Asphalt pavement anti-skid recovery technology decision-making method, system and medium

Abstract

The invention discloses an asphalt pavement anti-skid recovery technology decision-making method, which belongs to the technical field of road engineering, and comprises the following steps: acquiring road condition parameters of a target road section in real time, including a vehicle type, a design speed, a road radius, a road longitudinal slope and a road superelevation; determining an asphalt pavement dynamic friction coefficient threshold according to the road condition parameters of the target road section; if the asphalt pavement dynamic friction coefficient of the target road section is greater than the asphalt pavement dynamic friction coefficient threshold value, judging that the target road section does not need anti-skid maintenance; if the asphalt pavement dynamic friction coefficient of the target road section is not larger than the asphalt pavement dynamic friction coefficient threshold value, prediction is carried out according to the road condition parameters of the target road section and a pre-trained BP neural network, and an anti-skid maintenance decision is output. The problem that in the prior art, the anti-skid maintenance decision of the target road section cannot be output at a proper time is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to an asphalt pavement anti-skid recovery technical decision method, system and medium, belonging to the technical field of road engineering. BACKGROUND

[0002] Asphalt pavement preventive maintenance is increasingly valued by domestic and foreign experts and scholars, and the materials and methods used are also increasingly rich, but the current pavement maintenance is mostly based on rutting, potholes, and cracking, which are obvious pavement diseases, and there is little consideration from the perspective of pavement anti-skid, or only as an aspect for detection, and often when the pavement has obvious diseases, there is a safety hazard and the best preventive maintenance opportunity is missed, and pavement anti-skid deficiency often becomes the first inducement to traffic accidents, and ignoring the importance of pavement anti-skid to preventive maintenance has a great impact on social and economic benefits.

[0003] At present, the technical measures for asphalt pavement anti-skid recovery are relatively mature, but the selection of anti-skid recovery measures depends on previous engineering experience and the subjective decision experience of relevant experts, and the target road section anti-skid maintenance decision cannot be made at the right time, how to comprehensively summarize the existing anti-skid maintenance experience, select the appropriate method for different road sections at the right time, and maximize the practical value and economic benefit, still needs further research. SUMMARY

[0004] The purpose of the present application is to provide an asphalt pavement anti-skid recovery technical decision method, system and medium, which outputs anti-skid maintenance decisions at the right time by using BP neural network to predict output with dynamic friction coefficient as the anti-skid evaluation index according to the road condition parameters of the target road section in real time, to solve the problem that the prior art cannot output target road section anti-skid maintenance decisions at the right time.

[0005] To solve the above technical problems, the present application is realized by the following technical scheme.

[0006] In a first aspect, the present application provides an asphalt pavement anti-skid recovery technical decision method, comprising:

[0007] Real-time acquisition of road condition parameters of the target road section, including rainfall, traffic volume, pavement type, pavement pollution level, road age, and road type, vehicle type, design speed, road radius, road longitudinal slope, and road super-elevation;

[0008] Determining the asphalt pavement dynamic friction coefficient threshold according to the road condition parameters of the target road section;

[0009] If the asphalt pavement dynamic friction coefficient of the target road section is greater than the asphalt pavement dynamic friction coefficient threshold, it is determined that the target road section does not need anti-skid maintenance;

[0010] If the dynamic friction coefficient of the asphalt pavement of the target section is not greater than the dynamic friction coefficient threshold of the asphalt pavement, the anti-skid maintenance decision is predicted and output according to the road condition parameters of the target section and the pre-trained BP neural network.

[0011] Further, the dynamic friction coefficient threshold of the asphalt pavement is determined according to the road condition parameters of the target section, comprising:

[0012] The vehicle types include large vehicles and small vehicles;

[0013] The design speed is the highest speed limit of the target section;

[0014] If the current target section only includes small vehicles, the design speed is determined:

[0015] If the design speed is equal to the first preset speed, the road radius is determined: if the road radius is equal to the first preset radius, the dynamic friction coefficient threshold of the asphalt pavement is determined according to the road longitudinal slope and the road super-elevation; if the road radius is not equal to the first preset radius, the dynamic friction coefficient threshold of the asphalt pavement is determined according to the road longitudinal slope;

