A method and system for planning a cleaning route for a water sprinkler based on road dust accumulation

Abstract

The present invention provides a method and system for planning a cleaning route of a sprinkler truck based on road dust, and relates to the technical field of planning the cleaning route of a sprinkler truck. The method comprises the following steps: S1, obtaining road data of each road section in a target area and working data of a sprinkler truck; S2, screening each road section according to the road data, and dividing it into a first cleaning section and a second cleaning section, wherein the priority of the first cleaning section is higher than the priority of the second cleaning section; S3, with the goal of minimizing exposure to road dust after the sprinkler truck completes the cleaning work of the first cleaning section and the second cleaning section according to the priority, establishing a corresponding dust suppression cleaning route planning model for the sprinkler truck, and generating constraint conditions for the dust suppression cleaning route planning model for the sprinkler truck according to the road data and the working data of the sprinkler truck; S4, solving the dust suppression cleaning route planning model for the sprinkler truck by an adaptive large neighborhood search algorithm, and obtaining the dust suppression cleaning route for the sprinkler truck.

Description

Technical Field

[0001] The present invention relates to the technical field of water sprinkler cleaning route planning, and in particular to a water sprinkler cleaning route planning method and system based on road dust accumulation. Background Art

[0002] In urban environments, in order to effectively suppress dust on urban roads, a road dust cruise monitoring system is gradually being used to monitor road dust, and to guide urban road dust suppression and cleaning operations based on the distribution of road dust.

[0003] Existing sprinkler trucks usually clean urban roads according to fixed routes based on experience, lacking consideration for the overall exposure of road dust in urban areas, which often leads to a certain lag and non-targeted dust suppression on urban roads, and it is also difficult to effectively respond to the real-time changes of road dust. Therefore, how to minimize the exposure of urban road dust while completing fixed cleaning tasks is an urgent problem to be solved. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for planning a sprinkler truck cleaning route based on road dust accumulation. The sprinkler truck cleaning route planning method mainly aims at minimizing the exposure of road dust accumulation, establishes a corresponding sprinkler truck dust suppression cleaning route planning model, and solves the sprinkler truck dust suppression cleaning route planning model through an adaptive large neighborhood search algorithm. The sprinkler truck's dust suppression cleaning route can be flexibly adjusted according to changes in urban road dust accumulation, so that the sprinkler truck can reduce the exposure of urban road dust as much as possible while completing fixed cleaning tasks, thereby improving the control effect of urban road dust.

[0005] In order to solve the above technical problems, the present invention adopts the following solutions:

[0006] A method for planning a cleaning route for a sprinkler truck based on road dust accumulation, the method comprising the following steps:

[0007] S1. At time t1, obtain the road data of each road section in the target area and the working data of the sprinkler truck;

[0008] S2. Screening each road section according to the road data into a first cleaning road section and a second cleaning road section, wherein the priority of the first cleaning road section is higher than that of the second cleaning road section;

[0009] S3, with the goal of minimizing the exposure of road dust after the sprinkler truck completes the cleaning work of the first cleaning section and the second cleaning section according to the priority, establish a corresponding sprinkler truck dust suppression cleaning route planning model, and generate constraint conditions of the sprinkler truck dust suppression cleaning route planning model based on road data and sprinkler truck working data;

[0010] S4. Solve the sprinkler truck dust suppression cleaning route planning model through the adaptive large neighborhood search algorithm to obtain the current optimal solution, that is, the sprinkler truck dust suppression cleaning route at time t1.

[0011] Furthermore, the step S2 includes the following steps:

[0012] S21, extracting the road dust load and road section type at time t1 of each road section from the road data, and extracting the cleaning rules of the sprinkler truck from the working data of the sprinkler truck;

[0013] The road sections are divided into those that are passable by watering trucks and those that are not passable by watering trucks;

[0014] S22, marking the road section where the sprinkler truck can pass according to the sprinkler truck cleaning rule, that is, marking the road section where the sprinkler truck can pass as mandatory sprinkler or non-mandatory sprinkler;

[0015] S23. Determine each road section in the target area according to the road dust load and the road section type: if the road dust load of the road section exceeds the threshold and the road section type is passable by a sprinkler truck, the road section is screened into a first clean road section; if the road dust load of the road section does not exceed the threshold but the road section is marked as mandatory watering, the road section is screened into a first clean road section; if the road dust load of the road section does not exceed the threshold and the road section is marked as not mandatory watering, the road section is screened into a second clean road section.

