Single particle source intelligent analysis method and device based on scanning electron microscope energy spectrum analysis

Abstract

The invention discloses a single particle source intelligent analysis method and device based on scanning electron microscope energy spectrum analysis, and the method comprises the steps: analyzing a collected sample of a set pollution source through a scanning electron microscope controlled by a computer, obtaining an image, element data and particle size parameters of single particles in the sample of the pollution source, and constructing a pollution source single particle data set; mining the morphological characteristics of the single particle image through a residual network model, and obtaining a preliminary probability value of the single particle belonging to a set pollution source; combining the initial probability value of the single particle with the particle size parameter and the element data, and inputting into an extreme gradient lifting model to obtain a probability value of the single particle belonging to the set pollution source; and weighting the probability values of the single particles according to the mass or quantity of the single particles, and performing summation calculation processing according to source classes to obtain the mass or quantity contribution / proportion of the atmospheric particulates discharged by the set pollution source. The method can fully excavate the morphology, particle size and component characteristics of the particulate matters, identify the source of the particulate matters and quantify the contribution of different pollution sources.

Description

Technical Field

[0001] The present invention relates to the technical field of atmospheric particulate matter source analysis, and in particular to a single particle source intelligent analysis method and device based on scanning electron microscope energy spectrum analysis. Background Art

[0002] Atmospheric particulate matter pollution has a significant impact on climate, ecosystems and human health, and has attracted widespread attention from all walks of life in recent years. Particulate matter source analysis is an important tool for formulating particulate matter pollution reduction policies.

[0003] Although there are many source attribution methods now, most of them are based on the chemical composition of the whole sample, and there are still problems such as high uncertainty in the source attribution results and low level of refinement in source category identification. In order to further improve the accuracy and refinement of atmospheric particulate matter source attribution results and better serve the national atmospheric environment management needs, it is urgent to mine more particulate matter information and develop new source attribution methods. Electron microscopy analysis shows that particulate matter emitted from different pollution sources differs in morphology, particle size and composition, which provides valuable information for further accurate identification of the source of particulate matter. The development of computer-controlled scanning electron microscopes has enabled the rapid analysis of large amounts of particulate matter (several thousand particles / hour), but there is currently no source attribution method that can obtain quantitative source attribution results based on a large amount of single particle morphology, particle size and composition information.

[0004] Therefore, how to invent a source analysis method that can obtain quantitative source analysis results based on a large amount of single particle morphology, particle size and composition information has become an urgent problem to be solved. Summary of the invention

[0005] To this end, the present invention provides a single particle source intelligent analysis method and device based on scanning electron microscope energy spectrum analysis. This method can fully explore the morphology, particle size and composition characteristics of particulate matter, identify the source of particulate matter and quantify the contribution of different pollution sources. At the same time, it has more obvious advantages in identifying and quantifying collinear source classes.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a single particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis, comprising:

[0007] By using a computer-controlled scanning electron microscope to analyze the collected samples of the set pollution source, images, elemental data and particle size parameters of single particles in the samples of the set pollution source are obtained, and a single particle data set of the pollution source samples is constructed;

[0008] Extracting the image features of the single particle through a residual network model, and preliminarily predicting the source of the single particle based on the image features of the single particle, to obtain a preliminary probability value that the single particle belongs to a set pollution source;

[0009] The preliminary probability value that the single particle belongs to the set pollution source is combined with the particle size parameters and element data of the single particle, and the results are input into the extreme gradient boosting model. The probability value that the single particle belongs to the set pollution source is obtained through prediction by the extreme gradient boosting model.

[0010] The probability value of the single particle belonging to the set pollution source is weighted and summed up by source category according to the mass or quantity of the single particle to obtain the mass or quantity contribution / proportion of the atmospheric particulate matter emitted by the set pollution source.

[0011] As a preferred scheme of the single particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis, in the process of analyzing the collected samples of the set pollution sources by applying a computer-controlled scanning electron microscope, the set pollution sources include: soil dust, road dust, construction dust, coal smoke dust, biomass combustion dust and steel smelting dust.

