Air pollution simulation method, system, electronic device, and storage medium

Abstract

The application discloses an air pollution simulation method and system, an electronic device and a storage medium. The method comprises the following steps: obtaining preset pollutant data in a preset simulation area; predicting the first pollutant prediction data by using a particle filtering algorithm according to the preset pollutant data; predicting the second pollutant prediction data by using a Kalman filtering algorithm according to the preset pollutant data; and fusing and calculating the first pollutant prediction data and the second pollutant prediction data to obtain the pollutant simulation result. The embodiment of the application can effectively improve the accuracy and stability of air pollution simulation. The application can be widely applied in the technical field of environmental monitoring.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of environmental monitoring, and particularly relates to an air pollution simulation method and system, an electronic device and a storage medium. BACKGROUND

[0002] The air pollution simulation technology is a technology aiming to simulate the diffusion, transformation and deposition process of pollutants in the atmosphere to evaluate the air pollution situation. In the related technology, under the complex and changeable pollution source and diffusion mode, the accuracy of the air pollution simulation result is low, the simulation result deviates from the actual situation, and the stability of the simulation algorithm is poor.

[0003] To sum up, the technical problems in the related technology need to be improved. SUMMARY

[0004] The main purpose of the embodiments of the present application is to provide an air pollution simulation method, system, electronic device and storage medium, which can effectively improve the accuracy and stability of air pollution simulation.

[0005] To achieve the above-mentioned purpose, one aspect of the embodiments of the present application provides an air pollution simulation method, which comprises the following steps:

[0006] Obtaining preset pollutant data in a preset simulation area;

[0007] According to the preset pollutant data, a particle filtering algorithm is used for prediction to obtain first pollutant prediction data;

[0008] According to the preset pollutant data, a Kalman filtering algorithm is used for prediction to obtain second pollutant prediction data;

[0009] The first pollutant prediction data and the second pollutant prediction data are fused and calculated to obtain a pollutant simulation result.

[0010] In some embodiments, the obtaining of the preset pollutant data in the preset simulation area comprises:

[0011] The pollutant concentration data in the preset simulation area is dynamically collected by a preset pollutant sensor;

[0012] The pollutant concentration data is preprocessed to obtain the preset pollutant data.

[0013] In some embodiments, the preprocessing of the pollutant concentration data to obtain the preset pollutant data comprises:

[0014] The pollutant concentration data is denoised by a wavelet transform algorithm to obtain denoised data;

[0015] normalizing the denoised data to obtain preset pollutant data.

[0016] In some embodiments, the first pollutant prediction data is obtained by performing particle filtering on the preset pollutant data, including:

[0017] The motion of the pollutant is simulated by a Monte Carlo algorithm to obtain pollutant position data.

[0018] The pollutant weight data is calculated according to the pollutant position data and the preset pollutant data.

[0019] The first pollutant prediction data is calculated according to the pollutant weight data, wherein the first pollutant prediction data includes first position prediction data.

[0020] In some embodiments, the second pollutant prediction data is obtained by performing Kalman filtering on the preset pollutant data, including:

[0021] The prediction state data is calculated according to the historical position prediction data by a preset Kalman prediction formula, wherein the historical position prediction data includes pollutant position estimation data at the end of the previous time step.

[0022] The prediction error covariance is calculated according to the historical error covariance, wherein the historical error covariance includes error covariance at the previous time.

[0023] The Kalman gain data is calculated according to the prediction error covariance and an observation matrix.

[0024] The second pollutant prediction data is calculated according to the Kalman gain data, the prediction state data and the preset pollutant data, wherein the second pollutant prediction data includes second position prediction data.

[0025] In some embodiments, the pollutant simulation result is obtained by fusing the first pollutant prediction data and the second pollutant prediction data, including:

[0026] The pollutant simulation result is obtained by fusing the first pollutant prediction data and the second pollutant prediction data by a weighted fusion algorithm, wherein the pollutant simulation result includes pollutant prediction position data.

[0027] In some embodiments, before the pollutant simulation result is obtained by fusing the first pollutant prediction data and the second pollutant prediction data by a weighted fusion algorithm, the method further includes:

[0028] constructing a preset pollutant dataset;

[0029] determining a weight coefficient according to the preset pollutant dataset through a cross-validation algorithm.

[0030] To achieve the above object, another aspect of the embodiments of the present application provides an air pollution simulation system, which comprises:

[0031] A first module is configured to acquire preset pollutant data in a preset simulation area.

[0032] A second module is configured to predict according to the preset pollutant data through a particle filtering algorithm to obtain first pollutant prediction data.

[0033] A third module is configured to predict according to the preset pollutant data through a Kalman filtering algorithm to obtain second pollutant prediction data.

[0034] A fourth module is configured to perform fusion calculation on the first pollutant prediction data and the second pollutant prediction data to obtain a pollutant simulation result.

