Wet operation path planning method and system based on road real-time condition

Abstract

The invention provides a wet operation path planning method and system based on road real-time conditions, and relates to the technical field of operation path planning. The method comprises the following steps of S1, collecting multi-source data of road basic conditions, road flow conditions and meteorological conditions in real time on each dust suppression vehicle driving road section in a current wet operation area for calculation, and performing weighted fusion to obtain road real-time conditions corresponding to each dust suppression vehicle driving road section; s2, obtaining the total path cost corresponding to the current wet operation area according to the running road section of the dust suppression vehicle; s3, according to the road real-time state numerical value corresponding to each dust suppression vehicle driving road section, the road attention degree corresponding to the current wet method operation area is obtained; s4, establishing an MOGAPSO path planning model of the dust suppression vehicle by taking the total path cost and the road attention corresponding to the current wet operation area as assessment targets; and S5, solving the MOGAPSO path planning model of the dust suppression vehicle to obtain a transportation path planning result of the dust suppression vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of operation path planning, and in particular to a wet operation path planning method and system based on real-time road conditions. Background Art

[0002] As urban construction continues to advance, the problem of urban dust pollution has become more and more serious. As an important part of urban management, wet road operations are of great significance in improving urban environmental quality, enhancing the city's image, and reducing atmospheric pollutant emissions. However, in the current wet road operations, most of them rely on work experience for path planning, which is easily affected by personal factors, meteorological conditions, urban road conditions, etc., and lacks flexibility and globality, resulting in the current wet road operations often having problems such as poor results, high costs, and delays. Therefore, in response to the above-mentioned problems, this patent proposes a wet operation path planning method based on real-time road conditions. By calculating the real-time road conditions, it provides appropriate wet operation path planning, solves road dust problems in a timely manner, and improves environmental quality. Summary of the invention

[0003] The purpose of the present invention is to provide a wet operation path planning method and system based on real-time road conditions. Based on the dynamic assignment of real-time road conditions in the current wet operation area, through an improved multi-objective genetic algorithm, wet operation path planning can be intelligently realized, thereby improving the timeliness and effectiveness of dust suppression vehicles in handling road dust and improving environmental quality.

[0004] In order to solve the above technical problems, the present invention adopts the following solutions: A wet operation path planning method based on real-time road conditions, the method comprising the following steps: S1. In the current wet operation area, multi-source data on road basic conditions, road flow conditions and meteorological conditions are collected in real time on each road section where the dust suppression vehicle is traveling, and the corresponding road basic values, road flow values ​​and meteorological values ​​are obtained. The road basic values, road flow values ​​and meteorological values ​​are weightedly fused to obtain the real-time road conditions corresponding to each road section where the dust suppression vehicle is traveling; S2. Obtain the total path cost corresponding to the current wet operation area according to the road section traveled by the dust suppression vehicle; S3, obtaining the road attention corresponding to the current wet operation area according to the real-time road status value corresponding to each dust suppression vehicle driving section; S4. Taking the total path cost and road attention corresponding to the current wet operation area as the assessment target, the MOGAPSO path planning model of the dust suppression vehicle is established; S5. Solve the MOGAPSO path planning model of the dust suppression vehicle to obtain the transportation path planning result of the dust suppression vehicle.

[0005] Furthermore, the S1 specifically includes the following steps: S11, obtaining the road damage degree and road dust accumulation degree of each road section where the dust suppression vehicle is traveling in the current wet operation area, and obtaining the road basic value by weighted average of the road damage degree and the road dust accumulation degree; S12, obtaining the heavy vehicle flow and road checkpoint flow of each dust suppression vehicle driving section in the current wet operation area, and obtaining the road flow value by weighted average of the heavy vehicle flow and the road checkpoint flow; S13, obtaining meteorological values ​​of each road section where the dust suppression vehicle is traveling in the current wet operation area; S14, weighted fusion of the road basic value, road flow value and meteorological value corresponding to each dust suppression vehicle driving section to obtain the real-time road status value.

[0006] Furthermore, in S11, the road damage degree is comprehensively assessed based on manual inspection results, road video recognition results, and sensor vibration recognition results, and the road dust degree is calculated based on the total suspended particulate matter concentration and cruising speed of the road monitored in real time by the dust collection vehicle.

