Sprinkling flow prediction method and device for sanitation vehicle operation and storage medium

Abstract

The invention discloses a sprinkling flow prediction method and device for sanitation vehicle operation and a storage medium, and the method comprises the steps: obtaining the related data and historical weather data of a to-be-operated road segment before the sanitation vehicle operation; the road dust prediction model calculates an initial road dust prediction amount F0, an initial watering prediction flow Q0 and an initial operation total water consumption prediction amount W0 according to the acquired data; the environmental sanitation vehicle carries the initial operation total water consumption prediction amount W0, and operation is started on the designated road section with the initial water sprinkling prediction flow Q0; in the working period of the sanitation vehicle, real-time road data, real-time vehicle data and real-time weather data are collected, prediction is carried out by utilizing the road dust prediction model based on the obtained real-time data, judgment is carried out according to detected dust data in air, the road dust prediction model is continuously optimized and updated, and the road dust prediction efficiency is improved. And the sanitation vehicle completes all road operations of the specified road section. The method is accurate in prediction result and high in intelligent degree.

Description

Technical Field

[0001] The present invention belongs to the technical field of dust reduction of sanitation vehicles, and in particular relates to a method, a device and a storage medium for predicting watering flow rate used in sanitation vehicle operations. Background Art

[0002] In current sanitation operations, sprinkling water to suppress dust is the main means to reduce dust pollution caused by cleaning. The current working mode of sprinkling water to suppress dust is fixed-flow dust suppression: by programming the vehicle controller, the dust suppression flow rate is pre-set, and the start and end of sprinkling water is controlled manually; at the same time, the vehicle operator is required to manually control whether to start and the frequency of sprinkling water according to weather conditions.

[0003] The existing watering mode is constrained by manual operation, and still needs to be further improved and perfected in terms of timeliness of dust removal and energy saving. The dust removal system needs manual participation to be turned on and off, and the degree of automation is low; the flow of the dust removal system cannot be adjusted in time according to environmental conditions, the dust removal effect is poor, and the energy and water consumption are high. The vehicle cannot estimate the amount of water to be sprinkled in advance, and cannot add water reasonably, resulting in insufficient water carried, or too much water, which increases the energy consumption of the whole vehicle. Summary of the invention

[0004] In order to solve the above technical problems, the present invention proposes a method, a device and a storage medium for predicting the watering flow rate of a sanitation vehicle operation.

[0005] In order to achieve the above object, the technical solution of the present invention is as follows:

[0006] In a first aspect, the present invention discloses a method for predicting watering flow rate for sanitation vehicle operation, comprising:

[0007] Step S1: Before the sanitation vehicle operates, obtain relevant data of the road section to be operated and weather data of the road section to be operated from the last operation to the current time;

[0008] Step S2: the road dust prediction model calculates according to the data obtained in step S1 to obtain an initial road dust prediction amount F0, an initial watering prediction flow rate Q0, and an initial total operation water consumption prediction amount W0;

[0009] Step S3: The sanitation vehicle carries the initial total water consumption forecast W0 and starts working on the designated road section with the initial predicted watering flow Q0;

[0010] Step S4: During the operation of the sanitation vehicle, real-time road data, real-time vehicle data and real-time weather data are collected;

[0011] The road dust prediction model calculates the road dust prediction amount F at the target position i on the road ahead based on the real-time data obtained. i , Sprinkler predicted flow rate Qi And the time T consumed to reach the target position i i ;

[0012] Step S5: The sanitation vehicle arrives at the target location and predicts the flow rate Q by sprinkling water i Start working on the designated road section;

[0013] The dust data in the air is tested. If the detected dust content is greater than the dust threshold, the sanitation vehicle increases the water flow until the detected dust content is less than or equal to the dust threshold;

[0014] If the difference between the watering flow rate and the initial watering predicted flow rate Q0 is greater than △Q, and the duration exceeds the time threshold, the sanitation vehicle gradually reduces the watering flow rate until the detected dust content is equal to the dust threshold. The watering flow rate at this time is the optimal watering flow rate under the corresponding dust distribution state, and the road dust prediction model is updated;

[0015] Step S6: Repeat steps S4 to S5 until the sanitation vehicle completes all road operations on the designated road section and further improves the road dust prediction model.

