A coal yard inside and outside pollution coordinated monitoring and intelligent regulation system
By performing correlation analysis on monitoring data from both inside and outside the coal yard, a data-correlation mapping table and a pollution pattern prediction model are generated. This solves the problem of low efficiency in the coordinated monitoring and control of pollution inside and outside the coal yard, and achieves dynamic adjustment and efficient pollution control.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HUANENG CHAOHU POWER GENERATION CO LTD
- Filing Date
- 2026-01-21
- Publication Date
- 2026-06-19
AI Technical Summary
Existing coal yard pollution monitoring mainly focuses on the site itself, lacking coordinated monitoring of pollution inside and outside the coal yard. This makes it difficult to accurately analyze the correlation between external monitoring data and internal data, as well as the pollution diffusion pattern, resulting in low control efficiency and an inability to make dynamic adjustments.
By performing correlation analysis on each first monitoring data point in the external monitoring area of the coal yard and several second monitoring data points inside, a data-correlation mapping table is generated to identify pollution sources, construct a pollution pattern prediction model, and generate the optimal control strategy.
It improves the efficiency of pollution monitoring and control inside and outside the coal yard, and can dynamically adjust according to the coordination between external monitoring data and on-site data and meteorological conditions, thereby reducing the pollution impact on the surrounding environment.
Smart Images
Figure CN122238607A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of coal yard pollution monitoring technology, and in particular to a collaborative monitoring and intelligent control system for pollution inside and outside a coal yard. Background Technology
[0002] Coal yards are prone to generating dust and harmful gas pollution during coal storage and transportation, which not only affects the working environment on site, but may also spread to the surrounding area, posing a threat to the atmospheric environment and residents' health.
[0003] Existing coal yard pollution monitoring focuses primarily on on-site monitoring, lacking coordinated monitoring of pollution inside and outside the coal yard. This makes it difficult to accurately analyze the correlation between external monitoring data and on-site data, as well as the patterns of pollution diffusion. Furthermore, pollution control is mostly manual or operates in a fixed mode with single equipment, failing to dynamically adjust based on the coordination between external and on-site monitoring data and meteorological conditions. This results in low efficiency and poor effectiveness of control measures. Summary of the Invention
[0004] To address the aforementioned technical issues, this application provides a collaborative monitoring and intelligent control system for pollution inside and outside a coal yard. By performing correlation analysis on each first monitoring data point outside the coal yard and several second monitoring data points inside the coal yard, several data-correlation mapping tables are obtained. Pollution sources are identified, a pollution pattern prediction model is constructed, predicted pollution parameters for future periods are determined, and an optimal control strategy is generated, thereby improving monitoring and control efficiency.
[0005] In some embodiments of this application, a collaborative monitoring and intelligent control system for pollution inside and outside a coal yard is provided, including: The monitoring module is used to set up several external monitoring areas of the coal yard and acquire several first monitoring data of each external monitoring area in real time. The correlation module is used to perform correlation analysis on several primary monitoring data and several secondary monitoring data within the coal yard, and generate several data-correlation mapping tables based on the analysis results; The module is used to determine the comprehensive impact coefficient of each second monitoring data based on the data-association mapping table, identify several pollution sources, and construct a pollution pattern prediction model based on the pollution sources and the corresponding data-association mapping table. The control module is used to determine the predicted pollution parameters for future periods based on the pollution pattern prediction model and several second monitoring data, and to generate the optimal control strategy based on the predicted pollution parameters.
[0006] In some embodiments of this application, the system further includes: The data processing module is used to synchronously collect several first monitoring data from all external monitoring areas of the coal yard and several second monitoring data from inside the coal yard, and to preprocess, normalize, and align the data with timestamps to obtain several first monitoring data and several second monitoring data of the same time dimension and the same magnitude.
