Pollution source positioning method, device, equipment and storage medium based on multi-source data fusion

Abstract

The present application discloses a method, device, equipment and storage medium for locating pollution sources based on multi-source data fusion, which relates to the field of environmental monitoring technology, including: using a sensor network to obtain environmental and meteorological data, and through adaptive filtering and time synchronization processing, obtaining filtered environmental data and synchronized meteorological data respectively. Then, the improved Kriging interpolation algorithm and adaptive Kalman filtering are used to estimate the pollution source information in combination with these data to generate an initial state vector. Based on this vector, the location of the pollution source is predicted, a candidate coordinate set is formed, and the target pollution source location is selected through maximum likelihood estimation optimization, which overcomes the data transmission delay and meteorological disturbance problems of traditional methods and improves the accuracy and reliability of real-time positioning of VOCs pollution sources in industrial parks.

Description

Technical Field

[0001] The present invention relates to the field of environmental monitoring technology, and in particular to a pollution source positioning method, device, equipment and storage medium based on multi-source data fusion. Background Art

[0002] Volatile organic compounds (VOCs) are significant atmospheric pollutants generated during industrial production. Their atmospheric photochemical reactions generate ozone and secondary organic aerosols, making them a major precursor to smog and photochemical pollution. VOC emissions from industrial parks account for a significant portion of industrial pollution sources, but traditional monitoring methods struggle to quickly and accurately locate pollution sources, resulting in delayed emergency responses and increased risk of pollution spread.

[0003] Existing VOCs source location methods primarily rely on offline laboratory analysis or centralized computational models based on fixed monitoring stations. Offline laboratory analysis, due to its long sampling period, cannot meet real-time requirements; centralized computational models based on fixed monitoring stations are limited by data transmission bandwidth and processing latency. Especially under complex meteorological conditions, the time-varying and random nature of the diffusion paths of dynamic pollution sources can lead to significant errors in traditional models.

[0004] Despite the progress, existing technologies still have limitations in many aspects. First, the current technical solutions rely on the cloud for centralized processing, and a large amount of monitoring data needs to be remotely transmitted to the server, resulting in time delays of more than minutes. Secondly, the deployment density of fixed monitoring stations is insufficient, making it difficult to capture the dynamic gradient change characteristics of the VOCs concentration field. In addition, the traditional backdiffusion model assumes steady-state meteorological conditions and fails to fully consider non-ideal factors such as wind speed fluctuations and turbulence intensity, resulting in reduced positioning reliability in complex scenarios. Therefore, there is an urgent need for an efficient and accurate pollution source positioning method to meet the needs of pollution source positioning in industrial parks. Summary of the Invention

[0005] The main purpose of this application is to provide a pollution source positioning method, device, equipment and storage medium based on multi-source data fusion, aiming to solve the technical problem of how to improve the accuracy of pollution source positioning in industrial parks.

[0006] To achieve the above objectives, this application proposes a pollution source location method based on multi-source data fusion, including:

[0007] Obtain environmental and meteorological data;

[0008] Processing the environmental data through adaptive filtering to obtain filtered environmental data;

[0009] Performing time synchronization processing on the meteorological data to obtain synchronized meteorological data;

[0010] Obtaining pollution source information by processing the filtered environmental data and the synchronized meteorological data;

[0011] Calculating based on the pollution source information to obtain an initial state vector of the pollution source;

[0012] Calculating based on the initial state vector of the pollution source to obtain a candidate pollution source coordinate set;

[0013] The candidate pollution source coordinate set is selected through maximum likelihood estimation to obtain the target pollution source position.

[0014] In one embodiment, the step of performing adaptive filtering on the environmental data to obtain filtered environmental data includes:

[0015] Access historical environmental data;

[0016] The adaptive adjustment factor is calculated based on the historical environmental data. The specific formula is:

[0017] ;

[0018] in, is the adjustment coefficient, Indicates the number of historical environmental data, Indicates the The concentration value of the historical environmental data, is the moving window mean, is the window standard deviation;

[0019] Adaptive filtering is performed on the environmental data based on the adaptive adjustment factor to obtain filtered environmental data. The specific formula is:

[0020] ;

[0021] in, represents the concentration value of the environmental data, is the Laida criterion coefficient.

[0022] In one embodiment, the step of performing time synchronization processing on the meteorological data to obtain synchronized meteorological data includes:

[0023] Acquire local clock information according to the meteorological data, wherein the local clock information includes a local clock value and a clock deviation;

[0024] The edge computing correction value is obtained by calculating based on the local clock information and the theoretical synchronization time value. The specific formula is:

[0025] ;

[0026] in, is the theoretical synchronization time value, The number of sensors for obtaining the meteorological data, is the local clock value;

[0027] The local clock information is corrected based on the edge computing correction value to obtain the corrected clock information. The specific formula is:

[0028] ;

[0029] in, is the delayed clock, is the clock deviation, Calculate correction values for edges;

[0030] The synchronized meteorological data is obtained according to the corrected clock information. The specific formula is:

[0031] ;

[0032] in, Represents synchronized meteorological data, including wind speed and wind direction Meteorological variables, Indicates the meteorological data.

[0033] In one embodiment, the step of obtaining pollution source information by processing the filtered environmental data and the synchronized meteorological data includes:

[0034] The pollutant concentration field is constructed by processing the filtered environmental data using a spatial interpolation method. The specific interpolation formula is:

[0035] ;

[0036] in, For the The pollutant concentration at each detection point, For the The normalized weight coefficient corresponding to the detection points, and satisfying =1, the specific formula for obtaining the normalized weight coefficient is:

[0037] ;

[0038] ;

[0039] ;

[0040] in, is the spatial scale parameter, is the current position coordinate, is the wind speed at the current location, is the historical dominant wind speed, is the standard deviation of wind speed, is the wind direction at the current location, Leading the trend of history, is the standard deviation of wind direction fluctuation;

[0041] The pollutant concentration field is processed through coupling optimization to obtain the corrected concentration value of the pollutant. The specific formula is:

[0042] ;

[0043] in, For the The original concentration of each detection point;

[0044] Calculation is performed based on the corrected concentration value of the pollutant to obtain pollution source information.