[0016] Based on the above technical solution, the following improvements can be made:

[0017] As a preferred solution, in step S1, the relevant data of the road section to be operated includes one or more of the following data: the time T0 consumed for the last cleaning of the road section, road classification, surrounding environment classification, and traffic flow estimation data;

[0018] The weather data of the road section to be operated from the last operation to the current time includes one or more of the following data: rainfall, temperature, humidity, and wind speed.

[0019] As a preferred solution, step S4 includes:

[0020] Step S4.1: During the operation of the sanitation vehicle, real-time road data, real-time vehicle data and real-time weather data are collected;

[0021] Step S4.2: The road dust prediction model predicts the road dust prediction amount F at the target position i on the road ahead of the vehicle based on the acquired real-time road data i ;

[0022] And further based on the road dust prediction F i And real-time weather data, calculate the predicted watering flow Q at the target location i i ;

[0023] The time T required to reach the target location i is calculated based on the distance between the target location i and the current location and the real-time vehicle data. i .

[0024] As a preferred solution, in step S4.1,

[0025] Real-time road data includes: images of the road ahead;

[0026] Real-time vehicle data includes one or more of the following data: the speed of the sanitation vehicle, the speed and angle of the sweeping disc;

[0027] Real-time weather data includes one or more of the following data: wind speed, wind direction, and humidity.

[0028] In a second aspect, the present invention further discloses a watering flow prediction device for sanitation vehicle operation, comprising:

[0029] The initial data acquisition module is used to obtain relevant data of the road section to be operated and the weather data of the road section to be operated from the last operation to the current time before the sanitation vehicle operates;

[0030] The initial flow calculation module is used for the road dust prediction model to calculate the initial road dust prediction amount F0, the initial watering prediction flow Q0 and the initial total operation water consumption prediction W0 according to the data obtained by the initial data acquisition module;

[0031] The sanitation vehicle initial operation module is used for the sanitation vehicle to carry the initial total water consumption forecast W0 and start the operation on the designated road section with the initial watering forecast flow Q0;

[0032] The prediction module is used to collect real-time road data, real-time vehicle data and real-time weather data during the operation of the sanitation vehicle;

[0033] The road dust prediction model calculates the road dust prediction amount F at the target position i on the road ahead based on the real-time data obtained. i , Sprinkler predicted flow rate Q i And the time T consumed to reach the target position i i ;

[0034] The real-time operation module of the sanitation vehicle is used to predict the flow rate Q by sprinkling water when the sanitation vehicle reaches the target location. i Start working on the designated road section;

[0035] The dust data in the air is tested. If the detected dust content is greater than the dust threshold, the sanitation vehicle increases the water flow until the detected dust content is less than or equal to the dust threshold;

[0036] If the difference between the watering flow rate and the initial watering predicted flow rate Q0 is greater than △Q, and the duration exceeds the time threshold, the sanitation vehicle gradually reduces the watering flow rate until the detected dust content is equal to the dust threshold. The watering flow rate at this time is the optimal watering flow rate under the corresponding dust distribution state, and the road dust prediction model is updated;

[0037] The repeated execution module is used to repeatedly execute the methods in the prediction module and the sanitation vehicle real-time operation module until the sanitation vehicle completes all road operations on the designated road section and further improves the road dust prediction model.

[0038] As a preferred solution, in the initial data acquisition module, the relevant data of the road section to be operated includes one or more of the following data: the time T0 consumed in the last cleaning of the road section, road classification, surrounding environment classification, and traffic flow estimation data;

[0039] The weather data of the road section to be operated from the last operation to the current time includes one or more of the following data: rainfall, temperature, humidity, and wind speed.