[0007] Furthermore, in S12, the heavy vehicle flow is obtained by counting the GPS data of the heavy vehicles, and the road checkpoint flow is obtained by counting the flow of different vehicle types using checkpoint equipment that matches the road.

[0008] Furthermore, in S13, the meteorological value is calculated based on the impact of real-time rainfall on road dust.

[0009] Furthermore, in S2, the process of obtaining the total path cost corresponding to the current wet operation area according to the road section traveled by the dust suppression vehicle is specifically as follows: According to the driving section of the dust suppression vehicle, the path lengths of the watered section and the non-watered section are obtained, and according to the driving speed and path length of the dust suppression vehicle on the watered section and the non-watered section, the section time corresponding to the watered section and the non-watered section are obtained respectively. The section time corresponding to the watered section and the non-watered section are summed to obtain the total path cost corresponding to the current wet operation area.

[0010] Furthermore, in S3, the process of obtaining the road attention corresponding to the current wet operation area according to the real-time road status value corresponding to each dust suppression vehicle driving section is specifically as follows: The attention score of the road section where the dust suppression vehicle is traveling is obtained according to the real-time road status value corresponding to the road section where the dust suppression vehicle is traveling, and the inverse of the attention score is used as the road attention degree corresponding to the current wet operation area.

[0011] Furthermore, in S4, the method for establishing the MOGAPSO path planning model of the dust suppression vehicle is: ; Among them, min is the minimum function, F is the objective function, F1 is the total path cost, F2 is the road attention, and T is the transpose.

[0012] Further, in S5, the MOGAPSO path planning model of the dust suppression vehicle is solved to obtain the transportation path planning result of the dust suppression vehicle, including the following steps: The road network nodes are used for path encoding, and non-repeating and interconnected path combinations are randomly generated from the starting point of the dust suppression vehicle to the end point of the dust suppression vehicle. All path combinations are collected to form a particle population P, that is, a path combination is taken as a particle Ai, and the objective function of all particles is calculated to perform non-dominated sorting, thereby initializing the external archive set and obtaining the individual optimal solution pbest and the global optimal solution gbest; Select a particle Ai from the particle population P to perform sequential crossover and mutation operations with the individual optimal solution pbest and the global optimal solution gbest, calculate the objective function of the new particle, and compare the non-inferiority relationship between the two. If the new particle is better, update the individual optimal solution and the global optimal solution; if the new particle becomes inferior, do not change it; if they do not dominate each other, decide whether to accept the new particle according to probability; Select one particle Ai from the particle population P generated in each iteration in turn to compare with multiple guiding particles in the external archive set. If it is determined that particle Ai in the particle population P dominates the guiding particle Xi among multiple guiding particles, then particle Ai is added to the external archive set and guiding particle Xi is eliminated. If no dominance relationship can be determined, particle Ai is added to the external archive set. In addition, the number of multiple guiding particles in the external archive set is set equal to the number of particle population P. If the number of multiple guiding particles in the external archive set is greater than the number of particle population P, the number of multiple guiding particles in the external archive set is trimmed, an individual in the grid is randomly deleted, and then the individual crowding density is updated. This cycle is repeated until the external archive set meets the requirements and the Pareto front solution is output.

[0013] A wet operation path planning system based on real-time road conditions, using the wet operation path planning method based on real-time road conditions, comprising: Road real-time condition calculation module: collects multi-source data of road basic conditions, road flow conditions and meteorological conditions in real time on each dust suppression vehicle driving section in the current wet operation area for calculation, obtains the corresponding road basic values, road flow values ​​and meteorological values, and performs weighted fusion of the road basic values, road flow values ​​and meteorological values ​​to obtain the real-time road status values ​​corresponding to each dust suppression vehicle driving section; Total path cost calculation module: obtains the total path cost corresponding to the current wet operation area according to the road section traveled by the dust suppression vehicle; Road attention calculation module: obtain the road attention corresponding to the current wet operation area according to the real-time road status value corresponding to each dust suppression vehicle driving section; MOGAPSO path planning model building module: Taking the total path cost and road attention corresponding to the current wet operation area as the assessment target, the MOGAPSO path planning model of the dust suppression vehicle is established; Transport path planning result solving module: solves the MOGAPSO path planning model of the dust suppression vehicle to obtain the transport path planning result of the dust suppression vehicle.

