A drone system and method for atmospheric pollution source tracing

Abstract

The present application relates to the technical field of atmospheric pollution source tracing, and discloses a kind of unmanned aerial vehicle system and method for atmospheric pollution source tracing.The method collects the gas concentration distribution data of different spatial positions of target area, and synchronously obtains meteorological parameter data set;Determine a plurality of pollution diffusion stability factors based on the spatial distribution characteristics of gas concentration distribution data and meteorological parameter data set, construct atmospheric pollution source tracing space model;Based on the model, the pollution source search strategy of unmanned aerial vehicle cluster is generated, and the strategy is dynamically adjusted according to the real-time collected gas concentration distribution data;Each unmanned aerial vehicle independently generates local source tracing decision in combination with the environmental characteristic data of itself and adjacent unmanned aerial vehicle, and the consistency adjustment after collaborative decision mechanism is obtained collaborative decision result;According to pollution source search strategy and collaborative decision result, determine pollution source tracing response quantity, when response quantity exceeds preset threshold, execute pollution source positioning instruction, can improve the comprehensiveness, accuracy and efficiency of pollution source tracing.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of atmospheric pollution source tracing, in particular to a UAV system and method for atmospheric pollution source tracing. BACKGROUND

[0002] In atmospheric environmental protection work, quickly and accurately positioning the pollution source is the premise of pollution control. At present, atmospheric pollution source tracing mainly relies on ground monitoring stations, mobile monitoring vehicles and satellite remote sensing technology. Although ground monitoring stations can achieve long-term monitoring at fixed points, they are limited by fixed layout positions and have limited coverage, making it difficult to fully capture the spatial distribution differences of gas concentration in the region, especially in complex terrain or sparsely monitored areas, where monitoring blind spots are likely to occur, and complete gas concentration distribution data cannot be obtained in time.

[0003] Although mobile monitoring vehicles can move flexibly within a certain area, they are limited by road conditions and cannot enter complex terrain areas such as mountains and forests, and there are still obvious deficiencies in monitoring range and flexibility. Satellite remote sensing technology can achieve macro monitoring over a large area, but its monitoring accuracy is limited by satellite resolution, making it difficult to obtain small-scale, high-precision gas concentration distribution data, and it is greatly affected by weather conditions. In thick cloud cover, rainfall and other weather conditions, monitoring cannot be carried out normally, and it is difficult to meet the real-time and accurate tracing needs.

[0004] The existing tracing methods are often simple when dealing with the influence of meteorological factors on pollution diffusion, and only a few meteorological parameters such as wind speed and direction are considered, without a comprehensive and systematic analysis of the correlation between meteorological conditions and gas concentration distribution. It is difficult to accurately determine the stability of pollution diffusion, resulting in low accuracy of the constructed tracing model, and it is difficult to effectively guide the pollution source search work. In the search process, a fixed search path is often used, and there is a lack of dynamic adjustment capability according to real-time monitoring data, which can easily cause low search efficiency and fail to quickly lock the pollution source position. In addition, in terms of multi-device collaborative tracing, the existing methods lack effective collaborative decision-making mechanisms, and data sharing and collaborative decision-making between monitoring devices are difficult to achieve, resulting in the inability to effectively integrate local monitoring data into global tracing information, further affecting the accuracy and efficiency of tracing, and making it difficult to meet the urgent needs of current atmospheric pollution accurate control for fast and accurate tracing. SUMMARY

[0005] The present application aims to provide a UAV method for atmospheric pollution source tracing to solve the problems raised in the background art.

[0006] To achieve the above-mentioned purpose, the present application provides a UAV method for atmospheric pollution source tracing, which comprises:

[0007] Collecting gas concentration distribution data of different spatial positions in a target area, and synchronously collecting a meteorological parameter data set;

[0008] Determining a plurality of pollution diffusion stability factors based on spatial distribution characteristics of the gas concentration distribution data and the meteorological parameter data set;

[0009] Constructing an atmospheric pollution tracing space model through the plurality of pollution diffusion stability factors;

[0010] Generating a pollution source search strategy of a UAV cluster based on the atmospheric pollution tracing space model;

[0011] Dynamically adjusting the pollution source search strategy according to real-time collected gas concentration distribution data;

[0012] Each UAV independently generates a local tracing decision based on local environmental characteristic data collected by itself and environmental characteristic data sets of neighboring UAVs;

[0013] Adjusting the local tracing decisions for consistency through a cooperative decision mechanism to obtain a cooperative decision result;

[0014] Determining a pollution tracing response quantity according to the pollution source search strategy and the cooperative decision result;

[0015] When the pollution tracing response quantity exceeds a preset response threshold, executing a pollution source positioning instruction.