[0012] As a preferred solution of the single-particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis, in the process of extracting the image features of the single particle through the residual network model, the initial parameters of the residual network model are determined by training with a large ImageNet data set; in the training process of the residual network model, the performance of the residual network model is optimized by the Adam optimizer and the negative log-likelihood loss function.

[0013] As a preferred solution for the single particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis, in the process of predicting through the extreme gradient boosting model to obtain the probability value that the single particle belongs to the set pollution source, the hyperparameters that meet the set requirements are selected through a grid search strategy, and the performance of the extreme gradient boosting model is evaluated using a five-fold cross-validation strategy.

[0014] As a preferred solution of the single particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis, the mass proportion calculation formula of the atmospheric particulate matter emitted by the set pollution source is:

[0015]

[0016] Where M i is the mass contribution of particulate matter emitted by the i-th pollution source; p ij is the initial probability that particle j belongs to pollution source i; m j is the mass of particle j; k is the total number of set pollution sources; n is the total number of particles;

[0017] The calculation formula for the percentage of atmospheric particulate matter emitted by the set pollution source is:

[0018]

[0019] Where N i It is the contribution ratio of particulate matter emitted by the i-th pollution source.

[0020] The present invention also provides a single particle source intelligent analysis device based on scanning electron microscope energy spectrum analysis, which adopts the above-mentioned single particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis, including:

[0021] A single particle data set acquisition module is used to analyze the collected samples of the set pollution source by using a scanning electron microscope controlled by a computer, obtain the image, element data and particle size parameters of the single particles in the samples of the set pollution source, and construct a single particle data set of the pollution source samples;

[0022] A single particle pollution source preliminary prediction module is used to extract the image features of the single particle through a residual network model, and preliminarily predict the source of the single particle based on the image features of the single particle, and obtain a preliminary probability value that the single particle belongs to a set pollution source;

[0023] A single particle pollution source depth prediction module is used to combine the preliminary probability value of the single particle belonging to the set pollution source with the particle size parameters and element data of the single particle, and input them into the extreme gradient boosting model, and obtain the probability value of the single particle belonging to the set pollution source through the extreme gradient boosting model prediction;

[0024] The atmospheric particulate matter proportion data acquisition module is used to weight the probability value of the single particle belonging to the set pollution source by the mass or quantity of the single particle, and perform source-based summation calculation processing to obtain the mass or quantity contribution / proportion of the atmospheric particulate matter emitted by the set pollution source.

[0025] As a preferred solution of the single particle source intelligent analysis device based on scanning electron microscope energy spectrum analysis, in the single particle data set acquisition module, in the process of analyzing the collected samples of the set pollution source by applying a computer-controlled scanning electron microscope, the set pollution source includes: soil dust, road dust, construction dust, coal smoke dust, biomass combustion dust and steel smelting dust.

[0026] As a preferred solution of the single-particle source intelligent analysis device based on scanning electron microscope energy spectrum analysis, in the single-particle pollution source preliminary prediction module, in the process of extracting the image features of the single particle through the residual network model, the initial parameters of the residual network model are determined by training with a large ImageNet data set; during the training process of the residual network model, the performance of the residual network model is optimized by the Adam optimizer and the negative log-likelihood loss function.

[0027] As a preferred solution for the single particle source intelligent analysis device based on scanning electron microscope energy spectrum analysis, in the single particle pollution source depth prediction module, in the process of predicting through the extreme gradient boosting model to obtain the probability value of the single particle belonging to the set pollution source, the hyperparameters that meet the set requirements are selected through a grid search strategy, and the performance of the extreme gradient boosting model is evaluated using a five-fold cross-validation strategy.