[0014] Beneficial effects of the present invention: The present invention provides a wet operation path planning method and system based on real-time road conditions. The wet operation path planning method does not choose to perform wet operation path planning based on a single influencing factor as in the prior art, but performs wet operation path planning based on dynamic real-time road conditions. Moreover, the real-time road conditions are obtained after classifying and fusing a variety of road-related data collected in real time, so that the improved multi-objective genetic algorithm can learn and analyze based on historical conditions, dynamically adjust the weight ratio of road-related data of different classifications, and ensure the accuracy and rationality of the results. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 Schematic diagram of the process of wet operation path planning method in Example 1 of the present invention; Figure 2 This is a schematic diagram of the overall architecture of the wet process path planning method in Example 1 of the present invention; Figure 3 A schematic diagram of an undirected graph modeled on a road network in Embodiment 1 of the present invention; Figure 4 It is a flow chart of solving the objective function by using the genetic algorithm to improve the multi-objective particle swarm algorithm (MOGAPSO) in Example 1 of the present invention; Figure 5 This is a schematic diagram of sequential crossing in Example 1 of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present invention and its application or use. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] The relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0018] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0019] Additionally, descriptions of well-known structures, functions, and configurations may be omitted for clarity and conciseness.One of ordinary skill in the art will recognize that various changes and modifications may be made to the examples described herein without departing from the spirit and scope of the present disclosure.

[0020] Technologies, methods, and apparatus known to ordinary technicians in the relevant field may not be discussed in detail, but where appropriate, such technologies, methods, and apparatus should be considered part of the authorization specification.

[0021] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0022] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments: Example 1 In this embodiment, if Figure 1 As shown, a wet operation path planning method based on real-time road conditions is proposed, and the method includes the following steps: S1. In the current wet operation area, multi-source data on road basic conditions, road flow conditions and meteorological conditions are collected in real time on each road section where the dust suppression vehicle is traveling, and the corresponding road basic values, road flow values ​​and meteorological values ​​are obtained. The road basic values, road flow values ​​and meteorological values ​​are weightedly fused to obtain the real-time road conditions corresponding to each road section where the dust suppression vehicle is traveling; S2. Obtain the total path cost corresponding to the current wet operation area according to the road section traveled by the dust suppression vehicle; S3, obtaining the road attention corresponding to the current wet operation area according to the real-time road status value corresponding to each dust suppression vehicle driving section; S4. Taking the total path cost and road attention corresponding to the current wet operation area as the assessment target, the MOGAPSO path planning model of the dust suppression vehicle is established; S5. Solve the MOGAPSO path planning model of the dust suppression vehicle to obtain the transportation path planning result of the dust suppression vehicle.

[0023] The real-time road condition can represent the dust pollution value generated by the road. The dust pollution value generated by the road is used to plan the wet operation route planning of the dust suppression vehicle, intelligently realize the wet operation route planning, and improve the timeliness and effectiveness of road dust treatment. Since the basic state of the road and the road flow are linearly related to the dust pollution value generated by the road, the linear relationship between the data can be used to construct a linear calculation model for calculating the real-time road condition.

[0024] In another embodiment, if Figure 2 As shown, the real-time road condition D is obtained by weighted fusion based on the road basic value Z, the road flow value L and the meteorological value W, that is, , wherein the road basic value Z is composed of the road damage degree P and the road dust degree SL, the road flow value L is composed of the heavy vehicle flow L1 and the road checkpoint flow L2, and the meteorological value W is composed of meteorological values.

[0025] The road damage degree P is comprehensively assessed based on manual inspection results, road video recognition results, and sensor vibration recognition results. It can accurately identify the road damage degree and increase the data analysis source.

[0026] The manual inspection process is as follows: manually inspecting all road conditions of level 1-3 in the area offline, and classifying the damage of each road, with its threshold value recorded as P1; The process of road video recognition is as follows: collect video data of road damage through the dashcam, analyze the road video stream in real time based on computer vision technology, and convert the frames of road damage identified in the video into structured data. Use machine learning to analyze the structured damage video in real time, aggregate the data to grade the degree of road damage, and record its threshold as P2; The process of sensor vibration recognition is as follows: vibration data of the vehicle while driving on the road is collected through the vehicle-mounted sensor, the time series vibration data is analyzed based on a machine learning algorithm, the degree of road damage is identified and graded, and its threshold is recorded as P3.