[0016] Preferably, determining a plurality of pollution diffusion stability factors based on spatial distribution characteristics of the gas concentration distribution data and the meteorological parameter data set specifically includes:

[0017] Analyzing spatial gradient variation characteristics of the gas concentration distribution data;

[0018] Extracting wind speed distribution characteristics and wind direction stability parameters in the meteorological parameter data set;

[0019] Calculating pollution diffusion stability factors according to the spatial gradient variation characteristics, the wind speed distribution characteristics and the wind direction stability parameters.

[0020] Preferably, constructing an atmospheric pollution tracing space model through the plurality of pollution diffusion stability factors specifically includes:

[0021] Constructing a three-dimensional pollution tracing space coordinate system, wherein an X-axis represents a gas concentration gradient value, a Y-axis represents a wind speed influence factor, and a Z-axis represents a wind direction stability;

[0022] Mapping the pollution diffusion stability factors to the three-dimensional pollution tracing space coordinate system to form a tracing space point array;

[0023] Generate a pollution source probability distribution surface based on the traceable spatial dot matrix.

[0024] Preferably, the pollution source search strategy of the UAV cluster based on the atmospheric pollution traceable spatial model specifically comprises:

[0025] Extract a high-probability pollution area coordinate set from the atmospheric pollution traceable spatial model;

[0026] Divide the search responsibility area of the UAV cluster according to the high-probability pollution area coordinate set;

[0027] Generate a dynamic search path plan for each responsibility area.

[0028] Preferably, dynamically adjusting the pollution source search strategy according to the real-time collected gas concentration distribution data specifically comprises:

[0029] Monitor the concentration change rate of the current gas concentration distribution data relative to the historical gas concentration distribution data;

[0030] When the concentration change rate exceeds a preset change threshold, recalculate the pollution diffusion stability factor;

[0031] Update the atmospheric pollution traceable spatial model according to the recalculated pollution diffusion stability factor;

[0032] Correct the pollution source search strategy based on the updated atmospheric pollution traceable spatial model.

[0033] Preferably, each UAV independently generates a local traceable decision based on its own collected local environmental feature data and the environmental feature data set of its neighboring UAVs specifically comprises:

[0034] Fuse the local environmental feature data and the environmental feature data set of its neighboring UAVs to generate a local environmental feature vector;

[0035] Calculate the pollution source direction probability distribution according to the local environmental feature vector;

[0036] Select the maximum probability direction as the local traceable decision of the current UAV.

[0037] Preferably, the local traceable decisions are adjusted for consistency through a cooperative decision mechanism specifically comprises:

[0038] Collect the local traceable decisions of neighboring UAVs to form a decision set;

[0039] Calculate the decision deviation of the current UAV decision from the decision set;

[0040] When the decision deviation exceeds a preset deviation threshold, generate a decision correction vector;

[0041] Adjust the local traceability decision of the current UAV by using the decision correction vector.

[0042] Preferably, determining the pollution traceability response quantity according to the pollution source search strategy and the collaborative decision result specifically comprises:

[0043] Extracting a target area priority coefficient in the pollution source search strategy;

[0044] Calculating a decision confidence of the collaborative decision result;

[0045] Generating a pollution traceability response quantity based on the target area priority coefficient and the decision confidence.

[0046] Preferably, when the pollution traceability response quantity exceeds a preset response threshold, executing a pollution source positioning instruction specifically comprises:

[0047] Activating a high-precision gas component analysis device to collect pollution characteristic component data;

[0048] Generating a pollution source fingerprint spectrum according to the pollution characteristic component data;

[0049] Marking the current spatial position as a suspected pollution source coordinate.

[0050] Preferably, the present application further comprises a UAV system for atmospheric pollution source traceability, which comprises a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the UAV method for atmospheric pollution source traceability when executing the computer program.

[0051] Compared with the prior art, the present application has the following advantages:

[0052] The UAV method for atmospheric pollution source traceability can comprehensively master the spatial distribution characteristics of gas concentration in the target area and the meteorological conditions affecting pollution diffusion by collecting gas concentration distribution data at different spatial positions in the target area and synchronously obtaining a meteorological parameter data set, compared with the situation that the traditional ground monitoring station can only obtain fixed-point data and the mobile monitoring vehicle is restricted by the terrain, the UAV can flexibly fly at different spatial positions and is not restricted by complex terrain and road conditions, the obtained data is more comprehensive and complete, and the existence of monitoring blind areas can be effectively avoided, thereby providing more detailed basic data for subsequent traceability work.

[0053] The plurality of pollution diffusion stability factors are determined based on spatial distribution characteristics of the gas concentration distribution data and a meteorological parameter data set, breaking through the limitation of only considering a few meteorological parameters in the prior art, analyzing the relationship between meteorological conditions and pollution diffusion from multiple dimensions, and more accurately reflecting the actual situation of pollution diffusion, thereby providing strong support for constructing a precise atmospheric pollution source tracing spatial model. The atmospheric pollution source tracing spatial model is constructed by the plurality of pollution diffusion stability factors, so that the model can be more in line with the actual pollution diffusion law, and the accuracy of the model is greatly improved compared with the prior simple source tracing model, and the model can more effectively provide scientific guidance for pollution source search.