[0035] To achieve the above object, another aspect of the embodiments of the present application provides an electronic device, which comprises:

[0036] at least one processor;

[0037] at least one memory configured to store at least one program;

[0038] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0039] To achieve the above object, another aspect of the embodiments of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the above method.

[0040] The embodiments of the present application at least have the following beneficial effects: the present application provides an air pollution simulation method, system, electronic device and storage medium, which firstly obtains preset pollutant data in a preset simulation area. Then, the present application embodiment predicts the first pollutant prediction data according to the preset pollutant data through the particle filtering algorithm. At the same time, the present application embodiment predicts the second pollutant prediction data according to the preset pollutant data through the Kalman filtering algorithm. Finally, the present application embodiment fuses and calculates the first pollutant prediction data and the second pollutant prediction data to obtain the pollutant simulation result, and realizes the air pollution simulation. It is easy to understand that the present application embodiment can effectively improve the accuracy and stability of the air pollution simulation by combining the particle filtering algorithm and the Kalman filtering algorithm to process the preset pollutant data, and realizes stable and accurate air pollution simulation. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 is a step flow diagram of the air pollution simulation method provided by the embodiments of the present application;

[0042] Figure 2 is a system architecture diagram of the air pollution simulation provided by the embodiments of the present application;

[0043] Figure 3 is a whole work flow diagram of the air pollution simulation provided by the embodiments of the present application;

[0044] Figure 4 is a structure diagram of the air pollution simulation system provided by the embodiments of the present application;

[0045] Figure 5 is a hardware structure diagram of the electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical scheme and advantages of the present application clearer, the following will further describe the present application in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application. When the following description relates to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementation described in the following exemplary embodiments does not represent all the implementations consistent with the embodiments of the present application, but is only an example of devices and methods consistent with some aspects of the embodiments of the present application as described in the appended claims.

[0047] It can be understood that the terms "first", "second", and the like used in the present application can be used herein to describe various concepts, but unless specifically stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of the present application, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as the first information. Depending on the context, the word "if" as used herein can be interpreted as "when" or "upon determining" or "in response to determining".

[0048] The terms "at least one", "multiple", "each", "any" and the like used in the present application include one, two or more than two, multiple includes two or more than two, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one skilled in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0050] Before the embodiments of the present application are described in detail, first, some nouns and terms involved in the embodiments of the present application are described, and the nouns and terms involved in the embodiments of the present application are applicable to the following explanations.

[0051] Small-scale air pollution simulation: refers to the simulation of the diffusion, transformation and deposition of pollutant substances in a small-scale space (such as a city block, an industrial area, etc.).

[0052] Particle filter (PF) algorithm: an algorithm for estimating the state of a nonlinear, non-Gaussian dynamic system from a series of observation data containing noise.

[0053] Kalman filter (KF) algorithm: a linear minimum variance estimator for estimating a linear random process or system in the presence of noise.

[0054] Air pollution simulation technology is a technology aimed at simulating the diffusion, transformation and deposition of pollutants in the atmosphere to evaluate the air pollution situation. In related technologies, under the complex and variable pollution sources and diffusion modes, the accuracy of the air pollution simulation results is low, there is a problem that the simulation results deviate from the actual situation, and the stability of the simulation algorithm is poor.

[0055] Exemplarily, for example, small-scale air pollution simulation technology is one of the core technologies in the field of environmental monitoring and pollution control. At present, this technology mainly relies on data collection of air quality monitoring stations and air pollutants are simulated and predicted through a single filtering algorithm. These monitoring stations can monitor the concentration of various pollutants in the air in real time, such as PM2.5, PM10, sulfur dioxide, nitrogen dioxide, etc. However, in the face of complex and variable pollution sources and diffusion patterns, the related air pollution simulation method often cannot provide high-precision simulation results. For example, in the urban microenvironment, due to the complex layout of buildings, roads and human flow, the diffusion and transmission of air pollutants show strong nonlinear characteristics, which makes it difficult to directly apply traditional linear Gaussian simulation systems such as Kalman filtering. Among them, in the complex and variable pollution sources and diffusion patterns, traditional filtering methods such as extended Kalman filter and unscented Kalman filter need to linearize the system locally, which leads to a decrease in approximation accuracy under strong nonlinear conditions, thereby affecting the accuracy of the simulation results. In addition, when the nonlinearity of pollution sources and diffusion patterns increases, it will lead to filtering inconsistency problem, that is, the estimated error covariance does not match the true simulation error, and there is a possibility that the simulation results deviate from the actual situation. At the same time, the related simulation algorithm is easily affected by abnormal data and environmental changes. In actual application, due to the failure of monitoring equipment, delay or error of data transmission and other problems, abnormal values may occur in the monitoring data, which will seriously affect the stability of the air pollution simulation system. In addition, a single filter is difficult to adapt to the rapidly changing small-scale air pollution environment, especially when the pollution source intensity or diffusion condition changes significantly, the performance of the single filter will decrease significantly.

