interference coefficients corresponding to the different pavement grid areas in the second grid area in the visualized pavement model of the pavement to be compacted are obtained. The compaction intervention interference amounts corresponding to the different pavement grid areas in the second grid area in the visualized pavement model of the pavement to be compacted are respectively updated, and a real-time distribution map of the compaction of the visualized pavement model of the pavement to be compacted is obtained, so as to assist the administrator in making decisions on the compaction plan in the area to which the pavement to be compacted belongs.

2. The method for real-time prediction of road compaction based on big data analysis according to claim 1 is characterized in that: The visualized road surface model in the road surface to be compacted in S1 includes the corresponding area of ​​the road surface to be compacted, and the visualized road surface model in the road surface to be compacted and the corresponding area of ​​the road surface to be compacted are in equal proportion to each other; In the process of rasterizing the constructed visual road model, the specification of the raster is preset in the database, and the number of the i-th road grid area in the constructed visual road model is recorded as Ai; The compacted road surface state characteristic information in S2 includes equipment characteristic information and road surface characteristic information. The equipment characteristic information includes the number of compaction passes in each road surface grid area, the effective rolling time of the compaction equipment, and the compaction vibration frequency value; The road surface characteristic information includes the paving thickness, initial paving temperature and ambient temperature of asphalt in each road surface grid area.

3. The method for real-time prediction of road compaction based on big data analysis according to claim 2 is characterized in that: The method for obtaining the road surface compaction degree prediction function corresponding to the road surface to be compacted in S2 comprises the following steps: S21, the compacted pavement state characteristic information of each pavement compaction item during the compaction operation and the pavement compaction degree after the operation recorded in the historical data, constructing the first characteristic data pair corresponding to each pavement compaction item, recorded as ({B1, B2 / M, B3, B4, B5-B6}, Y); Among them, B1 represents the number of compaction passes of the corresponding road surface before the execution of the corresponding road surface compaction project; B2 represents the rolling time of the compaction equipment in the corresponding road surface area during the execution of the corresponding road surface compaction project; M represents the area of ​​the road surface area rolled by the compaction equipment during the execution of the corresponding road surface compaction project; B3 represents the compaction vibration frequency value of the compaction equipment during the execution of the corresponding road surface compaction project; B4 represents the average paving thickness of the asphalt in the road surface during the execution of the corresponding road surface compaction project; B5 represents the initial paving temperature of the corresponding road surface area when the corresponding road surface compaction project is executed; B6 represents the average ambient temperature of the corresponding road surface area when the corresponding road surface compaction project is executed; Y represents the average road surface compaction degree of the corresponding road surface area after the corresponding road surface compaction project is executed; S22. Fit the first characteristic data pair obtained according to the multivariate linear regression equation y=c1·x1+c2·x2+c3·x3+c4·x4+c5·x5+c6, in which y represents the degree of compaction, x1 represents the number of compaction passes, x2 represents the ratio of rolling time to the rolled road surface area, x3 represents the compaction vibration frequency value of the compaction equipment, x4 represents the paving thickness of the asphalt, x5 represents the difference between the initial paving temperature and the ambient temperature, and c1, c2, c3, c4, c5 and c6 are all compaction fitting coefficients; The coefficients c1, c2, c3, c4, c5 and c6 in the fitting results are used as the training results of the corresponding coefficient parameters in the road surface compaction prediction function model to obtain the road surface compaction prediction function corresponding to the road surface to be compacted, which is recorded as F.