[0016] If the design speed is not equal to the first preset speed, the dynamic friction coefficient threshold of the asphalt pavement is determined according to the road longitudinal slope;

[0017] If the current target section includes both small vehicles and large vehicles or only includes large vehicles, the design speed is determined:

[0018] If the design speed is equal to the first preset speed, the road radius is determined: if the road radius is equal to the second preset radius, the dynamic friction coefficient threshold of the asphalt pavement is determined according to the road longitudinal slope and the road super-elevation; if the road radius is not equal to the second preset radius, the dynamic friction coefficient threshold of the asphalt pavement is determined according to the road longitudinal slope;

[0019] If the design speed is equal to the second preset speed, the road radius is determined: if the road radius is equal to the third preset radius, the dynamic friction coefficient threshold of the asphalt pavement is determined according to the road longitudinal slope and the road super-elevation; if the road radius is not equal to the third preset radius, the dynamic friction coefficient threshold of the asphalt pavement is determined according to the road longitudinal slope;

[0020] If the design speed is not equal to the second preset speed, the dynamic friction coefficient threshold of the asphalt pavement is determined according to the road longitudinal slope.

[0021] Further, the dynamic friction coefficient threshold of the asphalt pavement is determined according to the road longitudinal slope and the road super-elevation or the dynamic friction coefficient threshold of the asphalt pavement is determined according to the road longitudinal slope by using the vehicle dynamics software CarSim / TruckSim.

[0022] Further, the road anti-skid threshold value is determined according to the prevention of vehicle side slip, the asphalt pavement dynamic friction coefficient threshold value is determined according to the road longitudinal slope and the road super elevation by the vehicle dynamics software CarSim / TruckSim, and the road anti-skid threshold value is determined according to the vehicle side slip, including:

[0023] A vehicle body model is established according to vehicle physical parameters, including the vehicle mass, the vehicle length, the vehicle width, the vehicle height and the height of the center of mass;

[0024] A vehicle dynamics model is established according to the tire parameters, the longitudinal force-slip rate curve and the lateral force-slip rate curve of the vehicle body model;

[0025] The vehicle driving process is simulated according to the vehicle body model and the vehicle dynamics model, and if the speed deviation exceeds the first preset deviation threshold value during the vehicle driving process, the vehicle is judged to have side slip;

[0026] The road anti-skid threshold value is determined according to the critical point of preventing the vehicle from side slip at the design speed;

[0027] The road anti-skid threshold value is taken as a judgment index to obtain the dynamic friction coefficient threshold value under different road longitudinal slopes and road super elevations.

[0028] Further, the road anti-skid threshold value is determined according to the braking distance, the asphalt pavement dynamic friction coefficient threshold value is determined according to the road longitudinal slope by the vehicle dynamics software CarSim / TruckSim, and the road anti-skid threshold value is determined according to the vehicle side slip, including:

[0029] A vehicle body model is established according to vehicle physical parameters, including the vehicle mass, the vehicle length, the vehicle width, the vehicle height and the height of the center of mass;

[0030] A vehicle dynamics model is established according to the tire parameters, the longitudinal force-slip rate curve and the lateral force-slip rate curve of the vehicle body model;

[0031] The vehicle driving process is simulated according to the vehicle body model and the vehicle dynamics model, the longitudinal driving distance from the start of the vehicle braking to the end of the braking is taken as the braking distance, and the braking distance is compared with the maximum braking distance determined by the critical safety distance model to determine the road anti-skid threshold value;

[0032] The road anti-skid threshold value is taken as a judgment index to obtain the dynamic friction coefficient threshold value under different road longitudinal slopes.

[0033] Further, the asphalt pavement dynamic friction coefficient of the target road section is obtained by the close-range photogrammetry technology and according to the texture calculation method.