[0040] As a preferred solution, the prediction module includes:

[0041] A data collection unit is used to collect real-time road data, real-time vehicle data and real-time weather data during the operation of the sanitation vehicle;

[0042] The prediction unit is used for the road dust prediction model to predict the road dust prediction amount F at the target position i on the road ahead of the vehicle based on the acquired real-time road data. i ;

[0043] And further based on the road dust prediction F i And real-time weather data, calculate the predicted watering flow Q at the target location i i ;

[0044] The time T required to reach the target location i is calculated based on the distance between the target location i and the current location and the real-time vehicle data. i .

[0045] As a preferred solution, in the data acquisition unit,

[0046] Real-time road data includes: images of the road ahead;

[0047] Real-time vehicle data includes one or more of the following data: the speed of the sanitation vehicle, the speed and angle of the sweeping disc;

[0048] Real-time weather data includes one or more of the following data: wind speed, wind direction, and humidity.

[0049] In a third aspect, the present invention further discloses a storage medium storing one or more computer-readable programs, wherein the one or more programs include instructions suitable for being loaded by a memory and executing any of the above-mentioned sprinkler flow prediction methods.

[0050] The present invention discloses a method, device and storage medium for predicting watering flow rate of sanitation vehicle operation, which has the following beneficial effects:

[0051] First, the present invention analyzes the relevant data of the working section and the historical weather data through the road dust prediction model, predicts the road dust distribution in advance, determines the initial watering prediction flow Q0 and the initial total water consumption prediction W0, realizes the accurate prediction of the water volume carried by the vehicle, and achieves the purpose of energy saving and high efficiency.

[0052] Secondly, during the operation of the sanitation vehicle, the present invention collects real-time road data, monitors the road surface, and predicts in advance the required watering flow rate for uncleaned locations, thereby achieving early suppression of dust from the operation and avoiding the generation of dust from the source.

[0053] Third, during the operation of the sanitation vehicle, the present invention realizes rapid adjustment of the prediction results of the road dust prediction model through analysis and processing of real-time data, thereby doubly ensuring the final dust reduction effect.

[0054] Fourth, the road dust prediction model of the present invention can continuously perform self-learning through real-time data to continuously improve its prediction accuracy.

[0055] Fifth, the present invention has a high degree of intelligence. During the operation of the sanitation vehicle, there is no need for manual operation of the on-board sprinkler control device, which reduces the workload of personnel and effectively reduces the project operation cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0057] Figure 1 A flow chart of a method for predicting watering flow provided in an embodiment of the present invention.

[0058] Figure 2 The watering flow prediction method provided by the embodiment of the present invention involves a system block diagram.

[0059] Figure 3 The watering flow prediction method provided in the embodiment of the present invention involves a structural diagram of the system.

[0060] Among them: 1-vehicle-mounted camera, 2-dust monitoring device, 3-meteorological monitoring equipment, 4-VCU, 5-TBOX, 6-cloud processor, 7-vehicle-mounted sprinkler control device. DETAILED DESCRIPTION

[0061] The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0062] 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, not all of the embodiments. 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.

[0063] The expression of “comprising” an element is an “open” expression, which merely means that a corresponding component or step exists, and should not be interpreted as excluding additional components or steps.

[0064] In order to achieve the purpose of the present invention, some embodiments of the method, device and storage medium for predicting the watering flow rate of sanitation vehicle operation are as follows: Figure 1 As shown in FIG. 1 , the sprinkler flow prediction method includes:

[0065] Step S1: Before the sanitation vehicle operates, obtain relevant data of the road section to be operated and weather data of the road section to be operated from the last operation to the current time;

[0066] The relevant data of the road section to be operated includes one or more of the following data: the time T0 consumed for the last cleaning of the road section, road classification, surrounding environment classification, and traffic flow estimation data;

[0067] The weather data of the road section to be operated from the last operation to the current time includes one or more of the following data: rainfall, temperature, humidity, wind speed;

[0068] Step S2: the road dust prediction model calculates according to the data obtained in step S1 to obtain an initial road dust prediction amount F0, an initial watering prediction flow rate Q0, and an initial total operation water consumption prediction amount W0;