[0028] As a preferred solution of the single particle source intelligent analysis device based on scanning electron microscope energy spectrum analysis, in the atmospheric particulate matter proportion data acquisition module, the mass proportion calculation formula of the atmospheric particulate matter emitted by the set pollution source is:

[0029]

[0030] Where M i is the mass contribution of particulate matter emitted by the i-th pollution source; p ij is the initial probability that particle j belongs to pollution source i; m j is the mass of particle j; k is the total number of set pollution sources; n is the total number of particles;

[0031] The calculation formula for the percentage of atmospheric particulate matter emitted by the set pollution source is:

[0032]

[0033] Where N i It is the contribution ratio of particulate matter emitted by the i-th pollution source.

[0034] The present invention has the following advantages: by using a computer-controlled scanning electron microscope to analyze the collected samples of the set pollution source, the image, element data and particle size parameters of the single particles in the samples of the set pollution source are obtained, and the single particle data set of the pollution source sample is constructed; the image features of the single particles are extracted through the residual network model, and the source of the single particles is preliminarily predicted based on the image features of the single particles, and the preliminary probability value of the single particle belonging to the set pollution source is obtained; the preliminary probability value of the single particle belonging to the set pollution source is merged with the particle size parameters and element data of the single particle, and input into the extreme gradient lifting model, and the probability value of the single particle belonging to the set pollution source is obtained through the extreme gradient lifting model prediction; the probability value of the single particle belonging to the set pollution source is weighted by the mass or quantity of the single particle, and the source class is summed and calculated, and the mass or quantity contribution / proportion of the atmospheric particulate matter emitted by the set pollution source is obtained. The present invention can fully explore the morphology, particle size and composition characteristics of particulate matter, identify the source of particulate matter and quantify the contribution of different pollution sources. At the same time, the combination of morphology and particle size characteristics has more obvious advantages in identifying and quantifying collinear source classes (particulate matter emitted by multiple pollution sources has similar chemical composition). BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the drawings required for the implementation methods or the prior art descriptions are briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0036] The structures, proportions, sizes, etc. illustrated in this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with the technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantial technical significance. Any structural modification, change in proportion or adjustment of size shall still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and purposes that can be achieved by the present invention.

[0037] Figure 1 A schematic diagram of a process flow of a single particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis provided in Example 1 of the present invention;

[0038] Figure 2 A schematic diagram of specific implementation steps of the single particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis provided in Example 1 of the present invention;

[0039] Figure 3A schematic diagram of the error between the particle mass and quantity source analysis results and the true values ​​calculated by the method in the single particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis provided in Example 1 of the present invention;

[0040] Figure 4 A schematic diagram of the error of the mass source analysis results of particles in different particle size segments calculated by the single particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis provided in Example 1 of the present invention;

[0041] Figure 5 A schematic diagram of the error in the source analysis results of the number of particles in different particle size segments calculated by the single particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis provided in Example 1 of the present invention;

[0042] Figure 6 A schematic diagram of the architecture of a single particle source intelligent analysis device based on scanning electron microscope energy spectrum analysis provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0043] The following is a description of the implementation of the present invention by specific embodiments. People familiar with the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Example 1

[0045] See also Figure 1 and Figure 2 Embodiment 1 of the present invention provides a single particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis, comprising:

[0046] S1. Analyze the collected samples of the set pollution source by using a computer-controlled scanning electron microscope to obtain images, elemental data and particle size parameters of single particles in the samples of the set pollution source, and construct a single particle data set of the pollution source samples;

[0047] S2. extracting the image features of the single particle through a residual network model, and preliminarily predicting the source of the single particle based on the image features of the single particle, to obtain a preliminary probability value that the single particle belongs to a set pollution source;

[0048] S3, combining the preliminary probability value that the single particle belongs to the set pollution source with the particle size parameters and element data of the single particle, and inputting the results into the extreme gradient boosting model, and obtaining the probability value that the single particle belongs to the set pollution source through prediction by the extreme gradient boosting model;

[0049] S4. The probability value of the single particle belonging to the set pollution source is weighted by the mass or quantity of the single particle, and the summation is calculated by source category to obtain the mass or quantity ratio of the atmospheric particulate matter emitted by the set pollution source.

[0050] In this embodiment, in step S1, in the process of analyzing the collected samples of the set pollution sources by applying a computer-controlled scanning electron microscope, the set pollution sources include: soil dust, road dust, construction dust, coal smoke dust, biomass combustion dust and steel smelting dust.