4. The method for real-time prediction of road surface compaction based on big data analysis according to claim 3 is characterized in that: When predicting the compaction degree corresponding to each road surface grid area in the visualized road surface model of the road surface to be compacted in real time in S3, the equipment characteristic information and road surface characteristic information corresponding to each road surface grid area in the compacted road surface state characteristic information are collected, and the first characteristic data pair corresponding to each road surface grid area is constructed, and the first characteristic data pair corresponding to each road surface grid area is respectively substituted into the road surface compaction degree prediction function F corresponding to the road surface to be compacted, and the compaction degree prediction value corresponding to each road surface grid area is obtained; When the compaction equipment performs compaction operation on the road surface to be compacted, the travel trajectory of the compaction equipment is obtained in real time, and each time the compaction equipment passes through the road surface grid area, the first feature data pair corresponding to the corresponding road surface grid area needs to be updated once the number of markings corresponding to the road surface grid area increases.

5. The method for real-time prediction of road compaction based on big data analysis according to claim 1, characterized in that: When the second grid area is obtained in S4, the second grid area is a grid area outside the first grid area outline and whose distance from different position points on the first grid area outline is less than or equal to the corresponding radiation radius of the corresponding position points; the radiation radius corresponding to different position points on the first grid area outline is different. When obtaining the wave and radiation radius corresponding to different position points on the first grid area contour, the wave and radiation radius corresponding to a certain position point on the first grid area contour is recorded as R, and R is smaller than the width of the road surface to be compacted; Assuming that the radiation radius is R1, if R1-β·e YS2-YS0 / e YS3-YS1 ∈U, then R1 is used as an alternative value of the wave and radiation radius R corresponding to the corresponding position point on the first grid area contour, and R is the minimum value among the corresponding alternative values ​​R1; Among them, U represents the tolerance range of the affected radiation radius deviation preset in the database; YS2 represents the average compaction degree of each road surface grid area in the first grid area after the compaction equipment passes through; YS0 represents the average compaction degree of each road surface grid area in the first grid area before the compaction equipment passes through; YS1 represents the average compaction degree of all road surface grid areas outside the outline of the first grid area and whose distance from the corresponding position on the edge of the outline of the first grid area is less than or equal to R1; YS3 represents the compaction requirement reference value corresponding to the area to be compacted in the database, and the compaction requirement reference value corresponding to the area to be compacted in the database is preset.

6. A real-time prediction method for road surface compaction based on big data analysis according to claim 5, characterized in that: The method for analyzing the compaction degree intervention interference coefficient of the first grid area corresponding to different road surface grid areas in the second grid area during the execution of the compaction equipment in S4 comprises the following steps: S41, obtaining the difference between the average value of the predicted compaction degree of each road surface grid area corresponding to the first grid area after the compaction equipment passes through and the average value of the predicted compaction degree of each road surface grid area corresponding to the second grid area before the compaction equipment passes through, and recording it as the first deviation; S42, recording the difference between the compaction requirement reference value corresponding to the area to be compacted in the database and the average value of the compaction prediction values ​​corresponding to each road grid area in the second grid area before the compaction equipment passes as the second deviation; the compaction requirement reference value corresponding to the area to be compacted in the database is preset; S43, obtaining the first grid area for different road surface grid areas in the second grid area during the execution of the compaction equipment The compaction degree intervention interference coefficient corresponding to the first grid area and the kth road surface grid area in the second grid area is recorded as Gk. Gk=[β1·e YP2-YP0 +β2·e YP2-YP1k ]·(1-rk / Rk), Wherein, β1 represents the first interference conversion coefficient; β2 represents the second interference conversion coefficient; both β1 and β2 are constants preset in the database; YP0 represents the average compaction degree of each road surface grid area in the first grid area before the compaction equipment passes by; YP1k represents the compaction degree of the kth road surface grid area in the second grid area; YP2 represents the average compaction degree of each road surface grid area in the first grid area after the compaction equipment passes by; rk represents the shortest distance between the kth road surface grid area in the second grid area and the first grid area; Rk represents the maximum radiation radius corresponding to each intersection point with the contour edge of the first grid area in each line segment corresponding to the shortest distance from the kth road surface grid area to the contour edge of the first grid area in the second grid area.