[0054] The pollution source search strategy of the UAV cluster is generated based on the atmospheric pollution source tracing spatial model, fully giving play to the advantages of the UAV cluster, and compared with single UAV search, the cluster operation can cover a larger range, and through reasonable search strategy planning, repeated search can be avoided, and search efficiency can be improved. According to the real-time collected gas concentration distribution data, the pollution source search strategy is dynamically adjusted, so that the search process is more flexible and targeted, the search direction and range can be adjusted in time according to the real-time change of pollution concentration, the problem of low efficiency caused by the use of fixed search path is avoided, and the pollution source area is focused more quickly.

[0055] Each UAV independently generates a local source tracing decision based on local environmental characteristic data collected by itself and environmental characteristic data sets of adjacent UAVs, can fully utilize real-time monitoring data of each UAV, quickly form a source tracing judgment of a local area, and avoid delay problems caused by data centralized transmission and processing. Through the consistency adjustment of the local source tracing decision by the cooperative decision mechanism, the local decisions of each UAV can be integrated into a globally unified cooperative decision result, effectively solving the problems of poor data sharing and difficult unified decision in the existing multi-device cooperation, making the source tracing decision more comprehensive and accurate, and avoiding the decision deviation caused by the limitation of local data of a single UAV.

[0056] According to the pollution source search strategy and the cooperative decision result, a pollution source tracing response quantity is determined, and when the response quantity exceeds a preset response threshold, a pollution source positioning instruction is executed, so that the positioning is performed only after sufficient and reliable source tracing information is obtained, the positioning accuracy is ensured, and compared with the prior art in which the response quantity is not determined and the positioning time is difficult to grasp, the reliability of the positioning is effectively improved, the target is accurately locked for subsequent pollution control work, and the atmospheric pollution control work is efficiently developed. BRIEF DESCRIPTION OF DRAWINGS

[0057] Figure 1 A working principle diagram of the UAV method for atmospheric pollution source tracing described in the present application;

[0058] Figure 2A work principle flow chart for determining pollution diffusion stability factors;

[0059] Figure 3 A work principle flow chart for generating pollution source search strategies for a UAV cluster;

[0060] Figure 4 A work principle flow chart for dynamic adjustment of pollution source search strategies. DETAILED DESCRIPTION

[0061] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0062] Please refer to Figure 1 The present application provides a UAV system and method for atmospheric pollution source tracing, the method comprising:

[0063] By collecting gas concentration distribution data at different spatial positions in the target area, and synchronously obtaining a meteorological parameter data set, a plurality of pollution diffusion stability factors are determined based on the spatial distribution characteristics of the gas concentration distribution data and the meteorological parameter data set. An atmospheric pollution tracing space model is constructed using these factors, and a pollution source search strategy for a UAV cluster is generated. The search strategy is dynamically adjusted according to the real-time collected gas concentration distribution data. Each UAV independently generates a local tracing decision based on its own collected local environmental characteristic data and the environmental characteristic data set of its neighboring UAVs. The local tracing decisions are adjusted for consistency through a collaborative decision mechanism, and a collaborative decision result is obtained. A pollution tracing response quantity is determined according to the pollution source search strategy and the collaborative decision result. When the pollution tracing response quantity exceeds a preset response threshold, a pollution source positioning instruction is executed.

[0064] Embodiment 1: Please refer to Figure 2 A cluster composed of multiple UAVs carrying high-precision gas sensors and micro weather stations is deployed above the target area. These UAVs fly according to a pre-planned grid path, covering the three-dimensional space from the ground to hundreds of meters in the air. Each UAV synchronously collects multiple gas concentration data at the location at a set frequency, including the concentration values of characteristic pollutants such as sulfur dioxide, nitrogen oxides, and volatile organic compounds, while recording the wind speed, wind direction, temperature, humidity, and air pressure data at the point. All data are provided with high-precision time stamp and spatial coordinate information, and are real-time aggregated to the data processing center of the cluster through the wireless data transmission module.

[0065] After the data collection phase, the system begins to analyze the spatial gradient variation characteristics of the gas concentration distribution data. The data processing center performs spatial interpolation on the acquired concentration data to generate a three-dimensional concentration distribution model of the target area. By analyzing this model, the system identifies the spatial variation of the concentration, including the degree of concentration change with distance and the distribution pattern of high concentration areas. For example, there may be a trend of increasing concentration with increasing distance in a certain downwind area, indicating a possible transport path of pollutants. The system calculates the concentration difference between adjacent sampling points and analyzes the spatial distribution pattern of these differences to quantitatively describe the spatial non-uniformity and variation direction of the concentration field.