[0016] Furthermore, the method further comprises the following steps:

[0017] S5. At time t2, after the sprinkler truck has completed all cleaning work according to the sprinkler truck dust suppression cleaning route at time t1, the road dust loads of the first cleaning section and the second cleaning section at time t1 are obtained, the first cleaning section and the second cleaning section at time t1 are updated according to the road dust loads at time t2, the working data of the sprinkler truck is updated according to the sprinkler truck dust suppression cleaning route at time t1, and the process goes to step S3;

[0018] The time t2 is later than the time t1.

[0019] Further, in S1, the road data includes road section geometric features and road dust load, the road section geometric features include road section type, road section length and width, and the road dust load can be obtained by monitoring the corresponding road section with monitoring equipment in the target area;

[0020] The working data of the sprinkler truck includes the water consumption and time consumption of each road section, the water tank capacity of the sprinkler truck, the time consumed by the sprinkler truck to travel from the end point of one road section to the end point of another road section, the sprinkler truck parking lot, the sprinkler truck watering point, and the sprinkler truck watering time.

[0021] Further, in S3, the goal is to minimize the exposure of road dust after the sprinkler truck completes the cleaning work of the first cleaning section and the second cleaning section according to the priority, and the goal is:

[0022] ;

[0023] in, represents the minimization function, represents the set of all sprinkler trucks, represents the set of first cleaning sections, represents the set of second cleaning segments, The set of virtual edges representing the watering points of the sprinkler truck, represents the set of virtual edges of the sprinkler parking lot, Indicates sprinkler truck Is the road section being cleaned? After cleaning section 0-1 variables, Indicates sprinkler truck Start cleaning the road moment, Indicates road segment The road dust load, Indicates road segment Length, Indicates road segment The width of Indicates road segment A 0-1 variable indicating whether it is cleaned. Indicates the maximum working time of the sprinkler truck.

[0024] Furthermore, in S3, the constraints of the sprinkler truck dust suppression cleaning route planning model are generated according to the road data and the sprinkler truck working data, and the constraints are:

[0025] ;

[0026] ;

[0027] ;

[0028] ;

[0029] ;

[0030] ;

[0031] ;

[0032] ;

[0033] ;

[0034] ;

[0035] ;

[0036] ;

[0037] ;

[0038] ;

[0039] ;

[0040] ;

[0041] ;

[0042] ;

[0043] ;

[0044] ;

[0045] ;

[0046] ;

[0047] ;

[0048] ;

[0049] ;

[0050] ;

[0051] ;

[0052] in, Indicates road segment Whether the starting point when cleaning is a 0-1 variable of i, and Respectively represent road sections The two endpoints of and Indicates road segment The two endpoints of , E represents the set of road sections where the sprinkler truck can pass are two-way traffic, A represents the set of road sections where the sprinkler truck can pass are one-way traffic, Indicates that vehicle k has finished cleaning the road section The remaining water after the sprinkler is turned on, Q represents the water tank capacity of the sprinkler, and M is a maximum value. Indicates road section being cleaned by a water truck The amount of water consumed, Indicates road section being cleaned by a water truck The time consumption, It indicates the minimum time required for a vehicle to travel from node i to node j.

[0053] Furthermore, the step S4 includes the following steps:

[0054] S41, randomly generating an initial feasible solution that satisfies the constraint conditions, taking the initial feasible solution as the current feasible solution and the global optimal solution, and setting initial parameters at the same time, wherein the initial parameters include the number of iterations, the initial score and selection weight of each neighborhood search operator, and each neighborhood search operator includes a destruction operator and a repair operator;

[0055] S42, according to the selection weight of each neighborhood search operator, select the destruction operator and the repair operator according to the roulette strategy, destroy and repair the current solution to generate a new feasible solution, and update the number of times the destruction operator and the repair operator are used;

[0056] S43, judging whether to accept the new feasible solution and updating the initial scores of the destruction operator and the repair operator: if the new feasible solution is better than the current optimal solution, then accept the new feasible solution and set the new feasible solution as the current feasible solution and the current optimal solution, and at the same time, update the initial scores of the corresponding destruction operator and the repair operator; if the new feasible solution is not better than the current optimal solution but better than the current feasible solution, then accept the new feasible solution and set the new feasible solution as the current feasible solution, and at the same time, update the initial scores of the corresponding destruction operator and the repair operator; if the new feasible solution is not better than the current feasible solution, then accept the new feasible solution with probability;

[0057] S44, updating the selection weights of the destruction operator and the repair operator: updating the selection weights of the destruction operator and the repair operator every preset number of iterations.