[0051] Specifically, in this embodiment, six types of pollution source samples were collected, including soil dust, road dust, construction dust, coal smoke, biomass combustion dust, and steel smelting dust. The pollution source samples were analyzed using the scanning electron microscope energy spectrum analysis (SEM-EDS) method to construct a single particle database of typical pollution sources. In particular, computer-controlled scanning electron microscope energy spectrum analysis (CCSEM-EDS) can realize automatic and rapid analysis of particulate matter samples (several thousand particles / hour), and it is recommended to use CCSEM-EDS for sample analysis. At least 10,000 particles are analyzed for each type of source sample, of which at least 2,000 particles are analyzed for each sample.

[0052] In this embodiment, in step S1, a single particle in the single particle data set is analyzed by a scanning electron microscope energy spectrum analysis strategy to obtain an image, elemental data and particle size parameters of the single particle;

[0053] Specifically, the data collected by SEM-EDS includes a microscopic image of the particles, particle size parameters and elemental data. The volume of the particles is calculated based on the particle size parameters, the density is calculated based on the chemical composition, and the mass is the product of the volume and density. All calculations are automatically completed by the CCSEM-EDS system.

[0054] In this embodiment, in step S2, in the process of extracting the image features of the single particle through the residual network model, the initial parameters of the residual network model are determined by training with a large ImageNet dataset; during the training of the residual network model, the performance of the residual network model is optimized by an Adam optimizer and a negative log-likelihood loss function.

[0055] Specifically, data augmentation techniques were applied to enhance the diversity of the dataset. Random rotation, flipping, and scaling of images, as well as random adjustment of image brightness, contrast, saturation, and hue were performed to mitigate the differences in microscopic images of different samples caused by differences in SEM analysis conditions. A ResNet model based on transfer learning was used to extract image features and predict the source of particles based on image features. The initial parameters of the model were trained based on the large ImageNet dataset. During training, the Adam optimizer was used, with the learning rate set to 1e-2, the step size set to 7, the decay rate set to 0.1, and the negative log-likelihood loss function used to optimize model performance. Finally, the probability values ​​of each particle coming from different sources were recorded.

[0056] In this embodiment, in step S3, in the process of predicting through the extreme gradient boosting model to obtain the probability value of the single particle belonging to the set pollution source, the hyperparameters that meet the set requirements are selected through the grid search strategy, and the performance of the extreme gradient boosting model is evaluated by the five-fold cross validation strategy.

[0057] Specifically, the preliminary probability value of the single particle belonging to the set pollution source predicted by the residual network model is combined with the particle size parameters and element data of the single particle as the input of the extreme gradient boosting (XGBoost) model, and the particle source label is the dependent variable. The extreme gradient boosting model training is completed, and the probability of each particle belonging to a different pollution source calculated by the extreme gradient boosting model is output. In the optimization process of the extreme gradient boosting model, grid search is used to select the most appropriate hyperparameters, and five-fold cross validation is used to evaluate the performance of the XGBoost model.

[0058] In this embodiment, in step S4, the probability value of the single particle belonging to the set pollution source is weighted and summed up by source category according to the mass or quantity of the single particle to obtain the mass or quantity contribution / proportion of the atmospheric particulate matter emitted by the set pollution source.

[0059] Specifically, the mass percentage calculation formula of the atmospheric particulate matter emitted by the set pollution source is:

[0060]

[0061] Where M i is the mass contribution of particulate matter emitted by the i-th pollution source; p ij is the initial probability that particle j belongs to pollution source i; m j is the mass of particle j; k is the total number of set pollution sources; n is the total number of particles;

[0062] The calculation formula for the percentage of atmospheric particulate matter emitted by the set pollution source is:

[0063]

[0064] Where N i It is the contribution ratio of particulate matter emitted by the i-th pollution source.

