Mobile intelligent-control spraying and dust-settling system

Abstract

The invention discloses a mobile intelligent control spraying and dust-settling system, and particularly relates to the technical field of compensation or utilization of an external environment of a spraying and dust-settling spraying vehicle under a wind field disturbance condition, which comprises a plurality of wind speed and wind direction sensing nodes mounted on a lifting rod in the advancing process of the spraying and dust-settling spraying vehicle, acquiring a plurality of local wind field parameters in different heights and directions, and constructing a wind speed gradient data set based on the local wind field parameters; and performing normalization and disturbance feature extraction processing on the wind speed gradient data set to generate a wind disturbance time sequence and a spatial disturbance distribution map. By constructing a time-space coupling control mechanism fusing wind disturbance feature extraction, trend prediction and path calibration, advanced sensing of non-steady-state wind field disturbance and dynamic correction of spray response parameters are achieved, and therefore the problems of sensing-control coupling lag and spray offset errors are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of compensating or utilizing the external environment of a spray dust suppression sprinkler under the disturbance of a wind field. More specifically, the present invention relates to a mobile intelligent control spray dust suppression system. Background Art

[0002] A mobile spray dust suppression system operating in an environment with frequent wind speed changes, namely a spray-type dust suppression sprinkler, faces the core problem of coupling lag between traditional perception and control. In the prior art, spray dust suppression sprinklers generally adopt a feedback control mechanism based on real-time wind speed monitoring and wind direction analysis, that is, real-time wind field data is sensed by a meteorological sensor, and accordingly, the nozzle angle, spray pressure or liquid spraying amount is adjusted. However, in areas with frequent microclimate disturbances and easily mutated wind speed directions such as coastal ports, canyon wind mouths, and high-rise construction zones, such control strategies will show obvious limitations; specifically manifested as: the wind field structure has a high degree of non-steadiness, air disturbances are discontinuously distributed in space and have a transition characteristic in time. The spray dust suppression system of the sprinkler always has a response delay based on the strategy of "current perception - derived regulation", and the spray trajectory is difficult to fit the dynamic center of the dust aggregation area. In addition, most current systems regard the wind field perception and spray execution chain as a linear causal structure, ignoring the non-linear feedback effect of the wind field itself on the fog mass propagation path. This "perception lag - regulation slowness" mechanism, especially in the initial stage of spraying, forms an obvious fog mass escape effect: that is, the spray is carried away from the target area by the rapidly changing wind disturbance, resulting in continuous offset errors and spraying dead zones, seriously reducing the dust suppression efficiency and resource utilization rate, and even forming secondary dust suspension in long slope or high tower areas. Therefore, the core problem faced by this system is not simply the untimely adjustment of the wind speed, but the lack of the ability to actively predict the future disturbance trend of the wind field and the structural pre-control mechanism of the air propagation path, which constitutes an obstacle to the operation of the spray system in a non-steady environment. Its essence is a problem of structural coupling error escape between perception and control. Summary of the Invention

[0003] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a mobile intelligent control spray dust suppression system, which realizes the early perception of non-steady wind field disturbances and the dynamic correction of spray response parameters by constructing a time - space coupling control mechanism integrating wind disturbance feature extraction, trend prediction and path calibration, thereby solving the problems of perception - control coupling lag and spray offset error existing in the background art.

[0004] To achieve the above object, the present invention provides the following technical solution: a mobile intelligent control spray dust suppression system, including an intelligent control system, an environmental governance system, and a spraying vehicle. The intelligent control system and the environmental governance system are installed on the spraying vehicle. The environmental governance system includes atomizing nozzles, a water storage tank, a power supply system, and a lifting rod; the intelligent control system includes a wind field construction module, a feature extraction module, a prediction module, a calibration module, and a compensation module; The wind field construction module is used to collect local wind field parameters at multiple different heights and directions by using a plurality of wind speed and direction sensing nodes installed on the lifting rod during the movement of the spray dust suppression spraying vehicle, and construct a wind speed gradient data set based on the local wind field parameters; The feature extraction module is used to perform normalization and perturbation feature extraction processing on the wind speed gradient data set to generate a wind disturbance time series and a spatial disturbance distribution map; The prediction module is used to input the wind disturbance time series and the spatial disturbance distribution map into a preset time-space dual-memory nested transformer prediction model, and output the prediction result of the wind disturbance change trend within the target time domain and the spray trajectory offset parameter; The calibration module is used to control some atomizing nozzles to release fog droplets for testing wind disturbances, and monitor the drift path of the fog droplets based on an image or acoustic wave return device, compare the drift path with the spray trajectory offset parameter, and update the spray trajectory offset parameter; The compensation module is used to generate control instructions for the attitude adjustment, spray angle correction, and spray pressure change of the atomizing nozzles according to the corrected spray trajectory offset parameter, and drive the environmental governance system through the intelligent control system to complete the spray compensation control.

[0005] In a preferred embodiment, the intelligent control system further includes a closed-loop regulation module. The closed-loop regulation module is used to re-collect the local wind field parameters of each wind speed and direction sensing node on the lifting rod after the compensation module completes the spray compensation control, and construct a new wind speed gradient data set; input the new wind speed gradient data set into the feature extraction module, and sequentially pass through the feature extraction module, the prediction module, the calibration module, and the compensation module; through the periodic linkage call of the intelligent control system, a closed-loop regulation mechanism for wind disturbance prediction and spray control is formed, with the change of local wind field parameters as the input and the update of control instructions as the output.