[0058] Further, in S42, in the process of selecting the destruction operator and the repair operator according to the roulette strategy, the destruction operator is selected to destroy the current solution, and the design of the destruction includes: random removal, sequence removal, worst removal, similar removal, idle time removal, and taboo removal.

[0059] Furthermore, in S42, in the process of selecting the destruction operator and the repair operator according to the roulette strategy, the repair operator is selected to repair the current solution after the destruction, and the design of the repair includes: dust exposure greedy repair, dust exposure regret value repair, and idle time greedy repair.

[0060] A system for planning a cleaning route for a sprinkler truck based on road dust accumulation, characterized in that the system applies the method for planning a cleaning route for a sprinkler truck based on road dust accumulation, comprising:

[0061] Data acquisition module: obtain road data of each road section in the target area and working data of the sprinkler truck;

[0062] Road section priority screening module: screening each road section according to the road data, and dividing it into a first cleaning section and a second cleaning section, wherein the priority of the first cleaning section is higher than that of the second cleaning section;

[0063] Sprinkler truck dust suppression cleaning route planning model construction module: With the goal of minimizing the exposure of road dust after the sprinkler truck completes the cleaning work of the first cleaning section and the second cleaning section according to the priority, a corresponding sprinkler truck dust suppression cleaning route planning model is established, and the constraints of the sprinkler truck dust suppression cleaning route planning model are generated based on the road data and the working data of the sprinkler truck;

[0064] Adaptive large neighborhood search algorithm solution module: Adopts the adaptive large neighborhood search algorithm to solve the sprinkler truck dust suppression cleaning route planning model and obtain the current optimal solution.

[0065] Beneficial effects of the present invention:

[0066] The present invention provides a method and system for planning a cleaning route for a sprinkler truck based on road dust accumulation. The method for planning a cleaning route for a sprinkler truck screens each road section based on the road dust load obtained by monitoring a road dust cruise monitoring system in the prior art, and divides the road sections into cleaning sections with different priorities, so that the present invention can flexibly adjust the dust suppression cleaning route of the sprinkler truck according to changes in dust accumulation on urban roads, thereby avoiding the difficulty in timely cleaning of dust accumulation on urban roads due to unreasonable route planning; and, with the goal of minimizing exposure to road dust accumulation, a corresponding dust suppression cleaning route planning model for a sprinkler truck is established, and the dust suppression cleaning route planning model for a sprinkler truck is solved by an adaptive large neighborhood search algorithm, so that the sprinkler truck can reduce exposure to urban road dust as much as possible while completing a fixed cleaning task, thereby improving the control effect of urban road dust. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 Schematic diagram of the flow of the method for planning a cleaning route for a sprinkler truck at time t1 in Example 1 of the present invention.

[0068] Figure 2 Schematic diagram of the flow of the method for planning a cleaning route for a sprinkler truck at time t2 in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0069] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means a limitation on 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 making creative work are within the scope of protection of the present invention.

[0070] 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.

[0071] 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.

[0072] 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.

[0073] 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.

[0074] 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.

[0075] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments:

[0076] Example 1

[0077] In this embodiment, a method for planning a cleaning route for a sprinkler truck based on road dust accumulation is proposed. Figure 1 As shown, the method comprises the following steps:

[0078] S1. At time t1, obtain the road data of each road section in the target area and the working data of the sprinkler truck;

[0079] S2. Screening each road section according to the road data into a first cleaning road section and a second cleaning road section, wherein the priority of the first cleaning road section is higher than that of the second cleaning road section;

[0080] S3, with the goal of minimizing the exposure of road dust after the sprinkler truck completes the cleaning work of the first cleaning section and the second cleaning section according to the priority, establish a corresponding sprinkler truck dust suppression cleaning route planning model, and generate constraint conditions of the sprinkler truck dust suppression cleaning route planning model based on road data and sprinkler truck working data;

[0081] S4. Solve the sprinkler truck dust suppression cleaning route planning model through the adaptive large neighborhood search algorithm to obtain the current optimal solution, that is, the sprinkler truck dust suppression cleaning route at time t1.

[0082] Specifically, the road data mainly includes road section geometric characteristics and road dust load. The road section geometric characteristics can be obtained from the road network structure in the target area. The road network structure includes all road sections, road section widths and lengths, and road section types in the target area. The road section types are divided into those that are passable by sprinkler trucks and those that are not passable by sprinkler trucks. The road dust load is obtained by monitoring the road dust cruise monitoring system in the prior art. The road dust cruise monitoring system can monitor each road section in real time to obtain the corresponding road dust load.