[0065] In this embodiment, the single particle data set obtained in step S1 is also divided into two subsets, and 80% of the single particle data in each type of pollution source are randomly selected as the first data set, which is mainly used for training the model in the present invention; the remaining 20% ​​of the single particle data in each type of pollution source is the second data set, which is used to verify the accuracy of the analysis results of the present invention.

[0066] The analysis results of this method were verified by the second data set. The real source analysis results and the results calculated by the present invention are as follows Figure 3 The calculation results of the present invention are very close to the real source contribution, and the errors of the average source contribution of the mass and number of particulate matter are 0.11% and 0.15% respectively. The error calculation formulas are:

[0067]

[0068]

[0069] In the formula, __M__E_ mass and __M__E_ number are the average errors contributed by the quality and quantity of all pollution sources respectively; M i,true and N i,true are the true mass contribution and quantity contribution of pollution source i respectively; M i and N i are respectively the mass contribution and quantity contribution of pollution source i calculated by the present invention.

[0070] The errors of the mass and quantity source analysis results of particles in different particle size segments calculated by the big data artificial intelligence particle source analysis method are as follows: Figure 4 and Figure 5 The accuracy of the source analysis results of particles in different particle size segments in the present invention has reached a very high level.

[0071] In summary, the present invention analyzes the collected samples of the set pollution source by using a computer-controlled scanning electron microscope to obtain the image, elemental data and particle size parameters of the single particles in the samples of the set pollution source, and construct a single particle data set of the pollution source sample; extract the image features of the single particle through the residual network model, and preliminarily predict the source of the single particle based on the image features of the single particle, and obtain the preliminary probability value that the single particle belongs to the set pollution source; merge the preliminary probability value that the single particle belongs to the set pollution source with the particle size parameters and elemental data of the single particle, and input them into the extreme gradient lifting model, and predict the probability value that the single particle belongs to the set pollution source through the extreme gradient lifting model; weight the probability value that the single particle belongs to the set pollution source obtained by the mass or quantity of the single particle, and perform source-based summation calculation processing to obtain the mass or quantity contribution / proportion of the atmospheric particulate matter emitted by the set pollution source. The present invention can fully explore the morphology, particle size and composition characteristics of particulate matter, identify the source of particulate matter and quantify the contribution of different pollution sources. At the same time, the combination of morphology and particle size characteristics has more obvious advantages in identifying and quantifying collinear source classes (particulate matter emitted by multiple pollution sources has similar chemical composition).

[0072] It should be noted that the method of the embodiment of the present disclosure can be performed by a single device, such as a computer or a server. The method of the present embodiment can also be applied in a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present disclosure, and the multiple devices will interact with each other to complete the described method.

[0073] It should be noted that the above describes some embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0074] Example 2

[0075] See also Figure 6 Embodiment 2 of the present invention provides a single particle source intelligent analysis device based on scanning electron microscope energy spectrum analysis, comprising:

[0076] The single particle data set acquisition module 001 is used to analyze the collected samples of the set pollution source by using a scanning electron microscope controlled by a computer, obtain the image, element data and particle size parameters of the single particles in the samples of the set pollution source, and construct the single particle data set of the pollution source samples;

[0077] The single particle pollution source preliminary prediction module 002 is used to extract the image features of the single particle through the residual network model, and preliminarily predict the source of the single particle according to the image features of the single particle, and obtain a preliminary probability value that the single particle belongs to a set pollution source;

[0078] The single particle pollution source depth prediction module 003 is used to combine the preliminary probability value of the single particle belonging to the set pollution source with the particle size parameters and element data of the single particle, and input them into the extreme gradient boosting model, and obtain the probability value of the single particle belonging to the set pollution source through the extreme gradient boosting model prediction;

[0079] The atmospheric particulate matter proportion data acquisition module 004 is used to weight the probability value of the single particle belonging to the set pollution source by the mass or quantity of the single particle, and perform source-based summation calculation processing to obtain the mass or quantity contribution / proportion of the atmospheric particulate matter emitted by the set pollution source.