[0034] Further, the asphalt pavement dynamic friction coefficient of the target road section is obtained by the close-range photogrammetry technology and according to the texture calculation method, including:

[0035] Three cameras with a depression angle of 45° are arranged in a ring with a spacing of 120°, and a shadowless lamp is used for lighting to obtain road surface texture, and a road surface texture image is obtained;

[0036] Image preprocessing is performed on the road surface texture image to obtain a preprocessed road surface texture image, and the image preprocessing includes image deformation correction, image segmentation, shadow removal, texture image noise reduction, brightness adjustment, and contrast enhancement;

[0037] Based on the preprocessed road surface texture image, the three-dimensional coordinates of the target road segment space points are calculated;

[0038] Based on the three-dimensional coordinates of the target road segment space points, point cloud reconstruction is performed, and a road surface texture 3D model is generated by triangular mesh division; based on the road surface texture 3D model, the three-dimensional elevation data of the road surface texture is obtained to reconstruct the road surface texture, and the target road segment road surface power spectral density curve and the rubber complex modulus curve are solved;

[0039] According to the target road segment road surface power spectral density curve and the rubber complex modulus curve, the asphalt pavement dynamic friction coefficient of the target road segment is calculated.

[0040] Further, the training method of the BP neural network comprises:

[0041] According to the actual engineering road segment anti-skid maintenance decision data, the historical road condition parameters and the historical anti-skid maintenance decision of the target road segment are obtained;

[0042] The historical road condition parameters of the target road segment are used as input data, and the historical anti-skid maintenance decision is used as the label of the input data to construct a training set;

[0043] Using the training set, the mean square error MSE is used as the loss function, and based on the preselected neural network layer number, the number of neurons in each layer, the size of each batch of data, the learning rate, the learning round, and the regularization parameter, the BP neural network is trained by an iterative method to output the anti-skid maintenance decision, and a trained BP neural network is obtained;

[0044] The anti-skid maintenance decision includes fine surface treatment, fine anti-skid gravel seal coat, drainage asphalt pavement, and ultra-thin wearing layer.

[0045] In the second aspect, the present application provides an asphalt pavement anti-skid recovery technology decision system for realizing the asphalt pavement anti-skid recovery technology decision method of the first aspect.

[0046] In the third aspect, the present application provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to realize the asphalt pavement anti-skid recovery technology decision method of the first aspect.

[0047] Compared with the prior art, the present application has the following beneficial effects:

[0048] The asphalt pavement anti-skid recovery technology decision method provided by the embodiment of the present application determines the asphalt pavement dynamic friction coefficient threshold according to the road condition parameters of the target section, and obtains the anti-skid maintenance decision of the target section by using the BP neural network based on the relationship between the asphalt pavement dynamic friction coefficient threshold and the road condition parameters, thereby assisting engineers in selecting appropriate recovery technologies for the sections that need anti-skid maintenance, and solving the problem that the prior art cannot output the anti-skid maintenance decision of the target section at the appropriate time. BRIEF DESCRIPTION OF DRAWINGS

[0049] Figure 1 is a flowchart of an asphalt pavement anti-skid recovery technology decision method provided by the embodiment of the present application;

[0050] Figure 2 is a flowchart of determining an asphalt pavement dynamic friction coefficient threshold provided by the embodiment of the present application;

[0051] Figure 3 is an interface diagram of an asphalt pavement anti-skid recovery technology decision system provided by the embodiment of the present application;

[0052] Figure 4 is an interface diagram of a target section that does not need anti-skid maintenance provided by the embodiment of the present application;

[0053] Figure 5 is an interface diagram of a target section that needs anti-skid maintenance and the corresponding anti-skid maintenance decision provided by the embodiment of the present application. DETAILED DESCRIPTION

[0054] The technical scheme of the present application will be described in detail below with reference to the drawings and specific embodiments. It should be understood that the specific features in the embodiments of the present application and the specific embodiments are detailed descriptions of the technical scheme of the present application, and are not limitations of the technical scheme of the present application. In the case of no conflict, the technical features in the embodiments of the present application and the specific embodiments can be combined with each other.

[0055] The term "and / or", only describes the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / ", generally represents that the front and rear associated objects are in an "or" relationship.

[0056] Embodiment 1

[0057] As Figure 1 shown, the present embodiment introduces an asphalt pavement anti-skid recovery technology decision method, which comprises:

[0058] Step one: real-time acquisition of road condition parameters of the target section.

[0059] In this embodiment, the road condition parameters include rainfall, traffic volume, road surface type, road surface pollution level, road age, and road type, vehicle type, design speed, road radius, road longitudinal slope, and road super-elevation.