[0083] The working data of the sprinkler truck mainly includes the cleaning rules of the sprinkler truck, the water consumption of the sprinkler truck for cleaning each section, the time consumption, the water tank capacity of the sprinkler truck, the time consumed by the sprinkler truck from one end point of a section to the end point of another section, the sprinkler truck parking lot, the sprinkler truck water filling point, and the sprinkler truck water filling time. Among them, the time consumed by the sprinkler truck from one end point of a section to the end point of another section can be obtained by calling the path planning API of Gaode Map, and the sprinkler truck water filling time can be chosen to be the average value of multiple water fillings of the sprinkler truck.

[0084] Preferably, step S2 includes the following steps:

[0085] S21, extracting the road dust load and road section type at time t1 of each road section from the road data, and extracting the cleaning rules of the sprinkler truck from the working data of the sprinkler truck;

[0086] The road sections are divided into those that are passable by watering trucks and those that are not passable by watering trucks;

[0087] S22, marking the road section where the sprinkler truck can pass according to the sprinkler truck cleaning rule, that is, marking the road section where the sprinkler truck can pass as mandatory sprinkler or non-mandatory sprinkler;

[0088] Specifically, the cleaning rules of the sprinkler truck are determined according to the local sanitation requirements. When the road section type is passable by the sprinkler truck, the road section can be marked as mandatory sprinkler or no mandatory sprinkler according to the local sanitation requirements;

[0089] S23. Determine each road section in the target area according to the road dust load and the road section type: if the road dust load of the road section exceeds the threshold and the road section type is passable by a sprinkler truck, the road section is screened into a first clean road section; if the road dust load of the road section does not exceed the threshold but the road section is marked as mandatory watering, the road section is screened into a first clean road section; if the road dust load of the road section does not exceed the threshold and the road section is marked as not mandatory watering, the road section is screened into a second clean road section.

[0090] In order to enable the present invention to flexibly adjust the dust suppression cleaning route of the sprinkler truck according to the change of dust accumulation on urban roads, in the present invention, each road section is screened according to the road dust load obtained in real time, and the road section is divided into a first cleaning section that the sprinkler truck must clean and a second cleaning section that the sprinkler truck can choose to clean. Specifically, each road section in the target area is judged according to the road dust load and the road section type, and the judgment process is as follows:

[0091] (1) The road sections with dust load exceeding 0.45g / m2 and the road section type being passable by sprinkler trucks are regarded as the sections that must be cleaned by sprinkler trucks, that is, the sections are screened as the first cleaning sections;

[0092] (2) The road sections where the dust load does not exceed 0.45 g / m2 but the road section type is marked as mandatory watering are regarded as the sections that must be cleaned by the sprinkler truck, that is, the sections are screened as the first cleaning sections;

[0093] (3) The road sections with dust load not exceeding 0.45 g / m2 and marked as no mandatory watering section are selected as the sections that can be cleaned by the sprinkler truck, that is, the sections are screened as the second cleaning sections.

[0094] In S3, a corresponding dust suppression cleaning route planning model for a sprinkler truck is established with the goal of minimizing exposure of road dust after the sprinkler truck completes the cleaning work of the first cleaning section and the second cleaning section according to the priority. The goal of the dust suppression cleaning route planning model for the sprinkler truck is:

[0095] ;

[0096] in, represents the minimization function, represents the set of all sprinkler trucks, represents the set of first cleaning sections, represents the set of second cleaning segments, The set of virtual edges representing the watering points of the sprinkler truck, represents the set of virtual edges of the sprinkler parking lot, Indicates sprinkler truck Is the road section being cleaned? After cleaning section 0-1 variables, Indicates sprinkler truck Start cleaning the road moment, Indicates road segment The road dust load, Indicates road segment Length, Indicates road segment The width of Indicates road segment A 0-1 variable indicating whether it is cleaned. Indicates the maximum working time of the sprinkler truck.

[0097] The constraints of the sprinkler truck dust suppression cleaning route planning model are specifically:

[0098] ;

[0099] ;

[0100] ;

[0101] ;

[0102] ;

[0103] ;

[0104] ;

[0105] ;

[0106] ;

[0107] ;

[0108] ;

[0109] ;

[0110] ;

[0111] ;

[0112] ;

[0113] ;

[0114] ;

[0115] ;

[0116] ;

[0117] ;

[0118] ;

[0119] ;

[0120] ;

[0121] ;

[0122] ;

[0123] ;

[0124] ;

[0125] in, Indicates road segment Whether the starting point when cleaning is a 0-1 variable of i, and Respectively represent road sections The two endpoints of and Indicates road segment The two endpoints of , E represents the set of road sections where the sprinkler truck can pass are two-way traffic, A represents the set of road sections where the sprinkler truck can pass are one-way traffic, Indicates that vehicle k has finished cleaning the road section The remaining water after the sprinkler is turned on, Q represents the water tank capacity of the sprinkler, and M is a maximum value. Indicates road section being cleaned by a water truck The amount of water consumed, Indicates road section being cleaned by a water truck The time consumption, It indicates the minimum time required for a vehicle to travel from node i to node j.