[0066] Simultaneously, in-depth analysis of the meteorological parameter dataset is carried out, and the system extracts wind speed distribution characteristics from the collected raw meteorological data. This includes not only the instantaneous wind speed values at each point, but more importantly, the analysis of the spatial distribution pattern of wind speed, such as the variation of wind speed with increasing height and the differences in wind speed at different horizontal areas. The system calculates statistical indicators such as the average wind speed and the standard deviation of wind speed at a certain height layer to represent the overall strength and fluctuation of the wind field. At the same time, the system focuses on extracting wind direction stability parameters by analyzing the wind direction data over a continuous time series to calculate the frequency and amplitude of wind direction changes. In the case of relatively stable wind direction, the pollutant transport path is more predictable; while frequent changes in wind direction increase the uncertainty of pollutant diffusion direction.

[0067] Based on the spatial gradient variation characteristics, wind speed distribution characteristics, and wind direction stability parameters obtained from the above analysis, the system enters the calculation phase of the pollution diffusion stability factor. This calculation process is not a simple arithmetic operation, but a comprehensive evaluation of multiple factors. The system performs correlation analysis on the spatial gradient variation characteristics and wind speed distribution characteristics to evaluate the degree of influence of the wind field on the spatial distribution pattern of pollutants. At the same time, considering the adjustment effect of the wind direction stability parameter on this influence relationship, when the wind direction is stable, the relationship between wind speed and concentration gradient is more explicit; while when the wind direction is unstable, even if the wind speed is large, its transport effect on pollutants may be weakened due to the change in direction.

[0068] The system will accurately calculate a pollution diffusion stability factor value for each sampling point or each analysis unit. The factor value is not just a numerical value, but a real reflection of the predictability and stability of the pollutant diffusion behavior under the atmospheric environmental conditions at the sampling point or analysis unit. Specifically, when the factor value of a certain area is high, it usually indicates that the wind direction of the area is stable, the wind speed is in the appropriate range, and the pollutant concentration gradient is significant. Such areas often have ideal conditions for tracing sources, which helps researchers track and locate pollution sources. On the contrary, if the factor value of a certain area is low, it may be due to the disorder of the wind direction, the wind speed being too low or too high, or the relatively uniform distribution of pollutant concentration. In such cases, the positioning of pollution sources will become more complex and difficult, increasing the difficulty and uncertainty of source tracing. Through this systematic calculation process, a set of pollution diffusion stability factors covering the target area is finally obtained, which constitutes the basis for building an atmospheric pollution source tracing spatial model. The entire implementation process embodies the technical characteristics of multi-source data fusion, spatio-temporal feature analysis, and environmental parameter comprehensive evaluation, providing key input parameters for intelligent source tracing decision-making of the UAV cluster.

[0069] Embodiment 2: Refer to Figure 3 First, the system constructs a three-dimensional pollution source tracing space coordinate system, which fully considers the key factors affecting pollutant diffusion. The X-axis represents the gas concentration gradient value, which is obtained by calculating the concentration difference between adjacent points in space, reflecting the uneven distribution of pollutants in space and the possible migration direction. The Y-axis represents the wind speed influence factor, which is obtained by normalizing the measured wind speed data, quantifying the contribution of the wind field to the transport capacity of pollutants. The Z-axis represents the wind direction stability, which is calculated by statistical analysis of the time series wind direction data, reflecting the change amplitude of the wind direction within a certain time period. The higher the stability of the wind direction, the higher the value. This coordinate system constructs a feature space specially for pollution source analysis, where each dimension is directly related to the key influencing factors of pollutant diffusion behavior.

[0070] In the process of mapping pollution dispersion stability factors to a three-dimensional coordinate system to construct a traceable spatial point array, precise data processing techniques are required. This process involves the accurate measurement and recording of three key parameters: gas concentration gradient values, wind speed influence factors, and wind direction stability for each sampling point. These parameter values will determine the specific location of each sampling point in the coordinate system. In the three-dimensional coordinate system, each sampling point is precisely located to a coordinate position, forming a point array. Each node in the point array not only contains spatial coordinate information but also includes the specific value of the pollution dispersion stability factor for that point. These values are quantitative representations of the pollution dispersion characteristics of that point and are of great importance in understanding and analyzing pollution dispersion processes. In this way, each node in the point array becomes a data point rich in information, and together they form a digital representation of the atmospheric dispersion conditions in the target area. This representation not only reveals the stability characteristics of pollution dispersion but also helps researchers more intuitively understand the processes and mechanisms of pollution dispersion. To connect the discrete point array nodes into a continuous distribution surface, the system uses a spatial interpolation algorithm. This algorithm can estimate the values of unknown nodes based on the known node values in the point array, thereby converting the discrete point array into a continuous surface. This continuous surface is a complete characterization of the pollution dispersion conditions in the entire region, providing more comprehensive and accurate pollution dispersion information.

