Self-adaptive adjusting method, device and equipment for pavement spraying maintenance and storage medium

Abstract

The invention relates to the technical field of road maintenance, and provides a self-adaptive adjustment method, device and equipment for pavement spraying maintenance and a storage medium. Space-time alignment and feature extraction are carried out on multi-source original data to generate environment working condition parameters, road surface feature quantitative analysis is carried out according to the environment working condition parameters to generate road surface maintenance demand vectors, and formula decision making and multi-target optimization are carried out in combination with a decision model to obtain a spraying control instruction set. Performing spray height optimization according to the positioning data and the spray control instruction set to obtain an anti-interference spray height set value, and performing multi-axis cooperative control according to the spray height data, the spray control instruction set and the anti-interference spray height set value to obtain an equipment control signal sequence. According to the invention, through deep fusion of the multi-source environment and the vehicle positioning data, real-time optimization of spraying control in the pavement maintenance process is realized, the precision and efficiency of pavement spraying maintenance are improved, and water resources and operation cost are saved.

Description

Technical Field

[0001] The present application relates to the technical field of road maintenance, and in particular to an adaptive adjustment method, device, equipment and storage medium for road surface spray maintenance. Background Art

[0002] Pavement maintenance plays a vital role in extending road life, ensuring driving safety, and improving travel comfort. Regular spray maintenance effectively removes dust from the road surface, suppresses dust emissions, reduces water accumulation and the risk of slippery roads during the rainy season, and replenishes essential bound moisture to prevent cracks in the asphalt layer due to drying or aging. Effective spray maintenance not only maintains the road surface's coefficient of friction, improving vehicle braking performance and steering stability, but also mitigates environmental pollution and improves air quality around roads, thereby playing a positive role in both traffic safety and urban environmental governance.

[0003] Currently, road maintenance vehicles rely on drivers or on-site operators to manually adjust the spraying equipment, setting the spray pressure, nozzle opening, and spray height based on experience, or selecting fixed spray modes (such as high-pressure mode and wide-coverage mode) through a pre-set control panel. A few vehicles are equipped with simple hydraulic or electric lifting devices, which can raise and lower the nozzle frame to two or three height settings while driving, but these still require manual switching based on road conditions and vehicle speed. Spraying flow is typically adjusted mechanically using a flow-limiting valve, which cannot respond to changes in the external environment in real time. Summary of the Invention

[0004] In view of this, the present application provides an adaptive adjustment method, device, equipment and storage medium for pavement spray maintenance to solve the problem that static adjustment causes the spray adjustment to be unable to adapt to real-time changes in the environment, resulting in poor spraying effect.

[0005] In a first aspect, the present application provides an adaptive adjustment method for pavement spray maintenance, the method comprising: Perform spatiotemporal alignment and feature extraction on the acquired multi-source raw data to generate environmental operating parameters; Performing quantitative analysis and processing of pavement characteristics according to the environmental working condition parameters to generate a pavement maintenance demand vector; Performing formulation decision-making and multi-objective optimization processing according to the pavement maintenance demand vector through a preset decision model to obtain a spray control instruction set; Performing spray height optimization processing based on the real-time collected positioning data and the spray control instruction set to obtain an anti-interference spray height setting value; Multi-axis collaborative control processing is performed based on the real-time collected spray height data, the spray control instruction set and the anti-interference spray height setting value to obtain an equipment control signal sequence.

[0006] In an optional embodiment, the multi-source raw data includes environmental detection data, road section images, and satellite positioning coordinates, and the performing spatiotemporal alignment and feature extraction processing on the acquired multi-source raw data to generate environmental operating condition parameters includes: Performing time sequence calibration and spatial mapping processing on the environmental detection data to obtain time-space synchronized environmental data; Performing gridding and disease identification processing on the road section image through a preset recognition model to obtain a road surface condition map; Performing terrain data mapping processing according to the satellite positioning coordinates using a preset digital terrain model to obtain the slope and slope direction corresponding to the satellite positioning coordinates; The spatiotemporal synchronized environmental data, the road surface state map, the slope, and the slope direction are formatted according to a preset data format to generate environmental operating condition parameters.

[0007] In an optional embodiment, the performing of quantitative analysis and processing of road surface characteristics according to the environmental working condition parameters to generate a road surface maintenance demand vector includes: Performing an icing risk assessment based on the environmental operating condition parameters using a preset icing risk algorithm to obtain an icing risk level indicator; Performing a statistical analysis of pavement crack characteristics on the pavement condition map to obtain a pavement crack density index; Performing threshold judgment on the environmental working condition parameters according to a preset hillside impact mapping table to obtain a slope impact level and a risk indicator; Data fusion is performed on the icing risk level index, the pavement crack density index, the slope impact level, and the risk identifier to generate a pavement maintenance demand vector.

[0008] In an optional embodiment, performing a recipe decision and a multi-objective optimization process based on the pavement maintenance demand vector using a preset decision model to obtain a spray control instruction set includes: Performing a main agent matching process according to the pavement maintenance demand vector through a preset decision model to obtain a main agent type; Calculating the main agent concentration according to the pavement maintenance demand vector and the main agent type using a preset concentration optimization algorithm to obtain a basic mixing concentration; Compensating and optimizing the basic mixture concentration according to the wind speed in the pavement maintenance demand vector to obtain a viscosity enhancer dosage; The main agent type, the basic mixing concentration and the viscosity enhancer dosage are packaged according to a preset instruction protocol to obtain a spray control instruction set.

[0009] In an optional embodiment, the performing spray height optimization processing based on the real-time collected positioning data and the spray control instruction set to obtain an anti-interference spray height setting value includes: The digital terrain model is used to map the terrain data based on the real-time collected positioning data to obtain the terrain slope corresponding to the current location; Performing a reference height calculation process according to a preset reference height algorithm and the spray control instruction set to obtain an initial spray height; Performing slope compensation processing on the initial spraying height according to the terrain slope to obtain a slope-corrected height; The slope correction height is subjected to wind speed compensation processing according to the wind speed collected in real time to obtain an anti-interference spray height setting value.

[0010] In an optional embodiment, performing multi-axis collaborative control processing based on the real-time collected spray height data, the spray control instruction set, and the anti-interference spray height setting value to obtain the equipment control signal sequence includes: Performing a pump speed ratio adjustment process according to the basic mixed concentration to obtain a flow pump driving signal; Performing closed-loop PID control processing on the anti-interference spray height setting value and the real-time collected spray height data to obtain a hydraulic cylinder position control signal; Perform safety monitoring based on the real-time collected pipeline pressure and preset execution status data to obtain blockage alarms and corresponding backwash signals; The flow pump drive signal, the hydraulic cylinder position control signal, the blockage alarm and the backwash signal are time-sequentially packaged to obtain a device control signal sequence.