[0006] In a preferred embodiment, the atomizing nozzles are installed on the atomizing bracket at the rear of the spraying vehicle. The atomizing nozzles are connected to the water storage tank through a liquid pipe. The power supply system is arranged at the chassis position of the spraying vehicle and provides power output for the atomizing nozzles, the lifting rod, and related control circuits through a line distribution interface respectively; the lifting rod is fixed on the bracket structure at the top of the spraying vehicle. The lifting rod integrates wind speed and direction sensing nodes, and at the same time, the wind speed and direction sensing nodes are used as the front-end acquisition devices for local wind field parameters. The output data of the wind speed and direction sensing nodes is transmitted to the intelligent control system; The intelligent control system and the environmental governance system are bidirectionally connected through a control wire harness and a data communication module. The intelligent control system is used to receive the local wind field parameters of the lifting rod and send a control instruction for spraying to the atomizing nozzle according to the prediction module, the calibration module and the compensation module.

[0007] In a preferred embodiment, when the feature extraction module performs normalization and disturbance feature extraction processing on the wind speed gradient data set, the normalization processing includes performing mean translation and range scaling processing on the wind speed and wind direction parameters at each height and azimuth angle obtained by collection according to a preset time window, that is, forming a wind speed gradient matrix under a unified scale; after completing the normalization processing, the feature extraction module calculates the wind speed vector difference and the wind direction rotation offset amount between adjacent measurement points at the same time section based on the wind speed gradient matrix, and statistically calculates the wind speed volatility, the wind direction rotation frequency and the wind speed derivative change rate within a specified time step as wind disturbance features, forming a wind disturbance feature vector group; Arrange the wind disturbance feature vector group in chronological order to construct a wind disturbance time series. At the same time, based on the spatial positions of the measurement points of the wind speed and wind direction sensing nodes, the feature extraction module performs spatial interpolation on the wind disturbance features within the corresponding time window and maps them to the wind field area distribution map, solves the local wind disturbance intensity gradient field and the rotation direction distribution map, and forms a spatial disturbance distribution map.

[0008] In a preferred embodiment, the wind speed volatility of the wind disturbance feature is calculated by calculating the ratio of the standard deviation to the mean value of the wind speed values at the same measurement point within a specified time window, so as to reflect the relative change range of the wind speed within the time window; The wind direction rotation frequency of the wind disturbance feature is measured by counting the number of times the wind direction changes exceeding a preset angle threshold within a specified time window and normalizing it to the change frequency per unit time, so as to measure the wind direction instability; The wind speed derivative change rate of the wind disturbance feature represents the mutation intensity of the wind speed change trend by calculating the difference value of the wind speed derivative in adjacent time steps and statistically calculating the derivative change within a unit time.

[0009] In a preferred embodiment, in the prediction module, based on the wind disturbance time series and the spatial disturbance distribution map generated by the feature extraction module, the wind speed volatility, the wind direction rotation frequency and the wind speed derivative change rate form a time input tensor at consecutive time steps. At the same time, the wind disturbance intensity gradient field and the rotation direction distribution map form a spatial input tensor, which is used to construct the joint input structure of the transformer prediction model; Input the time input tensor and the spatial input tensor into the time memory encoding module and the spatial memory encoding module of the transformer prediction model respectively. The time memory encoding module extracts the time trend features of wind disturbance changes based on the multi-head attention mechanism and the position nesting structure, and the spatial memory encoding module extracts the spatial correlation features of wind disturbance perturbations based on the position mapping and the perturbation distribution weighting mechanism; Perform feature fusion and residual connection operations on the time trend features and the spatial correlation features in the fusion control unit of the transformer prediction model to form a unified time-space coupling feature tensor; Input the time-space coupling feature tensor into the decoding module of the transformer prediction model, and according to the preset target time domain sliding window, predict the change trends of wind speed volatility, wind direction rotation frequency, and wind speed derivative change rate in the future target time period, and output the wind disturbance change trend prediction result; Based on the wind disturbance change trend prediction result and the historical disturbance trajectory distribution in the spatial disturbance distribution map, calculate the offset angle, offset direction, and offset amplitude of the spray trajectory in the target time domain, and output the spray trajectory offset parameters.

[0010] In a preferred embodiment, the decoding module of the transformer prediction model includes a position encoding unit, a multi-head attention mechanism layer, a feed-forward neural network layer, and an output mapping layer. The decoding module receives the time-space coupling feature tensor output by the fusion control unit, and combines the time index position of the currently observed time step. The position encoding unit encodes the position indexes of each prediction time step in the target time period to generate corresponding time position encodings, and embeds the generated time position encodings into the time-space coupling feature tensor; The multi-head attention mechanism layer in the decoding module is used to construct an attention mapping relationship between historical features and prediction positions at the target time position, extract context feature representations with weight values within a preset upper threshold range between the historical time steps corresponding to each prediction time step, and use the feed-forward neural network layer to perform non-linear transformation on the context feature representations, and output a prediction intermediate result with time recurrence features; The output mapping layer of the decoding module projects the prediction intermediate result into the prediction component spaces of wind speed volatility, wind direction rotation frequency, and wind speed derivative change rate respectively to form a wind disturbance change trend prediction result; Among them, the preset target time-domain sliding window slides backward from the current moment by a preset time length, and the preset time length corresponds to the number of future time steps set in the transducer prediction model; at each prediction time step within the target time-domain sliding window, the decoding module sequentially performs an attention weight allocation operation on the fused time-space coupled feature tensor, and inputs the attention-weighted result into the feed-forward neural network layer for feature mapping processing to generate the perturbation prediction output corresponding to this time step, gradually generating the prediction value sequence of each perturbation variable within the target time period, so as to obtain the output of the change trend of the wind speed volatility, the change trend of the wind direction rotation frequency, and the change trend of the wind speed derivative change rate.