[0069] Step S3: The sanitation vehicle carries the initial total water consumption forecast W0 and starts working on the designated road section with the initial predicted watering flow Q0;

[0070] Step S4: During the operation of the sanitation vehicle, real-time road data, real-time vehicle data and real-time weather data are collected;

[0071] The road dust prediction model calculates the road dust prediction amount F at the target position i on the road ahead based on the real-time data obtained. i , Sprinkler predicted flow rate Q i And the time T consumed to reach the target position i i ;

[0072] Step S5: The sanitation vehicle arrives at the target location and predicts the flow rate Q by sprinkling water i Start working on the designated road section;

[0073] The dust data in the air is tested. If the detected dust content is greater than the dust threshold, the sanitation vehicle increases the water flow until the detected dust content is less than or equal to the dust threshold;

[0074] If the difference between the watering flow rate and the initial watering predicted flow rate Q0 is greater than △Q, and the duration exceeds the time threshold, the sanitation vehicle gradually reduces the watering flow rate until the detected dust content is equal to the dust threshold. The watering flow rate at this time is the optimal watering flow rate under the corresponding dust distribution state, and the road dust prediction model is updated;

[0075] Step S6: Repeat steps S4 to S5 until the sanitation vehicle completes all road operations on the designated road section and further improves the road dust prediction model.

[0076] Further, step S4 includes:

[0077] Step S4.1: During the operation of the sanitation vehicle, real-time road data, real-time vehicle data and real-time weather data are collected;

[0078] Real-time road data includes: images of the road ahead;

[0079] Real-time vehicle data includes one or more of the following data: the speed of the sanitation vehicle, the speed and angle of the sweeping disc;

[0080] Real-time weather data includes one or more of the following: wind speed, wind direction, humidity;

[0081] Step S4.2: The road dust prediction model predicts the road dust prediction amount F at the target position i on the road ahead of the vehicle based on the acquired real-time road data i ;

[0082] And further based on the road dust prediction F i And real-time weather data, calculate the predicted watering flow Q at the target location i i ;

[0083] The time T required to reach the target location i is calculated based on the distance between the target location i and the current location and the real-time vehicle data. i .

[0084] It is worth noting that Figure 2-3 As shown, the road dust prediction model can be stored in the cloud processor 6. Step S1 can obtain relevant data of the road section to be operated from the database, and obtain weather data of the road section to be operated from the last operation to the current time from the public data.

[0085] During the operation of the sanitation vehicle, real-time road data can be, but is not limited to, collected by using the vehicle-mounted camera 1 to collect images of the road ahead; real-time vehicle data can be, but is not limited to, collected through the vehicle controller VCU4; real-time weather data can be, but is not limited to, collected through the meteorological monitoring equipment 3.

[0086] In actual application, step S4 uploads the collected real-time data to the cloud processor 6 via T-BOX5, and the road dust prediction model performs prediction. After obtaining the prediction result, it is transmitted to the vehicle controller VCU4 via T-BOX5.

[0087] After reaching the target position i, the vehicle controller VCU4 outputs the prediction result to the vehicle-mounted watering control device 7 for watering to prevent the generation of dust during cleaning, and continuously detects the dust data in the air and uploads it to the cloud processor 6 through T-BOX5. If the detected dust content is greater than the dust threshold, the road dust prediction model increases the watering flow rate for similar scenes until the detected dust content is less than or equal to the dust threshold;

[0088] If the difference between the watering flow rate and the initial predicted watering flow rate Q0 is greater than △Q, and the duration exceeds the time threshold, the sanitation vehicle gradually reduces the watering flow rate until the detected dust content is equal to the dust threshold. The watering flow rate at this time is the optimal watering flow rate under the corresponding dust distribution state, and the road dust prediction model is updated.

[0089] The dust data in the air can be detected by, but is not limited to, using a dust monitoring device 2 .