[0060] This embodiment provides dynamic and accurate basic data support for subsequent evaluation of asphalt pavement skid resistance and maintenance decision-making by real-time collection of multi-dimensional road condition parameters, ensures strong correlation between road condition information and actual traffic state, avoids decision-making lag or deviation caused by static data, and improves the pertinence of skid resistance maintenance.

[0061] Step two: determine the dynamic friction coefficient threshold of the asphalt pavement according to the road condition parameters of the target section.

[0062] This embodiment dynamically determines the dynamic friction coefficient threshold based on actual road condition parameters, breaking through the limitations of traditional fixed thresholds, making the threshold more suitable for the traffic characteristics (such as vehicle type, design speed) and geometric alignment (such as road radius, road longitudinal slope, and road super-elevation) of the target section, improving the adaptability and accuracy of skid resistance performance judgment, and laying the key foundation for scientific maintenance decision-making.

[0063] Step three: if the dynamic friction coefficient of the asphalt pavement of the target section is greater than the dynamic friction coefficient threshold of the asphalt pavement, it is determined that the target section does not need skid resistance maintenance.

[0064] This embodiment quickly screens out sections that do not need maintenance by threshold comparison, avoids resource waste caused by excessive maintenance, clearly defines the safety state determination standard, ensures reasonable allocation of maintenance resources, reduces unnecessary maintenance costs, and improves maintenance efficiency.

[0065] Step four: if the dynamic friction coefficient of the asphalt pavement of the target section is not greater than the dynamic friction coefficient threshold of the asphalt pavement, make a prediction according to the road condition parameters of the target section and the pre-trained BP neural network and output the skid resistance maintenance decision.

[0066] This embodiment uses the nonlinear fitting capability of the BP neural network to integrate road condition parameters and dynamic friction coefficient data, realizes intelligent prediction and decision optimization of skid resistance maintenance demand, solves the subjectivity problem of traditional experience decision-making, improves the scientificity, accuracy and adaptability of the maintenance scheme, and provides an efficient technical solution for skid resistance maintenance under complex road conditions.

[0067] Embodiment 2

[0068] Based on the same inventive concept as embodiment 1, this embodiment introduces the implementation steps of a skid resistance recovery technology decision-making method for asphalt pavement, including:

[0069] Step 1: Real-time acquisition of road condition parameters of the target section.

[0070] In the embodiment, the road condition parameters include rainfall, traffic volume, road surface type, road surface pollution level, road age, and road type, vehicle type, design speed, road radius, road longitudinal slope, and road super-elevation.

[0071] Step 2: determining the asphalt pavement dynamic friction coefficient threshold according to the road condition parameters of the target section.

[0072] In the embodiment, the asphalt pavement dynamic friction coefficient threshold is determined according to the road condition parameters of the target section, as shown in the following table. Figure 2 Figure 2 The circular curve radius in the table is the road radius in the embodiment, including:

[0073] The vehicle type includes large vehicles and small vehicles;

[0074] The design speed is the highest speed limit of the target section;

[0075] If the current target section only includes small vehicles, the design speed is determined as follows:

[0076] If the design speed is equal to the first preset speed 20 km / h, the road radius is determined as follows: if the road radius is equal to the first preset radius 95 km, the asphalt pavement dynamic friction coefficient threshold is determined according to the road longitudinal slope and the road super-elevation; if the road radius is not equal to the first preset radius 95 km, the asphalt pavement dynamic friction coefficient threshold is determined according to the road longitudinal slope;

[0077] If the design speed is not equal to the first preset speed 20 km / h, the asphalt pavement dynamic friction coefficient threshold is determined according to the road longitudinal slope;

[0078] If the current target section includes both small vehicles and large vehicles or only includes large vehicles, the design speed is determined as follows:

[0079] If the design speed is equal to the first preset speed 20 km / h, the road radius is determined as follows: if the road radius is equal to the second preset radius 115 km, the asphalt pavement dynamic friction coefficient threshold is determined according to the road longitudinal slope and the road super-elevation; if the road radius is not equal to the second preset radius 115 km, the asphalt pavement dynamic friction coefficient threshold is determined according to the road longitudinal slope;