[0007] In some embodiments of this application, several data-association mapping tables are generated based on the analysis results, including: Several first monitoring data and several second monitoring data after the data processing module are mapped to the blank point graph in chronological order, and several first monitoring data change curves and several second monitoring data change curves are constructed. Randomly select a second monitoring data change curve as the target curve, and extract several target curve segments from the target curve; Construct a first undetermined association dataset and a second undetermined association dataset for each target curve segment; The first undetermined association dataset includes several second monitoring data, and the second undetermined association dataset includes several second monitoring data and several first monitoring data, and each data corresponds to an initial association coefficient; Calculate the first correlation coefficient of the same second monitoring data in different first undetermined correlation datasets for all segments of the target curve, the second correlation coefficient of the same second monitoring data in different second undetermined correlation datasets, and the third correlation coefficient of the same first monitoring data in different second undetermined correlation datasets; The first and second correlation datasets of the target curve are determined based on the first correlation coefficient, the second correlation coefficient, and the third correlation coefficient. Generate a data-association mapping table for the target curve corresponding to the second monitoring data based on the first and second associated datasets; The data-association mapping table includes a pre-association mapping table and a post-association mapping table corresponding to the second monitoring data; Generate a data-association mapping table for each second monitoring data point in sequence.
[0008] In some embodiments of this application, constructing a first undetermined association dataset and a second undetermined association dataset for each target curve segment includes: Define the first and second associated time intervals for each target curve segment; Generate the first fluctuation characteristics of each second monitoring data change curve in the first associated time interval of each target curve segment, the second fluctuation characteristics in the second associated time interval, and the third fluctuation characteristics of each first monitoring data change curve in the second associated time interval of each target curve segment; Among them, the volatility characteristics include the degree of volatility and the volatility trend; Determine whether several first, second, and third fluctuation features satisfy the fluctuation correlation rule. If they satisfy the fluctuation correlation rule, calculate the corresponding initial correlation coefficient. The first undetermined correlation dataset and the second undetermined correlation dataset for each target curve segment are constructed using several second monitoring data that satisfy the fluctuation correlation rules and several first monitoring data.
[0009] In some embodiments of this application, second monitoring data from a first undetermined associated dataset of a target curve segment of the target curve is randomly selected as the first target data; Calculate the number of times the first target data appears in the first undetermined association dataset of other target curve segments of the same target curve, and calculate the first association coefficient of the first target data in combination with the corresponding initial association coefficient; The second monitoring data in the second undetermined associated dataset of a target curve segment is randomly selected as the second target data. Calculate the number of times the second target data appears in the second undetermined association dataset of other target curve segments of the same target curve, and calculate the second association coefficient of the second target data in combination with the corresponding initial association coefficient; The first monitoring data in the second undetermined associated dataset of a target curve segment is randomly selected as the third target data; Calculate the number of times the third target data appears in the second undetermined association dataset of other target curve segments of the same target curve, and calculate the third association coefficient of the third target data in combination with the corresponding initial association coefficient.
[0010] In some embodiments of this application, generating a data-association mapping table for each second monitoring data point further includes: A comparative analysis was conducted on the data-correlation mapping tables of different second monitoring data. Based on the analysis results, several correspondences of second monitoring data were determined, and each correspondence of second monitoring data included a corresponding group of second monitoring data and a corresponding group of correlation coefficients. The correlation coefficient difference is calculated based on the correlation coefficient corresponding group in each second monitoring data correspondence. If the correlation coefficient difference is less than the preset difference threshold, the corresponding second monitoring data corresponding group is retained. If the difference in correlation coefficients is not less than the preset difference threshold, then the corresponding group of the second monitoring data will be removed. The data-association mapping table of all second monitoring data is adjusted according to the corresponding group of the retained second monitoring data, and the adjusted data-association mapping table is used to replace the data-association mapping table of the corresponding second monitoring data.
[0011] In some embodiments of this application, the comprehensive impact coefficient of each second monitoring data is determined based on a data-association mapping table, and several pollution sources are identified, including: Calculate the first number of the second monitoring data in the first association mapping table, the second number of the second monitoring data in the second association mapping table, and the third number of the first monitoring data in the second association mapping table for each second monitoring data; The first influence coefficient of the corresponding second monitoring data is calculated based on the first number, the weight coefficient of the corresponding second monitoring data, and the corresponding first correlation coefficient. The second influence coefficient of the corresponding second monitoring data is calculated based on the second number, the weight coefficient of the corresponding second monitoring data, and the corresponding second correlation coefficient. The third influence coefficient of the corresponding second monitoring data is calculated based on the third number, the weight coefficient of the corresponding first monitoring data, and the corresponding third correlation coefficient. A comprehensive impact coefficient for the corresponding second monitoring data is generated based on the first impact coefficient, the second impact coefficient, and the third impact coefficient. The second monitoring data with a comprehensive impact coefficient greater than the preset impact coefficient threshold is set as the pollution source.