[0056] Therefore, in the embodiments of the present application, an air pollution simulation method, system, electronic device and storage medium are provided. First, preset pollutant data in a preset simulation area is obtained. Then, according to the preset pollutant data, first pollutant prediction data is obtained by a particle filtering algorithm. At the same time, according to the preset pollutant data, second pollutant prediction data is obtained by a Kalman filtering algorithm. Finally, the first pollutant prediction data and the second pollutant prediction data are fused and calculated to obtain a pollutant simulation result, so as to realize air pollution simulation and effectively improve the accuracy and stability of air pollution simulation.

[0057] The air pollution simulation method provided by the embodiments of the present application relates to the technical field of environmental monitoring. The air pollution simulation method provided by the embodiments of the present application can be applied to a terminal, can be applied to a server, and can also be software running in the terminal or the server. In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, a vehicle-mounted terminal, and the like, but is not limited thereto; the server end can be configured as a stand-alone physical server, can be configured as a server cluster or a distributed system formed by multiple physical servers, can be configured as a cloud server providing basic cloud computing services such as cloud service, cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN, and big data and artificial intelligence platform, and the server can also be a node server in a blockchain network; and the software can be an application for implementing the air pollution simulation method, and the like, but is not limited to the above forms.

[0058] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in a distributed computing environment in which tasks are performed by remote processing devices connected by a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0059] Figure 1 is an optional flowchart of the air pollution simulation method provided by the embodiments of the present application, Figure 1 The method in the flowchart can include, but is not limited to, steps S110 to S140.

[0060] Step S110: Obtain preset pollutant data in a preset simulation area.

[0061] Step S120: According to the preset pollutant data, a particle filtering algorithm is used for prediction to obtain first pollutant prediction data.

[0062] Step S130: According to the preset pollutant data, a Kalman filtering algorithm is used for prediction to obtain second pollutant prediction data.

[0063] Step S140: fusing the first pollutant prediction data and the second pollutant prediction data to obtain a pollutant simulation result.

[0064] In the working process of the embodiment, the preset pollutant data in the preset simulation region is first acquired. Specifically, the preset simulation region in the embodiment refers to a region that needs to be simulated, such as a relevant street region, an industrial park, etc. Correspondingly, the preset pollutant data in the embodiment refers to pollutant-related data that needs to be simulated, such as pollutant information, pollution source data, and meteorological condition data, etc. The embodiment first collects the preset pollutant data in the relevant region (the preset simulation region) to facilitate subsequent air pollution simulation prediction. Then, the embodiment predicts the first pollutant prediction data according to the preset pollutant data by using the particle filter algorithm. Specifically, the embodiment processes the preset pollutant data by using the particle filter algorithm to estimate the position information and the motion trajectory of the pollutant, so as to predict the first pollutant prediction data by using the nonlinear processing capability of the particle filter, to alleviate the problem of reduced approximation accuracy under strong nonlinear conditions, to affect the accuracy of the simulation result, and to alleviate the problem of filter inconsistency. Meanwhile, the embodiment predicts the second pollutant prediction data according to the preset pollutant data by using the Kalman filter algorithm. Specifically, the embodiment processes the preset pollutant data by using the Kalman filter algorithm to smooth the motion state of the pollutant, to improve the stability of the air pollution simulation. Finally, the embodiment fuses the first pollutant prediction data and the second pollutant prediction data to obtain the pollutant simulation result. Specifically, the embodiment fuses the first pollutant prediction data and the second pollutant prediction data by combining the results of the particle filter and the Kalman filter, to alleviate the problem that a single filter is difficult to provide a high-precision simulation result when facing complex and variable pollution sources and diffusion modes. Correspondingly, the embodiment effectively improves the accuracy and stability of the air pollution simulation by combining the nonlinear processing capability of the particle filter and the stability of the Kalman filter.

[0065] In some embodiments of the application, acquiring the preset pollutant data in the preset simulation region includes but is not limited to the following steps:

[0066] The pollutant concentration data in the preset simulation region is dynamically collected by using the preset pollutant sensor.

[0067] The pollutant concentration data is preprocessed to obtain the preset pollutant data.

[0068] In the specific embodiment, the embodiment of the present application first collects the pollutant concentration data in the preset simulation area by the preset pollutant sensor, and performs data preprocessing on the pollutant concentration data to obtain the preset pollutant data. Specifically, the preset pollutant sensor in the embodiment of the present application refers to a grid air pollutant concentration sensor deployed in the preset simulation area. For example, in the preset simulation area, the east-west and north-south intervals of each grid center are 100 meters, and the embodiment of the present application collects the pollutant concentration data in the area in real time by the deployed grid air pollutant concentration sensor, including PM2.5, PM10, sulfur dioxide, nitrogen dioxide and other parameters. Then, in order to facilitate subsequent data processing and improve the accuracy of air pollution simulation, the embodiment of the present application performs data preprocessing on the collected pollutant concentration data, such as noise filtering, outlier processing, etc.