[0090] During the operation of the sanitation vehicle, the cloud processor 6 calculates the real-time road dust prediction F i Comparison with the initial road dust prediction F0 and the real-time watering prediction flow Q i Compared with the initial watering prediction flow rate Q0, the road dust prediction model is continuously improved to improve the calculation accuracy of the initial road dust prediction F0 and the initial watering prediction flow rate Q0, and finally improve the prediction accuracy of the total water consumption W0 of the predicted operation.

[0091] The embodiment of the present invention also discloses a watering flow prediction device for sanitation vehicle operation, comprising:

[0092] The initial data acquisition module is used to obtain relevant data of the road section to be operated and the weather data of the road section to be operated from the last operation to the current time before the sanitation vehicle operates;

[0093] The initial flow calculation module is used for the road dust prediction model to calculate the initial road dust prediction amount F0, the initial watering prediction flow Q0 and the initial total operation water consumption prediction W0 according to the data obtained by the initial data acquisition module;

[0094] The sanitation vehicle initial operation module is used for the sanitation vehicle to carry the initial total water consumption forecast W0 and start the operation on the designated road section with the initial watering forecast flow Q0;

[0095] The prediction module is used to collect real-time road data, real-time vehicle data and real-time weather data during the operation of the sanitation vehicle;

[0096] The road dust prediction model calculates the road dust prediction amount F at the target position i on the road ahead based on the real-time data obtained. i , Sprinkler predicted flow rate Q i And the time T consumed to reach the target position i i ;

[0097] The real-time operation module of the sanitation vehicle is used to predict the flow rate Q by sprinkling water when the sanitation vehicle reaches the target location. i Start working on the designated road section;

[0098] The dust data in the air is tested. If the detected dust content is greater than the dust threshold, the sanitation vehicle increases the water flow until the detected dust content is less than or equal to the dust threshold;

[0099] If the difference between the watering flow rate and the initial watering predicted flow rate Q0 is greater than △Q, and the duration exceeds the time threshold, the sanitation vehicle gradually reduces the watering flow rate until the detected dust content is equal to the dust threshold. The watering flow rate at this time is the optimal watering flow rate under the corresponding dust distribution state, and the road dust prediction model is updated;

[0100] The repeated execution module is used to repeatedly execute the methods in the prediction module and the sanitation vehicle real-time operation module until the sanitation vehicle completes all road operations on the designated road section and further improves the road dust prediction model.

[0101] Furthermore, in the above-mentioned initial data acquisition module, the relevant data of the road section to be operated includes one or more of the following data: the time T0 consumed for the last cleaning of the road section, road classification, surrounding environment classification, and traffic flow estimation data;

[0102] The weather data of the road section to be operated from the last operation to the current time includes one or more of the following data: rainfall, temperature, humidity, and wind speed.

[0103] Furthermore, the above prediction module includes:

[0104] A data collection unit is used to collect real-time road data, real-time vehicle data and real-time weather data during the operation of the sanitation vehicle;

[0105] The prediction unit is used for the road dust prediction model to predict the road dust prediction amount F at the target position i on the road ahead of the vehicle based on the acquired real-time road data. i ;

[0106] And further based on the road dust prediction F i And real-time weather data, calculate the predicted watering flow Q at the target location i i ;

[0107] The time T required to reach the target location i is calculated based on the distance between the target location i and the current location and the real-time vehicle data. i .

[0108] Furthermore, in the above data acquisition unit,

[0109] Real-time road data includes: images of the road ahead;

[0110] Real-time vehicle data includes one or more of the following data: the speed of the sanitation vehicle, the speed and angle of the sweeping disc;

[0111] Real-time weather data includes one or more of the following data: wind speed, wind direction, and humidity.

[0112] In this embodiment, the specific content of the watering flow prediction device for sanitation vehicle operation is similar to the content of the watering flow prediction method for sanitation vehicle operation disclosed in the above embodiment, and will not be repeated here.

[0113] In addition, in some embodiments, the present invention further discloses a storage medium, which stores one or more computer-readable programs, and the one or more programs include instructions, and the instructions are suitable for being loaded by a memory and executing the sprinkler flow prediction method disclosed in any of the above embodiments.