[0126] Then, the dust suppression cleaning route planning model of the sprinkler truck is solved based on the adaptive large neighborhood search algorithm. The specific steps of the adaptive large neighborhood search algorithm are as follows:

[0127] S41, randomly generating an initial feasible solution that satisfies the constraint conditions, taking the initial feasible solution as the current feasible solution and the global optimal solution, and setting initial parameters at the same time, wherein the initial parameters include the number of iterations, the initial score and selection weight of each neighborhood search operator, and each neighborhood search operator includes a destruction operator and a repair operator;

[0128] Specifically, when setting the initial parameters, the maximum number of road sections to be removed when using the destruction operator For 20% of the sprinkler sections in the current solution, set the number of iterations to 3000 and set the initial score of each operator and select weights , and the initial score is 0, select weight is 1, the initial temperature ,in, Indicates the shortest travel time between the two road nodes that are farthest apart in the area;

[0129] S42, based on the selection weight of each neighborhood search operator , select the destruction operator and repair operator according to the roulette strategy, destroy and repair the current solution to generate a new feasible solution , and update the usage count of the destruction operator and the repair operator;

[0130] S43, new solution acceptance and operator score update:

[0131] If the new feasible solution Better than the current optimal solution, then accept the new feasible solution And the new feasible solution Set as the current feasible solution and the current optimal solution, and at the same time, generate a new feasible solution The damage counter and repair counter of the NPC are increased by 0.5 points;

[0132] If the new feasible solution If it is not better than the current optimal solution but better than the current feasible solution, then accept the new feasible solution. And the new feasible solution Set as the current feasible solution, and at the same time, generate a new feasible solution The damage counter and repair counter of the NPC are increased by 0.2 points;

[0133] If the new feasible solution If it is not better than the current feasible solution S, then the new feasible solution will be generated without changing it. The scores of the destruction operator and the repair operator are expressed as Accept new feasible solutions ,in, represents the objective function of the newly generated feasible solution, represents the objective function of the current solution, T represents the current temperature, ,in, is the current iteration number;

[0134] S44, updating the selection weights of the destruction operator and the repair operator: updating the selection weights of the destruction operator and the repair operator every preset number of iterations. Specifically, updating the selection weights of the destruction operator and the repair operator every 200 iterations. Updated to ,in, is the original weight of the operator, is the score of operator i, is the number of times operator i is used; and, after the calculation is completed, and All updated to 0;

[0135] S45. Determine whether the iteration is terminated: repeat steps S42 to S44 until the number of iterations is reached, return to the global optimal solution and exit the program.

[0136] Preferably, in S42, in the process of selecting the destruction operator and the repair operator according to the roulette strategy, the destruction operator is selected to destroy the current solution, and the design of the destruction includes: random removal, sequence removal, worst removal, similar removal, idle time removal, and taboo removal.

[0137] The process of random removal is: random removal There are currently several road sections being cleaned by sprinkler trucks.

[0138] The process of removing the sequence is as follows: removing a random road section in the current solution that is cleaned by a sprinkler truck using the same box of water.

[0139] The worst removal process is: The road segment that increases the objective function value the least after removal is removed from the current solution.

[0140] The similar removal process is as follows: first randomly select a seed section , then remove the The most similar road section With road section The similarity calculation formula is:

[0141] ;

[0142] ;

[0143] in, It indicates the difference in dust load between the section with the largest dust accumulation and the section with the smallest dust accumulation in the area. Indicates the area difference between the largest section and the smallest section in the region. Indicates the shortest travel time between the two road nodes that are farthest apart in the area.

[0144] The process of removing the idle time is as follows: Road sections removed.

[0145] The process of removing taboos is to remove the road sections that have not been removed in the past 30 iterations.

[0146] Preferably, in S42, in the process of selecting the destruction operator and the repair operator according to the roulette strategy, the repair operator is selected to repair the current solution after the destruction, and the design of the repair includes: dust exposure greedy repair, dust exposure regret value repair, and idle time greedy repair.

[0147] The process of greedy repair of dust exposure is as follows: when repairing, the first clean road segment is first added to the damaged solution under the premise of satisfying the constraint conditions, and each road segment is added to the position that can minimize the objective function. Then, the remaining second clean road segments that are not in the solution are added to the damaged solution under the premise of satisfying the constraint conditions, and each road segment is added to the position that can minimize the objective function.

