Fog sprayer control system and method based on multi-modal data

Abstract

The invention relates to the technical field of environmental governance, in particular to a fog sprayer control system and method based on multi-modal data. The method comprises the following steps: respectively acquiring environmental parameters, equipment states and spatial feature data, and fusing multi-source heterogeneous data to construct a three-dimensional data matrix; multi-source data are acquired in real time, abnormal conditions are detected, and a strategy is dynamically updated; generating a fog spraying operation control instruction based on the three-dimensional data matrix and the real-time updating data; the system comprises a three-dimensional data matrix construction module, a current data updating module and a fog spraying operation control module. By means of the mode, updating period adjustment based on working condition classification is achieved, the method adapts to the dynamic environment, and resource waste and insufficient coverage are avoided.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of environmental governance, and particularly relates to a spray device control system and method based on multi-modal data. BACKGROUND

[0002] The spray device is a device for realizing environmental governance by high-pressure spraying of fine mist droplets, and is widely used in dust suppression, cooling and humidification, disinfection and epidemic prevention, agricultural plant protection and other fields.

[0003] Most of the current spray device control systems use fixed update cycles and preset spraying parameters, which cannot adapt to dynamic environments, resulting in resource waste and insufficient coverage. Therefore, it is necessary to provide a spray device control system and method based on working condition classification to adjust the update cycle, adapt to dynamic environments, and avoid resource waste and insufficient coverage. SUMMARY

[0004] The present application relates to the technical field of environmental governance, and particularly relates to a spray device control system and method based on multi-modal data.

[0005] To achieve the above-mentioned purpose, the spray device control method based on multi-modal data adopted by the present application comprises the following steps: Respectively acquire environmental parameters, device states, and spatial feature data, fuse multi-source heterogeneous data to construct a three-dimensional data matrix; Real-time acquisition of multi-source data, detection of abnormal conditions, and dynamic update of strategies; Based on the three-dimensional data matrix and real-time update data, generate spray operation control instructions.

[0006] In the step of respectively acquiring environmental parameters, device states, and spatial feature data, and fusing multi-source heterogeneous data to construct a three-dimensional data matrix: Acquire environmental parameters, device states, and spatial feature data, and output; Space-time alignment of environmental parameters, device state data, and spatial feature data.

[0007] In the step of acquiring environmental parameters, device states, and spatial feature data, and outputting: Respectively collect particulate matter concentration and meteorological data, and output environmental parameters; Respectively monitor the current state of the spray device hydraulic, electrical, and mechanical, and output device state data; Respectively acquire dust source and obstacle positioning data, and output spatial feature data.

[0008] In the step of real-time acquisition of multi-source data, detection of abnormal conditions, and dynamic update of strategies: acquiring multi-source data in real time; analyzing abnormal conditions according to the current multi-source data, and outputting the current situation; judging the current working condition according to the current situation, and dynamically updating the period.

[0009] In the step of acquiring multi-source data in real time: setting a ring buffer to store the multi-source data.

[0010] In the step of analyzing abnormal conditions according to the current multi-source data, and outputting the current situation: calculating the mean and standard deviation of the data in the sliding window, judging the abnormal conditions of the current multi-source data, and performing spatio-temporal correlation analysis to infer the root cause of the abnormality, and outputting the current situation.

[0011] In the step of judging the current working condition according to the current situation, and dynamically updating the period: if the current working condition is a steady-state working condition, the update period is maintained; if the current working condition is a mutation working condition, the update period is adjusted, and the data is continuously collected to confirm the trend; if the current working condition is an emergency working condition, the update period is adjusted, and the device protection mechanism is triggered.

[0012] In the step of generating a jet mist operation control instruction based on a three-dimensional data matrix and real-time updated data: based on the three-dimensional matrix, combining the jet angle, range and droplet size parameters of the jet mist device, simulating the diffusion trajectory and coverage area of the droplets in space; fusing real-time environmental data, dynamically updating the risk map, and marking high-priority jet mist areas; acquiring the number of jet mist devices, water quantity limits, environmental safety threshold constraints, generating jet mist sequences, position adjustment paths and spraying parameters, and executing the control instruction.

[0013] After the step of acquiring the number of jet mist devices, water quantity limits, environmental safety threshold constraints, generating jet mist sequences, position adjustment paths and spraying parameters, and executing the control instruction: real-time monitoring of the jet mist coverage, comparing the expected and actual effects based on the three-dimensional matrix, calculating the coverage deviation, and triggering instruction correction according to the deviation value.