[0080] In this embodiment, in the single particle data set acquisition module 001, in the process of analyzing the collected samples of the set pollution source by applying a computer-controlled scanning electron microscope, the set pollution source includes: soil dust, road dust, construction dust, coal smoke dust, biomass combustion dust and steel smelting dust.

[0081] In this embodiment, in the single particle pollution source preliminary prediction module 002, in the process of extracting the image features of the single particle through the residual network model, the initial parameters of the residual network model are determined by training with a large ImageNet data set; during the training process of the residual network model, the performance of the residual network model is optimized by the Adam optimizer and the negative log-likelihood loss function.

[0082] In this embodiment, in the single particle pollution source depth prediction module 003, in the process of predicting through the extreme gradient boosting model to obtain the probability value of the single particle belonging to the set pollution source, the hyperparameters that meet the set requirements are selected through the grid search strategy, and the performance of the extreme gradient boosting model is evaluated by the five-fold cross validation strategy.

[0083] In this embodiment, in the atmospheric particulate matter proportion data acquisition module 004, the mass proportion calculation formula of the atmospheric particulate matter emitted by the set pollution source is:

[0084]

[0085] Where M i is the mass contribution of particulate matter emitted by the i-th pollution source; p ij is the initial probability that particle j belongs to pollution source i; m j is the mass of particle j; k is the total number of set pollution sources; n is the total number of particles;

[0086] The calculation formula for the percentage of atmospheric particulate matter emitted by the set pollution source is:

[0087]

[0088] Where N i It is the contribution ratio of particulate matter emitted by the i-th pollution source.

[0089] It should be noted that the information interaction, execution process, etc. between the modules / units of the above-mentioned system are based on the same concept as the method embodiment in Example 1 of the present application, and the technical effects they bring are the same as those of the method embodiment of the present application. For specific contents, please refer to the description in the method embodiment shown in the previous part of the present application, and will not be repeated here.

[0090] Example 3

[0091] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium, in which the program code of a single particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis is stored, and the program code includes instructions for executing embodiment 1 or any possible implementation method of the single particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis.

[0092] The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0093] Example 4

[0094] Embodiment 4 of the present invention provides an electronic device, including: a memory and a processor;

[0095] The processor and the memory communicate with each other via a bus; the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the single particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis of Example 1 or any possible implementation thereof.

[0096] Specifically, the processor can be implemented by hardware or by software. When implemented by hardware, the processor can be a logic circuit, an integrated circuit, etc.; when implemented by software, the processor can be a general-purpose processor implemented by reading software codes stored in a memory. The memory can be integrated in the processor or can be located outside the processor and exist independently.

[0097] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center.

[0098] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0099] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.

Claims

1. A single particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis, characterized in that: include: By using a computer-controlled scanning electron microscope to analyze the collected samples of the set pollution source, images, elemental data and particle size parameters of single particles in the samples of the set pollution source are obtained, and a single particle data set of the pollution source samples is constructed; Extracting the image features of the single particle through a residual network model, and preliminarily predicting the source of the single particle based on the image features of the single particle, to obtain a preliminary probability value that the single particle belongs to a set pollution source; The preliminary probability value that the single particle belongs to the set pollution source is combined with the particle size parameters and element data of the single particle, and the results are input into the extreme gradient boosting model. The probability value that the single particle belongs to the set pollution source is obtained through prediction by the extreme gradient boosting model. The probability value of the single particle belonging to the set pollution source is weighted and summed up by source category according to the mass or quantity of the single particle to obtain the mass or quantity contribution / proportion of the atmospheric particulate matter emitted by the set pollution source.

2. The single particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis according to claim 1 is characterized in that: In the process of analyzing the collected samples of the set pollution sources by applying a computer-controlled scanning electron microscope, the set pollution sources include: soil dust, road dust, construction dust, coal smoke dust, biomass combustion dust and steel smelting dust.

3. The single particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis according to claim 2 is characterized in that: In the process of extracting the image features of the single particle through the residual network model, the initial parameters of the residual network model are determined by training with a large ImageNet data set; during the training process of the residual network model, the performance of the residual network model is optimized by an Adam optimizer and a negative log-likelihood loss function.

