Sprinkler truck intelligent identification and control system based on artificial intelligence

Abstract

The present invention provides an intelligent identification and control system for a sprinkler truck based on artificial intelligence, and relates to the technical field of data processing. The system comprises: a vehicle environment data acquisition module, which is used to acquire environment data during the driving process of the sprinkler truck; an environment data processing module, which is used to perform data cleaning, denoising and feature extraction on the environment data; a road condition identification module, which is used to identify the road type, road humidity and traffic environment of the current road section in combination with the real-time positioning information of the road; a watering strategy generation module, which is used to generate watering strategy data; a watering execution module, which is used to execute the watering operation; and a feedback optimization module, which is used to provide feedback to the watering strategy generation module. The present invention improves the autonomy and accuracy of the intelligent identification and control system for a sprinkler truck.

Description

Technical Field

[0001] The invention relates to the technical field of data processing, and in particular to an intelligent identification and control system for a sprinkler truck based on artificial intelligence. Background Art

[0002] In the prior art, the intelligent identification and control system of sprinkler trucks is mostly based on preset program control, and obtains road information through sensors on the vehicle to determine whether watering is needed. Such systems usually use simple physical sensors, such as humidity sensors, temperature sensors, etc., to detect environmental conditions, and automatically adjust the amount of watering and the timing of watering according to the detection data through hardware control systems. In addition, some systems combine GPS positioning and cameras to identify specific areas and sprinkle water, but they mainly rely on fixed rules and conditions.

[0003] The performance of existing technologies in complex environments may still have technical defects. Taking urban roads as an example, the existing system cannot accurately adjust the amount of water sprayed in a relatively complex traffic environment, especially when encountering different road conditions such as different humidity and vehicle types. The control system based on traditional sensors cannot accurately adjust the amount of water sprayed. For example, when a sprinkler truck passes through a road section with heavy traffic, the traditional system may cause excessive watering in some sections and insufficient watering in other areas due to sensor errors or overly simple data, and cannot efficiently adjust the watering strategy according to the actual environment. This inaccurate water control mode not only wastes water resources, but may also affect road cleanliness and driving safety. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent identification and control system for sprinkler trucks based on artificial intelligence, aiming to solve the problems mentioned in the background technology.

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

[0006] The sprinkler truck intelligent identification and control system based on artificial intelligence includes:

[0007] The vehicle environment data acquisition module is used to obtain the environmental data of the sprinkler truck during driving, including road humidity, air temperature, traffic flow and traffic type;

[0008] Environmental data processing module, used to clean, denoise and extract features of environmental data to generate a standardized environmental feature data set;

[0009] The road condition recognition module is used to identify the road type, road humidity and traffic environment of the current road section based on the standardized environmental feature data set and combined with the real-time positioning information of the road, and generate road recognition feature data;

[0010] A watering strategy generation module is used to generate watering strategy data according to road recognition feature data;

[0011] A watering execution module is used to adjust the operating parameters of the watering equipment according to the watering strategy data and execute the watering operation;

[0012] The feedback optimization module is used to collect the operating status of the sprinkler equipment and the environmental change data after sprinkler irrigation, and provide feedback to the sprinkler strategy generation module.

[0013] Preferably, the environmental data processing module includes:

[0014] The data screening submodule is used to remove noise from environmental data to obtain screened data;

[0015] A data conversion submodule is used to normalize the screened data to obtain converted data;

[0016] The data extraction submodule is used to extract key features from the transformed data to obtain an environmental feature dataset.

[0017] Preferably, the road condition recognition module includes:

[0018] The humidity analysis submodule is used to analyze the road humidity conditions according to the environmental characteristic data set and obtain humidity data;

[0019] The road type matching submodule is used to match the corresponding road type according to the humidity data and the real-time positioning information of the road to obtain the road matching data;

[0020] The traffic environment assessment submodule is used to assess the road traffic status based on the road matching data, combined with the traffic flow and vehicle type information, and obtain the road identification feature data.

[0021] Preferably, the watering strategy generation module includes:

[0022] The watering amount calculation submodule is used to segmentally map the combined features of road humidity and road type according to the road identification feature data to obtain the watering amount data;

[0023] The watering time adjustment submodule is used to adjust the watering time interval according to the watering amount data and the real-time change trend of the traffic flow to obtain the watering time data;

[0024] The watering range optimization submodule is used to dynamically optimize the watering range according to the vehicle type and road type to obtain the watering strategy data.

[0025] Preferably, the watering execution module comprises:

[0026] The equipment parameter setting submodule is used to set the operating parameters of the sprinkler equipment according to the sprinkler strategy data and obtain the equipment control data;

[0027] The spraying control submodule is used to adjust the angle and spraying range of the sprinkler nozzle according to the equipment control data to obtain the spraying execution data;

[0028] The watering implementation submodule is used to control the watering equipment to perform the watering operation according to the spraying execution data.