[0011] In a preferred embodiment, the atomizing nozzles in the local area where the wind speed volatility exceeds the preset wind speed fluctuation threshold, or the atomizing nozzles in the local area where the wind speed derivative change rate exceeds the preset wind speed derivative change threshold are defined as partial atomizing nozzles; During the non-dust-suppression operation stage, test droplets are released based on a preset perturbation intensity sorting rule, and the droplets are sprayed in an intermittent spraying mode with a duration less than 1 second and a spraying pressure lower than 50% of the lower limit of the conventional operation pressure; The image or sound wave feedback device includes an image recognition device or a sound wave positioning device. Through the image recognition device or the sound wave positioning device arranged on the lifting rod, the movement process of the droplets is collected, and the drift path of the droplets is obtained based on the continuous frame matching and position inversion method; the drift path is subjected to path overlap analysis with the spray trajectory offset parameter output by the prediction module, and an offset error between the drift path and the predicted trajectory is constructed, so as to characterize the relative error between the prediction result and the actual perturbation response; Based on the offset error, error correction is sequentially performed on the offset angle, offset direction, and offset amplitude in the spray trajectory offset parameter. The error correction includes decomposing the offset error between the drift path and the predicted trajectory into corresponding offset direction angles and offset amplitude components in space, and respectively adjusting the corresponding parameters; at the same time, based on the time difference between the response moment of the droplet drift path and the time stamp corresponding to the predicted trajectory, the time offset is calculated, and the time offset is used as a reference for evaluating the prediction lag.

[0012] The technical effects and advantages of the present invention: By introducing a wind disturbance trend prediction mechanism based on a time-space dual memory structure, this system actively models key disturbance factors such as wind speed volatility, wind direction rotation frequency, and wind speed derivative change rate, realizes the advance prediction of disturbance trends under non-steady wind fields, solves the core problem of coupling lag in perception and control in traditional feedback spray systems, and improves the fitting ability of the spray trajectory to the dynamic distribution of dust; During the wind field modeling process, the system introduces the wind disturbance intensity gradient field and the rotation direction distribution map to achieve quantitative modeling of the disturbance spatial distribution trend and the dominant rotation direction, providing a structured spatio-temporal disturbance input for the prediction model, thereby enhancing the model's ability to depict the wind disturbance evolution process in complex microclimate regions; Through the strategy of releasing a small amount of fog droplets in a short period and at a low intensity, combined with the technology of reconstructing the image or acoustic wave transmission path, the system can achieve dynamic sampling of the disturbance feedback path and actual response monitoring, and accordingly construct the spatial offset error between the predicted trajectory and the actual drift path, providing a reference for the closed-loop correction of the spray control parameters; Adopt the wind disturbance intensity sorting rule to set the response priority of the high-pressure atomizing nozzle, and through the local area spraying disturbance test, ensure that the nozzle resource allocation is more reasonable, avoiding waste of operation energy consumption and interference of fog droplet diffusion; By constructing a control structure integrating feature extraction, trend prediction, path verification and instruction compensation, the system can complete the prediction model update and control instruction reconstruction within the next control cycle after the wind field changes, ensuring that the spray control strategy can adapt to environmental disturbance changes and maintain continuous and effective response. Brief Description of the Drawings

[0013] Figure 1 It is a schematic diagram of the system module of the present invention.

[0014] Figure 2 It is a physical diagram of the intelligent control system and the environmental governance system in the present invention. Detailed Embodiments

[0015] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0016] Referring to the attached Figure 1-2 description, a mobile intelligent control spray dust suppression system according to an embodiment of the present invention includes an intelligent control system, an environmental governance system and a spraying vehicle. The intelligent control system and the environmental governance system are installed on the spraying vehicle. The spraying vehicle is a carrier for providing mobility. The spraying vehicle provides a platform for basic transportation and energy docking for the intelligent control system and the environmental governance system. The environmental governance system includes a high-pressure atomizing nozzle, a water storage tank, a power supply system, and an automatic lifting rod; the intelligent control system includes a wind field construction module, a feature extraction module, a prediction module, a calibration module, and a compensation module; The wind field construction module is used to collect local wind field parameters at different heights and directions using multiple wind speed and direction sensor nodes installed on the automatic lifting mast while the spray dust suppression sprayer is moving, and to construct a wind speed gradient dataset based on the local wind field parameters; The feature extraction module is used to perform normalization and disturbance feature extraction processing on the wind speed gradient data set to generate a wind disturbance time series and a spatial disturbance distribution map; The prediction module is used to input the wind disturbance time series and spatial disturbance distribution map into the preset time-space dual memory nested transformer prediction model, and output the wind disturbance change trend prediction results and spray trajectory offset parameters in the target time domain; The calibration module is used to control some high-pressure atomizing nozzles to release trace droplets for testing wind disturbances. This is used for wind disturbance path testing and prediction result verification. The module also monitors the drift path of trace droplets based on image or sound wave return devices, compares the drift path with the spray trajectory offset parameters, and updates the spray trajectory offset parameters. The compensation module is used to generate control instructions for posture adjustment, spray angle correction and spray pressure change of the high-pressure atomizing nozzle based on the corrected spray trajectory offset parameters, and drive the environmental management system through the intelligent control system to complete the spray compensation control.