[0045] In one embodiment, the step of calculating based on the pollution source information to obtain the initial state vector of the pollution source includes:

[0046] Identify the target pollutant concentration field in the pollution source information to obtain a concentration gradient value;

[0047] Selecting the position where the concentration gradient reaches a preset value as the initial position of the pollution source;

[0048] Obtaining a concentration value at an initial position of the pollution source as an initial concentration;

[0049] Correcting the initial position and initial concentration of the pollution source according to the pollutant diffusion path in the pollution source information to obtain a corrected position and a corrected concentration;

[0050] The corrected position and the corrected concentration are combined to obtain an initial state vector of the pollution source.

[0051] In one embodiment, the step of performing calculation based on the initial state vector of the pollution source to obtain a set of candidate pollution source coordinates includes:

[0052] According to the initial state vector combined with the Gaussian diffusion model, the updated state vector is obtained. The specific formula is:

[0053] ;

[0054] in, represents the state transition matrix, represents process noise;

[0055] According to the updated state vector, a prediction is performed to obtain a priori estimated state vector. The specific formula is:

[0056] ;

[0057] in, represents the state vector estimated a priori, Indicates wind speed correction;

[0058] Mapping the a priori estimated state vector to obtain an observation vector;

[0059] Based on the observation vector, the state estimation value is obtained through the Kalman gain matrix, and the Kalman gain matrix is expressed as:

[0060] ;

[0061] in, is the observation vector, is the observation noise covariance matrix, is the forecast error covariance matrix;

[0062] The posterior probability is calculated based on the state estimation value. The specific calculation formula is:

[0063] ;

[0064] in, is the posterior probability of the pollution source location, is the estimated value of the state, is a priori probability distribution of pollution source locations, where the priori probability distribution is obtained based on historical environmental data;

[0065] A candidate pollution source coordinate set is generated according to the posterior probability.

[0066] In one embodiment, the step of selecting the candidate pollution source coordinate set by maximum likelihood estimation to obtain the target pollution source location includes:

[0067] Calculating based on the candidate pollution source coordinate set to obtain likelihood values corresponding to multiple pollution source coordinates;

[0068] Compare the multiple likelihood values to obtain the pollution source coordinates corresponding to the preset likelihood value. The specific calculation formula is:

[0069] ;

[0070] in, Preset distance for sensor spacing, are the coordinates of the target pollution source, are the candidate pollution source coordinates, is the number of sensors;

[0071] The target pollution source position is obtained by performing conversion according to the pollution source coordinates.

[0072] In addition, to achieve the above objectives, the present application also proposes a pollution source locating device based on multi-source data fusion, the pollution source locating device based on multi-source data fusion comprising:

[0073] Acquisition module, used to obtain environmental data and meteorological data;

[0074] a processing module, configured to process the environmental data through adaptive filtering to obtain filtered environmental data; and further configured to perform time synchronization processing on the meteorological data to obtain synchronized meteorological data;

[0075] a fusion module, configured to obtain pollution source information by processing the filtered environmental data and the synchronized meteorological data;

[0076] a calculation module, configured to calculate based on the pollution source information to obtain an initial state vector of the pollution source; and further configured to calculate based on the initial state vector of the pollution source to obtain a set of candidate pollution source coordinates;

[0077] The result module is used to select the candidate pollution source coordinate set through maximum likelihood estimation to obtain the target pollution source location.

[0078] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the pollution source positioning method based on multi-source data fusion as described above are implemented.

[0079] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the steps of the pollution source positioning method based on multi-source data fusion as described above.

[0080] This application obtains environmental data and meteorological data, processes the environmental data through adaptive filtering to obtain filtered environmental data, performs time synchronization processing on the meteorological data to obtain synchronized meteorological data, obtains pollution source information by processing the filtered environmental data and synchronized meteorological data, calculates based on the pollution source information, obtains the initial state vector of the pollution source, calculates based on the initial state vector of the pollution source, obtains a candidate pollution source coordinate set, selects the candidate pollution source coordinate set through maximum likelihood estimation, and obtains the target pollution source position. By using sensors to obtain environmental and meteorological data, and through adaptive filtering and time synchronization processing, respectively obtain filtered environmental data and synchronized meteorological data. Then, combined with these data, an improved Kriging interpolation algorithm and an adaptive Kalman filter are used to estimate the pollution source information and generate an initial state vector. Based on this vector, the pollution source position is predicted, a candidate coordinate set is formed, and the target pollution source position is optimized and selected through maximum likelihood estimation, achieving millisecond-level response and high-precision positioning, overcoming the data transmission delay and meteorological disturbance problems of traditional methods, and improving the accuracy and reliability of real-time positioning of VOCs pollution sources in industrial parks. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0082] Figure 1 This is a flow chart of the first embodiment of the pollution source location method based on multi-source data fusion of this application;

[0083] Figure 2 This is a flow chart of a second embodiment of the pollution source location method based on multi-source data fusion of this application;

[0084] Figure 3 This is a flow chart of the third embodiment of the pollution source location method based on multi-source data fusion of the present application;

[0085] Figure 4 This is a schematic diagram of the module structure of a pollution source locating device based on multi-source data fusion according to the first embodiment of the pollution source locating method based on multi-source data fusion of the present application;

[0086] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the pollution source positioning method based on multi-source data fusion in an embodiment of the present application.

[0087] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0088] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0089] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0090] Amidst the current rapid industrialization, volatile organic compounds (VOCs), a significant byproduct of industrial production, have become a major source of air pollution. These compounds not only directly harm human health but also, through participating in atmospheric photochemical reactions, generate ozone and secondary organic aerosols, serving as key precursors to haze and photochemical smog. Industrial parks, as concentrated areas of VOC emissions, have a particularly significant impact on surrounding air quality. However, traditional monitoring methods, such as offline laboratory analysis or centralized computing based on fixed monitoring stations, are insufficient for complex industrial emission scenarios, particularly in terms of real-time performance and accuracy. These challenges primarily manifest in response delays, limited spatial coverage, and poor model adaptability, making them unable to quickly and accurately locate pollution sources, thereby hindering the efficiency and effectiveness of emergency response.