[0071] By mapping pollution dispersion stability factors to a three-dimensional coordinate system and constructing a traceable spatial point array, researchers can more deeply explore the processes and mechanisms of pollution dispersion. This digital representation not only improves the accuracy and efficiency of pollution dispersion research but also provides important data support for pollution control and management. The next important step is to generate a pollution source probability distribution surface based on the traceable spatial point array. The system uses a spatial probability estimation algorithm to calculate the likelihood of the existence of a pollution source at each location in the three-dimensional coordinate system based on the stability factor values and their spatial distribution pattern in the point array. The probability calculation takes into account multiple factors: in areas with high concentration gradients, if accompanied by appropriate wind speed influence and high wind direction stability, they are assigned a higher probability of the existence of a pollution source; while in areas with low concentration gradients or wind direction turbulence, the probability value decreases accordingly. The final generated pollution source probability distribution surface is a continuous probability field, and the height value of each point on the surface represents the probability of the existence of a pollution source under the corresponding combination of atmospheric conditions.

[0072] In the process of extracting high-probability pollution area coordinate sets in the atmospheric pollution source tracing spatial model, the system operates based on a pre-set probability threshold. Specifically, the system conducts a detailed scan of the entire probability distribution surface to identify areas with probability values exceeding the pre-set threshold. Once these areas are identified, the system records their spatial coordinate ranges. Typically, these high-probability areas exhibit some degree of spatial clustering, which may be caused by one or more potential pollution sources. To better analyze and manage these high-probability areas, the system generates a spatial coordinate set for each identified area. This set includes not only the boundary coordinates of the area but also its probability distribution characteristics. In this way, the system can more accurately identify and track potential pollution sources, providing strong support for subsequent pollution control and environmental protection efforts.

[0073] Dividing the search responsibility areas of the UAV cluster based on the high-probability pollution area coordinate set requires considering multiple factors. The system first analyzes the spatial distribution pattern of each high-probability area, merging areas with similar spatial locations into larger search blocks. Then, based on the size of the UAV cluster and the performance parameters of each UAV, the entire search area is divided into several responsibility areas. During the division process, the size of each responsibility area is proportional to its probability value, i.e., the higher the probability, the more refined the search resources allocated. At the same time, appropriate overlap zones are left between responsibility areas to avoid the emergence of search blind spots.

[0074] Generating dynamic search path plans for each responsibility area is the final key step. For each divided responsibility area, the system designs an adaptive search path based on the characteristics of the probability distribution surface within that area. In areas with higher probability values, path points are set more densely, and flight height is appropriately lowered to obtain higher-precision environmental data; in areas with lower probability values, relatively sparse path point layouts are used to improve search efficiency. Path planning also fully considers real-time weather conditions, especially wind direction and speed changes, to ensure that the UAV is always in the optimal data collection position during the search process. The generated search paths have dynamic adjustment characteristics and can automatically optimize flight trajectories based on real-time collected environmental data.

[0075] Example 3: see Figure 4The implementation process begins with continuous monitoring of gas concentration distribution data. While flying according to the established search strategy, the UAV cluster continuously collects various gas concentration data at its location. These data are real-time aggregated to the central processing system through a wireless transmission network. The system establishes a time series database, recording the concentration values at different time points for each spatial coordinate point. The system calculates the concentration change rate of the current gas concentration distribution data relative to historical data. This calculation is independent for each sampling point, comparing the concentration difference at the same spatial location at different time points. The calculation of the concentration change rate not only considers the absolute difference, but also combines the time interval factor, reflecting the rate and trend of concentration change.

[0076] The system sets a preset change threshold as the trigger condition, which is determined according to the atmospheric characteristics, pollutant types and monitoring accuracy requirements of the specific monitoring scene. When the monitored concentration change rate exceeds this preset threshold, it indicates that the atmospheric environment or pollution emission conditions have changed significantly, and the existing pollution diffusion stability factor may not accurately reflect the current atmospheric conditions. At this time, the system starts the recalculation process, based on the latest concentration distribution data and real-time meteorological parameters, and re-executes the calculation process of the pollution diffusion stability factor. Although the algorithm logic of this recalculation process is consistent with the initial calculation, it uses a completely updated data set, including all environmental parameters collected within the latest time window. The new calculation fully considers the latest change characteristics of the concentration distribution in the spatial and temporal dimensions, especially those areas showing significant gradient changes and points with abnormal concentration values. The calculation process also integrates the changing meteorological condition elements, including the instantaneous fluctuations of wind speed and the real-time changes of wind direction, which directly affect the diffusion path and rate of pollutants.

[0077] When processing the updated data set, the system implements spatio-temporal alignment processing on the concentration distribution data to ensure the comparability of data collected at different time points in the spatial reference system. For meteorological parameters, the system pays special attention to the time series change characteristics of wind speed and direction, analyzing their statistical distribution rules and variation characteristics. In the process of recalculating the pollution diffusion stability factor, the system uses a sliding time window analysis method, giving higher weight to recent data to better reflect the dynamic change trend of environmental conditions.