[0029] Preferably, the feedback optimization module includes:

[0030] The watering effect monitoring submodule is used to collect the running status data of the watering equipment and obtain the watering status data;

[0031] The humidity change analysis submodule is used to analyze the impact of watering on road humidity based on the watering status data and the environmental data after watering, and obtain humidity adjustment data;

[0032] The watering strategy optimization submodule is used to correct the watering strategy data of the watering strategy generation module according to the humidity adjustment data.

[0033] Preferably, the watering amount calculation submodule includes:

[0034] The humidity level assessment submodule is used to classify the road humidity data into layers to obtain humidity level data;

[0035] The segmented mapping calculation submodule is used to segmentally map the combined characteristics of road humidity and road type according to the humidity level data to obtain watering amount calculation data; the calculation formula of the watering amount is:

[0036] ,

[0037] in, is the calculated value of watering amount, is the base watering amount, is the road humidity, expressed as a percentage, is the road type influencing factor, is the dirt road impact factor, is the cement road influencing factor, is the influencing factor of asphalt road, and are the minimum humidity level threshold and the maximum humidity level threshold, respectively. , is the watering coefficient of the cement road at normal humidity, , , is the low humidity watering coefficient of cement road, , , is the normal humidity watering coefficient of asphalt road, , , is the low humidity watering coefficient of asphalt road, Environmental impact factors;

[0038] in, , is the evaporation rate of road material, is the evaporation rate of the reference road material, is the water absorption rate of the road material, The water absorption rate of the reference road material;

[0039] in, , For reference air humidity, is the current air humidity, is the reference wind speed, is the current wind speed, is the reference air temperature, is the current air temperature, , and is the weight coefficient;

[0040] The dynamic compensation submodule is used to dynamically compensate the watering amount according to the watering amount calculation data and the historical watering records to obtain the compensated watering amount data; the calculation formula of the compensated watering amount is:

[0041] ,

[0042] in, To compensate for the amount of watering, This is the lowest watering amount in history. This is the largest amount of watering in history. and is the historical sprinkler compensation coefficient, is the watering error, is the base watering amount, The amount of water used last time.

[0043] Preferably, the watering time adjustment submodule includes:

[0044] The flow change detection submodule is used to monitor real-time traffic flow data, analyze flow change trends, and obtain flow trend data;

[0045] The interval adjustment calculation submodule is used to calculate the watering time interval according to the flow trend data and the compensation watering amount data to obtain the watering time interval data; the calculation formula of the watering time interval is:

[0046] ,

[0047] in, is the watering interval, is the benchmark watering time, is the traffic flow at the previous moment, is the traffic flow at the current moment, is the average historical traffic flow, and is the weight coefficient.

[0048] Preferably, the watering range optimization submodule includes:

[0049] The vehicle flow impact analysis submodule is used to analyze the impact of different vehicle types on the watering range and obtain vehicle flow impact data;

[0050] The range adjustment calculation submodule is used to calculate the optimal coverage area of ​​the watering range according to the traffic flow impact data and the road type information to obtain the watering range data; the calculation formula for the optimized watering range is:

[0051] ,in, For the watering range, As the basic watering range, is the traffic flow influencing factor at the current moment, , and is the adjustment coefficient;

[0052] in, , For the The flow of vehicles, and For the The adjustment coefficient of the vehicle, is the number of vehicle types.

[0053] Preferably, the watering range optimization submodule further includes a real-time dynamic correction submodule, which is used to dynamically correct the watering range according to the watering range data and in combination with the real-time traffic flow changes to obtain optimized watering range data;

[0054] , To optimize the watering range, is the traffic flow influencing factor at the previous moment, is the adjustment coefficient.

[0055] The above solution of the present invention includes at least the following beneficial effects:

[0056] The present invention realizes intelligent, precise and adaptive optimization of watering operations through the collaborative work of a vehicle environment data acquisition module, an environment data processing module, a road condition recognition module, a watering strategy generation module, a watering execution module and a feedback optimization module, overcomes the problem of inaccurate watering control in complex traffic environments in the prior art, improves the effectiveness of watering, and reduces water resource waste and interference with traffic.

[0057] Before the watering operation, the vehicle environmental data acquisition module can collect key environmental data such as road humidity, air temperature, traffic flow and traffic type in real time, providing a basis for the accurate formulation of watering strategies. Existing technologies mainly rely on single sensors, such as humidity sensors or temperature sensors. This single data source is easily affected by environmental interference, resulting in inaccurate data. For example, in rainy weather, relying solely on humidity sensors may misjudge the wetness of the road and ignore the influence of factors such as temperature and traffic flow. Through multi-sensor fusion, the system can not only comprehensively analyze environmental conditions, but also improve data stability and avoid deviations in watering amount calculations caused by single sensor errors.

[0058] The environmental data processing module performs data cleaning, denoising and feature extraction on the acquired environmental data to ensure the reliability and availability of the input data. Since sensors may be interfered with by external factors, such as dust coverage, temperature drift or traffic anomalies caused by sudden traffic events, directly using unprocessed data may lead to inaccurate watering decisions. The system improves data accuracy through technologies such as data denoising, outlier removal, and data normalization. For example, when collecting humidity data, if the humidity value in a certain area is suddenly much higher or lower, the module can identify and correct the data through data smoothing and anomaly detection algorithms, making the environmental data ultimately used for decision-making more stable.