[0091] Therefore, in order to overcome the above problems, the present application proposes a method for locating pollution sources efficiently and accurately. The main solution of the embodiment of the present application is: obtaining environmental data and meteorological data, processing the environmental data through adaptive filtering to obtain filtered environmental data, performing time synchronization processing on the meteorological data to obtain synchronized meteorological data, obtaining pollution source information by processing the filtered environmental data and the synchronized meteorological data, performing calculations based on the pollution source information to obtain the initial state vector of the pollution source, performing calculations based on the initial state vector of the pollution source to obtain a set of candidate pollution source coordinates, selecting the candidate pollution source coordinates through maximum likelihood estimation, and obtaining the location of the target pollution source.

[0092] Based on the above, the embodiment of the present application also provides a pollution source positioning method based on multi-source data fusion, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the pollution source location method based on multi-source data fusion of this application.

[0093] In this embodiment, the pollution source location method based on multi-source data fusion includes steps S10 to S70:

[0094] Step S10: Acquire environmental data and meteorological data.

[0095] It should be noted that environmental data is collected through the deployment of a high-density sensor network. These sensors, distributed across the industrial park, are capable of real-time monitoring of a variety of environmental parameters, including VOC concentrations, temperature, and humidity. Each sensor is equipped with advanced detection components, ensuring high-precision and stable data collection. Furthermore, the sensor network utilizes wireless communication technology, making data transmission more convenient and efficient, reducing wiring costs and complexity. Furthermore, to more accurately capture the impact of meteorological conditions on VOC dispersion, detailed meteorological data is also required from sensors. This includes, but is not limited to, key meteorological indicators such as wind speed, wind direction, and air pressure. Meteorological data not only helps understand how pollutants migrate and disperse in the atmosphere but also provides important context for subsequent data analysis. For example, in strong winds, pollutants can quickly spread over long distances; whereas, in low winds or calm weather, pollutants accumulate in a localized area, forming areas of high concentration.

[0096] Step S20 , performing adaptive filtering on the environmental data to obtain filtered environmental data.

[0097] It's important to note that to ensure high accuracy and reliability of environmental data acquired from sensor networks, effective preprocessing of the raw environmental data is necessary. Adaptive filtering can dynamically remove noise, providing more accurate data input, which is crucial for subsequent analysis. Raw environmental data often contains noise from sensor measurement errors as well as external interference. This noise can originate from transient interference factors such as electromagnetic pulses and mechanical vibration.

[0098] To address these issues, a dynamic adaptive filtering method was employed. Based on the Laida criterion (3σ principle), this method dynamically filters out outliers by calculating the mean and standard deviation within a moving window. By default, the threshold is set to 3σ to ensure that at least 95% of normal data is retained. This method not only effectively eliminates transient interference but also automatically adjusts the filtering threshold based on changing pollutant concentration trends, enhancing the system's robustness and adaptability.

[0099] Furthermore, an adaptive adjustment factor is introduced. This factor is calculated based on historical data statistics and reflects the average deviation of data over a period of time. Specifically, historical environmental data is obtained and calculated based on the historical environmental data to obtain the adaptive adjustment factor. The specific formula is:

[0100] ;

[0101] in, is the adjustment coefficient, Indicates the number of historical environmental data, Indicates the The concentration value of historical environmental data, is the moving window mean, is the window standard deviation.

[0102] Adaptive filtering is performed on the environmental data based on the adaptive adjustment factor to obtain filtered environmental data. The specific formula is:

[0103] ;

[0104] in, Indicates the concentration value of environmental data, is the Laida criterion coefficient. During the adaptive filtering process, each edge computing node performs preliminary processing on the sensor data within its area of responsibility. For each data point received at a given time point, a moving window mean and window standard deviation are calculated. The moving window mean refers to the average value of the data calculated within a fixed-size time window. With each newly collected data point, this time window slides to always include the latest data sample. For example, if the window size is set to 5 minutes, then for each new data point received, the average value of all data points within the last 5 minutes, including that data point, is calculated. The window standard deviation is calculated based on the same time window as the moving window mean. It measures the dispersion of the data points within the window relative to the window mean. A higher standard deviation indicates greater variation between the data points, which may indicate the presence of outliers or significant random noise, while a lower standard deviation indicates more concentrated and stable data.

[0105] Then, the pre-set Laida criterion is used to determine whether the current reading is an outlier. The Laida criterion is a statistical method used to identify and eliminate outliers. represents the standard deviation, This means that any data point that deviates from the mean by more than three standard deviations is considered an outlier. In this example, the Laida criterion coefficient is set to 3, meaning that if a data point deviates from the moving window mean by more than three standard deviations of the window in which it resides, it is considered an outlier and should be excluded or corrected. This ensures that at least 99.7% of normal data is retained while effectively filtering out extreme outliers.

[0106] Step S30: performing time synchronization processing on the meteorological data to obtain synchronized meteorological data.

[0107] It's important to note that due to the wide coverage of sensor networks, transmission delays between nodes, and local clock skew, directly collected meteorological data can face time synchronization issues. For example, consider a sensor network consisting of multiple weather stations, each collecting meteorological parameters such as wind speed and direction at a different frequency. Due to geographical differences, communication delays between each station and the central server can also vary. Without time synchronization, even events occurring at the same moment will have inconsistent timestamps recorded at different stations, impacting the accuracy of subsequent data analysis. To address these issues and ensure that all meteorological data can be compared and analyzed on a unified time basis, time synchronization is necessary.

[0108] First, to achieve accurate time synchronization, it is necessary to calculate a correction term based on edge computing. This correction term takes into account the number of sensors and the theoretical synchronization time. Through local computing, cloud data transmission delay is reduced, so that all meteorological data can achieve millisecond-level response accuracy. Specifically, local clock information is obtained based on meteorological data. Local clock information includes the local clock value and clock deviation. The edge computing correction value is calculated based on the local clock information and the theoretical synchronization time value. The specific formula is:

[0109] ;

[0110] in, is the theoretical synchronization time value, The number of sensors that obtain meteorological data, The local clock value.