[0069] In some embodiments of the present application, the data preprocessing of the pollutant concentration data to obtain the preset pollutant data includes but is not limited to the following steps:

[0070] The pollutant concentration data is denoised by the wavelet transform algorithm to obtain denoised data.

[0071] The denoised data is normalized to obtain the preset pollutant data.

[0072] In the specific embodiment, the embodiment of the present application first denoises the pollutant concentration data by the wavelet transform algorithm to obtain denoised data, and then normalizes the denoised data to obtain the preset pollutant data. Specifically, the data preprocessing of the pollutant concentration data in the embodiment of the present application includes denoising and normalization. Among them, the embodiment of the present application removes high-frequency noise in the pollutant concentration data by the wavelet transform algorithm to obtain denoised data. Correspondingly, the wavelet transform algorithm in the embodiment of the present application is a signal processing algorithm that decomposes signals by stretching and shifting operations using wavelet functions. Then, in order to facilitate subsequent data processing, the embodiment of the present application normalizes the denoised data after removing high-frequency noise to scale the data to the range of [0, 1], thereby eliminating the order of magnitude difference between different features and improving the accuracy of subsequent processing.

[0073] In some embodiments of the present application, the first pollutant prediction data is obtained by predicting the preset pollutant data by the particle filter algorithm, including but not limited to the following steps:

[0074] The pollutant position data is predicted by simulating the movement of the pollutant by the Monte Carlo algorithm.

[0075] The pollutant weight data is calculated according to the pollutant position data and the preset pollutant data.

[0076] The first pollutant prediction data is calculated by the pollutant weight data. The first pollutant prediction data includes first position prediction data.

[0077] In the embodiment, the pollutant position data is predicted by simulating the motion of the pollutant by the Monte Carlo algorithm, and the pollutant weight data is calculated according to the pollutant position data and preset pollutant data, and then the first pollutant prediction data is calculated by the pollutant weight data. Specifically, the embodiment initializes a plurality of particles, for example, 1000 particles. In the embodiment, each particle represents a possible position and velocity of the pollutant. Accordingly, the motion of the pollutant is simulated by the Monte Carlo algorithm to handle non-linear and non-Gaussian noise. In the embodiment, the particle weight update formula is shown in the following formula (1):

[0078]

[0079] In the formula, w i is the weight of the i-th particle, N is the total number of particles, x i is the particle position, z is the observation value, and σ is the standard deviation.

[0080] Accordingly, the first pollutant prediction data in the embodiment includes first position prediction data, i.e., pollutant position data predicted according to the pollutant weight data. For example, the first position prediction data is calculated by weighted average of the weight data and the corresponding position data of each particle.

[0081] For example, in a 100-meter long gas trajectory, the initial position of the pollutant is x i = 50 meters, and the initial velocity v0 = 0.5 m / s. The initial position and trajectory of the pollutant are estimated by the particle filtering algorithm. The embodiment initializes 1000 particles, and the particle positions are randomly distributed around the initial position, and the velocities are randomly distributed between 0.4 and 0.6 m / s. Then, the motion of 100 time steps is simulated by the Monte Carlo method, and each time step is 1 second. Accordingly, when the pollutant position z = 55 meters is observed at the 50th time step, the standard deviation σ = 1 meter. Accordingly, the weight of each particle is updated according to the observation value, as shown in the following formula (2):

[0082]

[0083] Accordingly, when the position x i of a particle is 55.2 meters, the weight of the particle can be calculated, as shown in the following formula (3):

[0084]

[0085] It is easy to understand that for this particular particle, the weight w i is 0.00098019867, which is the weight relative to other particles. Accordingly, the embodiment of the present application calculates the weight data of each particle to construct the particle weight data, and then performs a weighted average on all particles to obtain the first position prediction data.

[0086] In some embodiments of the present application, the second pollutant prediction data is obtained by predicting the preset pollutant data through a Kalman filtering algorithm, including but not limited to the following steps:

[0087] The prediction state data is calculated according to the historical position prediction data through a preset Kalman prediction formula. The historical position prediction data includes the pollutant position estimation data at the end of the previous time step.

[0088] The prediction error covariance is calculated according to the historical error covariance. The historical error covariance includes the error covariance at the previous time.

[0089] The Kalman gain data is calculated according to the prediction error covariance and the observation matrix.

[0090] The second pollutant prediction data is calculated according to the Kalman gain data, the prediction state data, and the preset pollutant data. The second pollutant prediction data includes the second position prediction data.