[0078] According to the recalculated pollution diffusion stability factor, the system implements a comprehensive update of the atmospheric pollution source tracing space model. This update process not only involves the recalibration of the three-dimensional coordinate system, but also includes dynamic adjustment of the coordinate axis scale range to adapt to the possible range of environmental parameters in the new data set. The system re-maps the updated pollution diffusion stability factor into the adjusted three-dimensional coordinate system to form a new source space point array distribution. Based on this updated point array, the system uses an improved interpolation algorithm to regenerate the pollution source probability distribution surface. The morphological characteristics and numerical distribution of the new surface reflect the latest status of the pollution source probability distribution under current atmospheric conditions.

[0079] The updated model may show a completely different high-probability area distribution pattern from the previous model. These changes may be reflected in multiple aspects: the spatial position of the high-probability area may shift, reflecting changes in the location of the pollution source or diffusion conditions; the distribution range of the probability value may change, indicating a change in the intensity of pollution; the relative importance of multiple high-probability areas may be reordered, meaning a redistribution of the contribution rate of the pollution source. The system will record these change characteristics in detail and analyze the environmental impact factors behind them.

[0080] The entire model updating process uses an incremental updating mechanism to quickly respond to environmental changes while maintaining the continuity of the model. The system compares the differences between the new and old models, and when the difference exceeds a certain threshold, it triggers a more in-depth model reconstruction process. This dynamic updating mechanism ensures that the atmospheric pollution source tracing space model always remains highly consistent with the actual situation, providing accurate and reliable spatial reference for the search decision of the UAV cluster.

[0081] The updated model not only reflects the current environmental conditions, but also provides a data basis for predicting the future development of pollution diffusion by analyzing the model change trend. The system will establish a model update history database to record the timestamp, change characteristics, and environmental impact factors of each update. These historical data provide important data support for analyzing the spatiotemporal variation of pollution sources. Based on the updated atmospheric pollution source tracing space model, the system modifies the pollution source search strategy of the UAV cluster. This modification process includes multiple aspects: re-extracting the coordinates of high-probability pollution areas, which may change in position or range due to model updating; re-dividing the search responsibility areas of the UAV cluster, adjusting the responsible range of each UAV according to the new high-probability area distribution; regenerating the dynamic search path planning of each responsibility area, optimizing the flight path and sampling point density according to the new probability distribution characteristics.

[0082] The entire dynamic adjustment process is realized through the following formula to quantify the concentration change rate and threshold judgment:

[0083]

[0084] wherein: represents the rate of concentration change, represents the current gas concentration measurement, represents the historical gas concentration reference value, represents the time interval between two measurements. When the value of exceeds a pre-set threshold , the system triggers a re-computation and model update process.

[0085] The feature of this embodiment is to establish a closed-loop feedback mechanism from data monitoring to strategy adjustment. The system not only can perceive environmental changes, but also can automatically adjust the monitoring strategy according to these changes, so that the UAV cluster always maintains the optimal search state. The dynamic characteristics of atmospheric pollutant diffusion are considered in the implementation process, and through continuous environmental perception and strategy optimization, the challenges of source tracing due to changes in meteorological conditions or fluctuations in pollution source emissions are effectively addressed.

[0086] In Example 4, each UAV continuously collects local environmental feature data at its location, including gas concentration readings, temperature, humidity, air pressure, and wind speed and direction. At the same time, through a wireless communication network, each UAV receives real-time environmental feature data sets from neighboring UAVs. The range of proximity is usually set according to the communication distance and environmental complexity, ensuring the timeliness and effectiveness of information exchange. The UAV fuses the local environmental feature data collected by itself with the data received from neighboring UAVs to generate a comprehensive local environmental feature vector. This fusion process uses a weighted average method, and the weight distribution is based on the time freshness and spatial proximity of data collection. The latest collected data and the data from UAVs closer in distance are given higher weights.

[0087] Based on the generated local environmental feature vector, the UAV calculates the probability distribution of the pollution source direction. This calculation process considers the comprehensive influence of multiple environmental factors, including concentration gradient direction, dominant wind direction, temperature distribution characteristics, etc. The system calculates the conditional probability of the existence of a pollution source for each possible direction angle, forming a complete probability distribution map. The probability calculation uses a pattern recognition method based on historical data and environmental features. The maximum probability direction is selected as the local source tracing decision of the current UAV. This selection process not only considers the size of the probability value, but also considers the concentration degree of the probability distribution. When a certain direction shows significantly higher probability values than other directions, the system determines it as the optimal search direction. The decision output includes the direction angle value and the corresponding probability confidence, providing a reference basis for subsequent collaborative adjustment. Referring to Table 1, the local environmental feature data collected by the UAV at a certain time.

[0088] Table 1: UAV local environmental feature data.