[0111] Secondly, the core goal of time synchronization processing is to eliminate the data arrival time differences caused by different transmission paths and the deviation between local clocks. Specifically, each edge computing node will perform preliminary corrections based on the raw meteorological data it receives and the local clock information. The improved time synchronization method introduces edge computing nodes to perform local clock corrections. By calculating the transmission delay and clock deviation compensation, the data of all sensors are mapped to a unified time axis. Specifically, the local clock information is corrected based on the edge computing correction value to obtain the corrected clock information. The specific formula is:

[0112] ;

[0113] in, is the delayed clock, is the clock deviation, The delay clock represents the clock offset corresponding to the delay caused by network transmission, while the clock deviation reflects the deviation of the sensor's local clock relative to the standard time. The synchronized meteorological data is obtained based on the corrected clock information. ,in, Represents synchronized meteorological data, including wind speed and wind direction Meteorological variables, This means that no matter where the sensor is located or when the data was collected, it can now be compared and analyzed within a unified time frame.

[0114] Step S40 , obtaining pollution source information by processing the filtered environmental data and the synchronized meteorological data.

[0115] It should be noted that the filtered environmental data are spatially interpolated using a flow-field-constrained kriging interpolation method. This method not only considers the spatial characteristics of sensor distribution but also incorporates the influence of key meteorological factors such as wind speed to optimize weight distribution and ensure that the reconstructed pollutant concentration field is both unbiased and has minimal variance.

[0116] Specifically, by analyzing VOC concentrations at different sensor locations and introducing a wind speed weighting factor, we can more accurately simulate the diffusion pattern of pollutants in the atmosphere and fill in data blind spots in areas with sparse sensor distribution. Next, we combine the optimized concentration field data with synchronized meteorological data to obtain pollution source information.

[0117] Step S50: Calculate based on the pollution source information to obtain the initial state vector of the pollution source.

[0118] It’s important to note that after acquiring filtered environmental data and time-synchronized meteorological data, the next step is to calculate the initial state vector of the pollution source based on this information. This process is crucial for accurately estimating the location of VOC pollution sources and their emission intensity.

[0119] Furthermore, step S50 includes: identifying the target pollutant concentration field in the pollution source information, obtaining a concentration gradient value, and selecting the location where the concentration gradient value reaches a preset value as the initial location of the pollution source. Specifically, the target pollutant concentration field constructed based on the filtered environmental data and synchronized meteorological data can identify the concentration gradient values at different locations. The concentration gradient reflects the rate at which the pollutant concentration changes with space, and usually reaches a maximum value near the pollution source. The location where the concentration gradient value reaches the maximum value is selected as the initial location of the pollution source, and the pollutant concentration value at this location is obtained as the initial concentration. Due to the presence of various interference factors in the actual environment, such as wind speed, the directly obtained concentration value deviates from the actual situation.

[0120] Therefore, it is also necessary to correct the initial position and initial concentration of the pollution source according to the pollutant diffusion path in the pollution source information to obtain the corrected position and corrected concentration, and then combine the corrected position and corrected concentration to obtain the initial state vector of the pollution source. Specifically, by using advanced algorithms such as adaptive Kalman filtering, combined with the latest meteorological data (such as wind speed and wind direction), the position and concentration estimates of the pollution source can be dynamically adjusted. For example, under high wind speed conditions, pollutants may spread rapidly, resulting in a position offset of the original estimate; while in calm weather, pollutants may accumulate in situ, making the concentration value higher than expected. By continuously updating the state transfer matrix and taking into account the diffusion and degradation process of pollutants in the atmosphere, the actual diffusion trajectory of pollutants can be simulated more accurately. Finally, the corrected position and concentration values are combined to form the initial state vector of the pollution source. , x and y represent the coordinates of the pollution source in the two-dimensional plane, represents the corrected initial pollutant concentration.

[0121] Step S60 , performing calculation based on the initial state vector of the pollution source to obtain a candidate pollution source coordinate set.

[0122] It should be noted that calculations are performed based on the initial state vector combined with the Gaussian diffusion model to update the state vector and generate a set of candidate pollution source coordinates. This process is implemented through a series of complex mathematical formulas and algorithms, aiming to provide accurate pollution source location estimates.

[0123] Furthermore, step S60 further includes: obtaining an updated state vector based on the initial state vector in combination with the Gaussian diffusion model. Specifically, based on the initial state vector , the updated state vector is obtained by combining the Gaussian diffusion model with the state transfer matrix and process noise. The specific formula is as follows:

[0124] ;

[0125] in, Represents the state transfer matrix, which takes into account the diffusion and degradation process of pollutants and is adjusted according to meteorological conditions (such as wind speed and direction). The state equation can be written as:

[0126] ;

[0127] Among them, the vector Indicates that the pollution source is The state vector of the time step, 、 is the predicted pollution source location coordinate, is the predicted pollution source concentration value. Vector Indicates that the pollution source is The state vector of the time step (the state transfer matrix is multiplied by it to achieve the linear evolution of the state), 、 Indicates the current pollution source location coordinates, represents the initial concentration of the current pollution source, represents the pollutant concentration attenuation coefficient, which is determined by the diffusion and degradation processes. is the degradation rate of pollutants, which is related to environmental conditions. represents the time step, Indicates speed, Indicates the pollution source at time The concentration change rate, Represents process noise, which is used to simulate the influence of uncertain factors such as environmental disturbances. is the state vector of the next time step. Based on the updated state vector, a prediction is performed to obtain the prior estimated state vector. In this step, a wind speed correction is introduced to more accurately describe the pollutant diffusion path. The specific formula is:

[0128] ;

[0129] in, Represents the state vector of the prior estimate, including the location coordinates of the pollution source and the concentration of the pollutant, Represents the wind speed correction. The state vector estimated a priori is mapped to obtain the observation vector, and then the state estimate is obtained based on the observation vector through the Kalman gain matrix. The Kalman gain matrix is expressed as:

[0130] ;

[0131] in, is the observation vector, is the observation noise covariance matrix, is the prediction error covariance matrix. Based on the state estimate, the posterior probability is calculated. The specific calculation formula is:

[0132] ;

[0133] in, is the posterior probability of the pollution source location, is the estimated value of the state, is the prior probability distribution of the pollution source location. The above prior probability distribution is obtained based on historical environmental data. The candidate pollution source coordinate set is generated according to the posterior probability. By comparing the posterior probability values of different locations, several locations with the highest probability can be screened out as candidate pollution source coordinates. The screening is based on historical data or regional experience.

[0134] Step S70 , selecting the candidate pollution source coordinate set by maximum likelihood estimation to obtain the target pollution source position.