[0091] In this specific embodiment, the embodiment of the present application first calculates the prediction state data according to the historical position prediction data through a preset Kalman prediction formula, and calculates the prediction error covariance according to the historical error covariance, to calculate the Kalman gain data according to the prediction error covariance and the observation matrix, and then calculate the second pollutant prediction data according to the Kalman gain data, the prediction state data, and the preset pollutant data. Specifically, the second position prediction data in the embodiment of the present application refers to the pollutant position data predicted by the Kalman filtering algorithm. Before smoothing the motion state of the pollutant through the Kalman filtering algorithm, the embodiment of the present application sets the state transition matrix A and the observation matrix H, as well as the process noise covariance Q and the observation noise covariance R. In the embodiment of the present application, the prediction and update steps are used to improve the stability of the estimation. Accordingly, the prediction and update formula of the Kalman filter in the embodiment of the present application is shown in the following formula (4):

[0092]

[0093] In the formula, the prediction state P is the prediction state, P k|k-1is the prediction error covariance, K k is the Kalman gain, z k is the observation value, I is the identity matrix, denotes the updated pollutant state, P k|k denotes the updated error covariance.

[0094] Exemplarily, in the embodiment of the present application, the state transition matrix A is set to 1 (indicating that the pollutant position changes linearly over time), the observation matrix H is set to 1 (indicating that the observation value is the same as the pollutant position), the process noise covariance Q is set to 0.1 (indicating the uncertainty of the position change), and the observation noise covariance R is set to 1 (indicating the uncertainty of the observation value). Accordingly, starting from the first time step, the embodiment of the present application predicts and updates the pollutant position at each time step. Wherein, if the pollutant position z = 55 meters is observed at the 50th time step, the embodiment of the present application calculates the predicted state, the prediction error covariance, the Kalman gain, the updated state and the updated error covariance according to the prediction and update formulas of the Kalman filter.

[0095] Wherein, the embodiment of the present application first calculates the predicted state data according to the prediction formula of the Kalman filter based on the historical position prediction data. Accordingly, the historical position data in the embodiment of the present application includes the pollutant position estimation data at the end of the previous time step. For example, at the end of the 49th time step, the pollutant position estimation is obtained as And at the beginning of the 50th time step, the embodiment of the present application predicts the state at the current time as That is, when there is no new observation data, the embodiment of the present application assumes that the position of the pollutant remains unchanged.

[0096] Then, the embodiment of the present application calculates the prediction error covariance by the historical error covariance, i.e. the error covariance at the previous time, which represents the uncertainty of the predicted state, as shown in the following formula (5):

[0097] P 50|49 = P 49|49 + Q (5)

[0098] Wherein, in the formula, P 49|49 is the error covariance at the previous time, and Q is the process noise covariance, which reflects the estimation of the random disturbance that may occur in the movement process of the pollutant.

[0099] Accordingly, the embodiment of the present application calculates the Kalman gain according to the prediction error covariance and the observation noise covariance (R), which is used to determine the degree of contribution of the observation data to the updated state, as shown in the following formula (6):

[0100] K 50 = P 50|49 H T(HP 50|49 H T +R) -1 (6)

[0101] where H is an identity matrix, indicating that the direct observation is the position of the pollutant.

[0102] Then, after obtaining the new observation data z 50 = 55 meters, the embodiment of the present application uses the Kalman gain to update the position estimation of the pollutant, as shown in the following formula (7):

[0103]

[0104] where the embodiment of the present application integrates the observation data into the predicted state, so as to obtain a more accurate position estimation of the pollutant. Then, the embodiment of the present application updates the error covariance to reduce the uncertainty of the updated state, thereby improving the accuracy of the estimation, as shown in the following formula (8):

[0105] P 50|50 = (I-H 50 H)P 50|49 (8)

[0106] It is easy to understand that the embodiment of the present application completes the prediction and update of the position of the pollutant at the 50th time step through the above steps. Wherein, if the position estimation of the pollutant obtained by the embodiment of the present application at the end of the 49th time step is meters, the process noise covariance Q = 1 meter 2 , and the observation noise covariance R = 2 meters 2 , the predicted state, the predicted error covariance, the Kalman gain, the updated state and the updated error covariance at the 50th time step can be calculated. For example, the predicted state meters is calculated in the embodiment of the present application. In addition, the predicted error covariance is P 50|49 = P 49|49 + Q = (an assumed error covariance value, such as 1 meter 2 ) + 1 meter 2 = 2 meters 2 . Accordingly, the Kalman gain is K 50 = P 50|49 H T (HP 50|49 H T +R) -1 = 2 x 1 / (1 x 2 + 2) = 2 / 4 = 0.5. At the same time, the updated state is meters, and the updated error covariance is P 50|50 = (I-K 50 H)P 50|49 = (1-0.5 x 1) x 2 = 1 meter2 wherein H is an identity matrix.

[0107] In some embodiments of the present application, the first pollutant prediction data and the second pollutant prediction data are fused to obtain the pollutant simulation result, including but not limited to the following steps:

[0108] The first pollutant prediction data and the second pollutant prediction data are fused by a weighted fusion algorithm to obtain the pollutant simulation result. The pollutant simulation result includes pollutant prediction position data.