[0012] In some embodiments of this application, a pollution pattern prediction model is constructed based on several pollution sources and corresponding data-association mapping tables, including: Several historical meteorological parameters that influence the diffusion characteristics of the first historical monitoring data were selected, including diffusion trend, diffusion rate, and diffusion path. Several meteorological scenarios are generated by randomly combining several selected historical meteorological parameters and then generating several combined historical meteorological parameters. Construct simulation models for different meteorological scenarios; By using a simulation model, combined with multiple historical second monitoring data of each pollution source in the pollution source sequence and the corresponding data-association mapping table, simulated first detection data and corresponding simulated diffusion data of each historical second monitoring data of different pollution sources under different meteorological scenarios are obtained. Historical second monitoring data of different pollution sources under different meteorological scenarios are used as training input data, and the corresponding simulated first detection data and the corresponding simulated diffusion data are used as training output data to train a neural network and obtain a pollution pattern prediction model.
[0013] In some embodiments of this application, pollution parameters for future periods are determined based on a pollution pattern prediction model and several second monitoring data, including: Several predicted second monitoring data points for future periods are generated based on several second monitoring data points and current demand instructions; Generate predicted meteorological data for future periods, and perform similarity analysis between the predicted meteorological data and historical meteorological data of the meteorological scene to obtain the similarity score; The meteorological scene with the highest similarity and several predicted second monitoring data are input into the pollution pattern prediction model to generate several predicted first monitoring data for future periods and the predicted diffusion data corresponding to the predicted first monitoring data. Several pollution assessment indicators are pre-set; Based on several pollution assessment indicators, a pollution assessment is performed on each predicted first monitoring data and the corresponding predicted diffusion data to obtain a pollution assessment value for each predicted first monitoring data. Pre-set pollution assessment thresholds; If the pollution assessment value is greater than the pollution assessment value threshold, then the corresponding first monitoring data for prediction is set as the predicted pollution parameter for the future period.
[0014] In some embodiments of this application, an optimal control strategy is generated based on predicted pollution parameters, including: Based on the full data-association mapping table, the pollution sources affecting each predicted pollution parameter are traced. By combining the pollution assessment values of the predicted pollution parameters, the corresponding predicted diffusion data, and the traced pollution sources, an initial set of control strategies is generated. The initial set of control strategies includes initial control strategies for different pollution sources. A feasibility assessment is conducted on each initial control strategy in the initial control strategy set. Based on the feasibility assessment results, several initial control strategies with higher feasibility are selected from the initial control strategy set to form a feasible control strategy set. For each initial control strategy in the set of feasible control strategies, the effect is simulated and predicted. Based on the effect simulation and prediction results, the optimal control strategy is determined.
[0015] The advantages of the collaborative monitoring and intelligent control system for pollution inside and outside coal yards provided in this application, compared with the prior art, are as follows: By performing correlation analysis on each first monitoring data point outside the coal yard and several second monitoring data points inside the coal yard, several data-correlation mapping tables are obtained. Pollution sources are identified, a pollution pattern prediction model is constructed, predicted pollution parameters for future periods are determined, and the optimal control strategy is generated, thereby improving monitoring efficiency and control efficiency. Attached Figure Description
[0016] Figure 1 This is a schematic diagram of a coal yard pollution collaborative monitoring and intelligent control system in an embodiment of this application. Detailed Implementation
[0017] The specific embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The following examples are used to illustrate this application, but are not intended to limit the scope of this application.
[0018] In the description of this application, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.
[0019] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.
[0020] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.