[0135] It's important to note that after generating a set of candidate pollution source coordinates, the next step is to further screen these coordinates using Maximum Likelihood Estimation (MLE) to determine the most likely target pollution source location. This process relies not only on statistical principles but also requires the integration of actual monitoring data and environmental background information to ensure the accuracy and reliability of the final location.

[0136] Specifically, after obtaining a set of candidate pollution source coordinates, the likelihood value of each coordinate needs to be calculated. The likelihood value reflects the probability of the observed data occurring given that coordinate as the pollution source location. Specifically, for each candidate coordinate, a probability density function (PDF) is constructed based on its corresponding pollutant concentration field model and actual sensor measurements. This probability density function, typically based on the Gaussian distribution assumption and accounting for observation noise, describes the expected distribution of sensor node measurements at a specific pollution source location. Next, the maximum likelihood principle is applied to select the coordinate that maximizes the likelihood function as the target pollution source location. This means finding a location that maximizes the probability of the current observation occurring at that location. In practice, due to the potential for multiple local maxima, directly solving the maximum likelihood estimate can lead to local optima. Therefore, iterative optimization algorithms such as gradient descent or Newton's method are often used in practice to find the global optimal solution. Furthermore, a multi-node collaborative verification mechanism can be combined to further enhance positioning accuracy by setting a kernel radius to measure the spatial consistency of the location results of each edge node. For example, if the support of multiple independent nodes is concentrated within a certain area, the coordinates within that area are more likely to be the true pollution source location.

[0137] Finally, the target pollution source location obtained through the above steps is not only the best estimate based on real-time observation data, but also takes into account the influence of multiple factors such as historical data and meteorological conditions, thereby improving the accuracy and robustness of positioning.

[0138] This embodiment acquires environmental data and meteorological data, processes the environmental data through adaptive filtering to obtain filtered environmental data, and performs time synchronization processing on the meteorological data to obtain synchronized meteorological data. Pollution source information is obtained by processing the filtered environmental data and synchronized meteorological data. Based on the pollution source information, calculations are performed to obtain the initial state vector of the pollution source. Based on the initial state vector of the pollution source, calculations are performed to obtain a set of candidate pollution source coordinates. The candidate pollution source coordinates are selected using maximum likelihood estimation to obtain the target pollution source location. Environmental and meteorological data are acquired using sensors and then processed through adaptive filtering and time synchronization to obtain filtered environmental data and synchronized meteorological data, respectively. Next, an improved Kriging interpolation algorithm and an adaptive Kalman filter are used to estimate pollution source information and generate an initial state vector. Based on this vector, the pollution source location is predicted, a set of candidate coordinates is formed, and the target pollution source location is optimized and selected through maximum likelihood estimation. This achieves millisecond-level response and high-precision positioning, overcoming the data transmission delay and meteorological disturbance issues of traditional methods and improving the accuracy and reliability of real-time positioning of VOC pollution sources in industrial parks.

[0139] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 2 The pollution source location method based on multi-source data fusion step S40 further includes steps S201 to S203:

[0140] Step S201 : constructing a pollutant concentration field by processing the filtered environmental data using a spatial interpolation method.

[0141] It should be noted that the filtered environmental data obtained contains the VOCs concentration measurement values at each sensor node. However, due to the limited density of the sensor network, directly using the data of these discrete points cannot fully reflect the distribution of pollutant concentrations in the entire area. Therefore, it is necessary to use spatial interpolation methods to expand these discrete data points into a continuous concentration field. Commonly used interpolation methods include inverse distance weighted method, Kriging method, etc. In this embodiment, the Kriging interpolation method based on flow field constraints is adopted. The specific interpolation formula is:

[0142] ;

[0143] in, For the The pollutant concentration at each detection point, For the The normalized weight coefficient corresponding to the detection points, and satisfying =1.

[0144] Furthermore, the Kriging interpolation method based on flow field constraints not only considers the distance relationship between sensor locations, but also combines the influence of key meteorological parameters such as wind speed and wind direction to optimize the weight distribution. Specifically, the optimal weight is determined by calculating the semi-variogram function, and an unbiased pollutant concentration field with minimum variance is reconstructed. This method can effectively make up for the data blind spots in areas where sensors are sparsely distributed, and provide a more accurate background concentration field model. For example, when the wind speed is high, pollutants will diffuse rapidly in a specific direction. At this time, relying solely on the distance weighted method may lead to large errors, while introducing flow field constraints can improve the accuracy of the interpolation results. In order to further enhance the adaptability and robustness of the model, the interpolation weights can also be adjusted in combination with historical dominant wind speed and wind direction information. For example, for those areas where high pollution concentrations have frequently occurred in history, higher weights are given to ensure that the model can better reflect the actual pollution conditions. This dynamic adjustment mechanism enables high prediction accuracy to be maintained even under complex and changeable meteorological conditions. Specifically:

[0145] ;

[0146] ;

[0147] ;

[0148] in, is the spatial scale parameter, is the current position coordinate, is the wind speed at the current location, is the historical dominant wind speed, is the standard deviation of wind speed, is the wind direction at the current location, Leading the trend of history, is the standard deviation of wind direction fluctuation.

[0149] Step S202 : performing coupled optimization processing on the pollutant concentration field to obtain a corrected concentration value of the pollutant.

[0150] It should be noted that the concentration field correction value obtained above is coupled with the concentration field using the flow field constrained Kriging interpolation method to perform optimization processing. During the coupled optimization process, the distribution of the concentration field will be dynamically adjusted to ensure that it is consistent with the actual pollutant diffusion trajectory. Specifically, for each sensor location, the corrected concentration value of that location will be calculated based on the current meteorological conditions. This corrected concentration value not only takes into account the original concentration measured by the sensor, but also combines the influence of meteorological parameters on pollutant diffusion. For example, under strong wind conditions, pollutants may diffuse rapidly to the downwind area, resulting in a significant decrease in concentration values in some areas, while the concentration values in other areas may increase due to the accumulation of pollutants. The specific formula is:

[0151] ;

[0152] in, For the The original concentration of each detection point, =1Finally, the coupled optimized pollutant concentration values provide a more realistic and reliable concentration distribution.

[0153] Step S203: Calculate based on the corrected concentration value of the pollutant to obtain pollution source information.