[0080] If the design speed is equal to the second preset speed 40 km / h, the road radius is determined as follows: if the road radius is equal to the third preset radius 135 km, the asphalt pavement dynamic friction coefficient threshold is determined according to the road longitudinal slope and the road super-elevation; if the road radius is not equal to the third preset radius 135 km, the asphalt pavement dynamic friction coefficient threshold is determined according to the road longitudinal slope;

[0081] If the design speed is not equal to the second preset speed 40 km / h, the asphalt pavement dynamic friction coefficient threshold is determined according to the road longitudinal slope. ​

[0082] In the embodiment, the asphalt pavement dynamic friction coefficient threshold is determined according to the road longitudinal slope and the road super elevation by the vehicle dynamics software CarSim / TruckSim.

[0083] In the embodiment, the pavement anti-skid threshold is determined according to the prevention of vehicle side slipping, the asphalt pavement dynamic friction coefficient threshold is determined according to the road longitudinal slope by the vehicle dynamics software CarSim / TruckSim, including:

[0084] The vehicle body model is established according to the vehicle physical parameters including the overall vehicle mass, the vehicle length, the vehicle width, the vehicle height and the height of the center of mass;

[0085] The vehicle dynamics model is established according to the tire parameters, the longitudinal force-slip ratio curve and the lateral force-slip ratio curve of the vehicle body model;

[0086] The vehicle driving process is simulated according to the vehicle body model and the vehicle dynamics model, and if the speed deviation during the vehicle driving process exceeds the first preset deviation threshold, the vehicle is judged to have side slipping;

[0087] The critical point of preventing the vehicle from side slipping at the design speed is used to determine the pavement anti-skid threshold;

[0088] The pavement anti-skid threshold is used as a judgment index to obtain the dynamic friction coefficient threshold under different road longitudinal slopes and road super elevations.

[0089] In the embodiment, the pavement anti-skid threshold is determined according to the braking distance, the asphalt pavement dynamic friction coefficient threshold is determined according to the road longitudinal slope by the vehicle dynamics software CarSim / TruckSim, including:

[0090] The vehicle body model is established according to the vehicle physical parameters including the overall vehicle mass, the vehicle length, the vehicle width, the vehicle height and the height of the center of mass;

[0091] The vehicle dynamics model is established according to the tire parameters, the longitudinal force-slip ratio curve and the lateral force-slip ratio curve of the vehicle body model;

[0092] The vehicle driving process is simulated according to the vehicle body model and the vehicle dynamics model, the longitudinal driving distance from the start of the vehicle braking to the end of the braking is used to represent the braking distance, and the pavement anti-skid threshold is determined by comparing the braking distance with the maximum braking distance determined by the critical safety vehicle distance model;

[0093] The pavement anti-skid threshold is used as a judgment index to obtain the dynamic friction coefficient threshold under different road longitudinal slopes.

[0094] In the embodiment, the specific analysis results obtained by the vehicle dynamics software CarSim / TruckSim are shown in Table 1, wherein μt is a dynamic friction coefficient threshold value, i is a slope of a road longitudinal slope, wherein the design speed is a design speed.

[0095] Table 1 Dynamic friction coefficient threshold value of asphalt pavement under different working conditions

[0096]

[0097] The embodiment is based on the calculation formula of the dynamic friction coefficient threshold value of the asphalt pavement under different working conditions in Table 1, and the dynamic friction coefficient threshold value of the asphalt pavement can be quickly solved through Python programming.

[0098] Step 3: If the dynamic friction coefficient of the asphalt pavement of the target road section is greater than the dynamic friction coefficient threshold value of the asphalt pavement, it is determined that the target road section does not need anti-skid maintenance.