[0059] The road condition recognition module uses standardized environmental feature data and combines it with real-time positioning information of the road to accurately identify the type of the current road section, road humidity, and traffic environment. Existing sprinkler systems generally sprinkle water through fixed areas or manually set sections, and lack the ability to dynamically identify road types. For example, cement roads and asphalt roads have completely different requirements for the amount of water sprinkled. The former requires strict control of the amount of water sprinkled to prevent the road from being slippery, while the latter may require a larger sprinkler range to reduce dust. The system matches the road type database through real-time GPS positioning to ensure that the sprinkler strategy matches the current road conditions. In addition, the module can also combine historical road humidity data to calculate the trend of road surface wetness changes, thereby optimizing the sprinkler time and amount.

[0060] The watering strategy generation module automatically generates watering strategy data based on road recognition feature data, including parameters such as watering amount, watering time, and watering range. Existing watering systems usually use fixed rules to control watering without considering the dynamic changes of the real-time environment, which easily leads to unreasonable watering plans. For example, when the humidity is low but the traffic volume is large, if water is sprinkled according to fixed rules, it may cause the road to be slippery and affect driving safety. This system uses a data-driven watering decision-making method to calculate the optimal watering coefficient based on environmental data and historical data to ensure that the watering strategy can meet the road wetting requirements without affecting traffic safety. For example, when the air temperature is high and the humidity is low, the module can increase the amount of watering, while in areas with dense traffic, the amount of watering will be appropriately reduced to reduce the impact on driving.

[0061] The sprinkler execution module accurately controls the operating parameters of the sprinkler equipment according to the sprinkler strategy data to ensure that the sprinkler operation is carried out according to the optimized parameters. Existing sprinkler systems usually adopt a fixed sprinkler mode, and the spraying angle, flow rate and nozzle pressure are all preset and cannot be adjusted dynamically, resulting in uneven sprinkler coverage. Through intelligent sprinkler control, this system enables the sprinkler equipment to adjust the nozzle opening, sprinkler pressure and spray width according to actual conditions to ensure the uniformity of the sprinkler operation. For example, on narrow roads or roads with heavy traffic, the system can automatically reduce the spraying pressure and narrow the spraying range to reduce the impact on driving; on open roads, the sprinkler range can be appropriately expanded to increase the sprinkler coverage rate, thereby improving sprinkler efficiency and optimizing water resource utilization.

[0062] The feedback optimization module further enhances the adaptive ability of the system, so that the watering strategy can be dynamically optimized as the environment changes. The existing sprinkler system lacks self-learning and adjustment capabilities, which makes it difficult to optimize the strategy after long-term use, and the watering efficiency gradually decreases. This system collects the operating status of the sprinkler equipment and the environmental change data after watering, calculates the humidity change trend before and after watering, and automatically feeds back to the sprinkler strategy generation module. For example, if it is detected that the humidity of a certain section of road does not reach the target value after watering, the system can increase the amount of watering during the next watering; if it is found that the road humidity is higher than expected for a long time, the system will reduce the amount of watering to prevent excessive watering and waste of water resources.

[0063] Overall, the sprinkler truck intelligent identification and control system has achieved intelligence and precision in environmental data acquisition, data processing, road identification, sprinkler decision-making, sprinkler execution and feedback optimization, significantly improving the adaptability and efficiency of the sprinkler system. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is an architecture diagram of an artificial intelligence-based sprinkler truck intelligent identification and control system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0065] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0066] like Figure 1 As shown, an embodiment of the present invention proposes an intelligent identification and control system for sprinkler trucks based on artificial intelligence, and the system includes:

[0067] The vehicle environment data acquisition module is used to obtain the environmental data of the sprinkler truck during driving, including road humidity, air temperature, traffic flow and traffic type;

[0068] Environmental data processing module, used to clean, denoise and extract features of environmental data to generate a standardized environmental feature data set;

[0069] The road condition recognition module is used to identify the road type, road humidity and traffic environment of the current road section based on the standardized environmental feature data set and combined with the real-time positioning information of the road, and generate road recognition feature data;

[0070] A watering strategy generation module is used to generate watering strategy data according to road recognition feature data;

[0071] A watering execution module is used to adjust the operating parameters of the watering equipment according to the watering strategy data and execute the watering operation;

[0072] The feedback optimization module is used to collect the operating status of the sprinkler equipment and the environmental change data after sprinkler irrigation, and provide feedback to the sprinkler strategy generation module.

[0073] In the embodiment of the present invention, the sprinkler truck intelligent identification and control system can achieve accurate perception of environmental conditions in actual applications, and generate the optimal sprinkler plan based on real-time data, thereby improving road sprinkler efficiency, optimizing water resource utilization, and reducing the impact of sprinkler on traffic flow.

[0074] The vehicle environment data acquisition module can collect key data such as road humidity, air temperature, traffic flow and traffic type in real time. These data are obtained by a sensor network, such as humidity sensors, temperature sensors, radars and cameras, to ensure that the system can perceive changes in the external environment. For example, in an environment with high temperature and low humidity, the system can detect the dryness of the road surface and provide corresponding watering strategies; in the case of heavy traffic, the system can avoid watering during peak hours to reduce the impact on driving safety.