[0148] The process of repairing the regret value of dust exposure is as follows: when repairing, first calculate the regret value of each first clean section when it is added to the suboptimal position of the solution after destruction compared to the optimal position of the solution after destruction, then add the first clean section with the largest regret value to the optimal position of the solution after destruction, and repeat the process until all the first clean sections are added to the solution. Then calculate the regret value of each second clean section when it is added to the suboptimal position of the solution after destruction compared to the optimal position of the solution after destruction, then add the second clean section with the largest regret value to the optimal position of the solution after destruction, and repeat the process until it is difficult to add the second clean section to the solution under the premise of satisfying the constraint conditions.

[0149] The process of greedy repair of idle time is as follows: during repair, the first clean road section is first added to the damaged solution on the premise of satisfying the constraint conditions, and each road section is added to the position that can shorten the idle time of the sprinkler truck. Then, the remaining second clean road sections that are not in the solution are added to the damaged solution on the premise of satisfying the constraint conditions, and each road section is added to the position that can shorten the idle time of the sprinkler truck.

[0150] To sum up, in this embodiment, the present invention proposes a method for planning a sprinkler truck cleaning route based on road dust. The method mainly screens each road section based on the road dust load obtained by monitoring the road dust cruise monitoring system, and reasonably plans the sprinkler truck based on the road dust. With the goal of minimizing road dust exposure, a corresponding sprinkler truck dust suppression cleaning route planning model is established. The sprinkler truck dust suppression cleaning route planning model is solved by an adaptive large neighborhood search algorithm, so that the sprinkler truck can complete the fixed cleaning task while minimizing the exposure of urban road dust and improve the control effect of urban road dust.

[0151] Example 2

[0152] On the basis of Example 1, Figure 2 As shown, the method for planning a cleaning route of a sprinkler truck based on road dust accumulation proposed by the present invention also includes the following steps:

[0153] S5. At time t2, after the sprinkler truck has completed all cleaning work according to the sprinkler truck dust suppression cleaning route at time t1, the road dust load of the first cleaning section and the second cleaning section at time t1 is obtained, the first cleaning section and the second cleaning section at time t1 are updated according to the road dust load at time t2, the working data of the sprinkler truck is updated according to the sprinkler truck dust suppression cleaning route at time t1, and go to step S3, wherein the time t2 is later than the time t1.

[0154] Since the present invention monitors and updates the road dust load of each road section in the target area in real time based on fixed environmental monitoring equipment and mobile environmental monitoring equipment in the city, the present invention can obtain the change of road dust load in real time, thereby flexibly adjusting the dust suppression and cleaning route of the sprinkler truck to avoid the difficulty in timely cleaning of urban road dust due to unreasonable route planning.

[0155] Specifically, the dust suppression cleaning route of the sprinkler truck is adjusted at regular intervals, and at time t1, the road dust load of each road section is obtained, and then the road section is screened into a first cleaning section and a second cleaning section according to the road dust load at time t1, and the dust suppression cleaning route of the sprinkler truck is planned based on the road dust load on the first cleaning section and the second cleaning section, and then the sprinkler truck is made to perform cleaning work according to the dust suppression cleaning route of the sprinkler truck at time t1, and then, at time t2, after the sprinkler truck has completed all cleaning work according to the dust suppression cleaning route of the sprinkler truck at time t1, the road dust load of each road section can be obtained, that is, the road dust load of the first cleaning section and the second cleaning section is obtained, and the first cleaning section and the second cleaning section at time t1 are updated according to the road dust load at time t2, and the updating process is:

[0156] (1) The first cleaning section at time t1 is updated: if the first cleaning section has been cleaned and the road dust load at time t2 drops below a preset threshold, the first cleaning section is updated to the second cleaning section; if the first cleaning section has not been cleaned but the road dust load at time t2 drops below a preset threshold and the section type is no forced watering, the first cleaning section is updated to the second cleaning section; the first cleaning section at other times t1 remains the first cleaning section;

[0157] (2) Updating the second clean section at time t1: If the road dust load at time t2 corresponding to the second clean section drops below a preset threshold, the second clean section remains as the second clean section; if the road dust load at time t2 corresponding to the second clean section rises above the preset threshold, the second clean section is updated to the first clean section.