[0089]

[0090] The consistency of local tracing decisions is optimized by means of a collaborative decision mechanism to ensure the collaboration and accuracy of each UAV in the tracing task. Each UAV first collects the local tracing decisions of nearby UAVs and integrates these decisions into a comprehensive decision set. When recording each decision, the direction angle and confidence level of each decision are recorded in detail for subsequent analysis and calculation. The deviation of the current UAV decision from other decisions in the decision set is calculated. This calculation process not only considers the difference in direction angle, but also takes into account the weighted effect of confidence level to ensure the comprehensiveness and reliability of the calculation results. The deviation is calculated using a ring statistical method, which fully considers the periodicity of angle data and avoids calculation errors caused by the periodicity of angles. When the calculated deviation exceeds the preset deviation threshold, the system automatically generates a decision correction vector. The direction and size of the correction vector are determined based on the overall trend of the decision set and the deviation of the current decision. If there is a large deviation between the current UAV decision and the group decision, the correction vector will guide the decision direction to adjust towards the group consensus direction. The correction strength is positively correlated with the deviation, which ensures the appropriateness and effectiveness of the adjustment, avoiding distortion caused by excessive correction.

[0091] The adjustment of the current UAV's local tracing decision using the decision correction vector is a comprehensive process. The adjusted decision not only retains the unique perception characteristics of individual UAVs to the environment, but also incorporates the consensus information of group decisions, achieving effective integration of individual and group. This adjustment process is achieved through vector synthesis, ensuring smooth transition and natural adjustment of the decision direction, avoiding unstable factors caused by sudden changes in decision. The adjusted decision not only serves as a guide for the next step of the current UAV, but also participates in the collaborative decision-making process of other UAVs, forming a dynamic and mutually complementary decision network, further improving the collaborative tracing efficiency of the entire UAV group.

[0092] Example 5: Implementation process begins with the extraction of target area priority coefficients in the pollution source search strategy, which have been determined in the previously established search strategy based on the probability distribution characteristics in the atmospheric pollution source tracing spatial model. Each designated search area is assigned a priority coefficient, which reflects the relative likelihood of the existence of a pollution source in that area. The assignment of priority coefficients takes into account multiple dimensions of influencing factors, including the peak height of the area in the probability distribution surface, the spatial continuity and size of the area, and the relative position of the area to the dominant wind direction. Areas with higher coefficient values usually correspond to significantly prominent peak areas on the probability surface, or potential pollution source aggregation areas pointed to by multiple environmental indicators. The system performs confidence assessment on the collaborative decision-making results of the UAV swarm. The calculation of decision confidence is based on the group decision-making characteristics formed in the collaborative decision-making process. The system analyzes the consistency of the decision directions of each UAV in the decision set, calculates the central tendency and dispersion of these direction data. When the decision directions of most UAVs in the swarm tend to be consistent, and the individual confidence values reported are relatively high, the system gives a high overall confidence to the collaborative decision-making result. Conversely, if the decision directions are scattered, or the individual confidence is generally low, the overall confidence is adjusted accordingly. The confidence assessment also takes into account the quality factors of environmental data, including the stability of sensor readings, the time synchronization and spatial coverage completeness of data acquisition.

[0093] Based on the target area priority coefficient and the decision confidence, the system generates a pollution source tracing response quantity, which is a comprehensive quantitative indicator that combines the priority coefficient and the decision confidence through an algorithm. In the algorithm design, both the priority coefficient and the decision confidence have corresponding weight assignments, reflecting their importance in the final decision. The numerical range of the response quantity is standardized to be within a unified dimension system, facilitating comparison with the pre-set response threshold. The calculation of the response quantity is performed in real time and dynamically updated with the continuous input of environmental data and new decisions. The system sets a pre-set response threshold as the action trigger condition, which needs to consider the specific needs of the actual application scenario, including the required level of accuracy in locating pollution sources, the acceptable level of false positives, and the precision standard of environmental monitoring. When the calculated pollution source tracing response quantity exceeds this pre-set threshold, it indicates that the system has accumulated sufficient evidence to support the judgment of the existence of a pollution source, and thus initiates the execution program of the pollution source positioning instruction.

[0094] The execution of the pollution source positioning instruction involves multiple precise operation steps. First, the high-precision gas component analysis devices carried are activated. These devices usually use advanced technologies such as spectral analysis or mass spectrometry and can finely identify the components of pollutants in the atmosphere. The devices collect the pollution characteristic component data of the current location, obtain the concentration levels and composition ratios of various pollutants. Based on these detailed component data, the system generates a pollution source fingerprint spectrum. The construction of the spectrum uses feature extraction and pattern recognition techniques to convert complex component data into a standardized set of feature vectors that can uniquely represent the emission characteristics of a specific pollution source. The system marks the current spatial location as a suspected pollution source coordinate. The coordinate record uses a high-precision positioning system to accurately record the latitude, longitude, altitude, and timestamp information. These coordinate data, together with the simultaneously collected environmental parameters, gas component data, and fingerprint spectrum, are stored and transmitted to form a complete pollution source identification record.

[0095] It should be noted that the relational terms herein such as first and second and the like are used solely to distinguish one from another entity or action, without necessarily requiring or implying any actual relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0096] While the embodiments of the application have been illustrated and described, it will be understood by those skilled in the art that various changes, modifications, substitutions, and alterations can be made therein without departing from the spirit and scope of the application, which is defined by the following claims and their equivalents.