[0021] like Figure 1 As shown in the figure, an embodiment of this application provides a collaborative monitoring and intelligent control system for pollution inside and outside a coal yard, comprising: The monitoring module is used to set up several external monitoring areas of the coal yard and acquire several first monitoring data of each external monitoring area in real time. The correlation module is used to perform correlation analysis on several primary monitoring data and several secondary monitoring data within the coal yard, and generate several data-correlation mapping tables based on the analysis results; The module is used to determine the comprehensive impact coefficient of each second monitoring data based on the data-association mapping table, identify several pollution sources, and construct a pollution pattern prediction model based on the pollution sources and the corresponding data-association mapping table. The control module is used to determine the predicted pollution parameters for future periods based on the pollution pattern prediction model and several second monitoring data, and to generate the optimal control strategy based on the predicted pollution parameters.
[0022] In this embodiment, the external monitoring area of the coal yard refers to the boundary of the coal yard and the surrounding sensitive areas. The surrounding sensitive areas include environmentally sensitive points such as residential areas, schools, and hospitals. The first monitoring data includes particulate matter concentration parameters (PM2.5, PM10), harmful gas concentration parameters (SO2, NOx, CO, CH4), and meteorological parameters (wind speed, wind direction, temperature, and humidity).
[0023] In this embodiment, several second monitoring data inside the coal yard include equipment operation data, coal pile temperature data, particulate matter concentration data inside the coal yard, and harmful gas concentration data inside the coal yard.
[0024] In some embodiments of this application, the system further includes: The data processing module is used to synchronously collect several first monitoring data from all external monitoring areas of the coal yard and several second monitoring data from inside the coal yard, and to preprocess, normalize, and align the data with timestamps to obtain several first monitoring data and several second monitoring data of the same time dimension and the same magnitude.
[0025] In some embodiments of this application, several data-association mapping tables are generated based on the analysis results, including: Several first monitoring data and several second monitoring data after the data processing module are mapped to the blank point graph in chronological order, and several first monitoring data change curves and several second monitoring data change curves are constructed. Randomly select a second monitoring data change curve as the target curve, and extract several target curve segments from the target curve; Construct a first undetermined association dataset and a second undetermined association dataset for each target curve segment; The first undetermined association dataset includes several second monitoring data, and the second undetermined association dataset includes several second monitoring data and several first monitoring data, and each data corresponds to an initial association coefficient; Calculate the first correlation coefficient of the same second monitoring data in different first undetermined correlation datasets for all segments of the target curve, the second correlation coefficient of the same second monitoring data in different second undetermined correlation datasets, and the third correlation coefficient of the same first monitoring data in different second undetermined correlation datasets; The first and second correlation datasets of the target curve are determined based on the first correlation coefficient, the second correlation coefficient, and the third correlation coefficient. Generate a data-association mapping table for the target curve corresponding to the second monitoring data based on the first and second associated datasets; The data-association mapping table includes a pre-association mapping table and a post-association mapping table corresponding to the second monitoring data; Generate a data-association mapping table for each second monitoring data point in sequence.
[0026] In this embodiment, several first monitoring data and several second monitoring data of the same time dimension and the same magnitude are mapped to a blank dot plot, which can intuitively show the changing trend of monitoring data of different regions and different types over time, providing a clear data visualization foundation for subsequent correlation analysis.
[0027] In this embodiment, the target curve segment refers to the curve segment in the target curve whose fluctuation degree is greater than the preset fluctuation degree.
[0028] In this embodiment, the first associated dataset consists of several second monitoring data points whose first association coefficient is greater than a preset first association coefficient threshold in the first undetermined associated dataset. The second associated dataset consists of several second monitoring data points whose second association coefficient is greater than a preset second association coefficient threshold in the second undetermined associated dataset, and several first monitoring data points whose third association coefficient is greater than a preset third association coefficient threshold. The preset first association coefficient threshold, the preset second association coefficient threshold, and the preset third association coefficient threshold are set as the minimum association coefficients that are related to and significantly affected by the fluctuation of the target curve segment.
[0029] In this embodiment, the pre-association mapping table is generated based on the first association dataset corresponding to the second monitoring data, and the post-association mapping table is generated based on the second association dataset corresponding to the second monitoring data. Each data in the data-association mapping table is mapped to an association coefficient with the corresponding second monitoring data.