[0154] It should be noted that after obtaining the pollutant concentration that has undergone coupled optimization processing, the concentration field provides the distribution of pollutants in the entire area. Combined with the calculated pollutant diffusion path, the trend and impact range of pollutants spreading outward from the source can be more intuitively observed. For example, under high wind speed conditions, pollutants may diffuse rapidly along the dominant wind direction; while under low wind speed or calm weather, pollutants may accumulate in situ to form local high concentration areas. By superimposing these diffusion paths on the concentration field, it is possible to clearly show how pollutants migrate over time and space. Next, dynamic prediction methods such as adaptive Kalman filtering are used, combined with the optimized concentration field and diffusion path, to further estimate the specific location of the pollution source and its release intensity. In order to further simulate the diffusion process of pollutants from the source to the perception point, this embodiment introduces a pollution diffusion path model to fuse the corrected concentration field with the possible diffusion path. By calculating the reverse diffusion probability distribution between the target point and multiple possible pollution sources, combined with the corrected concentration value of the pollutant, a pollutant concentration-diffusion path joint field is constructed. The specific formula is:

[0155] ;

[0156] in, The pollution source location is The probability of is the pollutant-corrected concentration value at the pollution source location, is the pollutant diffusion path, represents the data fusion function, which integrates the corrected pollutant concentrations and diffusion paths. Ultimately, based on the pollution source information generated from these integrated analysis results and the probability distribution calculated from the pollutant information, the most likely location of the pollution source is determined. This location not only has the highest probability value but also highly aligns with the data collected by the sensor network and the diffusion path. This provides important decision-making support for industrial parks, enabling them to identify and respond to potential pollution incidents promptly, implement effective control measures, reduce environmental pollution risks, and protect the ecological environment and public health.

[0157] This embodiment constructs accurate pollutant concentration fields and diffusion paths through spatial interpolation and meteorological data correction, and combines the two to obtain pollution source information, thereby improving positioning accuracy and enhancing adaptability to complex meteorological conditions.

[0158] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above introduction and will not be described in detail later. Figure 3 The pollution source location step S70 based on multi-source data fusion further includes steps S301 to S303:

[0159] Step S301 : Calculate based on the candidate pollution source coordinate set to obtain likelihood values corresponding to multiple pollution source coordinates.

[0160] It's important to note that after generating a set of candidate pollution source coordinates, the next step is to calculate the likelihood value corresponding to each coordinate to determine the most likely pollution source location. This process uses statistical methods to assess the likelihood of different locations being potential pollution sources, ensuring the accuracy and reliability of the positioning results.

[0161] First, for each candidate pollution source coordinate , based on its corresponding pollutant concentration field model and actual sensor measurement data, a probability density function is constructed ,in Represents the actual observation data of all sensor nodes. This probability density function is usually assumed to be a Gaussian distribution. Taking into account the existence of observation noise, it describes the expected distribution of the measurement values of each sensor node at a specific pollution source location. , the likelihood value can be calculated according to the likelihood function.

[0162] Step S302: compare multiple likelihood values to obtain the pollution source coordinates corresponding to the preset likelihood values.

[0163] It's important to note that after calculating the likelihood values for multiple candidate pollution source coordinates, the next step is to compare these likelihood values to determine the pollution source coordinates corresponding to the preset likelihood values. This process uses rigorous statistical analysis and optimization algorithms to ensure the accuracy and reliability of the final positioning results.

[0164] Specifically, the likelihood values of all candidate pollution source coordinates are sorted from high to low. Each likelihood value reflects the probability of the observed data appearing given that coordinate as the pollution source location. Generally, the coordinate with the highest likelihood value is the most likely true pollution source location. The specific formula is:

[0165] ;

[0166] in, Preset distance for sensor spacing, are the coordinates of the target pollution source, are the candidate pollution source coordinates, is the number of sensors. However, in actual operation, in order to improve the robustness and accuracy of positioning, a preset likelihood threshold is usually set. Only when the likelihood value of a certain coordinate exceeds this threshold will it be identified as a valid pollution source location. Assuming that we set a preset likelihood threshold, we need to find all candidate coordinates whose likelihood values are greater than or equal to the preset likelihood threshold. These coordinates are considered to be potential pollution source locations and are further verified and analyzed. For example, if the likelihood values of multiple candidate coordinates exceed the preset threshold, the multi-node collaborative verification mechanism can be combined to measure the spatial consistency of the positioning results of each edge node through the kernel radius (1.5 times the sensor spacing in this embodiment), and select the coordinates supported by the majority of nodes as the final coordinates of the pollution source location.

[0167] Step S303: convert the pollution source coordinates to obtain the target pollution source position.

[0168] It should be noted that after selecting the coordinates supported by the majority of nodes as the final target pollution source coordinates based on the spatial consistency of the positioning results of each edge node by setting the kernel radius, it is necessary to convert them from the local coordinate system to the global coordinate system. This step usually involves the application of geographic information system (GIS) data to ensure that all positioning information can be compared and analyzed within a unified map or spatial framework. For example, if the sensor nodes are distributed across different geographic areas, the local coordinates provided by each node need to be converted into unified Global Positioning System (GPS) coordinates in order to accurately identify the specific geographic location of the pollution source.

[0169] Ultimately, the location of the target pollution source after coordinate transformation and verification not only reflects the best estimate of real-time observations, but also takes into account the influence of environmental background and long-term trends, thereby improving the accuracy and robustness of positioning.

[0170] This embodiment calculates and compares the likelihood values of candidate pollution source coordinates, uses a preset distance between sensors to select the optimal coordinates, and then converts them to obtain the position of the target pollution source, thereby achieving accurate and rapid positioning of the pollution source and enhancing the efficiency and accuracy of the response to environmental pollution.

[0171] Based on the first embodiment of the present application, the present application also provides a pollution source positioning device based on multi-source data fusion, please refer to Figure 4 , the device comprises:

[0172] The acquisition module 10 is used to acquire environmental data and meteorological data.

[0173] The processing module 20 is used to process the environmental data through adaptive filtering to obtain filtered environmental data.

[0174] The processing module 20 is further configured to perform time synchronization processing on the meteorological data to obtain synchronized meteorological data.