[0075] The environmental data processing module further improves data availability. Since the data collected by the sensor may be subject to external interference, such as rain, dust, and sensor failure, this module can convert the raw data into a data set that can be used for decision-making through noise removal, normalization, and feature extraction technology to ensure the accuracy and stability of the data. For example, filtering technology can be used to eliminate abnormal humidity values ​​to avoid inaccurate watering strategies due to sensor errors.

[0076] The road condition recognition module is based on standardized environmental feature data, combined with GPS and map data, and can accurately identify the current road type, humidity conditions and traffic environment, so as to determine the appropriate watering strategy. For example, for highways, the system can identify its road conditions and limit the amount of watering to avoid slippery roads, while for rural roads, the amount of watering can be increased to reduce dust.

[0077] The watering strategy generation module combines road recognition feature data and uses intelligent decision-making algorithms to calculate the optimal watering strategy, including watering volume, watering time, and watering range. The module can dynamically adjust the watering coefficient to ensure the accuracy and adaptability of the watering process.

[0078] The sprinkler execution module can automatically adjust the operating parameters of the sprinkler equipment, such as the spraying angle, water flow rate, and spraying range, according to the generated sprinkler strategy to ensure the best sprinkler effect. The feedback optimization module further improves the adaptability of the system. By collecting real-time sprinkler effects and feeding them back to the sprinkler strategy generation module, the sprinkler volume is dynamically compensated.

[0079] In summary, the system has the capabilities of intelligent perception, real-time decision-making, precise execution and adaptive optimization. It can effectively reduce water waste, improve watering efficiency, and reduce the impact on traffic. It has broad application value.

[0080] In a preferred embodiment of the present invention, the environmental data processing module includes:

[0081] The data screening submodule is used to remove noise from environmental data to obtain screened data;

[0082] A data conversion submodule is used to normalize the screened data to obtain converted data;

[0083] The data extraction submodule is used to extract key features from the transformed data to obtain an environmental feature dataset.

[0084] In the embodiment of the present invention, the environmental data processing module performs noise reduction, feature extraction and data formatting on the raw data to ensure that the watering strategy is based on high-quality input data.

[0085] The data screening submodule can identify and remove abnormal data. For example, in a low-temperature environment, the temperature and humidity sensor may fail, resulting in large deviations in the measured values. This module uses historical data analysis and outlier detection algorithms to automatically remove data that is out of a reasonable range, ensuring the reliability of watering decisions.

[0086] The data conversion submodule converts data from different sources into a unified standard format through normalization. For example, traffic flow may be input as vehicles per minute, while humidity data may be expressed as a percentage. The data conversion module can standardize these data so that they have a unified dimension when making decisions and calculations, which is convenient for analysis and calculation.

[0087] The data extraction submodule further mines key features to improve the usability of data. For example, through principal component analysis (PCA) or time series analysis, this module can extract the key features that have the greatest impact on the watering strategy, such as humidity trends, temperature change rates, and traffic flow change rates, thereby optimizing the accuracy of watering decisions.

[0088] This module ensures that the environmental data obtained by the sprinkler system is accurate and reliable, significantly reduces the sprinkler decision-making errors caused by data noise, and improves the intelligence and adaptability of the system.

[0089] In a preferred embodiment of the present invention, the road condition recognition module includes:

[0090] The humidity analysis submodule is used to analyze the road humidity conditions according to the environmental characteristic data set and obtain humidity data;

[0091] The road type matching submodule is used to match the corresponding road type according to the humidity data and the real-time positioning information of the road to obtain the road matching data;

[0092] The traffic environment assessment submodule is used to assess the road traffic status based on the road matching data, combined with the traffic flow and vehicle type information, and obtain the road identification feature data.

[0093] In the embodiment of the present invention, the road condition recognition module can accurately identify the type, wetness and traffic environment of the road based on standardized environmental characteristic data, providing a reliable basis for subsequent watering decisions.

[0094] The humidity analysis submodule can combine historical humidity data and current environmental information to calculate the current road wetness. For example, the system can predict the evaporation rate of water on the road surface based on real-time humidity data and air temperature, thereby accurately determining whether watering is needed.

[0095] The road type matching submodule combines GPS and map data to identify the type of road the vehicle is currently on. For example, on an asphalt road, the module may allow a larger amount of watering, while on a cement road, the amount of watering will be limited to ensure vehicle safety.

[0096] The traffic environment assessment submodule uses real-time traffic data to identify the traffic status of the road. For example, if the system detects a sudden increase in traffic flow, it will postpone the watering time to avoid affecting traffic safety. Conversely, if it detects a decrease in traffic flow, it can appropriately increase the amount of watering to improve the watering effect.

[0097] This module ensures that the sprinkler system can adapt to different road conditions, improve the intelligence of sprinkler, and avoid driving safety affected by unreasonable sprinkler strategies.