[0030] In this embodiment, comprehensive and detailed monitoring and correlation lay the foundation for subsequent prediction and control mechanisms, effectively realizing the coordinated monitoring and intelligent control of pollution inside and outside the coal yard. This helps to reduce the pollution impact of coal yard operations on the surrounding environment and protect the environmental quality of surrounding residents, schools, hospitals and other environmentally sensitive areas.
[0031] In some embodiments of this application, constructing a first undetermined association dataset and a second undetermined association dataset for each target curve segment includes: Define the first and second associated time intervals for each target curve segment; Generate the first fluctuation characteristics of each second monitoring data change curve in the first associated time interval of each target curve segment, the second fluctuation characteristics in the second associated time interval, and the third fluctuation characteristics of each first monitoring data change curve in the second associated time interval of each target curve segment; Among them, the volatility characteristics include the degree of volatility and the volatility trend; Determine whether several first, second, and third fluctuation features satisfy the fluctuation correlation rule. If they satisfy the fluctuation correlation rule, calculate the corresponding initial correlation coefficient. The first undetermined correlation dataset and the second undetermined correlation dataset for each target curve segment are constructed using several second monitoring data that satisfy the fluctuation correlation rules and several first monitoring data.
[0032] In this embodiment, the fluctuation association rule refers to the fluctuation degree being greater than the preset fluctuation degree and the fluctuation trend being correlated with the fluctuation trend of the corresponding target curve segment. If the first fluctuation feature, the second fluctuation feature, and the third fluctuation feature satisfy the fluctuation association rule, then the corresponding second monitoring data or the first monitoring data will be used to construct the corresponding pending association dataset.
[0033] In this embodiment, by constructing a dataset of undetermined associations, monitoring data that has potential associations with the target curve segment can be accurately screened, providing a reliable data foundation for subsequent association coefficient calculation and data-association mapping table generation.
[0034] In some embodiments of this application, second monitoring data from a first undetermined associated dataset of a target curve segment of the target curve is randomly selected as the first target data; Calculate the number of times the first target data appears in the first undetermined association dataset of other target curve segments of the same target curve, and calculate the first association coefficient of the first target data in combination with the corresponding initial association coefficient; The second monitoring data in the second undetermined associated dataset of a target curve segment is randomly selected as the second target data. Calculate the number of times the second target data appears in the second undetermined association dataset of other target curve segments of the same target curve, and calculate the second association coefficient of the second target data in combination with the corresponding initial association coefficient; The first monitoring data in the second undetermined associated dataset of a target curve segment is randomly selected as the third target data; Calculate the number of times the third target data appears in the second undetermined association dataset of other target curve segments of the same target curve, and calculate the third association coefficient of the third target data in combination with the corresponding initial association coefficient.
[0035] In this embodiment, the first correlation coefficient refers to the average of the frequency of each first target data and multiple initial correlation coefficients. The calculation process of the second and third correlation coefficients is similar and will not be repeated here.
[0036] In this embodiment, by calculating the correlation coefficient of the same data in different target curve segments multiple times, the random error caused by a single data sample can be effectively reduced, making the final correlation coefficient more statistically significant and reliable. This ensures that the data-correlation mapping table can accurately reflect the inherent correlation between monitoring data inside and outside the coal yard, providing solid data support for the accurate identification of pollution sources and the construction of pollution pattern prediction models, and avoiding the bias in correlation analysis caused by individual abnormal data points.
[0037] In some embodiments of this application, generating a data-association mapping table for each second monitoring data point further includes: A comparative analysis was conducted on the data-correlation mapping tables of different second monitoring data. Based on the analysis results, several correspondences of second monitoring data were determined, and each correspondence of second monitoring data included a corresponding group of second monitoring data and a corresponding group of correlation coefficients. The correlation coefficient difference is calculated based on the correlation coefficient corresponding group in each second monitoring data correspondence. If the correlation coefficient difference is less than the preset difference threshold, the corresponding second monitoring data corresponding group is retained. If the difference in correlation coefficients is not less than the preset difference threshold, then the corresponding group of the second monitoring data will be removed. The data-association mapping table of all second monitoring data is adjusted according to the corresponding group of the retained second monitoring data, and the adjusted data-association mapping table is used to replace the data-association mapping table of the corresponding second monitoring data.