[0011] In an optional embodiment, the method further comprises: Collecting the coverage image and penetration depth data of the ground after spraying in real time, and performing grayscale value conversion on the coverage image to obtain a grayscale value matrix of the coverage area; Performing coverage uniformity analysis based on the coverage area grayscale value matrix to obtain a coefficient of variation; Performing regional penetration compliance testing and statistics based on the road condition map and the penetration depth data to obtain the number of compliance areas and the total number of areas; Performing spraying effect evaluation and parameter optimization processing according to the coefficient of variation, the number of qualified areas, and the total number of areas through a preset parameter optimization model to obtain a signal adjustment coefficient set; The device control signal sequence is compensated and optimized according to the signal adjustment coefficient set to obtain a modified adjustment control signal sequence.

[0012] The second aspect of the present application provides an adaptive adjustment device for road surface spray maintenance, the device comprising: The working condition extraction module is used to perform spatiotemporal alignment and feature extraction on the acquired multi-source raw data to generate environmental working condition parameters; a pavement analysis module, configured to perform quantitative analysis and processing of pavement characteristics according to the environmental working condition parameters to generate a pavement maintenance demand vector; A spray control module, configured to perform formulation decision making and multi-objective optimization processing according to the pavement maintenance demand vector through a preset decision model to obtain a spray control instruction set; A height setting module is used to optimize the spray height according to the real-time collected positioning data and the spray control instruction set to obtain an anti-interference spray height setting value; The collaborative control module is used to perform multi-axis collaborative control processing based on the real-time collected spray height data, the spray control instruction set and the anti-interference spray height setting value to obtain an equipment control signal sequence.

[0013] A third aspect of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the adaptive adjustment method for pavement spray maintenance as described above are implemented.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the adaptive adjustment method for pavement spray maintenance as described above.

[0015] In summary, this application has at least the following beneficial technical effects: 1. The mathematical optimization model automatically weighs multiple objectives when deciding on the spraying agent formula, thereby taking into account the requirements of indicators such as maintenance effect, water consumption, operation speed and equipment wear, so that the spraying operation can achieve the lowest operating cost while ensuring the maintenance quality.

[0016] 2. In view of the influencing factors of wind speed, traffic interference, and uneven road surface in actual operations, the spray height is optimized online by combining real-time positioning and the actual measured spray height to obtain an interference-resistant spray height setting value, thereby ensuring that the water mist can evenly cover the road surface under different working conditions and effectively reducing wind dispersion and spray leakage. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1 This is a flow chart of an adaptive adjustment method for pavement spray maintenance provided by an embodiment of the present application; Figure 2 This is a functional module diagram of an adaptive adjustment device for road surface spray maintenance provided by an embodiment of the present application; Figure 3 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0020] The adaptive adjustment method for pavement spray maintenance provided in the embodiments of this application is performed by an electronic device. Accordingly, the adaptive adjustment device for pavement spray maintenance operates within the electronic device. The electronic device in the embodiments of this application is used in a pavement maintenance vehicle to adjust the main agent ratio and spray height based on pavement conditions, thereby adapting to pavement spray maintenance in complex road conditions. The adaptive adjustment method for pavement spray maintenance provided in the embodiments of this application is described below from the perspective of an electronic device and in conjunction with the process of mountain road maintenance.

[0021] like Figure 1 FIG2 is a flow chart of the adaptive adjustment method for road surface spraying maintenance provided by an embodiment of the present application. The adaptive adjustment method for road surface spraying maintenance provided by an embodiment of the present application includes the following steps.

[0022] Step S1: performing spatiotemporal alignment and feature extraction processing on the acquired multi-source raw data to generate environmental working condition parameters.

[0023] Multi-source raw data refers to a heterogeneous data set collected by multiple sensor units and external information interfaces integrated in electronic devices, including but not limited to environmental detection data, road section images, and satellite positioning coordinates. Environmental detection data is obtained by the on-board meteorological module in real time to obtain physical quantities such as temperature, humidity, and wind speed, which are used to reflect the impact of the atmospheric conditions around the vehicle on the performance and distribution of the spray curing agent; satellite positioning coordinates are provided by the high-precision GPS module to provide longitude, latitude, and altitude data, which are used to determine the geographic location of the vehicle in the digital terrain model; road section images are composed of visible light and infrared images taken by the transportation bureau's remote cameras or on-board camera systems, which are used to identify cracks, water accumulation, and ice risks on the road surface. After obtaining the multi-source raw data, the environmental detection data is first subjected to time series calibration and spatial mapping processing to obtain spatiotemporally synchronized environmental data. Specifically, the onboard processor uses a built-in time synchronization protocol to align the temperature, humidity, and wind speed data collected by the meteorological module with the internal system clock. Then, combined with the GPS timestamp of the vehicle's current location, linear interpolation or Kalman filtering eliminates acquisition delay differences. Simultaneously, the sensor position coordinates are used to perform spatial mapping between the vehicle coordinate system and the world coordinate system, ensuring that each sensor quantity precisely corresponds to the same reference coordinate system at the same time. This process eliminates information deviations caused by sensor clock drift and data transmission delays, providing an accurate environmental basis for subsequent road condition analysis.

[0024] Then, the road section image is gridded and processed for disease identification through a preset recognition model to generate a road surface condition map. Specifically, the road section image is first divided into a 1m×1m grid, and then the color brightness, texture and infrared temperature features are extracted for each grid block. When the grayscale value of the visible light image is lower than the preset threshold, it is determined to be a water accumulation area, and when linear or arc-shaped dark lines appear in the image, it is marked as a crack, and when the temperature of the infrared thermal image is lower than the critical value, it is marked as an icing risk area. The recognition model used in the embodiment of the present application is a convolutional neural network weight obtained by training a large number of road disease samples to automatically distinguish the above-mentioned disease types, and finally the recognition results of each grid block are synthesized into a continuously covered road surface condition map to intuitively present the distribution of cracks, water accumulation patterns and icing tendencies.

[0025] Subsequently, terrain data is mapped against the digital terrain model based on the satellite positioning coordinates to obtain the slope and aspect information corresponding to the current coordinates. Specifically, the GPS longitude and latitude are first converted into a raster index in the digital terrain model. The elevation value of the point is then read from the digital terrain model database. The slope angle is calculated based on the elevation difference between adjacent pixels, and the slope direction is determined using a geographic projection algorithm. This mapping can quantitatively determine whether the current road section is uphill, downhill, or sideways, and whether it faces the sun or shade. This is crucial for selecting the appropriate main agent ratio and spraying height compensation.