[0098] Among them, the road type matching submodule can use a variety of existing technologies to perform road matching:

[0099] GPS and map matching: The current location of the sprinkler truck is collected through GPS and matched with the preloaded road information database to determine the current road type.

[0100] On-board cameras and machine learning: Use cameras to capture road images and use deep learning models such as CNN target recognition to analyze features such as the number of lanes, marking type, road material, etc. to identify the road type.

[0101] Inertial Navigation System (IMU): Uses gyroscopes and accelerometers to detect the driving characteristics of the sprinkler truck, such as driving speed and acceleration changes, to assist in determining the road type.

[0102] Road types mainly include road material attributes, such as dirt roads, cement roads, and asphalt roads.

[0103] Among them, the role of the traffic environment assessment submodule is to analyze traffic flow and traffic type in real time to ensure that watering operations will not affect normal driving, while optimizing watering efficiency.

[0104] This module collects traffic data in the following ways:

[0105] Radar sensor: detects information such as vehicle density and speed changes ahead and analyzes traffic flow.

[0106] Camera detection: Identify lane occupancy and calculate traffic density through video stream analysis technology.

[0107] V2X vehicle-to-everything (V2X) communication: Communicates with roadside units (RSUs) or other connected vehicles to obtain traffic flow data over a wider range.

[0108] The acquired data is analyzed to determine the current traffic environment:

[0109] Low traffic mode: On roads with low traffic volume, the system can appropriately increase the watering range to ensure the road is wetted quickly.

[0110] Medium flow mode: The system uses a moderate watering range and adjusts the watering time to ensure that the watering matches the traffic flow.

[0111] High flow mode: The system reduces the watering volume or stops watering to prevent the watering operation from affecting traffic safety.

[0112] In addition to traffic flow assessment, the module can also identify traffic types and perform targeted optimization:

[0113] Heavy vehicles such as trucks and buses: The system reduces the watering range to prevent the vehicles from being sprayed.

[0114] For small vehicles such as cars and motorcycles: the system can increase the watering range and improve the road wetting range to reduce dust pollution.

[0115] In a preferred embodiment of the present invention, the watering strategy generation module includes:

[0116] The watering amount calculation submodule is used to segmentally map the combined features of road humidity and road type according to the road identification feature data to obtain the watering amount data;

[0117] The watering time adjustment submodule is used to adjust the watering time interval according to the watering amount data and the real-time change trend of the traffic flow to obtain the watering time data;

[0118] The watering range optimization submodule is used to dynamically optimize the watering range according to the vehicle type and road type to obtain the watering strategy data.

[0119] In the embodiment of the present invention, the watering strategy generation module calculates the watering amount, watering time and watering range through an intelligent algorithm to achieve the optimal watering strategy.

[0120] The watering amount calculation submodule calculates the optimal watering amount based on road humidity and road type through segmented mapping. For example, when the humidity is lower than the set threshold, the watering amount will gradually increase, and when the humidity is close to the set upper limit, the watering amount will be reduced to avoid over-watering.

[0121] The watering time adjustment submodule combines the real-time traffic flow to dynamically adjust the watering time. For example, during peak hours, the system may delay watering, while during off-peak hours, the watering frequency may be appropriately increased.

[0122] The watering range optimization submodule combines the road type and vehicle type to calculate the optimal watering coverage area. For example, on spacious urban roads, the watering range can be appropriately expanded, while on narrow rural roads, the watering range should be reduced to reduce the impact of mud.

[0123] This module ensures that watering decisions dynamically adapt to the actual environment, improves watering effects, and optimizes water resource utilization.

[0124] In a preferred embodiment of the present invention, the watering execution module includes:

[0125] The equipment parameter setting submodule is used to set the operating parameters of the sprinkler equipment according to the sprinkler strategy data and obtain the equipment control data;

[0126] The spraying control submodule is used to adjust the angle and spraying range of the sprinkler nozzle according to the equipment control data to obtain the spraying execution data;

[0127] The watering implementation submodule is used to control the watering equipment to perform the watering operation according to the spraying execution data.

[0128] In the embodiment of the present invention, the watering execution module is responsible for converting the watering strategy into actual watering operation to ensure the execution accuracy.

[0129] The equipment parameter setting submodule can set the spraying angle, water flow rate and nozzle pressure according to the watering strategy data to ensure the best watering effect. The spraying control submodule can dynamically adjust the spraying angle and range of the sprinkler equipment to avoid wasting water resources.

[0130] The sprinkler implementation submodule finally executes the sprinkler operation and monitors the sprinkler status in real time to ensure that the sprinkler equipment operates according to the preset parameters.

[0131] This module ensures the efficiency and controllability of the watering process and improves system reliability.

[0132] In a preferred embodiment of the present invention, the feedback optimization module includes:

[0133] The watering effect monitoring submodule is used to collect the running status data of the watering equipment and obtain the watering status data;

[0134] The humidity change analysis submodule is used to analyze the impact of watering on road humidity based on the watering status data and the environmental data after watering, and obtain humidity adjustment data;

[0135] The watering strategy optimization submodule is used to correct the watering strategy data of the watering strategy generation module according to the humidity adjustment data.