[0014] The application also provides a jet mist device control system based on multi-modal data, comprising a three-dimensional data matrix construction module, a current data update module and a jet mist operation control module; wherein: The three-dimensional data matrix construction module is used to acquire environmental parameters, device states and spatial feature data respectively, and fuse multi-source heterogeneous data to construct a three-dimensional data matrix. The current data updating module is used for acquiring multi-source data in real time, detecting abnormal conditions, and dynamically updating strategies. The spray operation control module is used for generating a spray operation control instruction based on the three-dimensional data matrix and real-time updating data.

[0015] The spray device control system and method based on multi-modal data of the present application adopt the three-dimensional data matrix construction module, the current data updating module, and the spray operation control module to perform the following steps: acquiring environmental parameters, equipment states, and spatial feature data respectively, and constructing a three-dimensional data matrix by fusing multi-source heterogeneous data; acquiring multi-source data in real time, detecting abnormal conditions, and dynamically updating strategies; and generating a spray operation control instruction based on the three-dimensional data matrix and real-time updating data. In this way, the update cycle is adjusted based on working condition classification, the dynamic environment is adapted, and resource waste and insufficient coverage are avoided. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort based on these drawings.

[0017] Figure 1 is a step flow chart of the spray device control method based on multi-modal data of the present application.

[0018] Figure 2 is a step flow chart of S100 of the present application.

[0019] Figure 3 is a step flow chart of S200 of the present application.

[0020] Figure 4 is a step flow chart of S300 of the present application.

[0021] Figure 5 is a structure principle diagram of the spray device control system based on multi-modal data of the present application.

[0022] Figure 6 is a structure principle diagram of the electronic device of the present application.

[0023] 401-three-dimensional data matrix construction module, 402-current data updating module, 403-spray operation control module. DETAILED DESCRIPTION

[0024] The exemplary embodiments will be described in detail herein with reference to the attached drawings. In the following description, like reference numerals refer to like elements, unless the context clearly dictates otherwise. The following exemplary embodiments described herein represent the best now known to the inventors of performing the applications.

[0025] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0026] It is to be understood that the singular forms "a", "an", and "the" include plural referents unless the context clearly dictates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0027] Referring now to the drawings Figures 1-4 The present application provides a multi-modal data-based spray device control method, comprising the following steps: S100: acquiring environmental parameters, device states, and spatial feature data, respectively, and fusing multi-source heterogeneous data to construct a three-dimensional data matrix.

[0028] In this embodiment, environmental parameters, device states, and spatial feature data are acquired respectively, and multi-source heterogeneous data is fused to construct a three-dimensional data matrix. The specific process is as follows: S101: collecting particulate matter concentration and meteorological data, respectively, and outputting environmental parameters; S102: monitoring the current states of the hydraulic, electrical, and mechanical states of the spray device, respectively, and outputting device state data; S103: acquiring dust source and obstacle positioning data, respectively, and outputting spatial feature data; S104: performing spatio-temporal alignment on the environmental parameters, device state data, and spatial feature data.

[0029] In the above process, particulate matter concentration monitoring: real-time collection of particulate matter concentration data such as PM2.5 and PM10 by laser scattering sensors or beta-ray absorption method, sampling frequency ≥ 1 Hz, accuracy ± 5%.

[0030] Meteorological data collection: Integrate temperature and humidity sensors, anemometers, barometers to collect environmental temperature and humidity, wind speed (0-30 m / s), wind direction (0-360°), air pressure, etc. Parameters, data synchronization timestamp to millisecond level.

[0031] Output: Generate environmental parameter data stream with space-time label, format: [timestamp, coordinate (X, Y, Z), PM2.5, PM10, temperature, humidity, wind speed, wind direction].

[0032] Hydraulic system monitoring: Real-time collection of hydraulic pressure (0-20 MPa) and pump flow (0-100 L / min) of the sprayer through pressure sensors and flow meters to determine hydraulic system leakage or blockage risk.

[0033] Electrical system monitoring: Collect voltage (220V±10%), current (0-50A), power factor to detect motor overload, short circuit and other faults.

[0034] Mechanical system monitoring: Feedback sprayer gimbal angle (horizontal 0-360°, vertical -90°~+90°) and nozzle opening (0-100%) through encoders, combined with vibration sensors to monitor mechanical wear.

[0035] Output: Generate device status health index (0-100), below threshold (such as 70) to trigger warning.

[0036] Dust source positioning: Real-time tracking of moving dust sources (such as loaders, transport vehicles) coordinates (X, Y, Z) and motion trajectory through UWB (Ultra Wide Band) positioning technology or visual SLAM algorithm.