[0017] The intelligent control system also includes a closed-loop control module, which is used to re-collect the local wind field parameters of each wind speed and direction sensor node on the automatic lifting rod after the compensation module completes the spray compensation control, and construct a new wind speed gradient data set; input the new wind speed gradient data set into the feature extraction module, and sequentially undergo normalization and disturbance feature extraction by the feature extraction module, trend prediction by the prediction module, update of spray trajectory offset parameters by the calibration module, and spray compensation control generation by the compensation module; through the periodic linkage call of the intelligent control system, a closed-loop control mechanism of wind disturbance prediction and spray control is formed with changes in local wind field parameters as input and control instruction updates as output.

[0018] The high-pressure atomizing nozzle is installed on the atomizing bracket at the rear of the spraying vehicle. The high-pressure atomizing nozzle is connected to the water storage tank through a liquid pipe. The power supply system is set at the chassis of the spraying vehicle and provides power output to the high-pressure atomizing nozzle, the automatic lifting rod and the related control circuit through the line distribution interface. The automatic lifting rod is fixed to the bracket structure on the top of the spraying vehicle. The automatic lifting rod is integrated with a wind speed and direction sensor node. At the same time, the wind speed and direction sensor node is used as a front-end acquisition device for local wind field parameters. The output data of the wind speed and direction sensor node is transmitted to the intelligent control system. The intelligent control system and the environmental governance system establish a two-way connection through a control wire harness and a data communication module. The intelligent control system is used to receive the local wind field parameters of the automatic lifting rod, and send control commands for spraying to the high-pressure atomizing nozzle according to the prediction module, calibration module and compensation module. The data communication module includes, but is not limited to, a main control communication interface, a data conversion and distribution unit, a wireless communication module, and a signal synchronization and caching module, and is used to realize the two-way transmission of data between the intelligent control system and the environmental governance system. The power supply of the intelligent control system and the environmental governance system is docked with the main energy system provided by the spraying vehicle. The main energy system of the spraying vehicle includes a fuel power system or an electric power system (that is, an oil truck or an electric truck). Among them, the fuel power system of the spraying vehicle drives the integrated on-vehicle power generation unit to work through the engine, and the on-vehicle power generation unit outputs regulated direct current, which provides stable power to the intelligent control system and the environmental governance system through the power supply system. The electric power system is based on the battery pack configured on the spraying vehicle, and distributes the required working voltage to the power supply system through the on-vehicle power management module to realize the direct power supply to the intelligent control system and the environmental governance system. The above two types of power systems correspond to fuel-type spraying vehicles and electric-type spraying vehicles respectively, and realize the docking of energy support and control coordination through a unified power supply system interface and control bus. The high-pressure atomizing nozzle is also integrated with a liquid pumping execution component, an attitude adjustment mechanism, a spray angle adjustment device and a spray pressure control unit. Among them, the liquid pumping execution component is connected to the water storage tank through a liquid pipe and is used to transport the liquid in the water storage tank to the nozzle of the high-pressure atomizing nozzle. The attitude adjustment mechanism is connected to the bracket of the high-pressure atomizing nozzle through a mechanical connecting rod or an electric drive unit to realize the pitching adjustment function of the nozzle around a fixed axis. The spray angle adjustment device is arranged on the movable guiding component arranged at the front end of the nozzle and is used to adjust the deflection angle of the spray direction under the action of a control signal. The movable guiding component includes, but is not limited to, an electric servo swing mechanism, a two-axis servo motor component, a stepping motor rotary joint or an electric universal ball seat component, etc. The spray pressure control unit is connected to the power supply system and receives the pressure control command from the intelligent control system through a control wire harness, and is used to adjust the working pressure of the liquid atomization at the nozzle, so as to realize the spray compensation control under multi-dimensional linkage. In addition, in actual applications, the automatic lifting rod can be selected from an electric push rod type lifting rod (linear electric cylinder), a synchronous belt drive type lifting rod or a pneumatic lifting rod, etc. Among them, the wind speed and wind direction sensing nodes include, but are not limited to, selecting integrated ultrasonic wind speed and wind direction sensors such as Gill WindSonic, Vaisala-WXT536 or RM-Young series, which are suitable for high-frequency wind field monitoring of mobile spray platforms.

[0019] When the feature extraction module performs normalization and perturbation feature extraction processing on the wind speed gradient data set, the normalization processing includes performing mean translation and range scaling processing on the wind speed and wind direction parameters at each height and azimuth angle obtained by collection according to a preset time window, that is, forming a wind speed gradient matrix under a unified scale; after completing the normalization processing, the feature extraction module calculates the wind speed vector difference and the wind direction rotation offset between adjacent measurement points at the same time section based on the wind speed gradient matrix, and statistically calculates the wind speed volatility, the wind direction rotation frequency, and the wind speed derivative change rate within a specified time step as wind disturbance features, forming a wind disturbance feature vector group; Arrange the wind disturbance feature vector group in chronological order to construct a wind disturbance time series. At the same time, based on the spatial positions of each measurement point of the wind speed and wind direction sensing nodes, the feature extraction module performs spatial interpolation on the wind disturbance features within the corresponding time window and maps them to the wind field area distribution map, solves the local wind disturbance intensity gradient field and the rotation direction distribution map, and forms a spatial disturbance distribution map, thereby realizing the structured conversion from the wind speed gradient data set to the spatio-temporal disturbance expression form, providing an input basis for the subsequent prediction module to build a model; The local wind disturbance intensity gradient field is based on the spatial interpolation of the wind speed volatility, combined with the result of the spatially interpolated wind speed derivative change rate. At each interpolated grid point, the spatial first-order partial derivative of the wind speed volatility and the local fluctuation intensity of the wind speed derivative change rate are calculated respectively, and a composite gradient field representing the change rate of disturbance strength and mutation sensitivity is formed through vector superposition, which is used to describe the spatial distribution trend and dynamic disturbance evolution characteristics of the wind disturbance intensity in the local area; The rotation direction distribution map is based on the interpolation result of the wind direction rotation frequency in the spatial grid, constructs the rotation frequency change vector between adjacent interpolation points, and introduces the synchronization weight of the wind speed derivative change rate to calculate the time stability index and the spatial consistency index of the main rotation direction, which are used to comprehensively describe the spatial dominant direction and the rotation trend evolution mode of the wind direction change in the disturbance area.