[0136] In the embodiment of the present invention, the feedback optimization module monitors the watering effect in real time and dynamically adjusts the watering strategy to ensure the intelligence, adaptability and long-term optimization capability of the watering system.

[0137] The watering effect monitoring submodule collects real-time data on road environment changes after watering through humidity sensors, temperature sensors and cameras. For example, after watering, the module can detect the changing trend of road wetness and record the evaporation rate of water in the watering area to evaluate the actual effect of watering.

[0138] The humidity change analysis submodule calculates the humidity change curve based on the humidity data before and after watering, and predicts the humidity recovery trend of the road in combination with historical data. For example, in a high temperature environment, water evaporates quickly, and this module can predict the humidity drop rate, thus providing a decision basis for the next watering.

[0139] The watering strategy optimization submodule dynamically adjusts the watering strategy data based on real-time monitoring data and historical watering effects. For example, when abnormal humidity changes are detected, the module can appropriately adjust the watering amount or watering time interval to optimize the system's operating mode.

[0140] Through this module, the sprinkler system can achieve closed-loop control and adaptive optimization, significantly reduce sprinkler waste, improve sprinkler efficiency, and ensure that the sprinkler effect is stable and controllable.

[0141] In a preferred embodiment of the present invention, the watering amount calculation submodule includes:

[0142] The humidity level assessment submodule is used to classify the road humidity data into layers to obtain humidity level data;

[0143] The segmented mapping calculation submodule is used to segmentally map the combined characteristics of road humidity and road type according to the humidity level data to obtain watering amount calculation data; the calculation formula of the watering amount is:

[0144] ,

[0145] in, is the calculated value of watering amount, is the base watering amount, is the road humidity, expressed as a percentage, is the road type influencing factor, is the dirt road impact factor, is the cement road influencing factor, is the influencing factor of asphalt road, and are the minimum humidity level threshold and the maximum humidity level threshold, respectively. , is the watering coefficient of the cement road at normal humidity, , , is the low humidity watering coefficient of cement road, , , is the normal humidity watering coefficient of asphalt road, , , is the low humidity watering coefficient of asphalt road, Environmental impact factors;

[0146] in, , is the evaporation rate of road material, is the evaporation rate of the reference road material, is the water absorption rate of the road material, The water absorption rate of the reference road material;

[0147] in, , For reference air humidity, is the current air humidity, is the reference wind speed, is the current wind speed, is the reference air temperature, is the current air temperature, , and is the weight coefficient;

[0148] The dynamic compensation submodule is used to dynamically compensate the watering amount according to the watering amount calculation data and the historical watering records to obtain the compensated watering amount data; the calculation formula of the compensated watering amount is:

[0149] ,

[0150] in, To compensate for the amount of watering, This is the lowest watering amount in history. This is the largest amount of watering in history. and is the historical sprinkler compensation coefficient, is the watering error, which is the deviation between the historical watering record and the target humidity. is the base watering amount, The amount of water used last time.

[0151] In the embodiment of the present invention, the watering amount calculation submodule accurately calculates the optimal watering amount through humidity level, road type and historical watering data, thereby ensuring the scientificity and intelligence of the watering strategy.

[0152] The humidity level assessment submodule classifies the real-time humidity data into different levels, such as dry, moderate, and wet. For example, when the humidity is below the set threshold, the system will increase the amount of watering, while when the humidity is high, the system will reduce the amount of watering or stop watering to prevent over-watering.

[0153] The segmented mapping calculation submodule uses a nonlinear calculation method to calculate the amount of water to be sprinkled based on relative humidity and road type. For example, asphalt roads have strong water absorption, so the amount of water to be sprinkled increases accordingly, while cement roads have high reflectivity and low watering amounts.

[0154] The dynamic compensation submodule combines historical watering data to adaptively optimize the watering amount. For example, if it is detected that the humidity has not reached the target value after the last watering, the system will appropriately increase the current watering amount; conversely, if it is detected that the road humidity exceeds the target value, the system will reduce the watering amount to prevent water accumulation.

[0155] This module implements data-driven intelligent calculation of watering volume, ensuring that the sprinkler system can provide the optimal sprinkler solution in different environments.

[0156] In a preferred embodiment of the present invention, the watering time adjustment submodule includes:

[0157] The flow change detection submodule is used to monitor real-time traffic flow data, analyze flow change trends, and obtain flow trend data;

[0158] The interval adjustment calculation submodule is used to calculate the watering time interval according to the flow trend data and the compensation watering amount data to obtain the watering time interval data; the calculation formula of the watering time interval is:

[0159] ,

[0160] in, is the watering interval, is the benchmark watering time, is the traffic flow at the previous moment, is the traffic flow at the current moment, is the average historical traffic flow, and is the weight coefficient.

[0161] In the embodiment of the present invention, the watering time adjustment submodule calculates the watering time interval according to the flow change trend, ensures that the watering time interval can adapt to the actual traffic conditions, and optimizes the watering rhythm.