[0038] In this embodiment, the correspondence of the second monitoring data is set based on the second monitoring data that have a corresponding relationship in the front association mapping table and the back association mapping table of the data-association mapping table of different second monitoring data. For example, a and b are two second monitoring data. The front association mapping table of the data-association mapping table of a includes b, and the back association mapping table of the sub-data-association mapping table of b includes a. Then a second monitoring data correspondence group is generated, and the corresponding first association coefficient and second association coefficient are respectively constructed into the association coefficient correspondence group of the second monitoring data correspondence group.
[0039] In this embodiment, the preset difference refers to the minimum correlation coefficient difference that satisfies the credibility of the correlation coefficient. By setting a reasonable preset difference threshold, the corresponding group of the second monitoring data with higher credibility can be effectively screened out, thereby ensuring the accuracy and reliability of the data-correlation mapping table.
[0040] In this embodiment, the mapping relationship of the corresponding second monitoring data in the data-association mapping table is retained according to the group of the retained second monitoring data, and the mapping relationship of the second monitoring data that does not belong to the retained second monitoring data is removed, so that it can more accurately reflect the real correlation between the second monitoring data.
[0041] In this embodiment, by calculating the difference in correlation coefficients, the reliability of the data-correlation mapping table of different second monitoring data can be improved, thereby providing more accurate data support for subsequent determination of pollution source sequences and prediction and control.
[0042] In some embodiments of this application, the comprehensive impact coefficient of each second monitoring data is determined based on a data-association mapping table, and several pollution sources are identified, including: Calculate the first number of the second monitoring data in the first association mapping table, the second number of the second monitoring data in the second association mapping table, and the third number of the first monitoring data in the second association mapping table for each second monitoring data; The first influence coefficient of the corresponding second monitoring data is calculated based on the first number, the weight coefficient of the corresponding second monitoring data, and the corresponding first correlation coefficient. The second influence coefficient of the corresponding second monitoring data is calculated based on the second number, the weight coefficient of the corresponding second monitoring data, and the corresponding second correlation coefficient. The third influence coefficient of the corresponding second monitoring data is calculated based on the third number, the weight coefficient of the corresponding first monitoring data, and the corresponding third correlation coefficient. A comprehensive impact coefficient for the corresponding second monitoring data is generated based on the first impact coefficient, the second impact coefficient, and the third impact coefficient. The second monitoring data with a comprehensive impact coefficient greater than the preset impact coefficient threshold is set as the pollution source.
[0043] In this embodiment, ; ; ; Where Y1 is the first influence coefficient, y1 is the first influence conversion coefficient, and n1 is the first number. For the first correlation coefficient of the i-th second monitoring data in the preceding correlation mapping table corresponding to the second monitoring data, Let ai be the weight coefficient of the i-th second monitoring data, Y2 be the second influence coefficient, y2 be the second influence conversion coefficient, and n2 be the second number. This refers to the second correlation coefficient of the s-th second monitoring data in the post-correlation mapping table corresponding to the second monitoring data. The second correlation coefficient threshold is preset, as is the weight coefficient of the s-th second monitoring data, Y3 is the third influence coefficient, y3 is the third influence conversion coefficient, and n3 is the third number. This refers to the third correlation coefficient of the c-th first monitoring data in the post-correlation mapping table corresponding to the second monitoring data. The third correlation coefficient threshold is preset, and ac is the weight coefficient of the c-th first monitoring data.
[0044] In this embodiment, the comprehensive influence coefficient = Y1*0.3 + Y2*0.3 + Y3*0.4.
[0045] In this embodiment, the weighting coefficients of the first and second monitoring data are pre-set, mainly based on the degree of impact of each monitoring data on environmental pollution and its importance in the overall monitoring system. For example, for environmentally sensitive areas such as residential areas around coal yards, the weighting coefficients of monitoring data such as particulate matter concentration parameters (PM2.5, PM10), which directly affect air quality and residents' health, will be set higher.