[0020] The wind speed volatility of the wind disturbance feature is calculated by the ratio of the standard deviation to the mean of the wind speed values at the same measurement point within a specified time window, which reflects the relative change amplitude of the wind speed within this time window; The wind direction rotation frequency of the wind disturbance feature is measured by counting the number of times the wind direction changes exceeding a preset angle threshold within a specified time window and normalizing it to the change frequency per unit time, which measures the wind direction instability; The wind speed derivative change rate of the wind disturbance feature represents the mutation intensity of the wind speed change trend by calculating the difference value of the wind speed derivative in adjacent time steps and statistically calculating the derivative change within a unit time.

[0021] In the prediction module, based on the wind disturbance time series and spatial disturbance distribution map generated by the feature extraction module, the wind speed volatility, wind direction rotation frequency, and wind speed derivative change rate are used to form a time input tensor at consecutive time steps. At the same time, the wind disturbance intensity gradient field and rotation direction distribution map are used to form a spatial input tensor, which is used to construct the joint input structure of the transformer prediction model; The time input tensor and the spatial input tensor are respectively input into the time memory encoding module and the spatial memory encoding module of the transformer prediction model. The time memory encoding module extracts the time trend features of wind disturbance changes based on the multi-head attention mechanism and the position nesting structure, and the spatial memory encoding module extracts the spatial correlation features of wind disturbance perturbations based on the position mapping and perturbation distribution weighting mechanism; The time trend features and the spatial correlation features are subjected to feature fusion and residual connection operations in the fusion control unit of the transformer prediction model to form a unified time-space coupling feature tensor. It should be noted that the fusion control unit of the transformer prediction model calculates the interaction response relationship between the two types of features under the same position encoding by performing dimension alignment and attention weighted fusion operations between the time trend features and the spatial correlation features, and forms a fused joint feature representation. Subsequently, a residual connection mechanism is introduced to perform weighted superposition of the fusion result and the original features respectively to enhance the joint representation ability while maintaining the original feature structure, and finally output a unified time-space coupling feature tensor; The time-space coupling feature tensor is input into the decoding module of the transformer prediction model. According to the preset target time domain sliding window, the change trends of the wind speed volatility, wind direction rotation frequency, and wind speed derivative change rate in the future target time period are predicted, and the wind disturbance change trend prediction result is output; Based on the wind disturbance change trend prediction result and the historical disturbance trajectory distribution in the spatial disturbance distribution map, the offset angle, offset direction, and offset amplitude of the spray trajectory in the target time domain are calculated, and the spray trajectory offset parameters are output.

[0022] The decoding module of the transformer prediction model includes a position encoding unit, a multi-head attention mechanism layer, a feed-forward neural network layer, and an output mapping layer. The decoding module receives the time-space coupling feature tensor output by the fusion control unit, and combines the time index position of the currently observed time step. The position encoding unit encodes the position indexes of each prediction time step in the target time period to generate corresponding time position encodings, and embeds the generated time position encodings into the time-space coupling feature tensor to maintain the continuity of the time structure and the consistent conduction of the position dependence relationship during the prediction process; The multi-head attention mechanism layer in the decoding module is used to construct an attention mapping relationship between historical features and prediction positions at the target time position, extract context feature representations with weight values within a preset upper threshold range between historical time steps corresponding to each prediction time step, perform a non-linear transformation on the context feature representations using a feed-forward neural network layer, and output a prediction intermediate result with time recurrence features; The output mapping layer of the decoding module projects the prediction intermediate result into the prediction component spaces of wind speed volatility, wind direction rotation frequency, and wind speed derivative change rate respectively, forming a wind disturbance change trend prediction result; Among them, the preset target time-domain sliding window slides backward from the current moment by a preset time length, and the preset time length corresponds to the number of future time steps set in the transformer prediction model; at each prediction time step within the target time-domain sliding window, the decoding module sequentially performs attention weight assignment operations on the fused time-space coupled feature tensor, and inputs the attention-weighted result into the feed-forward neural network layer for feature mapping processing to generate the perturbation prediction output corresponding to this time step, gradually generating a sequence of predicted values of each perturbation variable within the target time period, so as to obtain the output of the wind speed volatility change trend, wind direction rotation frequency change trend, and wind speed derivative change rate change trend; in addition, the preset target time-domain sliding window refers to a fixed-length time interval extending backward from the current observation time point, used to determine the time range for the decoding module to perform continuous prediction within future time steps.