[0037] Obstacle modeling: Scan static obstacles (such as buildings, stockpiles) with laser radar (16 / 32 lines) to generate three-dimensional point cloud model, label obstacle height, contour and reflectivity.

[0038] Output: Spatial feature data includes [obstacle ID, coordinate (X, Y, Z), size (length, width, height), reflectivity] and dynamic trajectory of dust sources.

[0039] Space-time alignment: Synchronize all sensor data with GPS time or PTP precise clock protocol to eliminate time deviation; align laser radar point cloud with device coordinate system through ICP (Iterative Closest Point) algorithm.

[0040] Feature extraction: Perform sliding average filtering (window=10s) on environmental parameters to extract particulate matter concentration gradient; calculate RMS (Root Mean Square) value of device status data to evaluate vibration intensity; generate digital elevation model (DEM) for spatial feature data.

[0041] Output: The fused 3D data matrix, in the format [timestamp, spatial coordinates (X,Y,Z), environmental features, device status, spatial features].

[0042] S200: Real-time acquisition of multi-source data, detection of anomalies, and dynamic updating of strategies.

[0043] In this implementation, multi-source data is acquired in real time, anomalies are detected, and the strategy is dynamically updated. The specific process is as follows: S201: Acquire multi-source data in real time and set up a circular buffer to store the multi-source data; S202: Calculate the mean and standard deviation of the data within the sliding window, determine the current anomalies in the multi-source data, perform spatiotemporal correlation analysis, infer the root causes of the anomalies, and output the current situation; S203: Determine the current operating condition based on the current situation and dynamically update the cycle.

[0044] Furthermore, in the step of judging the current working condition based on the current situation and dynamically updating the cycle: If the current operating condition is a steady state, then maintain the update cycle; If the current operating condition is a sudden change, adjust the update cycle and continuously collect data to confirm the trend; If the current operating condition is an emergency condition, the update cycle will be adjusted and the equipment protection mechanism will be triggered.

[0045] In the above process, the circular buffer stores and preprocesses: Set up a circular buffer (capacity = 1000 data entries) to store the latest multi-source data according to the FIFO (First In First Out) principle to avoid memory overflow.

[0046] Normalize the data (e.g., scale to [0,1] using Min-Max) to eliminate dimensional differences.

[0047] Sliding window statistics: Calculate the average particulate matter concentration using a 30-second window. ) and standard deviation ( If the current value exceeds ±3 Then it is judged as abnormal.

[0048] Spatiotemporal correlation analysis: Combine wind speed and direction data to infer the direction of abnormal sources (such as pollution sources in the upwind direction); troubleshoot faults through equipment status data (such as sudden drop in hydraulic pressure causing interruption of fogging).

[0049] Output: Anomaly type (e.g., "PM2.5 exceeds standard" or "hydraulic failure"), anomaly location (coordinates), and confidence level (0-1).

[0050] Dynamic adjustment of operating condition assessment and update cycle: Steady state: If no abnormalities for 5 consecutive minutes, maintain data update period (e.g., 10s / minute).

[0051] Transient state: If a rapid increase in particulate matter concentration (>50μg / m 3 / min) is detected, shorten the update period to 1s / minute and continuously collect 3 sets of data to confirm the trend.

[0052] Emergency state: If the device state health index <50 or PM10>500μg / m 3 , immediately trigger the protection mechanism (such as emergency shutdown, start backup device), and adjust the update period to 0.1s / minute.

[0053] S300: Based on the three-dimensional data matrix and real-time update data, generate mist spray operation control instructions.

[0054] In this embodiment, based on the three-dimensional data matrix and real-time update data, generate mist spray operation control instructions. The specific process is: S301: Based on the three-dimensional matrix, combine the spray angle, range, and droplet size parameters of the mist sprayer to simulate the diffusion trajectory and coverage area of the droplets in space; S302: Fuse real-time environmental data to dynamically update the risk map and mark high-priority mist spray areas; S303: Obtain the number of mist sprayers, water quantity restrictions, environmental safety threshold constraints, generate mist spray sequences, position adjustment paths, and spray parameters, and execute control instructions; S304: Real-time monitor the mist spray coverage, compare the expected and actual effects based on the three-dimensional matrix, calculate the coverage deviation, and trigger instruction correction according to the deviation value.