4. The single particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis according to claim 3 is characterized in that: In the process of predicting and obtaining the probability value of the single particle belonging to the set pollution source through the extreme gradient boosting model, the hyperparameters that meet the set requirements are selected through the grid search strategy, and the performance of the extreme gradient boosting model is evaluated by the five-fold cross validation strategy.

5. The single particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis according to claim 4 is characterized in that: The calculation formula for the mass proportion of atmospheric particulate matter emitted by the set pollution source is: Where M i is the mass contribution of particulate matter emitted by the i-th pollution source; p ij is the probability that particle j belongs to pollution source i; m j is the mass of particle j; k is the total number of set pollution sources; n is the total number of particles; The calculation formula for the percentage of atmospheric particulate matter emitted by the set pollution source is: Where N i It is the contribution ratio of particulate matter emitted by the i-th pollution source.

6. A single particle source intelligent analysis device based on scanning electron microscope energy spectrum analysis, using the single particle source intelligent analysis method based on scanning electron microscope energy spectrum analysis described in claims 1-5 above, characterized in that: include: A single particle data set acquisition module is used to analyze the collected samples of the set pollution source by using a scanning electron microscope controlled by a computer, obtain the image, element data and particle size parameters of the single particles in the samples of the set pollution source, and construct a single particle data set of the pollution source samples; A single particle pollution source preliminary prediction module is used to extract the image features of the single particle through a residual network model, and preliminarily predict the source of the single particle based on the image features of the single particle, and obtain a preliminary probability value that the single particle belongs to a set pollution source; A single particle pollution source depth prediction module is used to combine the preliminary probability value of the single particle belonging to the set pollution source with the particle size parameters and element data of the single particle, and input them into the extreme gradient boosting model, and obtain the probability value of the single particle belonging to the set pollution source through the extreme gradient boosting model prediction; The atmospheric particulate matter proportion data acquisition module is used to weight the probability value of the single particle belonging to the set pollution source by the mass or quantity of the single particle, and perform source-based summation calculation processing to obtain the mass or quantity contribution / proportion of the atmospheric particulate matter emitted by the set pollution source.

7. The single particle source intelligent analysis device based on scanning electron microscope energy spectrum analysis according to claim 6 is characterized in that: In the single particle data set acquisition module, in the process of analyzing the collected samples of the set pollution sources by applying a computer-controlled scanning electron microscope, the set pollution sources include: soil dust, road dust, construction dust, coal smoke dust, biomass combustion dust and steel smelting dust.

8. The single particle source intelligent analysis device based on scanning electron microscope energy spectrum analysis according to claim 7 is characterized in that: In the single particle pollution source preliminary prediction module, in the process of extracting the image features of the single particle through the residual network model, the initial parameters of the residual network model are determined by training with a large ImageNet data set; during the training process of the residual network model, the performance of the residual network model is optimized by the Adam optimizer and the negative log-likelihood loss function.

9. The single particle source intelligent analysis device based on scanning electron microscope energy spectrum analysis according to claim 8, characterized in that: In the single particle pollution source depth prediction module, in the process of obtaining the probability value of the single particle belonging to the set pollution source through the extreme gradient boosting model prediction, the hyperparameters that meet the set requirements are selected through the grid search strategy, and the performance of the extreme gradient boosting model is evaluated by the five-fold cross validation strategy.

10. The single particle source intelligent analysis device based on scanning electron microscope energy spectrum analysis according to claim 9, characterized in that: In the atmospheric particulate matter proportion data acquisition module, the mass proportion calculation formula of the atmospheric particulate matter emitted by the set pollution source is: Where M i is the mass contribution of particulate matter emitted by the i-th pollution source; p ij is the initial probability that particle j belongs to pollution source i; m j is the mass of particle j; k is the total number of set pollution sources; n is the total number of particles; The calculation formula for the percentage of atmospheric particulate matter emitted by the set pollution source is: Where N i It is the contribution ratio of particulate matter emitted by the i-th pollution source.

Images