[0023] Define the high-pressure atomizing nozzles in the local area where the wind speed volatility exceeds the preset wind speed fluctuation threshold, or the high-pressure atomizing nozzles in the local area where the wind speed derivative change rate exceeds the preset wind speed derivative change threshold as partial high-pressure atomizing nozzles; During the non-dust-suppression operation stage, release test micro-droplets based on a preset perturbation intensity ranking rule. The injection of micro-droplets adopts a short-duration intermittent injection method with a duration less than 1 second and a spray pressure lower than 50% of the lower limit of the normal operation pressure to ensure that the droplet distribution is controllable during the test and does not interfere with the normal dust-suppression operation; among them, the perturbation intensity ranking rule passes the standard values of the preset wind speed volatility and wind speed derivative change rate, and defines a linear combination formula for the two: perturbation intensity value = α × wind speed volatility + β × wind speed derivative change rate, where α and β are fixed weight coefficients, and are sorted from large to small according to the calculated perturbation intensity value to determine the nozzle response priority; where the duration less than 1 second and the spray pressure lower than 50% of the lower limit of the normal operation pressure are used to avoid the formation of a large-scale fog mass diffusion, so that the injection of micro-droplets is only used for the perturbation path test without interfering with the normal spray dust-suppression operation; The image or sound wave return device includes an image recognition device or a sound wave positioning device, which is installed on an automatic lifting rod to collect the movement process of the trace droplets and obtain the drift path of the trace droplets based on continuous frame matching and position inversion methods; the drift path is subjected to path overlap analysis with the spray trajectory offset parameter output by the prediction module, and an offset error between the drift path and the predicted trajectory is constructed to characterize the relative error between the predicted result and the actual disturbance response; Based on the offset error, error correction is performed on the offset angle, offset direction and offset amplitude in the spray trajectory offset parameters in turn. The error correction includes spatially decomposing the offset error between the drift path and the predicted trajectory into corresponding offset direction angle and offset amplitude components, and adjusting the corresponding parameters respectively; at the same time, based on the time difference between the response moment of the trace droplet drift path and the timestamp corresponding to the predicted trajectory, the time offset is calculated, and the time offset is used as a reference for evaluating the prediction hysteresis; based on the offset direction angle and offset amplitude components, the corrected offset angle, offset direction and offset amplitude results are fed back to the compensation module for real-time updating of the subsequent spray compensation control strategy, thereby constructing a dynamic correction mechanism that guides the adaptive adjustment of control parameters based on prediction deviation.

[0024] It should be generally explained that the formation process of this scheme is based on the problem background of drastic changes in the wind disturbance environment during the mobile operation of the spraying vehicle. By building a complete set of intelligent control spray dust reduction system, the interference problem of wind disturbance environment on spray trajectory control and dust reduction accuracy is systematically solved; its formation path starts from the real-time collection of wind field parameters at different heights and directions by the wind speed and direction sensors on the spraying platform. These sensor nodes are installed on the automatic lifting rod. As the first layer of information source for wind field perception, a wind speed gradient data set containing spatial structure is constructed; then the feature extraction module standardizes and features the data set Extraction operation, in which normalization processing unifies the scale of wind speed and direction data through mean shift and range scaling to ensure the comparability of data from different measurement points and time periods. Disturbance characteristics are then extracted by calculating wind speed vector differences and wind direction rotation offsets. A wind disturbance feature vector group is constructed through statistics of wind speed fluctuation rate, wind direction rotation frequency, and wind speed derivative change rate. A wind disturbance time series is then constructed through time sequence combination. A wind disturbance intensity gradient field and rotation direction distribution map are generated through spatial interpolation. Finally, a comprehensive spatial disturbance distribution map is formed, realizing a structured conversion from wind speed gradient data to disturbance spatiotemporal expression. In the modeling and prediction stage, the scheme introduces a transformer prediction model with double nested time-space memory. The transformer prediction model takes the wind disturbance time series and the spatial disturbance distribution map as joint inputs, constructs the time input tensor and the spatial input tensor respectively, and inputs them into the time memory encoding module and the spatial memory encoding module of the model. Through the attention mechanism, the core features between the disturbance trend and the spatial structure are extracted, and then the attention weighted fusion and residual connection operations are performed by the fusion control unit to form a unified time-space coupling feature tensor, ensuring that the time evolution pattern and the spatial disturbance characteristics jointly drive the prediction logic; The decoding module, through the position encoding and the feature attention mechanism, extracts the context dependence for each future time step within the target time domain sliding window and outputs the trend prediction results of the wind speed volatility, the wind direction rotation frequency and the wind speed derivative change rate at continuous time points, and then combines the historical disturbance trajectory to complete the calculation of the spray trajectory offset parameter, providing a basis for subsequent calibration and compensation control; After the prediction is completed, the calibration module is used to release a small amount of test droplets, track their drift paths through image recognition or acoustic positioning devices, and perform an overlapping analysis of the actual drift path and the predicted spray trajectory offset parameter to form a spatial offset error; The offset error is further decomposed into the offset direction angle and the offset amplitude for error correction of the original offset parameter; At the same time, the system also records the time difference between the actual occurrence time of the drift response and the predicted time point, and calculates the time offset as a reference index to measure the prediction lag; Finally, the corrected offset angle, offset direction and offset amplitude results are fed back to the compensation module to drive it to generate multi-dimensional control instructions including attitude adjustment, injection angle correction and spray pressure control in real time, so as to complete the adaptive adjustment of the spray control parameters; The whole feedback chain forms a closed-loop regulation mechanism of prediction-check-compensation-feedback. The closed-loop regulation module ensures that the system re-collects new wind field data and re-enters the complete process after each round of compensation control, so as to achieve the continuous adaptation and self-optimization of the system in the dynamic wind disturbance environment; The design adopts a modular structure consisting of wind field acquisition, feature modeling, spatio-temporal prediction, real-time verification, and closed-loop control to ensure that the system has anti-disturbance ability and execution ability. The introduction of three types of disturbance features, namely wind speed volatility, wind direction rotation frequency, and wind speed derivative change rate, covers the amplitude change, direction instability, and mutation trend of wind field disturbances, improving the accuracy of wind disturbance modeling. The time-space dual memory structure enables the model to predict mutation points and trend turns by jointly modeling the time recurrence and spatial propagation characteristics of disturbances. During the verification stage, an intermittent spraying strategy with short time periods and low pressure is adopted, and only micro-droplet tests are triggered in areas ranked high in terms of disturbance intensity, ensuring that the test process is precisely controllable and does not affect the dust suppression operation. Finally, through the iterative optimization of high-frequency feedback correction and compensation commands, the system achieves stable control of the spraying trajectory under complex wind disturbance conditions, improving the dust suppression efficiency and operation accuracy, and having the prospect of engineering application.