[0026] Finally, the aforementioned spatiotemporally synchronized environmental data, road condition maps, slope, and aspect information are uniformly formatted according to a preset data format to generate structured environmental operating condition parameters. During the formatting process, all numerical values ​​and image annotation items are stored in the data packet as key-value pairs, where environmental parameters are represented as floating-point numbers, road condition maps are stored as matrices or coded layers, and slope and aspect are encoded as angle values ​​and enumerated tags. Timestamps and coordinate information are also uniformly recorded so that subsequent decision-making modules can directly read and complete maintenance needs analysis and formulation decisions based on these environmental operating condition parameters. Through the above-mentioned fusion preprocessing, the messy raw information can be converted into a machine-readable structured data packet, achieving accurate modeling of complex mountain road environments and providing a reliable data foundation for main agent ratios and spray height adjustments.

[0027] Step S2: Quantitative analysis and processing of pavement characteristics are performed based on the environmental working condition parameters to generate a pavement maintenance demand vector.

[0028] First, a pre-set icing risk algorithm assesses icing risk based on environmental parameters. This algorithm, trained on extensive winter icing accident data from mountain roads, uses road surface temperature, air humidity, and near-surface wind speed as inputs. An empirically fitted model assesses the likelihood of road icing under low-temperature, high-humidity, and low-wind conditions. The algorithm then categorizes the risk into three levels: high, medium, and low, based on the probability output by the empirically fitted model. For example, if the road infrared temperature is below the freezing point deviation threshold and the relative humidity is above 80%, the icing risk algorithm identifies a high risk. If the temperature is slightly above freezing and the humidity is between 60% and 80%, the risk is medium; and all other situations are classified as low risk. This process accurately identifies icing risks in shaded mountain roads or during nighttime cooling, providing important insights for subsequent decisions on deicing agent dosage and formulation.

[0029] At the same time, a statistical analysis of crack characteristics is performed on the pavement condition map, which is a regionalized annotation output by the previous grid-based defect identification model, with each grid representing one square meter of road surface. The statistical analysis process first iterates through each grid marker, calculating the ratio of the total number of cracked grids to the total number of grids to obtain a percentage-based crack density. Combined with a crack width estimation method, crack grids with widths greater than a preset threshold are weighted to further refine the priority of critical defect areas. For example, when the crack density exceeds 20% and the weighted data remains above the preset threshold, it indicates that the road section requires the injection of a regeneration agent or sealing repair agent. Conversely, the weighting of the crack indicator is reduced to avoid wasted resources. Quantifying the crack density indicator helps maintain sensitivity to the surface crack distribution patterns caused by the undulations of mountain roads and automatically adapts to the fatigue response characteristics of different road paving materials.

[0030] At the same time, thresholds for environmental parameters are determined based on a pre-set slope impact mapping table. This table, created during the project research phase by collecting experimental data on the impact of different slopes on liquid spray coverage in typical mountainous areas, categorizes slopes into three levels: gentle (≤5°), moderate (5°-10°), and steep (≥10°). These levels are then assigned risk indicators based on the orientation (sunny vs. shaded). During execution, the slope and aspect recorded in the environmental parameters are read and matched one-to-one with the mapping table to obtain the corresponding slope impact level (e.g., "moderate slope impact") and risk indicator (e.g., "shaded high risk"). For example, a 12° slope on a shaded uphill section at an altitude of 2,100 meters would be assigned the "steep shaded high risk" category. This prioritizes slope risk in the demand vector, ensuring that subsequent formulation decisions prioritize enhanced spray penetration and anti-icing effectiveness.

[0031] Finally, data fusion is performed on the aforementioned icing risk level, crack density index, slope impact level, and risk indicator. The data fusion process in this embodiment of the application utilizes a weighted normalization method. After standardizing each indicator to a uniform dimension, it is linearly combined according to preset weights to form a multidimensional vector. The weight coefficients are determined during the research and development phase based on road maintenance priorities and test feedback. For example, icing risk has the highest weight, followed by crack density, and then slope risk. During the fusion process, the weights are also adjusted in real time based on the vehicle's current speed and remaining maintenance dosage to balance maintenance efficiency and resource utilization. For example, in the case of a continuous downhill slope and a significant increase in humidity, the system will temporarily increase the weights for icing risk and slope risk to ensure that the spray height and formulation are focused on responding to such emergencies. The generated pavement maintenance demand vector is ultimately output in a fixed format, containing the numerical risk level, density index, and risk indicator. This serves as input for the next step of formulation decision-making and spray control, completing a closed-loop link from data perception to decision output.

[0032] Step S3: performing recipe decision and multi-objective optimization processing according to the pavement maintenance demand vector through a preset decision model to obtain a spray control instruction set.

[0033] In an embodiment of the present application, a decision model (e.g., a decision tree model) is pre-stored in the electronic equipment used in a road maintenance vehicle. This model, based on extensive road maintenance test data and simulation analysis results, learns and optimizes maintenance agent mixes for different climatic conditions, disease types, and terrain parameters. When the road maintenance demand vector output by the environmental perception module enters the decision module, the model first matches and identifies the icing risk level, crack density, slope impact, and other indicators contained in the vector to determine the type of main agent to use. Main agent types include, but are not limited to, deicing agents, asphalt regeneration agents, and mixtures thereof. For example, when the icing risk level in the risk vector is extremely high and the crack density is low, the model tends to select a high-concentration deicing agent. Conversely, when the crack density exceeds a preset threshold and the icing risk is low, asphalt regeneration agents are preferred. In certain scenarios with both icing and cracking risks, the model determines a mixing ratio of the two main agents based on historical test optimization results. For example, a ratio of seven parts deicing agent to three parts regeneration agent is used to achieve a balanced combination of antifreeze and crack sealing.

[0034] After completing the matching of the main agent, the system calls in the concentration optimization algorithm, which comprehensively considers the viscosity changes of the main agent under different temperature and humidity conditions and its influence on the spray atomization characteristics, and determines the basic mixing concentration through iterative solution or table lookup. The algorithm is based on rheological models and experimental calibration curves. For any given road maintenance demand vector, it can quickly calculate the optimal concentration value that can ensure that the maintenance agent penetrates the cracks without causing material waste due to excessive concentration. Taking the specific example of low temperature and high humidity at night in the valley, when the main agent is selected as a snow melting agent and the surface infrared temperature is below minus five degrees Celsius, the concentration optimization algorithm will set the upper limit of the concentration to about 60% on the basis of ensuring the concentration of the solution below the freezing point, so as to ensure sufficient snow melting capacity after spraying and take into account economy.