[0175] The fusion module 30 is used to obtain pollution source information by processing the filtered environmental data and the synchronized meteorological data.

[0176] The calculation module 40 is used to perform calculations based on the pollution source information to obtain the initial state vector of the pollution source.

[0177] The calculation module 40 is further configured to perform calculations based on the initial state vector of the pollution source to obtain a candidate pollution source coordinate set.

[0178] The result module 50 is used to select the candidate pollution source coordinate set through maximum likelihood estimation to obtain the target pollution source location.

[0179] The pollution source location device based on multi-source data fusion provided in this application, which employs the pollution source location method based on multi-source data fusion in the above-mentioned embodiments, can solve the technical problem of how to improve the accuracy of pollution source location in industrial parks. Compared with the prior art, the beneficial effects of the pollution source location device based on multi-source data fusion provided in this application are the same as the beneficial effects of the pollution source location method based on multi-source data fusion provided in the above-mentioned embodiments. The other technical features of the pollution source location device based on multi-source data fusion are the same as those disclosed in the above-mentioned embodiments and are not further described here.

[0180] In one embodiment, the processing module 20 is further configured to obtain historical environmental data; perform calculations based on the historical environmental data to obtain an adaptive adjustment factor; and perform adaptive filtering on the environmental data based on the adaptive adjustment factor to obtain filtered environmental data.

[0181] In one embodiment, the processing module 20 is also used to obtain local clock information based on meteorological data, where the local clock information includes a local clock value and a clock deviation; calculate based on the local clock information and the theoretical synchronization time value to obtain an edge computing correction value; correct the local clock information based on the edge computing correction value to obtain corrected clock information; and obtain synchronized meteorological data based on the corrected clock information.

[0182] In one embodiment, the fusion module 30 is further used to construct a pollutant concentration field by processing the filtered environmental data using a spatial interpolation method; obtain a corrected concentration value of the pollutant by processing the pollutant concentration field through coupling optimization; and obtain pollution source information by performing calculations based on the corrected concentration value of the pollutant.

[0183] In one embodiment, the calculation module 40 is further used to identify the target pollutant concentration field in the pollution source information to obtain a concentration gradient value; select the position where the concentration gradient value reaches a preset value as the initial position of the pollution source; obtain the concentration value at the initial position of the pollution source as the initial concentration; correct the initial position and initial concentration of the pollution source according to the pollutant diffusion path in the pollution source information to obtain a corrected position and a corrected concentration; and combine the corrected position and the corrected concentration to obtain an initial state vector of the pollution source.

[0184] In one embodiment, the calculation module 40 is also used to obtain an updated state vector based on the initial state vector in combination with the Gaussian diffusion model; perform prediction based on the updated state vector to obtain a priori estimated state vector; map the priori estimated state vector to obtain an observation vector; obtain a state estimate value based on the observation vector through the Kalman gain matrix; perform calculation based on the state estimate value to obtain a posterior probability; and generate a candidate pollution source coordinate set based on the posterior probability.

[0185] In one embodiment, the result module 50 is further used to perform calculations based on the candidate pollution source coordinate set to obtain likelihood values corresponding to multiple pollution source coordinates; compare multiple likelihood values to obtain pollution source coordinates corresponding to preset likelihood values; and perform conversion based on the pollution source coordinates to obtain the target pollution source position.

[0186] The present application provides a pollution source positioning device based on multi-source data fusion, and the pollution source positioning device based on multi-source data fusion includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the pollution source positioning method based on multi-source data fusion in the above-mentioned embodiment one.

[0187] Reference below Figure 5 , which shows a schematic diagram of the structure of a pollution source location device based on multi-source data fusion suitable for implementing the embodiments of the present application. The pollution source location device based on multi-source data fusion in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The pollution source positioning device based on multi-source data fusion shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0188] like Figure 5As shown, the pollution source location device based on multi-source data fusion may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the pollution source location device based on multi-source data fusion. Processing device 1001, ROM 1002, and RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, hard disk, etc.; and communication devices 1009. Communication devices 1009 can allow the pollution source location device based on multi-source data fusion to communicate wirelessly or wired with other devices to exchange data. Although various pollution source location devices based on multi-source data fusion are shown in the figure, it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.

[0189] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0190] The pollution source location device based on multi-source data fusion provided in this application, which employs the pollution source location method based on multi-source data fusion in the above-mentioned embodiment, can solve the technical problem of how to improve the accuracy of pollution source location in industrial parks. Compared with the prior art, the beneficial effects of the pollution source location device based on multi-source data fusion provided in this application are the same as the beneficial effects of the pollution source location method based on multi-source data fusion provided in the above-mentioned embodiment, and the other technical features of the pollution source location device based on multi-source data fusion are the same as those disclosed in the method of the previous embodiment, and are not further described here.

[0191] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0192] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0193] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, and the computer-readable program instructions are used to execute the pollution source location method based on multi-source data fusion in the above embodiment.

[0194] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible storage medium that contains or stores a program that can be executed by instructions, used by a device, or used in conjunction with it. The program code contained on the computer-readable storage medium may be transmitted using any suitable storage medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0195] The computer-readable storage medium may be included in the pollution source location device based on multi-source data fusion; or it may exist independently without being assembled into the pollution source location device based on multi-source data fusion.

[0196] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the pollution source locating device based on multi-source data fusion, the pollution source locating device based on multi-source data fusion can be written in one or more programming languages or a combination thereof to write computer program codes for performing the operations of the present application. The programming languages include object-oriented programming languages such as Java, Smalltalk, and C++, as well as conventional procedural programming languages such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, through the Internet using an Internet service provider).

[0197] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based implementation that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0198] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0199] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned pollution source location method based on multi-source data fusion. This computer-readable storage medium can address the technical problem of improving the accuracy of pollution source location in industrial parks. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are similar to those of the pollution source location method based on multi-source data fusion provided in the aforementioned embodiments, and are not further elaborated here.

[0200] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the pollution source location method based on multi-source data fusion as described above.

[0201] The computer program product provided in this application can solve the technical problem of improving the accuracy of locating pollution sources in industrial parks. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the pollution source locating method based on multi-source data fusion provided in the above embodiment, and will not be elaborated here.