[0025] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A mobile intelligent control spray dust suppression system, comprising an intelligent control system, an environmental governance system and a spraying vehicle. The intelligent control system and the environmental governance system are installed on the spraying vehicle. The environmental governance system includes atomizing nozzles, a water storage tank, a power supply system and a lifting rod, and is characterized in that: The intelligent control system includes a wind field construction module, a feature extraction module, a prediction module, a calibration module, and a compensation module; The wind field construction module is used to collect local wind field parameters at multiple different heights and directions by using multiple wind speed and direction sensing nodes installed on the lifting rod during the movement of the spray dust suppression vehicle, and construct a wind speed gradient data set based on the local wind field parameters; The feature extraction module is used to perform normalization and disturbance feature extraction processing on the wind speed gradient data set to generate a wind disturbance time series and a spatial disturbance distribution map; The prediction module is used to input the wind disturbance time series and the spatial disturbance distribution map into a preset time-space dual memory nested transformer prediction model, and output the prediction result of the wind disturbance change trend and the spray trajectory offset parameter within the target time domain; The calibration module is used to control some atomizing nozzles to release droplets for testing wind disturbance, and monitor the drift path of the droplets based on an image or acoustic wave return device, compare the drift path with the spray trajectory offset parameter, and update the spray trajectory offset parameter; The compensation module is used to generate control instructions for the attitude adjustment, spray angle correction, and spray pressure change of the atomizing nozzles according to the corrected spray trajectory offset parameter, and drive the environmental governance system through the intelligent control system to complete spray compensation control.

2. The mobile intelligent control spray dust suppression system according to claim 1, wherein: The intelligent control system further includes a closed-loop regulation module. The closed-loop regulation module is used to, after the compensation module completes the spray compensation control, re-collect the local wind field parameters of each wind speed and direction sensing node on the lifting rod, and construct a new wind speed gradient data set; input the new wind speed gradient data set into the feature extraction module, and sequentially pass through the feature extraction module, the prediction module, the calibration module, and the compensation module; through the periodic linkage call of the intelligent control system, form a closed-loop regulation mechanism for wind disturbance prediction and spray control with the change of local wind field parameters as the input and the update of control instructions as the output.

3. The mobile intelligent control spray dust suppression system according to claim 2, wherein: The atomizing nozzles are installed on the atomizing bracket at the rear of the spraying vehicle. The atomizing nozzles are connected to the water storage tank through liquid pipes. The power supply system is arranged at the position of the spraying vehicle chassis, and provides power output for the atomizing nozzles, the lifting rod, and related control circuits respectively through a line distribution interface; the lifting rod is fixed on the bracket structure at the top of the spraying vehicle. The lifting rod integrates wind speed and direction sensing nodes, and at the same time, the wind speed and direction sensing nodes are used as the front-end acquisition devices for local wind field parameters. The output data of the wind speed and direction sensing nodes is transmitted to the intelligent control system; The intelligent control system and the environmental governance system establish a two-way connection through a control wire harness and a data communication module. The intelligent control system is used to receive the local wind field parameters of the lifting rod, and send control instructions for spraying to the atomizing nozzles according to the prediction module, the calibration module, and the compensation module.

4. The mobile intelligent control spray dust suppression system according to claim 3, wherein: When the feature extraction module performs normalization and perturbation feature extraction processing on the wind speed gradient data set, the normalization processing includes performing mean translation and range scaling processing on the wind speed and wind direction parameters at each height and azimuth angle obtained by acquisition according to a preset time window, that is, forming a wind speed gradient matrix under a unified scale; After the normalization processing is completed, the feature extraction module calculates the wind speed vector difference and the wind direction rotation offset between adjacent measurement points at the same time section based on the wind speed gradient matrix, and statistically calculates the wind speed volatility, the wind direction rotation frequency, and the wind speed derivative change rate within a specified time step as wind disturbance features, forming a wind disturbance feature vector group; Arrange the wind disturbance feature vector group in chronological order to construct a wind disturbance time series. At the same time, based on the spatial positions of each measurement point of the wind speed and wind direction sensing nodes, the feature extraction module performs spatial interpolation on the wind disturbance features within the corresponding time window and maps them to the wind field area distribution map, and solves the local wind disturbance intensity gradient field and the rotation direction distribution map to form a spatial disturbance distribution map.