[0035] After determining the base mixing concentration, the system optimizes the base concentration using real-time wind speed information recorded in the maintenance demand vector. Wind speed compensation automatically calculates the amount of thickener required by analyzing the effect of wind speed on spray particle size and impact point offset, ensuring that droplets are not excessively dispersed during spraying due to strong winds. For example, when wind speeds exceed 5 m / s, a specific amount of polymer thickener is automatically added based on a pre-calibrated wind speed-thickening curve, thereby improving the adhesion of the curing agent and reducing crosswind drift.

[0036] After wind speed compensation is complete, all recipe parameters (i.e., base agent type, base mix concentration, and viscosity enhancer dosage) are packaged into a command format that conforms to the communication protocol between the electronic device and the actuator. This command protocol defines the encoding position and length of the base agent identifier, concentration value, and viscosity enhancer dosage fields, ensuring that upon receiving the data, the device can accurately interpret each parameter and drive the corresponding pumps and valves to output the curing solution at the corresponding concentration. This completes the spray control command set into a complete sequence that can be issued to the mechanical actuator.

[0037] Step S4: performing spray height optimization processing according to the real-time collected positioning data and the spray control instruction set to obtain an anti-interference spray height setting value.

[0038] In an embodiment of the present application, the electronic device first obtains the vehicle's current latitude, longitude, and elevation data through a built-in GPS module and a digital terrain model interface. These latitude, longitude, and elevation data are collectively referred to as satellite positioning coordinates and are used to accurately locate the road maintenance vehicle's spatial position on mountain roads. After receiving this real-time positioning data, the latitude and longitude coordinates are mapped to corresponding grid locations in the digital terrain model database through a conversion module. The neighborhood elevation information for the area containing the grid is retrieved from the database, and the terrain slope is calculated based on this information. Terrain slope refers to the inclination angle corresponding to the ratio of the average elevation difference between the current position and several adjacent pixels to their horizontal distance. This angle directly reflects the degree of inclination of the road surface and the geometric relationship between the interaction between droplets and the ground during spray coverage. Slope information is critical for setting the spray height: excessive inclination angles can lead to increased spray loss, and the slope direction can also affect the trajectory of droplets under the influence of gravity and inertia. On a typical shady uphill section of a mountain road, if the slope angle reaches 15°, if the spray droplets are released at a height parallel to the horizontal plane, they will prematurely wash the side slope or be blocked by the terrain when moving downward, resulting in a dead angle for spraying.

[0039] After completing terrain mapping and obtaining the slope value, the electronics invoke a preset baseline height algorithm and the current spray control instruction set. Using spray physical parameters such as the main agent type and mixture concentration as input, combined with spray hardware parameters such as nozzle type, spray angle, and flow characteristics, the formulated baseline height algorithm calculates the ideal spray height. Based on experimental calibration curves and an aerodynamic model, the baseline height algorithm maps variables such as nozzle outlet liquid particle size, spray velocity, spray cone angle, and mixture viscosity to a height value. For example, using a medium-flow nozzle and a room-temperature deicing agent, calibration results indicate that for optimal coverage with an average nozzle outlet droplet diameter of 200 microns and a spray velocity of 10 m / s, the initial spray height from the nozzle to the road surface should be set at approximately 0.5 m. If the viscosity increases due to increased spray concentration, the baseline algorithm adjusts the height to 0.55 m to ensure that the particle size distribution matches the impact kinetic energy. During continuous road patrol, the initial spray height at each time point is calculated in real time on the vehicle main control board and packaged together with the spatiotemporally synchronized spray control instruction set for subsequent dynamic compensation.

[0040] After determining the initial spray height, slope compensation is performed based on the terrain gradient. This process applies the slope angle to the slope compensation function, adding a correction term that is positively correlated with the slope to the initial spray height. The magnitude of this correction term depends on the slope level, with a smaller correction factor for gentle sections and a larger correction factor for steeper slopes. For example, during a patrol in a shady valley, when the equipment detected a 12-degree slope, the compensation function added a correction distance of approximately 0.05 meters to the initial spray height of 0.5 meters, ensuring stable landing of the spray on the inclined road surface. On a gentle slope of only 3 degrees, the compensation value was approximately 0.01 meters, striking a balance between energy conservation and preventing overspray. This slope compensation takes into account both the tendency of droplets to slide down the slope due to gravity and lateral inertial deflection, ensuring that the kinetic energy and landing distribution of droplets upon impact with the road surface meet the requirements for crack penetration or snowmelt.

[0041] After the slope correction height is generated, it is also necessary to combine the atmospheric wind speed information collected in real time to perform wind speed compensation processing. Specifically, the latest wind speed value is read from the environmental working condition parameters. When the wind speed value exceeds the preset wind speed threshold, the amount of height increase is automatically calculated based on the preset wind speed-height correction curve, so that the spray can better resist crosswind drift in the air flow field. For example, when patrolling on a ridge at an altitude of 2000m, the meteorological module detects that the wind speed reaches 6m / s and increases the slope correction height by 0.08m on the basis of 0.55m to ensure that the spray particles do not deviate from the target area due to strong winds after leaving the nozzle, and at the same time avoid excessive spraying causing the spray to evaporate in the air and reduce maintenance efficiency. Wind speed compensation takes into account the effects of turbulence intensity, wind speed gradient and droplet size on drift characteristics. The calibration data obtained from laboratory wind tunnels and field tests form a key parameter library, which provides a corresponding correction height ratio for each wind speed.

[0042] After continuously performing terrain mapping, baseline height calculation, slope compensation, and wind speed compensation, the electronic device determines an interference-resistant spray height setting that comprehensively considers road inclination, atmospheric conditions, and spray characteristics. This interference-resistant spray height setting not only adapts to complex terrain but also maintains precise spray coverage in high wind speeds, significantly improving safety and energy efficiency in mountain road maintenance. This height optimization process is completed within milliseconds before each spray start, ensuring that the nozzle can update the optimal spray height in real time when entering a new road section or negotiating a curve.

[0043] Step S5: performing multi-axis collaborative control processing according to the real-time collected spray height data, the spray control instruction set, and the anti-interference spray height setting value to obtain an equipment control signal sequence.