[0027] After obtaining the manual inspection results, road video recognition results, and sensor vibration recognition results through the above operations, the result data is matched with the road section where the dust suppression vehicle is traveling. Different weights can be assigned to the manual inspection results, road video recognition results, and sensor vibration recognition results, and then the sum and average are obtained to obtain the degree of road damage, which is recorded as P, that is, , at this time, x=3.

[0028] The road dust accumulation level SL is calculated based on the total suspended particulate matter concentration TSP and the cruising speed v of the road monitored in real time by the dust collection vehicle. When calculating the road dust accumulation level SL, the specific process is as follows: The GPS data of the dust collection vehicle is matched with the driving section of the dust suppression vehicle, and then matched to the road. Then, the road dust accumulation degree SL is calculated through the relationship between TSP and cruising speed, that is, The road dust level SL can be graded and defined. For example, when sL < 0.5, the road dust level is rated as excellent; when 0.5 ≤ sL < 1, it is rated as good; when 1 ≤ sL < 1.5, it is rated as medium; and when sL ≥ 1.5, it is rated as poor.

[0029] The road flow value L is the sum of the road flow evaluation results obtained by weighted average by assigning different weighted indexes to the heavy vehicle flow L1 and the road checkpoint flow L2.

[0030] In actual situations, if a heavy vehicle is not thoroughly cleaned before leaving the road, it will carry mud on the road, which will cause the mud to fall and increase the generation of road dust. At the same time, the heavy vehicle body is heavy, and it is easy to bump when passing through damaged or dusty sections, which is very likely to cause serious dust flying. Therefore, in this embodiment, the flow of heavy vehicles is considered separately, and different weighted indexes are assigned to the heavy vehicle flow L1 and the road checkpoint flow L2.

[0031] The heavy vehicle flow L1 is obtained by counting the GPS data of heavy vehicles. By accessing the GPS data of heavy vehicles, the GPS data can be matched with the driving section of the dust suppression vehicle, and then sorted according to the release time, and duplicates and abnormal data can be removed to count the heavy vehicle flow L1 on the driving section of the dust suppression vehicle.

[0032] The road checkpoint flow L2 is obtained by counting the flow of different models of vehicles by the checkpoint equipment matching the road. The specific process is: access the checkpoint flow data, take each dust suppression vehicle driving section as a unit, match the checkpoint data of one hour to the corresponding dust suppression vehicle driving section, then remove duplicate vehicles, count the flow of different models, and calculate the coverage of the road checkpoint equipment. Therefore, using the road section traffic flow, basic road characteristics, and surrounding characteristics as training samples, a convolutional generative adversarial network model based on mask matrix evaluation is established to infer the road section flow without the deployment of monitoring equipment, and finally train a model that conforms to the traffic flow law of the entire urban road network, recorded as L2.

[0033] During the rainfall process, TSP will be adsorbed into the rainwater and settle. The greater the rainfall and the longer the rainfall duration, the more obvious the weakening of particulate matter. Therefore, it is necessary to consider the impact of real-time meteorological factors on road dust. The rainfall data of the period [Tt-n......Tt] can be obtained through meteorological data, and the data with rainfall greater than 0.1 in this period can be selected, recorded as Wlist, and the maximum rainfall in Wlist is extracted and the weight is increased. The weight is recorded as K, and divided by the rainfall duration to obtain the balanced rainfall coefficient, and the meteorological value W is obtained, that is, ,at this time, Indicates the maximum rainfall, Indicates the duration of rainfall with the maximum rainfall.

[0034] To sum up, the wet operation path planning method is mainly based on the dynamic real-time road conditions for wet operation path planning, and the real-time road conditions are obtained after classifying and fusing a variety of road-related data collected in real time, aiming to break through the limitations of traditional path planning and pioneeringly use multi-data fusion analysis technology to judge the real-time road conditions. The improved multi-objective genetic algorithm can also learn and analyze based on historical conditions, and dynamically adjust the weight ratio of road-related data of different categories to ensure the accuracy and rationality of the results.