[0055] In the above process, the droplet diffusion trajectory simulation: Based on the spatial coordinates and obstacle models in the three-dimensional matrix, combine the mist sprayer parameters (spray angle θ=30°~90°, range R=20~100m, droplet size Dv50=50~200μm), and use CFD (Computational Fluid Dynamics) to simulate the droplet motion trajectory.

[0056] Output the droplet coverage probability map, mark the coverage blind area (probability <30%) and overlapping area (probability >80%).

[0057] Fuse real-time environmental data (such as wind speed changes causing droplet deviation), adjust the risk map weight: High-risk area: PM2.5>75μg / m 3 and wind speed <3m / s (fast droplet settling); Medium-risk area: PM2.5 for 35~75μg / m 3Or wind speed is 3~10m / s; Low-risk area: the rest of the region.

[0058] Output risk level heat map, superimposed on the three-dimensional matrix.

[0059] Control command generation and execution: Constraints: number of aerosol N = 4, maximum water volume Q = 10m 3 , environmental safety threshold (such as ground humidity <80% to avoid slipping).

[0060] Optimization algorithm: genetic algorithm is used to generate mist spray sequence (preferably cover high-risk area), gimbal adjustment path (shortest moving distance) and spray parameters (pressure = 5MPa, pulse frequency = 2Hz).

[0061] Execution: send instructions to the aerosol through CAN bus or Modbus protocol, format is [device ID, target angle ), range (R), spray time (t)].

[0062] Coverage monitoring: real-time acquisition of mist spray area image through camera or infrared sensor, and identification of mist droplet coverage range by YOLOv8 model.

[0063] Deviation calculation: compare the IoU (intersection over union) of the expected coverage area and the actual coverage area, if IoU <0.7, trigger instruction correction.

[0064] Correction strategy: adjust the spray pressure (+10%) or gimbal angle (+5°), and regenerate the control command.

[0065] Corresponding to the foregoing embodiment of the aerosol control method based on multi-modal data, the application also provides an embodiment of the aerosol control system based on multi-modal data.

[0066] Figure 5 is a kind of based on multi-modal data's aerosol control system block diagram according to an exemplary embodiment. Refer to Figure 5 , the system can include: three-dimensional data matrix construction module 401, current data update module 402, mist spray operation control module 403;Wherein: The three-dimensional data matrix construction module 401 is used to obtain environmental parameters, device state, spatial feature data respectively, and fuse multi-source heterogeneous data to construct three-dimensional data matrix; The current data update module 402 is used to obtain multi-source data in real time, detect abnormal conditions, and dynamically update strategy; The mist spray operation control module 403 is used to generate mist spray operation control command based on three-dimensional data matrix and real-time update data.

[0067] In the embodiment, the three-dimensional data matrix construction module 401 respectively acquires environment parameters, device states, and spatial feature data, fuses multi-source heterogeneous data to construct a three-dimensional data matrix; the current data updating module 402 acquires multi-source data in real time, detects abnormal conditions, and dynamically updates strategies; the spray operation control module 403 generates a spray operation control instruction based on the three-dimensional data matrix and real-time updating data. Through the above manner, the update cycle adjustment based on working condition classification is realized, the dynamic environment is adapted, and resource waste and insufficient coverage are avoided As to the system in the above embodiment, the specific manner in which various modules perform operations has been described in detail in the embodiment related to the method, and will not be described in detail here.

[0068] For the system embodiment, since it basically corresponds to the method embodiment, the related parts can refer to the part of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place or distributed on multiple network units. According to actual needs, some or all of the modules can be selected to achieve the purpose of the present application scheme. Those skilled in the art can understand and implement it without creative labor.

[0069] Correspondingly, the present application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the spray controller control method based on multi-modal data as described above. As Figure 6 shown, a hardware structure diagram of a spray controller control system based on multi-modal data provided by an embodiment of the present application is in any device with data processing capability. In addition to Figure 6 the processor, the memory and the network interface, any device with data processing capability in the embodiment usually includes other hardware according to the actual function of the device with data processing capability, which will not be described here.

[0070] Correspondingly, the application further provides a computer readable storage medium, which stores computer instructions, and the instructions are executed by a processor to implement the above-mentioned method for controlling a jet sprayer based on multi-modal data. The computer readable storage medium can be an internal storage unit of any device with data processing capability, such as a hard disk or a memory. The computer readable storage medium can also be an external storage device, such as a plug-in hard disk, a smart media card (SMC), an SD card, a flash card, etc. Further, the computer readable storage medium can include both the internal storage unit of any device with data processing capability and the external storage device. The computer readable storage medium is used to store the computer program and other programs and data required by the device with data processing capability, and can also be used to temporarily store data that has been output or will be output.