[0044] After spray height optimization is complete, the system uses real-time collected spray height data, a previously generated spray control instruction set, and an anti-interference spray height setpoint as input. The built-in multi-axis coordinated controller generates the final device control signal sequence issued to the actuators, ensuring synchronized coordination of liquid mixing flow, boom raising and lowering movements, and safety responses. First, the flow pump drive signal is automatically adjusted based on the base mixture concentration parameter in the spray control instruction set. The base mixture concentration is derived from a main agent matching and concentration optimization algorithm, and its value reflects the viscosity and rheological properties of the mixed solution under current environmental conditions. A higher base concentration requires the corresponding flow pump to deliver more material at the same pump port diameter and outlet pressure. Therefore, the system calculates a new pump speed ratio using a built-in pump speed ratio algorithm. This mapping from concentration to pump speed is achieved by comprehensively considering the pump characteristic curve and the effect of liquid viscosity on flow. This mapping is obtained through testing of multiple concentration samples and is applied in real time during runtime via a table lookup or interpolation method. This generates a precise flow pump drive signal, which directly drives the variable frequency controller to adjust the pump motor speed, ensuring that the spray system achieves the desired mixed liquid flow rate without delay.

[0045] The hydraulic lift system simultaneously implements closed-loop PID control to counteract interference between the set spray height and real-time measured spray height data. Spray height data is continuously fed back by an onboard laser ranging sensor and transmitted to the main control unit via a high-speed data bus. This data is used to monitor the actual height of the nozzle at the end of the boom above the road surface. PID control utilizes a three-component system: proportional, integral, and differential. The proportional component directly generates an adjustment based on the current height error, the integral component accumulates historical errors to eliminate steady-state deviations, and the differential component suppresses sudden errors and improves system response speed. The closed-loop controller is calibrated prior to departure based on the boom structure, oil circuit damping, and hydraulic cylinder inertia. During operation, it continuously and automatically corrects the output signal based on height feedback. A built-in interrupt mechanism promptly handles height anomalies, enabling the hydraulic cylinder to complete micron-level displacement adjustments in a very short time. This closed-loop PID control ensures the nozzle maintains its set height precisely even when navigating hilly terrain or turning, avoiding blind spots in spray coverage caused by sudden changes in terrain.

[0046] Simultaneously, pipeline pressure and execution status data are monitored in real time, triggering a blockage alarm and backflush signal when a blockage or abnormally high pressure is detected. Pipeline pressure is collected by a high-precision pressure sensor installed between the pump outlet and the boom inlet, capable of detecting pressure changes within the hydraulic oil and spray pipes at a frequency of milliseconds. When the system performs multi-axis motions and the flow pump drive signal surges, the fluid resistance within the pipe increases, causing the pressure curve to rise sharply for a short period of time. If the pressure exceeds a preset threshold and persists for a set duration, the safety monitoring module immediately identifies a pipe blockage and generates a blockage alarm. Furthermore, by reading execution status data, including pump motor current, hydraulic cylinder feedback current, and boom position limit switch status, the system can further identify anomalies such as leaks, mechanical shock, or unexpected travel. If the safety strategy determines that anomalies are short-term and within a controllable range, a warning is issued to prompt further manual investigation. However, if high pressure or sudden flow drops occur repeatedly, the system automatically generates a backflush signal, instructing the pump to switch to reverse output mode. High-pressure pulses are used to flush out residual impurities and crystals within the pipe and nozzle, restoring normal system flow.

[0047] Finally, the multi-axis collaborative controller encapsulates and processes each signal according to a preset timing protocol, forming a unified device control signal sequence. This timing encapsulation not only includes the transmission time of each signal but also includes dependencies and priorities between signals, ensuring seamless integration of pump speed changes, boom height adjustment, and safety emergency response. Specifically, the protocol stipulates that within each control cycle, a pump speed drive signal is first issued to adjust the spray flow rate. Spraying is then allowed only after the hydraulic cylinder position has stabilized to a high level of interference resistance. During spraying, the pipeline pressure is continuously monitored. If the pipeline pressure is abnormal, the system immediately interrupts the normal spraying process and issues a backflush signal with the highest priority. The protocol also assigns a redundant checksum field to each signal to enable slave devices to verify the integrity of the instructions, ensuring reliable communication when multiple axes operate simultaneously. The resulting control signal sequence is sorted by timestamp and transmitted to each execution node via the vehicle's CAN bus or Ethernet industrial bus, ensuring that execution units such as the flow pump, hydraulic cylinder, pressure valve, and agitator operate in a unified and coordinated rhythm.

[0048] In an optional embodiment, to further enhance the responsiveness of the spray maintenance system to road surface coverage in complex mountainous environments, the adaptive adjustment method for road surface spray maintenance in the embodiment of the present application further includes: Firstly, the real-time spraying effect data is collected by the rear high-speed camera and the microwave humidity sensor unit. The spraying effect data includes the coverage image and the penetration depth data. The coverage image contains the optical reflection characteristics of the curing agent film in different areas of the road surface. The penetration depth data is measured by the microwave sensor, which reflects the millimeter-level change of the liquid penetration depth in the cracks or pores. The spraying effect data reflects the uniformity of the curing agent distribution and the penetration performance in the real environment, which is crucial for the next round of formula update and control signal adjustment.

[0049] For the coverage image, the collected coverage image is first converted into a grayscale value image to eliminate the recognition interference caused by color and light differences. This conversion is achieved through linear mapping or gamma correction, which maps the RGB color space to a single-channel grayscale space, making the liquid film on the road surface and the bare road surface clearly distinguishable in grayscale values. For example, the liquid film area usually shows higher grayscale values due to the liquid reflection characteristics, while the uncovered area shows lower grayscale values. With this difference, the curing agent coverage area can be accurately segmented. After dividing the converted grayscale image into the same fixed unit blocks as the grid-based disease identification, the grayscale value distribution is recorded by traversing the grayscale matrix of each unit block, and finally the coverage area grayscale value matrix is generated. The coverage area grayscale value matrix can be regarded as a grayscale distribution heat map of the road coverage image in space.

[0050] Next, the coverage area grayscale value matrix is analyzed for coverage uniformity to obtain the coefficient of variation. The coefficient of variation is a standardized index that measures the dispersion of image grayscale distribution, defined as the ratio of the standard deviation of grayscale values to the average value of grayscale values. By calculating the average value and standard deviation of the grayscale values of all unit blocks in the entire curing area, the final value is obtained according to the coefficient of variation formula. This coefficient of variation can intuitively reflect the uniformity of the sprayed liquid film: the smaller the coefficient of variation, the smaller the grayscale difference, and the more uniform the spray coverage; otherwise, it indicates that the spray agent is too concentrated or missed in some areas. Taking the night spraying on a steep slope as an example, the coefficient of variation measured after the initial spraying in a windless state is 0.15, indicating that the coverage is relatively uniform, while it may rise above 0.35 when encountering sudden gusts, indicating the need to re-optimize the spray bar height or the amount of tackifier.