[0099] The embodiment obtains the dynamic friction coefficient of the asphalt pavement of the target road section through the close-range photogrammetry technology and according to the texture calculation method, including:

[0100] Three cameras with a depression angle of 45° are arranged in a ring at an interval of 120°, and a shadowless lamp is used for lighting to obtain the pavement texture, and pavement texture images are obtained;

[0101] The pavement texture images are subjected to image preprocessing to obtain preprocessed pavement texture images, and the image preprocessing includes image deformation correction, image segmentation, shadow removal, texture image noise reduction, brightness adjustment and contrast enhancement;

[0102] Based on the preprocessed pavement texture images, three-dimensional coordinates of the spatial points of the target road section are calculated;

[0103] Based on the three-dimensional coordinates of the spatial points of the target road section, point cloud reconstruction is performed, a pavement texture 3D model is generated through triangular mesh division, three-dimensional elevation data of the pavement texture are obtained based on the pavement texture 3D model to reconstruct the pavement texture, and a pavement power spectral density curve and a rubber complex modulus curve of the target road section are solved;

[0104] The dynamic friction coefficient of the asphalt pavement of the target road section is calculated according to the pavement power spectral density curve and the rubber complex modulus curve of the target road section.

[0105] Step 4: If the dynamic friction coefficient of the asphalt pavement of the target road section is not greater than the dynamic friction coefficient threshold value of the asphalt pavement, the road condition parameters of the target road section and the pre-trained BP neural network are used for prediction and output of the anti-skid maintenance decision.

[0106] The embodiment assists decision-making through training of the BP neural network, converts the human decision-making problem into a machine learning classification problem, selects a suitable anti-skid maintenance decision, and positions the input data as the road condition parameters of the marked road section, which are divided into two types of numerical and text types. The road condition parameters have different expression methods in the neural network. In the embodiment, the text type is processed by One-Hot Encoding. The specific features and the division in the neural network are shown in Table 2.

[0107] Table 2 Input features of the BP neural network

[0108]

[0109] The embodiment adopts four commonly used anti-skid maintenance technologies, namely, the fine surface treatment, fine anti-skid chip seal, drainage asphalt pavement and ultra-thin wearing layer for anti-skid recovery as output features, and also adopts One-Hot Encoding, which is represented by (1, 0, 0, 0), (0, 1, 0, 0), (0, 0, 1, 0) and (0, 0, 0, 1) respectively. In the embodiment, more than 3000 sets of road section data are sorted out from the Shanghai-Shaanxi Expressway (Pingchao-Guangling section), Ningyuanjing Expressway, Chongqing-Fuling Expressway, Chongqing Port Road and Wanzhong Road to construct a training set. The trained BP neural network is used for prediction and output of the anti-skid maintenance decision. In the embodiment, as shown in Figure 4 、 Figure 5 The anti-skid maintenance decision includes the fine surface treatment, fine anti-skid chip seal, drainage asphalt pavement and ultra-thin wearing layer.

[0110] In the embodiment, the training method of the BP neural network includes:

[0111] According to the anti-skid maintenance decision data of the actual engineering road section, the historical road condition parameters and the historical anti-skid maintenance decision of the target road section are obtained.

[0112] The historical road condition parameters of the target road section are taken as the input data, and the historical anti-skid maintenance decision is taken as the label of the input data to construct a training set.

[0113] The training set is used to take the mean square error (MSE) as a loss function, and the BP neural network is trained based on the preselected neural network layer number, the number of neurons in each layer, the size of each batch of data, the learning rate, the learning round and the regularization parameter through an iterative method to output the anti-skid maintenance decision, and a trained BP neural network is obtained.

[0114] The anti-skid maintenance decision includes the fine surface treatment, fine anti-skid chip seal, drainage asphalt pavement and ultra-thin wearing layer.

[0115] Embodiment 3

[0116] Based on the same inventive concept as other embodiments, this embodiment introduces a bituminous pavement anti-skid recovery technology decision system for implementing the steps of the bituminous pavement anti-skid recovery technology decision method as described in Embodiment 1 or 2.

[0117] The BP neural network trained in Embodiment 2 is coupled with a visualization program developed based on Qt library by using QtGui and other modules through PyQt5 toolkit to complete the windowing of input parameters and anti-skid maintenance decision-making, as shown in Figure 3 Figure 3 is an interface schematic diagram of the bituminous pavement anti-skid recovery technology decision system provided by the present application, wherein the design speed is the design speed, and the partial anti-skid maintenance decision is shown in Table 3.