[0158] Moreover, in step S5, the working data of the sprinkler truck can also be updated according to the dust suppression and cleaning route of the sprinkler truck at time t1. It is mainly based on the dust suppression and cleaning route of the sprinkler truck at time t1 and the GPS track data of the sprinkler truck to infer the position, remaining water volume and maximum working time of the sprinkler truck at time t2. This inference method is a prior art means and will not be repeated here.

[0159] At time t2, based on the sprinkler truck dust suppression cleaning route and change values ​​at time t1, the updated first cleaning section, the second cleaning section and the maximum working time of the sprinkler truck can be obtained. The updated data is directly substituted into the sprinkler truck dust suppression cleaning route planning model, and the sprinkler truck dust suppression cleaning route planning model is solved using an adaptive large neighborhood search algorithm to obtain the sprinkler truck dust suppression cleaning route at time t2.

[0160] In summary, the present invention can flexibly adjust the dust suppression cleaning route of the sprinkler truck based on the road dust through the model and algorithm, so that the urban dust suppression cleaning operation can effectively adapt to the changes in the distribution of road dust.

[0161] 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 method for planning a cleaning route for a sprinkler truck based on road dust, characterized in that: The method for planning the cleaning route of a water sprinkler comprises the following steps: S1. At time t1, obtain the road data of each road section in the target area and the working data of the sprinkler truck; S2. Screening each road section according to the road data into a first cleaning road section and a second cleaning road section, wherein the priority of the first cleaning road section is higher than that of the second cleaning road section; The step S2 includes the following steps: S21, extracting the road dust load and road section type at time t1 of each road section from the road data, and extracting the cleaning rules of the sprinkler truck from the working data of the sprinkler truck; The road sections are divided into those that are passable by watering trucks and those that are not passable by watering trucks; S22, marking the road section where the sprinkler truck can pass according to the sprinkler truck cleaning rule, that is, marking the road section where the sprinkler truck can pass as mandatory sprinkler or non-mandatory sprinkler; S23, judging each road section in the target area according to the road dust load and the road section type: if the road dust load of the road section exceeds the threshold and the road section type is passable by a sprinkler truck, the road section is screened into a first clean road section; if the road dust load of the road section does not exceed the threshold but the road section is marked as mandatory sprinkler, the road section is screened into a first clean road section; if the road dust load of the road section does not exceed the threshold and the road section is marked as not mandatory sprinkler, the road section is screened into a second clean road section; S3, with the goal of minimizing the exposure of road dust after the sprinkler truck completes the cleaning work of the first cleaning section and the second cleaning section according to the priority, establish a corresponding sprinkler truck dust suppression cleaning route planning model, and generate constraint conditions of the sprinkler truck dust suppression cleaning route planning model based on road data and sprinkler truck working data; S4. Solve the sprinkler truck dust suppression cleaning route planning model through the adaptive large neighborhood search algorithm to obtain the current optimal solution, that is, the sprinkler truck dust suppression cleaning route at time t1.

2. A method for planning a cleaning route for a sprinkler truck based on road dust according to claim 1, characterized in that: The method further comprises the following steps: S5. At time t2, after the sprinkler truck has completed all cleaning work according to the sprinkler truck dust suppression cleaning route at time t1, the road dust loads of the first cleaning section and the second cleaning section at time t1 are obtained, the first cleaning section and the second cleaning section at time t1 are updated according to the road dust loads at time t2, the working data of the sprinkler truck is updated according to the sprinkler truck dust suppression cleaning route at time t1, and the process goes to step S3; The time t2 is later than the time t1.

3. A method for planning a cleaning route for a sprinkler truck based on road dust according to claim 1, characterized in that: In S1, the road data includes road section geometric features and road dust load, wherein the road section geometric features include road section type, length and width of the road section, and the road dust load can be obtained by monitoring the corresponding road section with monitoring equipment in the target area; The working data of the sprinkler truck includes the water consumption and time consumption of each road section, the water tank capacity of the sprinkler truck, the time consumed by the sprinkler truck to travel from the end point of one road section to the end point of another road section, the sprinkler truck parking lot, the sprinkler truck watering point, and the sprinkler truck watering time.

4. A method for planning a cleaning route for a sprinkler truck based on road dust according to claim 1, characterized in that: In S3, the goal is to minimize the exposure of road dust after the sprinkler truck completes the cleaning work of the first cleaning section and the second cleaning section according to the priority. The goal is: Among them, Min represents the minimization function, K represents the set of all sprinkler trucks, and L R represents the set of the first cleaning sections, L nR represents the set of the second cleaning sections, L w The set of virtual edges representing the watering point of the sprinkler truck, L d represents the set of virtual edges of the sprinkler parking lot, Indicates whether the sprinkler k has finished cleaning the road section l m Post-cleaning section n 0-1 variables, Indicates that the sprinkler k starts cleaning the road section l n moment, dust n Indicates road segment l n Road dust load, d n Indicates road segment l n The length, r n Indicates road segment l n Width, Z n Indicates road segment l n 0-1 variable indicating whether to be cleaned, T max Indicates the maximum working time of the sprinkler truck.