[0051] Meanwhile, the regional penetration compliance detection and statistics are performed according to the pavement condition map and the penetration depth data. The pavement condition map marks whether each unit block has a crack, water accumulation or icing risk in a grid manner; the penetration depth data reflects the penetration depth of the liquid in different sub-regions. The coverage area is divided into two categories: “crack area” and “non-crack area”, and a penetration compliance threshold is set for each category. The penetration depth index requirement of the crack area is usually higher than 3 mm to ensure that the liquid can penetrate into the crack for repair, while the penetration depth index requirement of the non-crack area is below 0.5 mm to avoid waste and road water accumulation. In the statistics process, first, identify which sub-regions have met the corresponding threshold, and determine them as “compliance units”. Then, count the number of compliance units and compare it with the total number of units. Finally, output the number of compliance areas and the total number of areas. For example, in a high-cold shady mountain road detection, a total of 200 units are divided, of which 150 units in the crack area have a penetration depth of more than 3 mm and are determined to be compliance, and the other 50 units in the non-crack area have a penetration depth of less than 0.5 mm and are also considered to be compliance. The total number of compliance units is 200, accounting for the full score.

[0052] After obtaining the coefficient of variation and the penetration compliance statistics, a preset parameter optimization model is called to evaluate and optimize the spraying effect to obtain a set of signal adjustment coefficients. The parameter optimization model is a multi-objective optimization framework based on the Bayesian optimization algorithm and historical operation data, which considers both the spraying uniformity (with the reciprocal of the coefficient of variation as one of the targets) and the penetration compliance rate (the ratio of the number of compliance units to the total number of units as the second target), and jointly optimizes key parameters such as the height compensation coefficient of the spray bar, the pump speed ratio correction coefficient and the tackifier addition ratio under the premise of ensuring safety monitoring margin. When the model runs, the coefficient of variation and the penetration compliance rate are used as sample return indicators, and the Gaussian process or random forest regressor is input combined with the current operation environment vector (including terrain slope, wind speed, temperature and humidity, etc.). An optimal set of signal adjustment coefficients is calculated through iterative search or table lookup. For example, in the aforementioned gust environment, if the coefficient of variation exceeds 0.3 and the penetration compliance rate is less than 90%, the optimization model may increase the height compensation value of the spray bar by 0.02 meters and the tackifier addition ratio by 0.03, and slightly reduce the pump speed ratio to reduce the scattering of molten liquid, thereby achieving a synergistic improvement of the spraying effect.

[0053] Finally, the originally issued equipment control signal sequence is compensated and optimized based on the obtained signal adjustment coefficient set to generate a corrected adjustment control signal sequence. The signal compensation logic couples the original pump speed drive signal, hydraulic cylinder position control signal and safety monitoring instruction with the adjustment coefficient, adjusts the corresponding duty cycle and frequency in the pump speed instruction, modifies the target height offset in the hydraulic cylinder motion trajectory, and fine-tunes the pipeline pressure threshold when necessary. For example, when encountering complex valleys with repeated depressions, the compensation module will first increase the boom lifting speed and amplitude to avoid liquid retention in the depressed areas; in continuous high-temperature sections, the system will appropriately reduce the pump speed ratio to slow down the evaporation rate of the liquid film. All corrected signals will be repackaged as equipment control signal sequences and sent to the pump and valve control unit and hydraulic drive unit through the real-time communication bus, so that the next round of spraying operations can immediately absorb online evaluation feedback and achieve true adaptive closed-loop optimization.

[0054] This application is applied to the field of road maintenance technology. It generates environmental operating parameters by performing spatiotemporal alignment and feature extraction on multi-source raw data, and then performs quantitative analysis of road surface characteristics based on the environmental operating parameters to generate a road maintenance demand vector. The decision model is combined to perform formulation decision-making and multi-objective optimization to obtain a spray control instruction set. The spray height is optimized based on the positioning data and the spray control instruction set to obtain an anti-interference spray height setting value. Multi-axis collaborative control is performed based on the spray height data, the spray control instruction set, and the anti-interference spray height setting value to obtain an equipment control signal sequence. This application achieves real-time optimization of spray control during the road maintenance process by deeply integrating multi-source environment and vehicle positioning data, thereby improving the accuracy and efficiency of road spray maintenance, saving water resources and operating costs, extending the service life of the road surface, and ensuring traffic safety.

[0055] like Figure 2 , which is a functional module diagram of an adaptive adjustment device for pavement spray maintenance provided in an embodiment of the present application.

[0056] In some embodiments, the self-adaptive adjustment device 2 for road surface spray maintenance may include a plurality of functional modules composed of computer program segments. The computer program of each program segment in the self-adaptive adjustment device 2 for road surface spray maintenance may be stored in a memory of a server and executed by at least one processor to execute (see Figure 1 (Describe) the functionality of an adaptive adjustment method for pavement spray maintenance.

[0057] In the embodiment, the self-adaptive adjusting device 2 for road surface spraying maintenance can be divided into multiple functional modules according to the functions performed by the self-adaptive adjusting device 2. The functional modules can include a working condition extraction module 21, a road surface analysis module 22, a spraying control module 23, a height setting module 24, a cooperative control module 25, and a feedback adjusting module 26. The module referred to in the present application refers to a series of computer program segments capable of being executed by at least one processor and capable of completing a fixed function, which are stored in a memory. In the embodiment, the functions of the modules will be described in detail in subsequent embodiments.

[0058] The working condition extraction module 21 is configured to perform spatio-temporal alignment and feature extraction processing on the acquired multi-source original data to generate environmental working condition parameters.

[0059] In an optional implementation, the working condition extraction module 21 is specifically configured to: perform timing calibration and spatial mapping processing on the environmental detection data to obtain spatio-temporal synchronous environmental data; perform gridding and disease identification processing on the road section image through a preset identification model to obtain a road surface state map; perform terrain data mapping processing on the satellite positioning coordinates through a preset digital terrain model to obtain a slope and a slope direction corresponding to the satellite positioning coordinates; perform format processing on the spatio-temporal synchronous environmental data, the road surface state map, the slope, and the slope direction according to a preset data format to generate environmental working condition parameters.

[0060] The road surface analysis module 22 is configured to perform road surface feature quantization analysis processing on the environmental working condition parameters to generate a road surface maintenance demand vector.

[0061] In an optional implementation, the road surface analysis module 22 is specifically configured to: perform icing risk assessment on the environmental working condition parameters through a preset icing risk algorithm to obtain an icing risk level index; perform road surface crack feature statistical analysis on the road surface state map to obtain a road surface crack density index; perform threshold value judgment on the environmental working condition parameters according to a preset mountain slope influence mapping table to obtain a slope influence level and a risk identifier; perform data fusion on the icing risk level index, the road surface crack density index, the slope influence level, and the risk identifier to generate a road surface maintenance demand vector.