[0118] Table 3: Bituminous pavement anti-skid maintenance recovery technology decision example

[0119]

[0120] Through the above analysis, it can be known that the present application determines the bituminous pavement dynamic friction coefficient threshold according to the road condition parameters of the target road section, and obtains the anti-skid maintenance decision of the target road section by using the BP neural network based on the relationship between the bituminous pavement dynamic friction coefficient threshold and the road condition parameters, thereby assisting engineers in selecting appropriate recovery technology for the road section in need of anti-skid maintenance, and solving the problem that the prior art cannot output the anti-skid maintenance decision of the target road section at the appropriate time.

[0121] Embodiment 4

[0122] Based on the same inventive concept as other embodiments, this embodiment introduces a computer readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the steps of the method of Embodiments 1 or 2.

[0123] In summary of the above embodiments, those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0124] ​The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart

[0125] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart

[0126] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart

[0127] The embodiments of the present application described above are merely intended to illustrate the present application, but not to limit the present application. The skilled in the art can make many modifications and improvements without departing from the spirit and scope of the present application, which should be protected as long as they fall within the scope of the present application.

Claims

1. A method for asphalt pavement skid resistance restoration technology decision, characterized in that, The method comprises the following steps: Real-time acquisition of road condition parameters of the target section, including rainfall, traffic volume, road surface type, road surface pollution level, road age, and road type, vehicle type, design speed, road radius, road longitudinal slope, and road super-elevation; Determination of the asphalt pavement dynamic friction coefficient threshold value according to the road condition parameters of the target section; If the asphalt pavement dynamic friction coefficient of the target section is greater than the asphalt pavement dynamic friction coefficient threshold value, it is determined that the target section does not require anti-skid maintenance; If the asphalt pavement dynamic friction coefficient of the target section is not greater than the asphalt pavement dynamic friction coefficient threshold value, a prediction is made according to the road condition parameters of the target section and the pre-trained BP neural network, and an anti-skid maintenance decision is output.

2. The asphalt pavement skid-resistance restoration technique decision-making method according to claim 1, characterized in that, Determination of the asphalt pavement dynamic friction coefficient threshold value according to the road condition parameters of the target section comprises: The vehicle type includes large vehicles and small vehicles; The design speed is the highest speed limit of the target section; If the current target section only includes small vehicles, the design speed is determined as follows: If the design speed is equal to the first preset speed, the road radius is determined as follows: if the road radius is equal to the first preset radius, the asphalt pavement dynamic friction coefficient threshold value is determined according to the road longitudinal slope and the road super-elevation; if the road radius is not equal to the first preset radius, the asphalt pavement dynamic friction coefficient threshold value is determined according to the road longitudinal slope; If the design speed is not equal to the first preset speed, the asphalt pavement dynamic friction coefficient threshold value is determined according to the road longitudinal slope; If the current target section includes both small vehicles and large vehicles or only includes large vehicles, the design speed is determined as follows: If the design speed is equal to the first preset speed, the road radius is determined as follows: if the road radius is equal to the second preset radius, the asphalt pavement dynamic friction coefficient threshold value is determined according to the road longitudinal slope and the road super-elevation; if the road radius is not equal to the second preset radius, the asphalt pavement dynamic friction coefficient threshold value is determined according to the road longitudinal slope; If the design speed is equal to the second preset speed, the road radius is determined as follows: if the road radius is equal to the third preset radius, the asphalt pavement dynamic friction coefficient threshold value is determined according to the road longitudinal slope and the road super-elevation; if the road radius is not equal to the third preset radius, the asphalt pavement dynamic friction coefficient threshold value is determined according to the road longitudinal slope; If the design speed is not equal to the second preset speed, the asphalt pavement dynamic friction coefficient threshold value is determined according to the road longitudinal slope.

3. The asphalt pavement skid-resistance restoration technique decision-making method according to claim 1, characterized in that, Determination of the asphalt pavement dynamic friction coefficient threshold value according to the road longitudinal slope and the road super-elevation or determination of the asphalt pavement dynamic friction coefficient threshold value according to the road longitudinal slope by the vehicle dynamics software CarSim / TruckSim.