[0035] Then, if Figure 3 As shown, in the current wet operation area, the road network of the current dust suppression vehicle can be modeled as an undirected graph, expressed as , where v represents the set of all intersection nodes, ,node Represents the water filling point of the dust suppression vehicle, i.e. the starting point, The parking lot for the dust suppression vehicle is the end point. Represents the set of all dust suppression vehicle driving sections. , represents the length of the directed road from intersection i to j. Specifically, the dust suppression vehicle starts from the watering location and ends at the parking lot, passing through all sections that require wet operation to form a dust suppression vehicle driving section. Among them, the maximum watering distance of a single dust suppression vehicle is 20km, so the maximum number of dust suppression vehicles that can operate simultaneously in each wet operation area is limited.

[0036] In addition, the total path cost and road attention corresponding to the current wet operation area are used as the assessment target, that is, the objective function, to establish the MOGAPSO path planning model of the dust suppression vehicle, that is, , where min is the minimum function, F is the objective function, F1 is the total path cost, F2 is the road attention, and T is the transpose.

[0037] The total path cost F1 is the time spent on the driving route. Since the driving sections of the dust suppression vehicle are divided into the vehicle-passing watering sections and the vehicle-passing non-watering sections, the total path cost F1 can be obtained by summing up the time spent by the dust suppression vehicle on the vehicle-passing watering sections and the vehicle-passing non-watering sections, that is, , where T1 represents the total time spent by the dust suppression vehicle on the watered section where the vehicle passes, and T2 represents the total time spent by the dust suppression vehicle on the non-watered section where the vehicle passes.

[0038] Specifically, after obtaining the current driving section of the dust suppression vehicle, the driving section of the dust suppression vehicle can be divided into a water-sprinkling section where the vehicle passes and a non-water-sprinkling section where the vehicle passes according to the wet operation of the current dust suppression vehicle, and the total time spent by the dust suppression vehicle on the water-sprinkling section where the vehicle passes and the non-water-sprinkling section where the vehicle passes can be calculated respectively.

[0039] The calculation process for the road section where vehicles pass through the sprinkler is as follows: obtain the path length of the road section corresponding to the road section where vehicles pass through the sprinkler, then obtain the driving speed of the dust suppression vehicle on the road section where vehicles pass through the sprinkler, and calculate the total time T1 spent by the dust suppression vehicle on the road section where vehicles pass through the sprinkler based on the path length and the driving speed, that is, , where u1 represents the speed of the dust suppression vehicle on the watering section where the vehicle passes, and Bk represents the watering section where the vehicle passes; the calculation process for the non-watering section where the vehicle passes is as shown above. Based on the path length and the driving speed, the total time T2 spent by the dust suppression vehicle on the non-watering section where the vehicle passes can be obtained.

[0040] The road attention degree F2 is the inverse of the attention score. Since the attention elements such as width, grade, basic conditions, and real-time conditions of different roads are different, the degree of attention to the path planned for wet operation will also change accordingly. The higher the attention score of the road, the more wet operation is needed. The scores of the same type of attention indicators can be normalized first, and different indicators can be summed to obtain the final attention score f of the road. Then, the inverse of the attention score f is calculated to obtain the road attention degree F2. The specific formula is as follows: ; ; Among them, f ij Indicates the road The attention score of m is the number of attention elements. In addition, for roads that do not require wet work, f is directly assigned a value of 0.

[0041] Based on the above principle, the objective function corresponding to the path combination consisting of different vehicles passing through the watering section and / or the vehicles passing through the non-watering section can be solved, so as to obtain the transportation path planning result of the dust suppression vehicle. The wet operation path planning in the present invention refers to solving the objective function by using the genetic algorithm to improve the multi-objective particle swarm algorithm (MOGAPSO), which can quickly solve the Pareto frontier under the premise of ensuring the diversity of particle iteration, such as Figure 4 The specific process is as follows: (1) Use the road network nodes to encode the path and randomly generate the path from the starting point of the dust suppression vehicle. To the dust suppression vehicle terminal , a combination of non-repeating and interconnected paths, such as the path combination , collect all path combinations Ai to form the initial population P0; Then calculate the objective function of all path combinations Ai, perform non-dominated sorting, initialize the external archive set Archive, and obtain the initialized individual optimal solution pbest and the global optimal solution gbest.