5. The mobile intelligent control spray dust reduction system according to claim 4, wherein: The wind speed volatility of the wind disturbance feature is calculated by calculating the ratio of the standard deviation to the mean value of the wind speed values at the same measurement point within a specified time window, so as to reflect the relative change range of the wind speed within this time window; The wind direction rotation frequency of the wind disturbance feature is measured by counting the number of times the wind direction changes exceeding a preset angle threshold within a specified time window and normalizing it to the change frequency per unit time, so as to measure the instability of the wind direction; The wind speed derivative change rate of the wind disturbance feature represents the mutation intensity of the wind speed change trend by calculating the difference value of the wind speed derivative in adjacent time steps and statistically calculating the derivative change within a unit time.

6. The mobile intelligent control spray dust reduction system according to claim 5, wherein: In the prediction module, based on the wind disturbance time series and the spatial disturbance distribution map generated by the feature extraction module, the wind speed volatility, the wind direction rotation frequency, and the wind speed derivative change rate form a time input tensor at consecutive time steps. At the same time, the wind disturbance intensity gradient field and the rotation direction distribution map form a spatial input tensor, which is used to construct the joint input structure of the transformer prediction model; Input the time input tensor and the spatial input tensor into the time memory encoding module and the spatial memory encoding module of the transformer prediction model respectively. The time memory encoding module extracts the time trend features of the wind disturbance change based on the multi-head attention mechanism and the position nesting structure, and the spatial memory encoding module extracts the spatial correlation features of the wind disturbance based on the position mapping and the perturbation distribution weighting mechanism; Perform feature fusion and residual connection operations on the time trend features and the spatial correlation features in the fusion control unit of the transformer prediction model to form a unified time-space coupled feature tensor; Input the time-space coupled feature tensor into the decoding module of the transformer prediction model, and predict the change trends of the wind speed volatility, the wind direction rotation frequency, and the wind speed derivative change rate within the future target time period according to the preset target time domain sliding window, and output the prediction result of the wind disturbance change trend; Based on the prediction result of the wind disturbance change trend and the historical disturbance trajectory distribution in the spatial disturbance distribution map, calculate the offset angle, offset direction and offset amplitude of the spray trajectory within the target time domain, and output the spray trajectory offset parameters.

7. The mobile intelligent control spray dust reduction system according to claim 6, characterized in that: The decoding module of the transducer prediction model includes a position encoding unit, a multi-head attention mechanism layer, a feed-forward neural network layer and an output mapping layer. The decoding module receives the time-space coupled feature tensor output by the fusion control unit, and combines the time index position of the currently observed time step. Through the position encoding unit, the position indexes of each prediction time step within the target time period are encoded to generate corresponding time position encodings, and the generated time position encodings are embedded into the time-space coupled feature tensor; The multi-head attention mechanism layer in the decoding module is used to construct an attention mapping relationship between historical features and prediction positions at the target time position, extract context feature representations with weight values within the preset upper threshold range between the historical time steps corresponding to each prediction time step, and use the feed-forward neural network layer to perform a non-linear transformation on the context feature representations, and output a prediction intermediate result with time recurrence features; The output mapping layer of the decoding module projects the prediction intermediate result into the prediction component spaces of the wind speed volatility, the wind direction rotation frequency and the wind speed derivative change rate respectively to form a prediction result of the wind disturbance change trend; Among them, the preset target time domain sliding window slides backward from the current moment by a preset time length, and the preset time length corresponds to the number of future time steps set in the transducer prediction model; At each prediction time step within the target time domain sliding window, the decoding module sequentially performs attention weight distribution operations on the fused time-space coupled feature tensor, and inputs the attention weighted result into the feed-forward neural network layer for feature mapping processing to generate the disturbance prediction output corresponding to this time step, and gradually generates a sequence of predicted values of each disturbance variable within the target time period, so as to obtain the output of the wind speed volatility change trend, the wind direction rotation frequency change trend and the wind speed derivative change rate change trend.

8. The mobile intelligent control spray dust reduction system according to claim 7, characterized in that: Define the atomizing nozzles in the local area where the wind speed volatility exceeds the preset wind speed fluctuation threshold, or the atomizing nozzles in the local area where the wind speed derivative change rate exceeds the preset wind speed derivative change threshold as partial atomizing nozzles; During the non-dust reduction operation stage, test fog droplets are released based on a preset disturbance intensity sorting rule, and the fog droplets are sprayed in an intermittent spraying mode with a duration less than 1 second and a spraying pressure lower than 50% of the lower limit of the normal operation pressure; The image or acoustic wave transmission device includes an image recognition device or an acoustic wave positioning device. Through the image recognition device or the acoustic wave positioning device arranged on the lifting rod, the movement process of the fog droplets is collected, and the drift path of the fog droplets is obtained based on the continuous frame matching and position inversion method. Perform path overlap analysis on the drift path and the spray trajectory offset parameters output by the prediction module, and construct the offset error between the drift path and the predicted trajectory, so as to characterize the relative error between the prediction result and the actual disturbance response; Based on the offset error, perform error correction on the offset angle, offset direction, and offset amplitude in the spray trajectory offset parameters in sequence. The error correction includes spatially decomposing the offset error between the drift path and the predicted trajectory into corresponding offset direction angles and offset amplitude components, and adjusting the corresponding parameters respectively; at the same time, based on the time difference between the response moment of the droplet drift path and the time stamp corresponding to the predicted trajectory, calculate the time offset, and use the time offset as a reference for evaluating the prediction lag.

Images