[0114] The present invention discloses a method, device and storage medium for predicting watering flow rate of sanitation vehicle operation, which has the following beneficial effects:

[0115] First, the present invention analyzes the relevant data of the working section and the historical weather data through the road dust prediction model, predicts the road dust distribution in advance, determines the initial watering prediction flow Q0 and the initial total water consumption prediction W0, realizes the accurate prediction of the water volume carried by the vehicle, and achieves the purpose of energy saving and high efficiency.

[0116] Secondly, during the operation of the sanitation vehicle, the present invention collects real-time road data, monitors the road surface, and predicts in advance the required watering flow rate for uncleaned locations, thereby achieving early suppression of dust from the operation and avoiding the generation of dust from the source.

[0117] Third, during the operation of the sanitation vehicle, the present invention realizes rapid adjustment of the prediction results of the road dust prediction model through analysis and processing of real-time data, thereby doubly ensuring the final dust reduction effect.

[0118] Fourth, the road dust prediction model of the present invention can continuously perform self-learning through real-time data to continuously improve its prediction accuracy.

[0119] Fifth, the present invention has a high degree of intelligence. During the operation of the sanitation vehicle, there is no need for manual operation of the on-board sprinkler control device, which reduces the workload of personnel and effectively reduces the project operation cost.

[0120] It should be understood that the various techniques described herein can be implemented in combination with hardware or software, or a combination thereof. Thus, the method and apparatus of the present invention, or some aspects or portions of the method and apparatus of the present invention, can take the form of program codes (i.e., instructions) embedded in a tangible medium, such as a floppy disk, a CD-ROM, a hard disk drive, or any other machine-readable storage medium, wherein when the program is loaded into a machine such as a computer and executed by the machine, the machine becomes a device for practicing the present invention.

[0121] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for illustrating the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which shall fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for predicting watering flow rate for sanitation vehicle operation, characterized in that: include: Step S1: Before the sanitation vehicle operates, obtain relevant data of the road section to be operated and weather data of the road section to be operated from the last operation to the current time; Step S2: the road dust prediction model calculates according to the data obtained in step S1 to obtain an initial road dust prediction amount F0, an initial watering prediction flow rate Q0, and an initial total operation water consumption prediction amount W0; Step S3: The sanitation vehicle carries the initial total water consumption forecast W0 and starts working on the designated road section with the initial predicted watering flow Q0; Step S4: During the operation of the sanitation vehicle, real-time road data, real-time vehicle data and real-time weather data are collected; The road dust prediction model calculates the road dust prediction amount F at the target position i on the road ahead based on the real-time data obtained. i , Sprinkler predicted flow rate Q i And the time T consumed to reach the target position i i ; Step S5: The sanitation vehicle arrives at the target location and predicts the flow rate Q by sprinkling water i Start working on the designated road section; The dust data in the air is tested. If the detected dust content is greater than the dust threshold, the sanitation vehicle increases the water flow until the detected dust content is less than or equal to the dust threshold; If the difference between the watering flow rate and the initial watering predicted flow rate Q0 is greater than △Q, and the duration exceeds the time threshold, the sanitation vehicle gradually reduces the watering flow rate until the detected dust content is equal to the dust threshold. The watering flow rate at this time is the optimal watering flow rate under the corresponding dust distribution state, and the road dust prediction model is updated; Step S6: Repeat steps S4 to S5 until the sanitation vehicle completes all road operations on the designated road section and further improves the road dust prediction model.

2. The method for predicting watering flow rate according to claim 1, characterized in that: In the step S1, the relevant data of the road section to be operated includes one or more of the following data: the time T0 consumed for the last cleaning of the road section, road classification, surrounding environment classification, and traffic flow estimation data; The weather data of the road section to be operated from the last operation to the current time includes one or more of the following data: rainfall, temperature, humidity, and wind speed.