[0202] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A pollution source location method based on multi-source data fusion, characterized in that: The method comprises: Obtain environmental and meteorological data; Processing the environmental data through adaptive filtering to obtain filtered environmental data; Performing time synchronization processing on the meteorological data to obtain synchronized meteorological data; Obtaining pollution source information by processing the filtered environmental data and the synchronized meteorological data; Calculating based on the pollution source information to obtain an initial state vector of the pollution source; Calculating based on the initial state vector of the pollution source to obtain a candidate pollution source coordinate set; The candidate pollution source coordinate set is selected through maximum likelihood estimation to obtain the target pollution source position.

2. The method according to claim 1, wherein The step of processing the environmental data through adaptive filtering to obtain filtered environmental data includes: Access historical environmental data; The adaptive adjustment factor is calculated based on the historical environmental data. The specific formula is: in, is the adjustment coefficient, Indicates the number of historical environmental data, Indicates the The concentration value of the historical environmental data, is the moving window mean, is the window standard deviation; Adaptive filtering is performed on the environmental data based on the adaptive adjustment factor to obtain filtered environmental data. The specific formula is: in, represents the concentration value of the environmental data, is the Laida criterion coefficient.

3. The method according to claim 1, wherein The step of performing time synchronization processing on the meteorological data to obtain synchronized meteorological data includes: Acquire local clock information according to the meteorological data, wherein the local clock information includes a local clock value and a clock deviation; The edge computing correction value is obtained by calculating based on the local clock information and the theoretical synchronization time value. The specific formula is: in, is the theoretical synchronization time value, The number of sensors for obtaining the meteorological data, is the local clock value; The local clock information is corrected based on the edge computing correction value to obtain the corrected clock information. The specific formula is: in, is the delayed clock, is the clock deviation, Calculate correction values for edges; The synchronized meteorological data is obtained according to the corrected clock information. The specific formula is: in, Represents synchronized meteorological data, including wind speed and wind direction Meteorological variables, Indicates the meteorological data.

4. The method according to claim 1, wherein The step of obtaining pollution source information by processing the filtered environmental data and the synchronized meteorological data includes: The pollutant concentration field is constructed by processing the filtered environmental data using a spatial interpolation method. The specific interpolation formula is: in, For the The pollutant concentration at each detection point, For the The normalized weight coefficient corresponding to the detection points, and satisfying =1, the specific formula for obtaining the normalized weight coefficient is: in, is the spatial scale parameter, is the current position coordinate, is the wind speed at the current location, is the historical dominant wind speed, is the standard deviation of wind speed, is the wind direction at the current location, Leading the trend of history, is the standard deviation of wind direction fluctuation; The pollutant concentration field is processed through coupling optimization to obtain the corrected concentration value of the pollutant. The specific formula is: in, For the The original concentration of each detection point; Calculation is performed based on the corrected concentration value of the pollutant to obtain pollution source information.

5. The method according to claim 1, wherein The step of calculating based on the pollution source information to obtain the initial state vector of the pollution source includes: Identify the target pollutant concentration field in the pollution source information to obtain a concentration gradient value; Selecting the position where the concentration gradient reaches a preset value as the initial position of the pollution source; Obtaining a concentration value at an initial position of the pollution source as an initial concentration; Correcting the initial position and initial concentration of the pollution source according to the pollutant diffusion path in the pollution source information to obtain a corrected position and a corrected concentration; The corrected position and the corrected concentration are combined to obtain an initial state vector of the pollution source.

6. The method according to claim 1, wherein The step of performing calculation based on the initial state vector of the pollution source to obtain a candidate pollution source coordinate set includes: According to the initial state vector combined with the Gaussian diffusion model, the updated state vector is obtained. The specific formula is: in, represents the state transition matrix, represents process noise; According to the updated state vector, a prediction is performed to obtain a priori estimated state vector. The specific formula is: in, represents the state vector estimated a priori, is the location coordinate of the pollution source, is the pollutant concentration, Indicates wind speed correction; Mapping the a priori estimated state vector to obtain an observation vector; Based on the observation vector, the state estimation value is obtained through the Kalman gain matrix, and the Kalman gain matrix is expressed as: in, is the observation vector, is the observation noise covariance matrix, is the forecast error covariance matrix; The posterior probability is calculated based on the state estimation value. The specific calculation formula is: in, is the posterior probability of the pollution source location, is the estimated value of the state, is a priori probability distribution of pollution source locations, where the priori probability distribution is obtained based on historical environmental data; A candidate pollution source coordinate set is generated according to the posterior probability.

7. The method according to claim 1, wherein The step of selecting the candidate pollution source coordinate set by maximum likelihood estimation to obtain the target pollution source location includes: Calculating based on the candidate pollution source coordinate set to obtain likelihood values corresponding to multiple pollution source coordinates; Compare the multiple likelihood values to obtain the pollution source coordinates corresponding to the preset likelihood value. The specific calculation formula is: in, Preset distance for sensor spacing, are the coordinates of the target pollution source, are the candidate pollution source coordinates, is the number of sensors; The target pollution source position is obtained by performing conversion according to the pollution source coordinates.

8. A pollution source positioning device based on multi-source data fusion, characterized in that: The device comprises: Acquisition module, used to obtain environmental data and meteorological data; a processing module, configured to process the environmental data through adaptive filtering to obtain filtered environmental data; and further configured to perform time synchronization processing on the meteorological data to obtain synchronized meteorological data; a fusion module, configured to obtain pollution source information by processing the filtered environmental data and the synchronized meteorological data; a calculation module, configured to calculate based on the pollution source information to obtain an initial state vector of the pollution source; and further configured to calculate based on the initial state vector of the pollution source to obtain a set of candidate pollution source coordinates; The result module is used to select the candidate pollution source coordinate set through maximum likelihood estimation to obtain the target pollution source location.

9. A pollution source positioning device based on multi-source data fusion, characterized in that: The device includes: a memory, a processor, and a pollution source location program based on multi-source data fusion stored in the memory and running on the processor, wherein the pollution source location program based on multi-source data fusion is configured to implement the steps of the pollution source location method based on multi-source data fusion as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a pollution source locating program based on multi-source data fusion. When the pollution source locating program based on multi-source data fusion is executed by the processor, the steps of the pollution source locating method based on multi-source data fusion as described in any one of claims 1 to 7 are implemented.

Images