[0042] (2) Select a particle Ai from the particle population P0 and perform sequential crossover and mutation operations with the individual optimal solution pbest and the global optimal solution gbest, calculate the objective function of the new solution, and compare the non-inferiority relationship between the particles. If the new solution becomes better, update the individual optimal solution pbest and the global optimal solution gbest, and update the particle population to P; if it becomes worse, do not change; if they do not dominate each other, decide whether to accept the new solution according to probability.

[0043] Among them, the specific operations of sequential crossover and mutation are as follows: The sequential crossover method is used to make the parent individuals complete the gene exchange of some chromosomes according to the gene arrangement order, thereby generating new individuals. Randomly select a path from the parent A1, such as Figure 5 As shown, select the fragment at position 3-4 and insert it into the beginning of the child B1. For the elements in A2 that are different from the fragment, arrange them according to the original order of A2 and insert them into the child in sequence, finally generating the child B1. Similarly, generate the child B2; Perform mutation operation on the selected path, randomly select non-starting and ending road network node i as mutation node, find out the node set S adjacent to the mutation node i in the road network, and randomly select a node from S as the mutated node j. Check whether the node m before and the node n after the generated mutation node i are directly connected to the changed node j. If so, replace i with node j to complete the mutation operation process. If not, repeat the steps until the mutation condition is met or the mutation operation is canceled.

[0044] (3) Adopt the adaptive grid method to achieve the expectation of gbest uniform distribution. To meet the objective function, the value of objective function F1 is set as the y-axis, and function F2 is set as the x-axis to form a two-dimensional grid of ngrid×ngrid. The grid width is calculated by the following formula: ; in, and They represent the maximum and minimum values ​​of the objective function of x under target i, di represents the target width of x in the i-th dimension, and ngrid is The number of grid divisions.

[0045] All non-dominated solutions are divided into grids according to the values ​​of objective functions F1 and F2. The number of particles in each grid is calculated, and the probability of selection of the grid is calculated based on the number of particles. The fewer the individuals, the greater the probability of selection. The sum of the normalized selection probabilities of all grids is 1. Using the roulette algorithm, a grid is finally selected. If there is only one particle in the grid, it is directly set as the guiding particle. If there are multiple particles, a particle is randomly selected, set as the guiding particle, and added to the gbest candidate set.

[0046] (4) Each particle in the new population P generated in each iteration must be compared with the particles NP in the Archive for non-inferiority. If Ai in P dominates Xi in NP, then Ai enters the Archive and Xi is eliminated. If the dominance relationship cannot be determined, then Ai also enters the Archive.

[0047] Set NP=P. If NP>P, NP needs to be trimmed. According to the individual crowding density calculated by the adaptive grid method, find the candidate grid with the largest crowding density, randomly delete an individual in the grid, and then update the individual crowding density. Repeat this cycle multiple times until the Archive size meets the requirement.

[0048] In summary, the present invention collects and processes data such as manual inspection, video recognition, and dust-collecting vehicle navigation, matches road information, and analyzes the basic conditions of the road. Combined with the fusion analysis of heavy vehicle GPS and traffic checkpoint flow data, the real-time road conditions are obtained. The road conditions are dynamically assigned, and the model can also dynamically adjust the assignment based on the learning and analysis of historical conditions to ensure the accuracy and rationality of the results.

[0049] In addition, the total path cost and wet operation focus path assignment are used as assessment targets, and the MOGAPSO algorithm is established to solve the optimization path, making the planning scheme more diverse, effectively ensuring the richness and convergence accuracy, and providing a variety of options for the selection of the optimal path for wet operations, thereby improving processing efficiency. This method can not only reduce implementation costs and improve efficiency, but also be widely applicable to various types of sprinkler trucks, effectively reduce the harm to human health caused by road dust and improve the urban environment of residents, providing a more flexible and efficient wet operation planning for urban management.