[0109] In the specific embodiment, the first pollutant prediction data and the second pollutant prediction data are fused by a weighted fusion algorithm to obtain the pollutant simulation result. Specifically, the pollutant simulation result includes pollutant prediction position data, i.e., the prediction position information of the related pollutant. Accordingly, the results of the particle filter and the Kalman filter, i.e., the first pollutant prediction data and the second pollutant prediction data, are combined by a weighted fusion method to improve the tracking accuracy and robustness. For example, the weighted fusion formula in the present embodiment is shown in the following formula (9):

[0110]

[0111] wherein is the fused position estimate, is the position estimate of the particle filter, is the position estimate of the Kalman filter, and α represents the weight of the particle filter result (the first pollutant prediction data), and β represents the weight of the Kalman filter result (the second pollutant prediction data).

[0112] For example, in the present embodiment, the weight coefficients α and β are set to 0.6 and 0.4, respectively. If the position estimate of the particle filter is 53 meters and the position estimate of the Kalman filter is 54 meters at the 50th time step, the final position is calculated according to the fusion formula as follows: meters.

[0113] In some embodiments of the present application, before performing the fusion calculation according to the first pollutant prediction data and the second pollutant prediction data by the weighted fusion algorithm to obtain the pollutant simulation result, the air pollution simulation method provided by the present embodiment further includes but is not limited to the following steps:

[0114] A preset pollutant data set is constructed.

[0115] The weight coefficients are determined by a cross-validation algorithm according to the preset pollutant data set.

[0116] Specifically, the embodiment of the present application first constructs a preset pollutant data set, and determines the weight coefficients according to the preset pollutant data through a cross-validation algorithm. Specifically, the embodiment of the present application determines the weight data (weight coefficients) of the weighted fusion algorithm, such as the weight a of the first pollutant prediction data and the weight β of the second pollutant prediction data, through a cross-validation algorithm according to the characteristics of the actual tracking environment and the related pollutants. Accordingly, the embodiment of the present application first acquires the related data of the pollutants, such as the diffusion data, the historical position data, the motion speed, etc. of the pollutants, and constructs a preset pollutant data set. Then, the embodiment of the present application divides the preset pollutant data set into a training set and a test set, and uses the training set to evaluate different weight combinations to select the weight combination with the minimum tracking error, and then verifies it through the test set. For example, after cross-validation, it is determined that when a = 0.6 and β = 0.4, the tracking error is the smallest, and then the weight coefficients are determined as a = 0.6 and β = 0.4.

[0117] It should be noted that the embodiment of the present application outputs the fused tracking result (pollutant simulation result) for guiding the pollutant treatment and environmental management. Among them, the output result in the embodiment of the present application includes the estimated position, the motion speed and the direction of the pollutant. For example, the embodiment of the present application predicts that at the 50th time step, the estimated position of the pollutant is 53.4 meters, the motion speed is 0.5 meters / second (the same as the initial speed), and the direction is downstream of the wind direction.

[0118] Next, in combination with a specific air pollution simulation scene, the scheme of the embodiment of the present application is described in detail:

[0119] Exemplarily, in the small-scale air pollution simulation application scene, the air pollution simulation accuracy is low, there is a possibility that the simulation result deviates from the actual situation, and the stability of the simulation algorithm is poor. Accordingly, the embodiment of the present application simulates small-scale air pollutants by fusing particle filtering and Kalman filtering, to combine the nonlinear processing capability of particle filtering and the stability of Kalman filtering, and at the same time, to improve the tracking accuracy and robustness through a weighted fusion algorithm, effectively alleviating the problems of low air pollution simulation accuracy and poor stability. Specifically, as shown in Figure 2 The system module in the embodiment of the present application includes an air pollutant sensor network, a data preprocessing unit, a particle filtering algorithm module, a Kalman filtering algorithm module, a weighted fusion unit, and a tracking result output module. At the same time, referring to Figure 3The embodiment of the present application firstly deploys an air pollutant sensor network to collect pollutant concentration data in a simulated area in real time. Then, the embodiment of the present application performs denoising processing on the collected original data through a data preprocessing unit. Next, the embodiment of the present application estimates the initial position and motion trajectory of the pollutant through a particle filtering algorithm module to obtain first pollutant prediction data. Meanwhile, the embodiment of the present application performs smoothing processing on the motion state of the pollutant through a Kalman filtering algorithm module to obtain second pollutant prediction data. Further, the embodiment of the present application performs weighted fusion of the results of the particle filtering and the Kalman filtering through a weighted fusion unit to obtain a pollutant simulation result. The weight coefficient is determined through a cross-validation algorithm. Correspondingly, the embodiment of the present application outputs the fused tracking result to guide pollutant treatment and small-scale environmental management.