[0062] The spraying control module 23 is configured to perform formula decision and multi-objective optimization processing on the road surface maintenance demand vector through a preset decision model to obtain a spraying control instruction set.

[0063] In an optional embodiment, the spray control module 23 is specifically configured to: Performing a main agent matching process according to the pavement maintenance demand vector through a preset decision model to obtain a main agent type; Calculating the main agent concentration according to the pavement maintenance demand vector and the main agent type using a preset concentration optimization algorithm to obtain a basic mixing concentration; Compensating and optimizing the basic mixture concentration according to the wind speed in the pavement maintenance demand vector to obtain a viscosity enhancer dosage; The main agent type, the basic mixing concentration and the viscosity enhancer dosage are packaged according to a preset instruction protocol to obtain a spray control instruction set.

[0064] The height setting module 24 is used to perform spray height optimization processing based on the real-time collected positioning data and the spray control instruction set to obtain an anti-interference spray height setting value.

[0065] In an optional embodiment, the height setting module 24 is specifically configured to: The digital terrain model is used to map the terrain data based on the real-time collected positioning data to obtain the terrain slope corresponding to the current location; Performing a reference height calculation process according to a preset reference height algorithm and the spray control instruction set to obtain an initial spray height; Performing slope compensation processing on the initial spraying height according to the terrain slope to obtain a slope-corrected height; The slope correction height is subjected to wind speed compensation processing according to the wind speed collected in real time to obtain an anti-interference spray height setting value.

[0066] The collaborative control module 25 is used to perform multi-axis collaborative control processing according to the real-time collected spray height data, the spray control instruction set and the anti-interference spray height setting value to obtain an equipment control signal sequence.

[0067] In an optional embodiment, the collaborative control module 25 is specifically configured to: Performing a pump speed ratio adjustment process according to the basic mixed concentration to obtain a flow pump driving signal; Performing closed-loop PID control processing on the anti-interference spray height setting value and the real-time collected spray height data to obtain a hydraulic cylinder position control signal; Perform safety monitoring based on the real-time collected pipeline pressure and preset execution status data to obtain blockage alarms and corresponding backwash signals; The flow pump drive signal, the hydraulic cylinder position control signal, the blockage alarm and the backwash signal are time-sequentially packaged to obtain a device control signal sequence.

[0068] In an optional embodiment, the adaptive adjustment device 2 for road surface spray maintenance further includes a feedback adjustment module 26, which is specifically configured to: Collecting the coverage image and penetration depth data of the ground after spraying in real time, and performing grayscale value conversion on the coverage image to obtain a grayscale value matrix of the coverage area; Performing coverage uniformity analysis based on the coverage area grayscale value matrix to obtain a coefficient of variation; Performing regional penetration compliance testing and statistics based on the road condition map and the penetration depth data to obtain the number of compliance areas and the total number of areas; Performing spraying effect evaluation and parameter optimization processing according to the coefficient of variation, the number of qualified areas, and the total number of areas through a preset parameter optimization model to obtain a signal adjustment coefficient set; The device control signal sequence is compensated and optimized according to the signal adjustment coefficient set to obtain a modified adjustment control signal sequence.

[0069] It should be understood that the various variations and specific embodiments of the methods provided in the above embodiments are also applicable to the adaptive adjustment device for pavement spraying maintenance in this embodiment. Through the above detailed description of the adaptive adjustment method for pavement spraying maintenance, those skilled in the art can clearly understand the implementation method of the adaptive adjustment device for pavement spraying maintenance in this embodiment. For the sake of brevity of the specification, it will not be described in detail here.

[0070] like Figure 3 , which is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0071] In a preferred embodiment of the present invention, the electronic device 3 may include, but is not limited to: a memory 31 , at least one processor 32 and at least one communication bus 33 .

[0072] Those skilled in the art should understand that Figure 3 The structure of the electronic device 3 shown does not constitute a limitation of the embodiment of the present invention. The electronic device 3 may also include more or less other hardware or software than shown in the figure, or a different component arrangement.

[0073] In some embodiments, the electronic device 3 is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits, programmable gate arrays, digital processors and embedded devices.

[0074] It should be noted that the electronic device 3 is only an example, and other existing or future electronic products can also be applicable to the present application, and should be included in the protection scope of the present application and included herein by reference.

[0075] In some embodiments, the memory 31 stores a computer program which, when executed by the at least one processor 32, implements all or part of the steps of the adaptive adjustment method for road surface spraying maintenance as described. The memory 31 includes a Read-Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an Electrically-Erasable Programmable Read-Only Memory (EEPROM), a Compact Disc Read-Only Memory (CD-ROM) or other optical disk memory, a magnetic disk memory, a magnetic tape memory, or any other computer readable medium capable of carrying or storing data. Further, the computer readable storage medium can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.

[0076] In some embodiments, the at least one processor 32 serves as the control core (Control Unit) of the electronic device 3. It utilizes various interfaces and circuits to connect the various components of the electronic device 3. It executes programs or modules stored in the memory 31 and accesses data stored in the memory 31 to perform various functions and process data in the electronic device 3. For example, when executing the computer program stored in the memory 31, the at least one processor 32 implements all or part of the steps of the adaptive adjustment method for pavement spray maintenance described in the embodiments of this application; or implements all or part of the functions of the adaptive adjustment device for pavement spray maintenance. The at least one processor 32 can be comprised of an integrated circuit, such as a single packaged integrated circuit or multiple packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips.

[0077] In some embodiments, the at least one communication bus 33 is configured to enable communication between the memory 31 and the at least one processor 32. Although not shown, the electronic device 3 may also include a power supply (e.g., a battery) to power various components. Preferably, the power supply can be logically connected to the at least one processor 32 via a power management device, thereby enabling the power management device to manage charging, discharging, and power consumption. The power supply may also include one or more DC or AC power supplies, a recharging device, a power failure detection circuit, a power converter or inverter, a power status indicator, and other components. The electronic device 3 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be detailed here.

[0078] The above-mentioned integrated unit implemented in the form of a software functional module can be stored in a computer-readable storage medium. The above-mentioned software functional module stored in a storage medium includes a number of instructions for causing an electronic device (which can be a personal computer, electronic device, or network device, etc.) or a processor to execute portions of the methods described in various embodiments of the present application.

[0079] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the module division is only a logical function division, and other division methods may be used in actual implementation.