[0050] Example 2 A wet operation path planning system based on real-time road conditions, using the wet operation path planning method based on real-time road conditions, comprising: Road real-time condition calculation module: collects multi-source data of road basic conditions, road flow conditions and meteorological conditions in real time on each dust suppression vehicle driving section in the current wet operation area for calculation, obtains the corresponding road basic values, road flow values ​​and meteorological values, and performs weighted fusion of the road basic values, road flow values ​​and meteorological values ​​to obtain the real-time road status values ​​corresponding to each dust suppression vehicle driving section; Total path cost calculation module: obtains the total path cost corresponding to the current wet operation area according to the road section traveled by the dust suppression vehicle; Road attention calculation module: obtain the road attention corresponding to the current wet operation area according to the real-time road status value corresponding to each dust suppression vehicle driving section; MOGAPSO path planning model building module: Taking the total path cost and road attention corresponding to the current wet operation area as the assessment target, the MOGAPSO path planning model of the dust suppression vehicle is established; Transport path planning result solving module: solves the MOGAPSO path planning model of the dust suppression vehicle to obtain the transport path planning result of the dust suppression vehicle.

[0051] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. According to the technical essence of the present invention, within the spirit and principles of the present invention, any simple modification, equivalent replacement and improvement made to the above embodiment still falls within the protection scope of the technical solution of the present invention.

Claims

1. A wet operation path planning method based on real-time road conditions, characterized in that: The method comprises the following steps: S1. In the current wet operation area, multi-source data on road basic conditions, road flow conditions and meteorological conditions are collected in real time on each road section where the dust suppression vehicle is traveling, and the corresponding road basic values, road flow values ​​and meteorological values ​​are obtained. The road basic values, road flow values ​​and meteorological values ​​are weightedly fused to obtain the real-time road status values ​​corresponding to each road section where the dust suppression vehicle is traveling; S2. Obtain the total path cost corresponding to the current wet operation area according to the road section traveled by the dust suppression vehicle; S3, obtaining the road attention corresponding to the current wet operation area according to the real-time road status value corresponding to each dust suppression vehicle driving section; S4. Taking the total path cost and road attention corresponding to the current wet operation area as the assessment target, the MOGAPSO path planning model of the dust suppression vehicle is established; S5. Solve the MOGAPSO path planning model of the dust suppression vehicle to obtain the transportation path planning result of the dust suppression vehicle.

2. A wet operation path planning method based on real-time road conditions according to claim 1, characterized in that: The S1 specifically includes the following steps: S11, obtaining the road damage degree and road dust accumulation degree of each road section where the dust suppression vehicle is traveling in the current wet operation area, and obtaining the road basic value by weighted average of the road damage degree and the road dust accumulation degree; S12, obtaining the heavy vehicle flow and road checkpoint flow of each dust suppression vehicle driving section in the current wet operation area, and obtaining the road flow value by weighted average of the heavy vehicle flow and the road checkpoint flow; S13, obtaining meteorological values ​​of each road section where the dust suppression vehicle is traveling in the current wet operation area; S14, weighted fusion of the road basic value, road flow value and meteorological value corresponding to each dust suppression vehicle driving section to obtain the real-time road status value.

3. A wet operation path planning method based on real-time road conditions according to claim 2, characterized in that: In S11, the road damage degree is comprehensively assessed based on manual inspection results, road video recognition results, and sensor vibration recognition results. The road dust accumulation degree is calculated based on the total suspended particulate matter concentration and cruising speed of the road monitored in real time by the dust collection vehicle.

4. A wet operation path planning method based on real-time road conditions according to claim 2, characterized in that: In S12, the heavy vehicle flow rate is obtained by counting the GPS data of the heavy vehicles, and the road checkpoint flow rate is obtained by counting the flow rates of different vehicle types using checkpoint equipment that matches the road.

5. The wet operation path planning method based on real-time road conditions according to claim 2 is characterized in that: In S13, the meteorological value is calculated based on the impact of real-time rainfall on road dust.

6. A wet operation path planning method based on real-time road conditions according to claim 1, characterized in that: In S2, the process of obtaining the total path cost corresponding to the current wet operation area according to the road section traveled by the dust suppression vehicle is as follows: According to the driving section of the dust suppression vehicle, the path lengths of the watered section and the non-watered section are obtained, and according to the driving speed and path length of the dust suppression vehicle on the watered section and the non-watered section, the section time corresponding to the watered section and the non-watered section are obtained respectively. The section time corresponding to the watered section and the non-watered section are summed to obtain the total path cost corresponding to the current wet operation area.