[0120] It is easy to understand that the embodiment of the present application significantly improves the accuracy and robustness of small-scale atmospheric pollutant tracking through the fusion of particle filtering and Kalman filtering. In a nonlinear and non-Gaussian noise environment, the traditional filtering method needs to be locally linearized, which reduces the approximation accuracy under strong nonlinear conditions, thereby affecting the tracking accuracy. The embodiment of the present application processes nonlinear and non-Gaussian noise through a particle filtering algorithm, simulates the motion of the pollutant through a Monte Carlo method, and effectively improves the tracking accuracy. At the same time, the motion state of the pollutant is smoothed through a Kalman filtering algorithm, which improves the stability of the estimation. Correspondingly, the embodiment of the present application combines the results of the particle filtering algorithm and the Kalman filtering algorithm through a weighted fusion method, further improving the tracking accuracy and robustness. The application of the embodiment of the present application can reduce the occurrence of atmospheric pollution events in small-scale areas such as industrial parks and blocks, reduce the risk of environmental pollution, and has important social and economic value. At the same time, by using big data technology, combining historical monitoring data and real-time data, a comprehensive database can be established to facilitate long-term trend analysis and evaluation. This way not only reveals the change law of the atmospheric environment system, but also provides support for the decision-making process. By establishing a mathematical model to simulate the dynamic changes of the small-scale atmospheric environment system in the region, the future development trend is predicted, the efficiency and effectiveness of atmospheric environment management are improved, and strong technical support is provided for environmental protection and resource management.

[0121] Please refer to Figure 4 The embodiment of the present application also provides an air pollution simulation system, which can implement the above-mentioned air pollution simulation method. The system comprises:

[0122] The first module 210 is configured to obtain preset pollutant data in a preset simulation area.

[0123] The second module 220 is configured to predict the first pollutant prediction data according to the preset pollutant data by using a particle filter algorithm.

[0124] The third module 230 is configured to predict the second pollutant prediction data according to the preset pollutant data by using a Kalman filter algorithm.

[0125] The fourth module 240 is configured to fuse and calculate the first pollutant prediction data and the second pollutant prediction data to obtain the pollutant simulation result.

[0126] It can be understood that the content in the above method embodiments is applicable to the present system embodiment, the present system embodiment specifically implements the same functions as the above method embodiments, and achieves the same beneficial effects as the above method embodiments.

[0127] The present application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor implements the above air pollution simulation method when executing the computer program. The electronic device can be any intelligent terminal, such as a tablet computer or a vehicle-mounted computer.

[0128] It can be understood that the content in the above method embodiments is applicable to the present device embodiment, the present device embodiment specifically implements the same functions as the above method embodiments, and achieves the same beneficial effects as the above method embodiments.

[0129] Please refer to Figure 5 , Figure 5 The present application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor implements the above air pollution simulation method when executing the computer program. The electronic device can be any intelligent terminal, such as a tablet computer or a vehicle-mounted computer.

[0130] The processor 310 can be implemented in a general-purpose CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, and is used to execute related programs to implement the technical solutions provided by the present application.

[0131] The memory 320 can be implemented in the form of a read only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), etc. The memory 320 can store an operating system and other application programs. When the technical solutions provided by the embodiments of the present specification are implemented by software or firmware, the related program codes are stored in the memory 320 and are called and executed by the processor 310 to perform the air pollution simulation method of the embodiments of the present application.

[0132] The input / output interface 330 is configured to realize information input and output.

[0133] The communication interface 340 is configured to realize the communication interaction between the device and other devices. The communication can be realized by a wired manner (for example, a USB, a network cable, etc.) or a wireless manner (for example, a mobile network, WIFI, Bluetooth, etc.).

[0134] The bus 350 is configured to transmit information between various components (for example, the processor 310, the memory 320, the input / output interface 330, and the communication interface 340) of the device.

[0135] The processor 310, the memory 320, the input / output interface 330, and the communication interface 340 are connected to each other through the bus 350 to realize the communication connection between the device.

[0136] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the air pollution simulation method described above.

[0137] It can be understood that the contents in the above method embodiments are applicable to the present storage medium embodiments. The functions implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved by the present storage medium embodiments are also the same as those of the above method embodiments.

[0138] The memory is a non-transitory computer readable storage medium, which can be used to store non-transitory software programs and non-transitory computer executable programs. In addition, the memory can include a high-speed random access memory and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory remotely arranged relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0139] The embodiments described in the present application are to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0140] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and can include more or fewer steps than those shown in the figures, or combine certain steps, or different steps.

[0141] The device embodiments described above are only schematic, and the units described as separate components can or can not be physically separate, that is, can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0142] Those skilled in the art can understand that all or some of the steps in the above disclosed method, the function modules / units in the system and the device can be implemented as software, firmware, hardware and their appropriate combinations.

[0143] The terms "first", "second", "third", "fourth" and the like (if any) in the specification of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0144] It should be understood that, in the application, "at least one" refers to one or more, and "multiple" refers to two or more. "And / or" is used to describe the association relationship of the associated objects, which means that there can be three relationships, for example, "A and / or B" can represent three cases of only A, only B, and A and B existing at the same time, wherein A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after it. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c can represent a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, and c can be single or multiple.