[0162] The traffic change detection submodule obtains real-time road vehicle traffic data through traffic monitoring equipment and calculates the current traffic trend. For example, during peak hours, the system will detect an increase in traffic flow and automatically adjust the watering plan to avoid watering affecting driving safety.

[0163] The interval adjustment calculation submodule uses the flow trend data and the compensated watering volume data to calculate the watering time interval. For example, when the flow rate is high or the watering volume is large, the watering time interval is extended, and when the flow rate decreases or the watering volume decreases, the watering time interval is shortened, thereby optimizing the watering frequency.

[0164] The optimization and calibration submodule further adjusts the watering time to match the long-term watering trend. For example, in historical data analysis, if the road humidity drops rapidly during a certain period of time, the system will appropriately adjust the watering time to keep the road at the appropriate level of humidity.

[0165] This module ensures that the sprinkler system can dynamically adapt to changes in road traffic, improve the intelligence level of sprinkler operations, optimize water resource utilization efficiency, and reduce the interference of sprinkler operations on traffic.

[0166] In a preferred embodiment of the present invention, the watering range optimization submodule includes:

[0167] The vehicle flow impact analysis submodule is used to analyze the impact of different vehicle types on the watering range and obtain vehicle flow impact data;

[0168] The range adjustment calculation submodule is used to calculate the optimal coverage area of ​​the watering range according to the traffic flow impact data and the road type information to obtain the watering range data; the calculation formula for the optimized watering range is:

[0169] ,in, For the watering range, As the basic watering range, is the traffic flow influencing factor at the current moment, , and is the adjustment coefficient;

[0170] in, , For the The flow of vehicles, and For the The adjustment coefficient of the vehicle, is the number of vehicle types.

[0171] In the embodiment of the present invention, the watering range optimization submodule calculates the optimal coverage area of ​​the watering range according to the traffic impact data and the road type information, to ensure that the watering range can effectively cover the road without affecting normal driving.

[0172] The traffic flow impact analysis submodule calculates the impact of traffic density on the watering range based on real-time traffic flow data. For example, on roads with high traffic volume, the watering range will be automatically reduced to prevent watering from interfering with driving; on roads with low traffic volume, the watering range can be appropriately expanded to improve the watering effect.

[0173] The range adjustment calculation submodule combines road type information to calculate the watering coverage under different road environments. For example, on cement roads, the system will limit the watering range to avoid the risk of vehicles skidding due to watering; on asphalt roads, the watering range can be appropriately increased to improve the watering effect.

[0174] The real-time dynamic correction submodule fine-tunes the watering range according to the traffic flow change data during the watering process. For example, if a sudden increase in traffic flow is detected during the watering operation, the watering range can be immediately reduced to reduce the impact on traffic.

[0175] Through this module, the sprinkler system can adapt to different road and traffic conditions, ensuring that the sprinkler range always remains in the optimal range, improving sprinkler efficiency and road safety.

[0176] In a preferred embodiment of the present invention, the watering range optimization submodule further includes a real-time dynamic correction submodule, which is used to dynamically correct the watering range according to the watering range data and in combination with the real-time traffic flow changes to obtain optimized watering range data;

[0177] , To optimize the watering range, is the traffic flow influencing factor at the previous moment, is the adjustment coefficient.

[0178] In the embodiment of the present invention, during the watering operation, the real-time dynamic correction submodule intelligently adjusts the watering range by combining the watering range data and traffic flow changes to ensure the accuracy and flexibility of the watering operation.

[0179] For example, when the traffic density increases, the watering range will automatically shrink to reduce the impact on driving; when the traffic density decreases, the watering range can be appropriately expanded to increase the watering coverage rate.

[0180] This module ensures the intelligence, adaptability and dynamic optimization capabilities of the sprinkler system, ensuring that sprinkler operations always meet optimal conditions, improving sprinkler efficiency while reducing interference with traffic.