4. The asphalt pavement skid-resistance restoration technique decision-making method according to claim 3, characterized in that, Determination of the asphalt pavement dynamic friction coefficient threshold value according to the road longitudinal slope and the road super-elevation by the vehicle dynamics software CarSim / TruckSim for preventing vehicle sideslip, comprising: Establishment of a vehicle body model according to vehicle physical parameters, including vehicle mass, vehicle length, vehicle width, vehicle height, and center of mass height; Establishment of a vehicle dynamics model according to tire parameters, longitudinal force-slip ratio curve, and lateral force-slip ratio curve of the vehicle body model; Simulation of the vehicle driving process according to the vehicle body model and the vehicle dynamics model, and determination of vehicle sideslip if the speed deviation during the vehicle driving process exceeds a first preset deviation threshold value. The critical point of preventing vehicle from side slipping at design speed is used to determine the pavement anti-skid threshold value; The pavement anti-skid threshold value is used as a judgment index to obtain the dynamic friction coefficient threshold value under different road longitudinal slopes and road super-elevations.

5. The asphalt pavement skid-resistance restoration technique decision-making method according to claim 3, characterized in that, The pavement anti-skid threshold value is determined according to the braking distance, and the dynamic friction coefficient threshold value under different road longitudinal slopes is determined by using the vehicle dynamics software CarSim / TruckSim, including: A vehicle body model is established according to vehicle physical parameters, including the overall vehicle mass, vehicle length, vehicle width, vehicle height and center of mass height; A vehicle dynamics model is established according to the tire parameters, longitudinal force-slip ratio curve and lateral force-slip ratio curve of the vehicle body model; The vehicle driving process is simulated according to the vehicle body model and the vehicle dynamics model, the longitudinal driving distance from the start of braking to the end of braking is used to represent the braking distance, and the braking distance is compared with the maximum braking distance determined by the critical safety distance model to determine the pavement anti-skid threshold value; The pavement anti-skid threshold value is used as a judgment index to obtain the dynamic friction coefficient threshold value under different road longitudinal slopes.

6. The asphalt pavement skid-resistance restoration technique decision-making method of claim 1, wherein, The dynamic friction coefficient of the target road section is obtained by using close-range photogrammetry technology and according to a texture calculation method.

7. The asphalt pavement skid-resistance restoration technique decision-making method according to claim 6, characterized in that, The dynamic friction coefficient of the target road section is obtained by using close-range photogrammetry technology and according to a texture calculation method, including: Three cameras with a depression angle of 45° are arranged in a ring at an interval of 120°, and a shadowless lamp is used for lighting to obtain pavement texture, and pavement texture images are obtained; Image preprocessing is performed on the pavement texture images to obtain preprocessed pavement texture images, and the image preprocessing includes image deformation correction, image segmentation, shadow removal, texture image noise reduction, brightness adjustment and contrast enhancement; Three-dimensional coordinates of the target road section space points are calculated based on the preprocessed pavement texture images; Point cloud reconstruction is performed based on the three-dimensional coordinates of the target road section space points, and a pavement texture 3D model is generated by triangular mesh division; three-dimensional elevation data of the pavement texture are obtained based on the pavement texture 3D model to reconstruct the pavement texture, and the pavement power spectral density curve and the rubber complex modulus curve of the target road section are solved; The dynamic friction coefficient of the target road section is calculated based on the pavement power spectral density curve and the rubber complex modulus curve of the target road section.

8. The asphalt pavement skid-resistance restoration technique decision-making method of claim 6, wherein, The training method of the BP neural network includes: The historical road condition parameters and historical anti-skid maintenance decisions of the target road section are obtained according to the actual engineering road section anti-skid maintenance decision data; The historical road condition parameters of the target road section are used as input data, and the historical anti-skid maintenance decisions are used as labels of the input data to construct a training set; The training set is used to train the BP neural network output anti-skid maintenance decisions by using the mean square error MSE as the loss function, based on the preselected neural network layer number, the number of neurons in each layer, the size of each batch of data, the learning rate, the learning round and the regularization parameter by the iterative method, to obtain the trained BP neural network; The anti-skid maintenance decisions include fine surface treatment, fine anti-skid macadam overlay, drainage asphalt pavement and ultra-thin wearing layer.

9. A pavement skid resistance restoration technology decision system characterized by, The asphalt pavement anti-skid recovery technical decision method is used to realize the asphalt pavement anti-skid recovery technical decision method of any one of claims 1-8.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by a processor, implements the asphalt pavement skid resistance restoration technique decision method according to any one of claims 1-8.

Images