5. A method for planning a cleaning route for a sprinkler truck based on road dust according to claim 4, characterized in that: In S3, the constraints of the sprinkler truck dust suppression cleaning route planning model are generated according to the road data and the sprinkler truck working data. The constraints are: in, Indicates road segment l n Whether the starting point when being cleaned is a 0-1 variable of i, n1 and n2 represent the road section l respectively n The two endpoints, m1 and m2 represent the road segment l m The two endpoints of , E represents the set of road sections where the sprinkler truck can pass are two-way traffic, A represents the set of road sections where the sprinkler truck can pass are one-way traffic, Indicates that vehicle k has cleaned section l n The remaining water after the sprinkler is removed, Q represents the water tank capacity of the sprinkler, M is a maximum value, q n Indicates the road section cleaned by the sprinkler truck l n Water consumption, t m Indicates the road section cleaned by the sprinkler truck l m The time consumption, trav ij It represents the minimum time required for a vehicle to travel from node i to node j, L k Indicates that the sprinkler k is Start cleaning the road section at that time.

6. A method for planning a cleaning route for a sprinkler truck based on road dust according to claim 1, characterized in that: The step S4 includes the following steps: S41, randomly generating an initial feasible solution that satisfies the constraint conditions, taking the initial feasible solution as the current feasible solution and the global optimal solution, and setting initial parameters at the same time, wherein the initial parameters include the number of iterations, the initial score and selection weight of each neighborhood search operator, and each neighborhood search operator includes a destruction operator and a repair operator; S42, according to the selection weight of each neighborhood search operator, select the destruction operator and the repair operator according to the roulette strategy, destroy and repair the current solution to generate a new feasible solution, and update the number of times the destruction operator and the repair operator are used; S43, judging whether to accept the new feasible solution and updating the initial scores of the destruction operator and the repair operator: if the new feasible solution is better than the current optimal solution, then accept the new feasible solution and set the new feasible solution as the current feasible solution and the current optimal solution, and at the same time, update the initial scores of the corresponding destruction operator and the repair operator; if the new feasible solution is not better than the current optimal solution but better than the current feasible solution, then accept the new feasible solution and set the new feasible solution as the current feasible solution, and at the same time, update the initial scores of the corresponding destruction operator and the repair operator; if the new feasible solution is not better than the current feasible solution, then accept the new feasible solution with probability; S44, updating the selection weights of the destruction operator and the repair operator: updating the selection weights of the destruction operator and the repair operator every preset number of iterations.

7. A method for planning a cleaning route for a sprinkler truck based on road dust according to claim 6, characterized in that: In S42, in the process of selecting the destruction operator and the repair operator according to the roulette strategy, the destruction operator is selected to destroy the current solution, and the destruction design includes: random removal, sequence removal, worst removal, similar removal, idle time removal, and taboo removal.

8. A method for planning a cleaning route for a sprinkler truck based on road dust according to claim 6, characterized in that: In S42, in the process of selecting the destruction operator and the repair operator according to the roulette strategy, the repair operator is selected to repair the current solution after the destruction, and the design of the repair includes: dust exposure greedy repair, dust exposure regret value repair, and idle time greedy repair.

9. A sprinkler cleaning route planning system based on road dust, characterized in that: A method for planning a cleaning route for a sprinkler truck based on road dust accumulation as described in any one of claims 1 to 8 is applied, comprising: Data collection module: obtain the road data of each section in the target area and the working data of the sprinkler truck; Road section priority screening module: screening each road section according to the road data, and dividing it into a first cleaning section and a second cleaning section, wherein the priority of the first cleaning section is higher than that of the second cleaning section; Sprinkler truck dust suppression cleaning route planning model construction module: With the goal of minimizing the exposure of road dust after the sprinkler truck completes the cleaning work of the first cleaning section and the second cleaning section according to the priority, a corresponding sprinkler truck dust suppression cleaning route planning model is established, and the constraints of the sprinkler truck dust suppression cleaning route planning model are generated based on the road data and the working data of the sprinkler truck; Adaptive large neighborhood search algorithm solution module: Adopts the adaptive large neighborhood search algorithm to solve the sprinkler truck dust suppression cleaning route planning model and obtain the current optimal solution.

Images