Claims

1. A drone method for tracing the sources of air pollution, characterized in that, The method includes: Collect gas concentration distribution data at different spatial locations in the target area and simultaneously acquire meteorological parameter datasets; Based on the spatial distribution characteristics of the gas concentration distribution data and the meteorological parameter dataset, multiple pollution diffusion stability factors are determined. A spatial model for tracing atmospheric pollution sources was constructed using the aforementioned multiple pollution diffusion stability factors. A pollution source search strategy for the UAV swarm is generated based on the aforementioned atmospheric pollution source tracing spatial model; The pollution source search strategy is dynamically adjusted based on real-time collected gas concentration distribution data; Each UAV independently generates local source tracing decisions based on its own collected local environmental feature data and the environmental feature datasets of its neighboring UAVs; The local tracing decisions are adjusted for consistency through a collaborative decision-making mechanism to obtain collaborative decision-making results; The pollution source tracing response quantity is determined based on the pollution source search strategy and the collaborative decision-making results. When the pollution source tracing response exceeds a preset response threshold, a pollution source location command is executed; Each drone independently generates local source tracing decisions based on its own collected local environmental feature data and the environmental feature datasets of neighboring drones. Specifically, this includes: The local environmental feature data and the environmental feature dataset of neighboring UAVs are fused to generate a local environmental feature vector; Calculate the probability distribution of pollution source directions based on the local environmental feature vectors; The direction with the highest probability is selected as the local source tracing decision for the current drone; The consistency adjustment of the local tracing decision through the collaborative decision-making mechanism specifically includes: Collect local source tracing decisions from nearby drones to form a decision set; Calculate the deviation between the current UAV decision and the decision set; When the decision deviation exceeds a preset deviation threshold, a decision correction vector is generated; The decision correction vector is applied to adjust the local source tracing decision of the current UAV; Determining the pollution source tracing response quantity based on the pollution source search strategy and the collaborative decision-making results specifically includes: Extract the target area priority coefficient from the pollution source search strategy; Calculate the decision confidence level of the collaborative decision-making results; The pollution source tracing response quantity is generated based on the target area priority coefficient and the decision confidence level.

2. The UAV method for tracing air pollution sources as described in claim 1, characterized in that, Based on the spatial distribution characteristics of the gas concentration distribution data and the meteorological parameter dataset, multiple pollution diffusion stability factors are determined, including: Analyze the spatial gradient variation characteristics of the gas concentration distribution data; Extract the wind speed distribution characteristics and wind direction stability parameters from the meteorological parameter dataset; The pollution diffusion stability factor is calculated based on the spatial gradient variation characteristics, wind speed distribution characteristics, and wind direction stability parameters.

3. The UAV method for tracing air pollution sources as described in claim 1, characterized in that, The construction of an atmospheric pollution source tracing spatial model using the aforementioned multiple pollution diffusion stability factors specifically includes: A three-dimensional pollution source tracing spatial coordinate system is constructed, where the X-axis represents the gas concentration gradient value, the Y-axis represents the wind speed influence factor, and the Z-axis represents the wind direction stability. The pollution diffusion stability factor is mapped to the three-dimensional pollution source tracing spatial coordinate system to form a source tracing spatial lattice. A pollution source probability distribution surface is generated based on the aforementioned source tracing spatial lattice.

4. The UAV method for tracing air pollution sources as described in claim 1, characterized in that, The pollution source search strategy for generating UAV swarms based on the aforementioned atmospheric pollution source tracing spatial model specifically includes: Extract the coordinate set of high-probability pollution areas from the aforementioned spatial model for tracing atmospheric pollution sources; The search responsibility area of ​​the drone swarm is divided according to the coordinate set of the high-probability contamination area; Generate dynamic search path plans for each area of ​​responsibility.

5. The UAV method for tracing air pollution sources as described in claim 1, characterized in that, The specific steps of dynamically adjusting the pollution source search strategy based on real-time collected gas concentration distribution data include: Monitor the rate of change of current gas concentration distribution data relative to historical gas concentration distribution data; When the concentration change rate exceeds a preset change threshold, the pollution diffusion stability factor is recalculated. The atmospheric pollution source tracing spatial model is updated based on the recalculated pollution diffusion stability factor; The pollution source search strategy is revised based on the updated spatial model for tracing atmospheric pollution sources.

6. The UAV method for tracing air pollution sources as described in claim 1, characterized in that, When the pollution source tracing response exceeds a preset response threshold, the execution of the pollution source location command specifically includes: Activate the high-precision gas composition analyzer to collect data on the characteristic components of pollutants; A pollution source fingerprint map is generated based on the pollution characteristic component data; Mark the current spatial location as the coordinates of a suspected pollution source.

7. A drone system for tracing air pollution sources, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the UAV method for tracing atmospheric pollution sources as described in any one of claims 1 to 6.

Images