[0145] In several embodiments provided in the application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the above units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed mutual ones can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0146] The units described above as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0147] In addition, each functional unit in each embodiment of the application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0148] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes multiple instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program storage media.

[0149] The preferred embodiments of the embodiments of the present application are described above with reference to the accompanying drawings, and are not limited to the scope of the embodiments of the present application. Any modifications, equivalent replacements and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of the embodiments of the present application.

Claims

1. An air pollution simulation method, characterized in that, The method includes the following steps: Acquire preset pollutant data within a preset simulation area; Based on the preset pollutant data, a particle filter algorithm is used to predict the first pollutant prediction data. Based on the preset pollutant data, a Kalman filter algorithm is used to predict the second pollutant prediction data. The first pollutant prediction data and the second pollutant prediction data are fused and calculated to obtain the pollutant simulation results; The step of obtaining the first pollutant prediction data by predicting the pollutant data using a particle filter algorithm based on the preset pollutant data includes: The Monte Carlo algorithm is used to simulate the movement of pollutants in order to predict their location data. Pollutant weight data is calculated based on the pollutant location data and the preset pollutant data. The first pollutant prediction data is calculated using the pollutant weight data; wherein, the first pollutant prediction data includes first location prediction data; The step of obtaining second pollutant prediction data by predicting the pollutant data using the Kalman filter algorithm based on the preset pollutant data includes: Predicted state data is calculated based on historical location prediction data using a preset Kalman prediction formula; wherein, the historical location prediction data includes pollutant location estimation data at the end of the previous time step; The prediction error covariance is calculated based on the historical error covariance; wherein, the historical error covariance includes the error covariance of the previous time step. Kalman gain data are calculated based on the prediction error covariance and the observation matrix. The second pollutant prediction data is calculated based on the Kalman gain data, the predicted state data, and the preset pollutant data; wherein, the second pollutant prediction data includes the second location prediction data.

2. The method according to claim 1, characterized in that, The acquisition of preset pollutant data within a preset simulation area includes: Pollutant concentration data within the preset simulation area are dynamically collected using preset pollutant sensors. The pollutant concentration data is preprocessed to obtain the preset pollutant data.

3. The method according to claim 2, characterized in that, The step of preprocessing the pollutant concentration data to obtain the preset pollutant data includes: The pollutant concentration data is denoised using a wavelet transform algorithm to obtain denoised data. The denoised data is normalized to obtain the preset pollutant data.

4. The method according to claim 1, characterized in that, The step of fusing the first pollutant prediction data and the second pollutant prediction data to obtain pollutant simulation results includes: The pollutant simulation results are obtained by fusion calculation using a weighted fusion algorithm based on the first pollutant prediction data and the second pollutant prediction data; wherein, the pollutant simulation results include pollutant prediction location data.

5. The method according to claim 4, characterized in that, Before performing the weighted fusion calculation based on the first pollutant prediction data and the second pollutant prediction data using a weighted fusion algorithm to obtain the pollutant simulation result, the method further includes: Construct a pre-defined pollutant dataset; The weighting coefficients are determined using a cross-validation algorithm based on the preset pollutant dataset.

6. An air pollution simulation system, characterized in that, The system includes: The first module is used to acquire preset pollutant data within a preset simulation area; The second module is used to predict the first pollutant prediction data by using a particle filter algorithm based on the preset pollutant data. The third module is used to predict the second pollutant based on the preset pollutant data using a Kalman filter algorithm. The fourth module is used to fuse and calculate the first pollutant prediction data and the second pollutant prediction data to obtain the pollutant simulation results; The step of obtaining the first pollutant prediction data by predicting the pollutant data using a particle filter algorithm based on the preset pollutant data includes: The Monte Carlo algorithm is used to simulate the movement of pollutants in order to predict their location data. Pollutant weight data is calculated based on the pollutant location data and the preset pollutant data. The first pollutant prediction data is calculated using the pollutant weight data; wherein, the first pollutant prediction data includes first location prediction data; The step of obtaining second pollutant prediction data by predicting the pollutant data using the Kalman filter algorithm based on the preset pollutant data includes: Predicted state data is calculated based on historical location prediction data using a preset Kalman prediction formula; wherein, the historical location prediction data includes pollutant location estimation data at the end of the previous time step; The prediction error covariance is calculated based on the historical error covariance; wherein, the historical error covariance includes the error covariance of the previous time step. Kalman gain data are calculated based on the prediction error covariance and the observation matrix. The second pollutant prediction data is calculated based on the Kalman gain data, the predicted state data, and the preset pollutant data; wherein, the second pollutant prediction data includes the second location prediction data.

7. An electronic device, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method as described in any one of claims 1-5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 5.

Images