[0080] The modules illustrated as separated components can or can not be physically separate, and the components illustrated as modules can or can not be physical units, and can be located in one position, or distributed on a plurality of network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment.

[0081] The above are preferred embodiments of the present application, and are not intended to limit the protection scope of the present application, therefore: all equivalent changes made according to the structure, shape, principle of the present application should be covered within the protection scope of the present application.

Claims

1. An adaptive adjustment method for road spray maintenance, characterized in that: The method comprises: Perform spatiotemporal alignment and feature extraction on the acquired multi-source raw data to generate environmental operating parameters; Performing quantitative analysis and processing of pavement characteristics according to the environmental working condition parameters to generate a pavement maintenance demand vector; Performing formulation decision-making and multi-objective optimization processing according to the pavement maintenance demand vector through a preset decision model to obtain a spray control instruction set; Performing spray height optimization processing based on the real-time collected positioning data and the spray control instruction set to obtain an anti-interference spray height setting value; Multi-axis collaborative control processing is performed based on the real-time collected spray height data, the spray control instruction set and the anti-interference spray height setting value to obtain an equipment control signal sequence.

2. The adaptive adjustment method for road surface spray maintenance according to claim 1, characterized in that: The multi-source raw data includes environmental detection data, road section images, and satellite positioning coordinates. The spatiotemporal alignment and feature extraction processing of the acquired multi-source raw data to generate environmental working condition parameters includes: Performing time sequence calibration and spatial mapping processing on the environmental detection data to obtain time-space synchronized environmental data; Performing gridding and disease identification processing on the road section image through a preset recognition model to obtain a road surface condition map; Performing terrain data mapping processing according to the satellite positioning coordinates using a preset digital terrain model to obtain the slope and slope direction corresponding to the satellite positioning coordinates; The spatiotemporal synchronized environmental data, the road surface state map, the slope, and the slope direction are formatted according to a preset data format to generate environmental operating condition parameters.

3. The adaptive adjustment method for road surface spray maintenance according to claim 2, characterized in that: The quantitative analysis and processing of road surface characteristics according to the environmental working condition parameters to generate a road surface maintenance demand vector includes: Performing an icing risk assessment based on the environmental operating condition parameters using a preset icing risk algorithm to obtain an icing risk level indicator; Performing a statistical analysis of pavement crack characteristics on the pavement condition map to obtain a pavement crack density index; Performing threshold judgment on the environmental working condition parameters according to a preset hillside impact mapping table to obtain a slope impact level and a risk indicator; Data fusion is performed on the icing risk level index, the pavement crack density index, the slope impact level, and the risk identifier to generate a pavement maintenance demand vector.

4. The adaptive adjustment method for road surface spray maintenance according to claim 1, characterized in that: The method of performing a recipe decision and a multi-objective optimization process based on the pavement maintenance demand vector by using a preset decision model to obtain a spray control instruction set includes: Performing a main agent matching process according to the pavement maintenance demand vector through a preset decision model to obtain a main agent type; Calculating the main agent concentration according to the pavement maintenance demand vector and the main agent type using a preset concentration optimization algorithm to obtain a basic mixing concentration; Compensating and optimizing the basic mixture concentration according to the wind speed in the pavement maintenance demand vector to obtain a viscosity enhancer dosage; The main agent type, the basic mixing concentration and the viscosity enhancer dosage are packaged according to a preset instruction protocol to obtain a spray control instruction set.

5. The adaptive adjustment method for road surface spray maintenance according to claim 2, characterized in that: The spray height optimization process is performed based on the real-time collected positioning data and the spray control instruction set to obtain an anti-interference spray height setting value, including: The digital terrain model is used to map the terrain data based on the real-time collected positioning data to obtain the terrain slope corresponding to the current location; Performing a reference height calculation process according to a preset reference height algorithm and the spray control instruction set to obtain an initial spray height; Performing slope compensation processing on the initial spraying height according to the terrain slope to obtain a slope-corrected height; The slope correction height is subjected to wind speed compensation processing according to the wind speed collected in real time to obtain an anti-interference spray height setting value.

6. The adaptive adjustment method for road surface spray maintenance according to claim 4, characterized in that: The multi-axis collaborative control process is performed based on the real-time collected spray height data, the spray control instruction set, and the anti-interference spray height setting value to obtain a device control signal sequence, including: Performing a pump speed ratio adjustment process according to the basic mixed concentration to obtain a flow pump driving signal; Performing closed-loop PID control processing on the anti-interference spray height setting value and the real-time collected spray height data to obtain a hydraulic cylinder position control signal; Perform safety monitoring based on the real-time collected pipeline pressure and preset execution status data to obtain blockage alarms and corresponding backwash signals; The flow pump drive signal, the hydraulic cylinder position control signal, the blockage alarm and the backwash signal are time-sequentially packaged to obtain a device control signal sequence.

7. The adaptive adjustment method for road surface spray maintenance according to claim 2, characterized in that: The method further comprises: Collecting the coverage image and penetration depth data of the ground after spraying in real time, and performing grayscale value conversion on the coverage image to obtain a grayscale value matrix of the coverage area; Performing coverage uniformity analysis based on the coverage area grayscale value matrix to obtain a coefficient of variation; Performing regional penetration compliance testing and statistics based on the road condition map and the penetration depth data to obtain the number of compliance areas and the total number of areas; Performing spraying effect evaluation and parameter optimization processing according to the coefficient of variation, the number of qualified areas, and the total number of areas through a preset parameter optimization model to obtain a signal adjustment coefficient set; The device control signal sequence is compensated and optimized according to the signal adjustment coefficient set to obtain a modified adjustment control signal sequence.

8. An adaptive adjustment device for road spray maintenance, characterized in that: The device comprises: The working condition extraction module is used to perform spatiotemporal alignment and feature extraction on the acquired multi-source raw data to generate environmental working condition parameters; a pavement analysis module, configured to perform quantitative analysis and processing of pavement characteristics according to the environmental working condition parameters to generate a pavement maintenance demand vector; A spray control module, configured to perform formulation decision making and multi-objective optimization processing according to the pavement maintenance demand vector through a preset decision model to obtain a spray control instruction set; A height setting module is used to optimize the spray height according to the real-time collected positioning data and the spray control instruction set to obtain an anti-interference spray height setting value; The collaborative control module is used to perform multi-axis collaborative control processing based on the real-time collected spray height data, the spray control instruction set and the anti-interference spray height setting value to obtain an equipment control signal sequence.

9. An electronic device, characterized in that: The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the adaptive adjustment method for pavement spray maintenance according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the adaptive adjustment method for pavement spray maintenance according to any one of claims 1 to 7 are implemented.

Images