[0181] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. The sprinkler truck intelligent identification and control system based on artificial intelligence is characterized by: The system comprises: The vehicle environment data acquisition module is used to obtain the environmental data of the sprinkler truck during driving, including road humidity, air temperature, traffic flow and traffic type; Environmental data processing module, used to clean, denoise and extract features of environmental data to generate a standardized environmental feature data set; The road condition recognition module is used to identify the road type, road humidity and traffic environment of the current road section based on the standardized environmental feature data set and combined with the real-time positioning information of the road, and generate road recognition feature data; A watering strategy generation module is used to generate watering strategy data according to the road recognition feature data; wherein the watering strategy generation module includes: The watering amount calculation submodule is used to segmentally map the combined features of road humidity and road type according to the road identification feature data to obtain the watering amount data; The watering time adjustment submodule is used to adjust the watering time interval according to the watering amount data and the real-time change trend of the traffic flow to obtain the watering time data; The watering range optimization submodule is used to dynamically optimize the basic watering range according to the vehicle type and road type to obtain the watering range data; A watering execution module is used to adjust the operating parameters of the watering equipment according to the watering strategy data and execute the watering operation; The feedback optimization module is used to collect the operating status of the sprinkler equipment and the environmental change data after sprinkler watering, and provide feedback to the sprinkler strategy generation module; The watering amount calculation submodule includes: The humidity level assessment submodule is used to classify the road humidity data into layers to obtain humidity level data; The segmented mapping calculation submodule is used to segmentally map the combined characteristics of road humidity and road type according to the humidity level data to obtain watering amount calculation data; the calculation formula of the watering amount is: ， in, is the calculated value of watering amount, is the base watering amount, is the road humidity, expressed as a percentage, is the road type influencing factor, is the dirt road impact factor, is the cement road influencing factor, is the influencing factor of asphalt road, and are the minimum humidity level threshold and the maximum humidity level threshold, respectively. , is the watering coefficient of the cement road at normal humidity, , , is the low humidity watering coefficient of cement road, , , is the normal humidity watering coefficient of asphalt road, , , is the low humidity watering coefficient of asphalt road, Environmental impact factors; in, , is the evaporation rate of road material, is the evaporation rate of the reference road material, is the water absorption rate of the road material, The water absorption rate of the reference road material; in, , For reference air humidity, is the current air humidity, is the reference wind speed, is the current wind speed, is the reference air temperature, is the current air temperature, , and is the weight coefficient; The dynamic compensation submodule is used to dynamically compensate the watering amount according to the watering amount calculation data and the historical watering records to obtain the compensated watering amount data; the calculation formula of the compensated watering amount is: ， in, To compensate for the amount of watering, This is the lowest watering amount in history. This is the largest amount of watering in history. and is the historical sprinkler compensation coefficient, is the watering error, The standard watering amount The amount of watering last time.

2. The sprinkler truck intelligent identification and control system based on artificial intelligence according to claim 1 is characterized in that: The environmental data processing module comprises: The data screening submodule is used to remove noise from environmental data to obtain screened data; A data conversion submodule is used to normalize the screened data to obtain converted data; The data extraction submodule is used to extract key features from the transformed data to obtain an environmental feature dataset.

3. The sprinkler truck intelligent identification and control system based on artificial intelligence according to claim 2 is characterized in that: The road condition recognition module comprises: The humidity analysis submodule is used to analyze the road humidity conditions according to the environmental characteristic data set and obtain humidity data; The road type matching submodule is used to match the corresponding road type according to the humidity data and the real-time positioning information of the road to obtain the road matching data; The traffic environment assessment submodule is used to assess the road traffic status based on the road matching data, combined with the traffic flow and vehicle type information, and obtain the road identification feature data.

4. The sprinkler truck intelligent identification and control system based on artificial intelligence according to claim 3 is characterized in that: The watering execution module comprises: The equipment parameter setting submodule is used to set the operating parameters of the sprinkler equipment according to the sprinkler strategy data and obtain the equipment control data; The spraying control submodule is used to adjust the angle and spraying range of the sprinkler nozzle according to the equipment control data to obtain the spraying execution data; The watering implementation submodule is used to control the watering equipment to perform the watering operation according to the spraying execution data.

5. The sprinkler truck intelligent identification and control system based on artificial intelligence according to claim 4 is characterized in that: The feedback optimization module comprises: The watering effect monitoring submodule is used to collect the running status data of the watering equipment and obtain the watering status data; The humidity change analysis submodule is used to analyze the impact of watering on road humidity based on the watering status data and the environmental data after watering, and obtain humidity adjustment data; The watering strategy optimization submodule is used to correct the watering strategy data of the watering strategy generation module according to the humidity adjustment data.

6. The sprinkler truck intelligent identification and control system based on artificial intelligence according to claim 5 is characterized in that: The watering time adjustment submodule includes: The flow change detection submodule is used to monitor real-time traffic flow data, analyze flow change trends, and obtain flow trend data; The interval adjustment calculation submodule is used to calculate the watering time interval according to the flow trend data and the compensation watering amount data to obtain the watering time interval data; the calculation formula of the watering time interval is: ， in, is the watering interval, is the benchmark watering time, is the traffic flow at the previous moment, is the traffic flow at the current moment, is the average historical traffic flow, and is the adjustment coefficient.

7. The sprinkler truck intelligent identification and control system based on artificial intelligence according to claim 6 is characterized in that: The watering range optimization submodule includes: The vehicle flow impact analysis submodule is used to analyze the impact of different vehicle types on the watering range and obtain vehicle flow impact data; The range adjustment calculation submodule is used to calculate the optimal coverage area of ​​the watering range according to the traffic flow impact data and the road type information to obtain the watering range data; the calculation formula of the watering range is: ,in, For the watering range, As the basic watering range, is the traffic flow influencing factor at the current moment, , and is the adjustment coefficient; in, , For the The traffic volume of vehicles, and For the The adjustment coefficient of the vehicle, is the number of vehicle types.

8. The sprinkler truck intelligent identification and control system based on artificial intelligence according to claim 7 is characterized in that: The watering range optimization submodule also includes a real-time dynamic correction submodule, which is used to dynamically correct the watering range according to the watering range data and in combination with the real-time traffic flow changes to obtain optimized watering range data; the calculation formula for the optimized watering range is: , To optimize the watering range, is the traffic flow influencing factor at the previous moment, is the adjustment coefficient.

Images