7. The real-time prediction method for pavement compaction based on big data analysis according to claim 1 is characterized by: When obtaining the compaction degree intervention interference amount corresponding to different road surface grid areas in the second grid area in the visualized road surface model of the road surface to be compacted in S5, the compaction degree intervention interference amount corresponding to the k-th road surface grid area in the second grid area in the visualized road surface model of the road surface to be compacted is recorded as Hk, and the value of HK is equal to the product of the compaction degree corresponding to the k-th road surface grid area in the second grid area and the compaction degree intervention interference coefficient corresponding to the k-th road surface grid area in the second grid area; When the compaction degree of each pavement grid area in the second grid area is updated according to the obtained compaction intervention interference amount in S5, the updated result of the compaction degree of the kth pavement grid area in the second grid area in the visualized pavement model of the pavement to be compacted is recorded as Dk, and Dk is equal to the difference between the compaction degree of the kth pavement grid area in the second grid area before the update and HK in the visualized pavement model of the pavement to be compacted.

8. A road surface compaction real-time prediction system based on big data analysis, the system is implemented by a road surface compaction real-time prediction method based on big data analysis according to any one of claims 1 to 7, characterized in that: The system includes the following modules: A model rasterization analysis module, wherein the model rasterization analysis module obtains the regional position of the road surface to be compacted, constructs a visual road surface model of the road surface to be compacted, rasterizes the constructed visual road surface model to obtain various road surface grid areas with the same specifications, and numbers each road surface grid area; The road surface compaction prediction module obtains the road surface to be compacted before the compaction operation is performed. Compacting pavement state characteristic information; training each coefficient parameter in the pavement compaction degree prediction function model according to the compaction pavement state characteristic information of each pavement compaction project during the compaction operation and the pavement compaction degree after the operation recorded in the historical data, and obtaining the pavement compaction degree prediction function corresponding to the pavement to be compacted; A compaction track marking module, which obtains the travel track of the compaction device in real time during the compaction operation of the compaction device on the road surface to be compacted, and marks the road surface grid area that the compaction device passes through each time; Combined with the pavement compaction prediction function corresponding to the pavement to be compacted, the compaction corresponding to each pavement grid area in the visualized pavement model of the pavement to be compacted is predicted in real time, and the corresponding compaction prediction value is bound to the corresponding pavement grid area; A compaction area interference intervention analysis module, wherein the compaction area interference intervention analysis module obtains the road surface grid area passed by the compaction equipment during the travel process, which is recorded as the first grid area; obtains the associated affected grid area around the first grid area, which is recorded as the second grid area; and analyzes the compaction degree intervention interference coefficient corresponding to the first grid area to different road surface grid areas in the second grid area during the execution of the compaction equipment; A compaction degree update and auxiliary management module, in which the compaction degree update and auxiliary management module is combined with the obtained compaction equipment execution process, the first grid area corresponds to the compaction degree intervention interference coefficient of different pavement grid areas in the second grid area, obtains the compaction degree intervention interference amount corresponding to different pavement grid areas in the second grid area in the visual pavement model of the pavement to be compacted, and updates the compaction degree of each pavement grid area in the second grid area according to the obtained compaction degree intervention interference amount, obtains the real-time distribution map of the compaction degree of the visual pavement model of the pavement to be compacted, and assists the administrator to make decisions on the compaction plan in the area to which the pavement to be compacted belongs.

9. The real-time prediction system for road compaction based on big data analysis according to claim 8 is characterized by: The compaction area interference intervention analysis module includes a first grid area acquisition unit, a second grid area acquisition unit and an intervention interference analysis unit. The first grid area acquisition unit acquires a road surface grid area that the compaction equipment passes through during the moving process, and records it as a first grid area; The second grid region acquisition unit acquires the associated grid region around the first grid region, which is recorded as the second grid region; The intervention interference analysis unit analyzes the compaction degree intervention interference coefficients corresponding to different road surface grid areas in the second grid area from the first grid area during the execution of the compaction equipment.

Images