[0071] Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. It is intended that the application embrace any and all variations of the present application that fall within the scope of the general inventive concept as defined by the appended claims and their equivalents. Accordingly, the application is not limited to only those embodiments that have been specifically described herein.

[0072] It will be understood that the application is not limited to the precise structures herein described and illustrated in the drawings, and that various modifications and changes can be made without departing from the scope of the present application.

Claims

1. A fog cannon control method based on multimodal data, characterized in that, Includes the following steps: Environmental parameters, equipment status, and spatial feature data are acquired separately, and multi-source heterogeneous data are fused to construct a three-dimensional data matrix; Real-time acquisition of multi-source data, detection of anomalies, and dynamic updating of strategies; Based on the three-dimensional data matrix and real-time updated data, fog spray operation control commands are generated.

2. The fog cannon control method based on multimodal data as described in claim 1, characterized in that, In the steps of separately acquiring environmental parameters, equipment status, and spatial feature data, and then fusing multi-source heterogeneous data to construct a three-dimensional data matrix: Acquire environmental parameters, equipment status, and spatial characteristic data, and output them; Spatiotemporal alignment of environmental parameters, equipment status data, and spatial characteristic data.

3. The fog cannon control method based on multimodal data as described in claim 2, characterized in that, In the steps of acquiring and outputting environmental parameters, equipment status, and spatial characteristic data: Particulate matter concentration and meteorological data were collected separately, and environmental parameters were output. Monitor the current status of the hydraulic, electrical, and mechanical components of the fog cannon, and output equipment status data; Acquire dust source and obstacle location data respectively, and output spatial feature data.

4. The fog cannon control method based on multimodal data as described in claim 1, characterized in that, In the steps of real-time acquisition of multi-source data, anomaly detection, and dynamic strategy updating: Real-time acquisition of multi-source data; Based on the current multi-source data, perform anomaly analysis and output the current situation; Assess the current operating conditions based on the current situation and dynamically update the cycle.

5. The fog cannon control method based on multimodal data as described in claim 4, characterized in that, In the process of acquiring multi-source data in real time: Set up a circular buffer to store data from multiple sources.

6. The fog cannon control method based on multimodal data as described in claim 4, characterized in that, In the steps of analyzing anomalies based on current multi-source data and outputting the current situation: Calculate the mean and standard deviation of the data within the sliding window, identify anomalies in the current multi-source data, perform spatiotemporal correlation analysis, infer the root cause of the anomalies, and output the current situation.

7. The fog cannon control method based on multimodal data as described in claim 4, characterized in that, In the step of judging the current working condition based on the current situation and dynamically updating the cycle: If the current operating condition is a steady state, then maintain the update cycle; If the current operating condition is a sudden change, adjust the update cycle and continuously collect data to confirm the trend; If the current operating condition is an emergency condition, the update cycle will be adjusted and the equipment protection mechanism will be triggered.

8. The fog cannon control method based on multimodal data as described in claim 1, characterized in that, In the step of generating fog spray operation control commands based on a three-dimensional data matrix and real-time updated data: Based on a three-dimensional matrix, combined with the spray angle, range, and droplet size parameters of the fog cannon, the diffusion trajectory and coverage area of ​​the droplets in space are simulated; By integrating real-time environmental data, the risk map is dynamically updated, and high-priority fogging areas are marked. The system acquires the number of fog cannons, water volume limits, and environmental safety threshold constraints, generates a fog cannon sequence, a position adjustment path, and spray parameters, and executes control commands.

9. The fog cannon control method based on multimodal data as described in claim 8, characterized in that, After obtaining the number of fog cannons, water volume limits, environmental safety threshold constraints, generating the fogging sequence, position adjustment path, and spray parameters, and executing control commands: The system monitors the fog coverage in real time, compares the expected and actual effects using a 3D matrix, calculates the coverage deviation, and triggers commands to correct it based on the deviation value.

10. A fog cannon control system based on multimodal data, applied to the fog cannon control method based on multimodal data as described in claim 1, characterized in that, It includes a 3D data matrix construction module, a current data update module, and a fog injection operation control module; among which: The three-dimensional data matrix construction module is used to acquire environmental parameters, equipment status, and spatial feature data respectively, and to fuse multi-source heterogeneous data to construct a three-dimensional data matrix. The current data update module is used to acquire multi-source data in real time, detect anomalies, and dynamically update strategies. The fog spraying operation control module is used to generate fog spraying operation control commands based on a three-dimensional data matrix and real-time updated data.

Images