7. The wet operation path planning method based on real-time road conditions according to claim 1 is characterized in that: In S3, the process of obtaining the road attention corresponding to the current wet operation area according to the real-time road status value corresponding to each dust suppression vehicle driving section is as follows: The attention score of the road section where the dust suppression vehicle is traveling is obtained according to the real-time road status value corresponding to the road section where the dust suppression vehicle is traveling, and the inverse of the attention score is used as the road attention degree corresponding to the current wet operation area.

8. The wet operation path planning method based on real-time road conditions according to claim 1 is characterized in that: In S4, the method for establishing the MOGAPSO path planning model of the dust suppression vehicle is: ； Among them, min is the minimum function, F is the objective function, F1 is the total path cost, F2 is the road attention, and T is the transpose.

9. The wet operation path planning method based on real-time road conditions according to claim 1 is characterized in that: In S5, the MOGAPSO path planning model of the dust suppression vehicle is solved to obtain the transportation path planning result of the dust suppression vehicle, including the following steps: The road network nodes are used for path encoding, and non-repeating and interconnected path combinations are randomly generated from the starting point of the dust suppression vehicle to the end point of the dust suppression vehicle. All path combinations are collected to form a particle population P, that is, a path combination is taken as a particle Ai, and the objective function of all particles is calculated to perform non-dominated sorting, thereby initializing the external archive set and obtaining the individual optimal solution pbest and the global optimal solution gbest; Select a particle Ai from the particle population P to perform sequential crossover and mutation operations with the individual optimal solution pbest and the global optimal solution gbest, calculate the objective function of the new particle, and compare the non-inferiority relationship between the two. If the new particle is better, update the individual optimal solution and the global optimal solution; if the new particle becomes inferior, do not change it; if they do not dominate each other, decide whether to accept the new particle according to probability; Adopting the adaptive grid method, the value of objective function F1 is set as the y-axis, and the value of objective function F2 is set as the x-axis to form a two-dimensional grid. All solutions are divided into the grid, the number of particles in each grid is calculated, and the particles in the grid are selected as the guiding particles Xi through the roulette algorithm. Select one particle Ai from the particle population P generated in each iteration in turn to compare with multiple guiding particles in the external archive set. If it is determined that particle Ai in the particle population P dominates the guiding particle Xi among multiple guiding particles, then particle Ai is added to the external archive set and guiding particle Xi is eliminated. If no dominance relationship can be determined, particle Ai is added to the external archive set. In addition, the number of multiple guiding particles in the external archive set is set equal to the number of particle population P. If the number of multiple guiding particles in the external archive set is greater than the number of particle population P, the number of multiple guiding particles in the external archive set is trimmed, an individual in the grid is randomly deleted, and then the individual crowding density is updated. This cycle is repeated until the external archive set meets the requirements and the Pareto front solution is output.

10. A wet operation path planning system based on real-time road conditions, characterized in that: A wet operation path planning method based on real-time road conditions as described in claims 1 to 9 is applied, comprising: Road real-time condition calculation module: collects multi-source data of road basic conditions, road flow conditions and meteorological conditions in real time on each dust suppression vehicle driving section in the current wet operation area for calculation, obtains the corresponding road basic values, road flow values ​​and meteorological values, and performs weighted fusion of the road basic values, road flow values ​​and meteorological values ​​to obtain the real-time road status values ​​corresponding to each dust suppression vehicle driving section; Total path cost calculation module: obtains the total path cost corresponding to the current wet operation area according to the road section traveled by the dust suppression vehicle; Road attention calculation module: obtain the road attention corresponding to the current wet operation area according to the real-time road status value corresponding to each dust suppression vehicle driving section; MOGAPSO path planning model building module: Taking the total path cost and road attention corresponding to the current wet operation area as the assessment target, the MOGAPSO path planning model of the dust suppression vehicle is established; Transport path planning result solving module: solves the MOGAPSO path planning model of the dust suppression vehicle to obtain the transport path planning result of the dust suppression vehicle.

Images