3. The method for predicting watering flow rate according to claim 1, characterized in that: The step S4 comprises: Step S4.1: During the operation of the sanitation vehicle, real-time road data, real-time vehicle data and real-time weather data are collected; Step S4.2: The road dust prediction model predicts the road dust prediction amount F at the target position i on the road ahead of the vehicle based on the acquired real-time road data i ; And further based on the road dust prediction F i And real-time weather data, calculate the predicted watering flow Q at the target location i i ; The time T required to reach the target location i is calculated based on the distance between the target location i and the current location and the real-time vehicle data. i .

4. The method for predicting watering flow rate according to claim 3, characterized in that: In the step S4.1, Real-time road data includes: images of the road ahead; Real-time vehicle data includes one or more of the following data: the speed of the sanitation vehicle, the speed and angle of the sweeping disc; Real-time weather data includes one or more of the following data: wind speed, wind direction, and humidity.

5. A watering flow prediction device for sanitation vehicle operation, characterized in that: include: The initial data acquisition module is used to obtain relevant data of the road section to be operated and the weather data of the road section to be operated from the last operation to the current time before the sanitation vehicle operates; The initial flow calculation module is used for the road dust prediction model to calculate the initial road dust prediction amount F0, the initial watering prediction flow Q0 and the initial total operation water consumption prediction W0 according to the data obtained by the initial data acquisition module; The sanitation vehicle initial operation module is used for the sanitation vehicle to carry the initial total water consumption forecast W0 and start the operation on the designated road section with the initial watering forecast flow Q0; The prediction module is used to collect real-time road data, real-time vehicle data and real-time weather data during the operation of the sanitation vehicle; The road dust prediction model calculates the road dust prediction amount F at the target position i on the road ahead based on the real-time data obtained. i , Sprinkler predicted flow rate Q i And the time T consumed to reach the target position i i ; The real-time operation module of the sanitation vehicle is used to predict the flow rate Q by sprinkling water when the sanitation vehicle reaches the target location. i Start working on the designated road section; The dust data in the air is tested. If the detected dust content is greater than the dust threshold, the sanitation vehicle increases the water flow until the detected dust content is less than or equal to the dust threshold; If the difference between the watering flow rate and the initial watering predicted flow rate Q0 is greater than △Q, and the duration exceeds the time threshold, the sanitation vehicle gradually reduces the watering flow rate until the detected dust content is equal to the dust threshold. The watering flow rate at this time is the optimal watering flow rate under the corresponding dust distribution state, and the road dust prediction model is updated; The repeated execution module is used to repeatedly execute the methods in the prediction module and the sanitation vehicle real-time operation module until the sanitation vehicle completes all road operations on the designated road section and further improves the road dust prediction model.

6. The sprinkler flow prediction device according to claim 5, characterized in that: In the initial data acquisition module, the relevant data of the road section to be operated includes one or more of the following data: the time T0 consumed for the last cleaning of the road section, road classification, surrounding environment classification, and traffic flow estimation data; The weather data of the road section to be operated from the last operation to the current time includes one or more of the following data: rainfall, temperature, humidity, and wind speed.

7. The sprinkler flow rate prediction device according to claim 5, characterized in that: The prediction module comprises: A data collection unit is used to collect real-time road data, real-time vehicle data and real-time weather data during the operation of the sanitation vehicle; The prediction unit is used for the road dust prediction model to predict the road dust prediction amount F at the target position i on the road ahead of the vehicle based on the acquired real-time road data. i ; And further based on the road dust prediction F i And real-time weather data, calculate the predicted watering flow Q at the target location i i ; The time T required to reach the target location i is calculated based on the distance between the target location i and the current location and the real-time vehicle data. i .

8. The sprinkler flow rate prediction device according to claim 7, characterized in that: In the data acquisition unit, Real-time road data includes: images of the road ahead; Real-time vehicle data includes one or more of the following data: the speed of the sanitation vehicle, the speed and angle of the sweeping disc; Real-time weather data includes one or more of the following data: wind speed, wind direction, and humidity.

9. A storage medium, characterized in that The storage medium stores one or more computer-readable programs, and the one or more programs include instructions, and the instructions are suitable for being loaded by the memory and executing the sprinkler flow prediction method described in any one of claims 1 to 4.

Images