[0046] In this embodiment, y1, y2, and y3 refer to the values of the sum of the differences in the first, second, and third correlation coefficients converted into the same dimension as the influence coefficients. When the sum of the differences in the first correlation coefficients is smaller, the first influence coefficient is larger, and vice versa. When the sum of the differences in the second or third correlation coefficients is larger, the second or third influence coefficient is larger, and vice versa.
[0047] In this embodiment, the smaller the first number in the preceding correlation mapping table of each second monitoring data and the smaller the first correlation coefficient and weight coefficient of the corresponding second monitoring data, the less affected the corresponding second monitoring data is, and the lower the possibility of it being a pollution source. On the other hand, when the second number in the following correlation mapping table and the second correlation coefficient and weight coefficient of the corresponding second monitoring data are large, or when the third number in the following correlation mapping table and the third correlation coefficient and weight coefficient of the corresponding first monitoring data are large, it indicates that the second monitoring data has a significant impact on other monitoring data, and thus indicates that it is more likely to be a pollution source.
[0048] In this embodiment, the preset impact coefficient threshold is set based on the minimum impact coefficient that has a significant impact on the spread of pollution inside and outside the coal yard, ensuring that subsequent prediction and control measures can accurately address the main pollution problems.
[0049] In this embodiment, by calculating and comparing comprehensive influence coefficients, major pollution sources can be scientifically and objectively identified, providing clear targets and directions for subsequent pollution control and regulation. Furthermore, by identifying pollution sources, relevant data can be monitored and managed in a focused manner, providing a crucial basis for accurately predicting the diffusion patterns of pollution inside and outside the coal yard and formulating targeted control strategies. This effectively improves the targeting and efficiency of coal yard pollution prevention and control, adapting to real-time changes in pollution emissions during coal yard operation and ensuring the effectiveness and timeliness of control measures.
[0050] In some embodiments of this application, a pollution pattern prediction model is constructed based on several pollution sources and corresponding data-association mapping tables, including: Several historical meteorological parameters that influence the diffusion characteristics of the first historical monitoring data were selected, including diffusion trend, diffusion rate, and diffusion path. Several meteorological scenarios are generated by randomly combining several selected historical meteorological parameters and then generating several combined historical meteorological parameters. Construct simulation models for different meteorological scenarios; By using a simulation model, combined with multiple historical second monitoring data of each pollution source in the pollution source sequence and the corresponding data-association mapping table, simulated first detection data and corresponding simulated diffusion data of each historical second monitoring data of different pollution sources under different meteorological scenarios are obtained. Historical second monitoring data of different pollution sources under different meteorological scenarios are used as training input data, and the corresponding simulated first detection data and the corresponding simulated diffusion data are used as training output data to train a neural network and obtain a pollution pattern prediction model.
[0051] In this embodiment, the simulated first detection data and simulated diffusion data are compared and verified with the actual historical first monitoring data and historical diffusion data. Based on the comparison results, optimization and adjustment are made to ensure that the pollution pattern prediction model can accurately reflect the impact of changes in different pollution sources on the corresponding first monitoring data and diffusion patterns.
[0052] In this embodiment, the simulated diffusion data includes information such as diffusion concentration, diffusion path and diffusion range, and the time of arrival at each environmentally sensitive point. This simulated diffusion data can accurately reflect the specific impact of pollutants generated by various pollution sources on the surrounding environment under different combinations of meteorological conditions. For example, in a meteorological scenario with a specific combination of wind direction, wind speed, temperature, and humidity, the simulated diffusion data can clearly show the diffusion trajectory of particulate matter or harmful gases emitted by a certain pollution source in the air, as well as the concentration values reached at different distances and directions.
[0053] In this embodiment, through these detailed simulated diffusion data, we can gain a more comprehensive and in-depth understanding of the predicted first monitoring data of pollution sources under different meteorological scenarios and the corresponding pollution diffusion patterns. This provides a solid data foundation for the subsequent accurate prediction of the diffusion of pollution inside and outside the coal yard, and helps to formulate more scientific and effective pollution control strategies to reduce the pollution risks caused by coal yard operations to the surrounding environment and protect the environmental quality of the surrounding area.
[0054] In some embodiments of this application, pollution parameters for future periods are determined based on a pollution pattern prediction model and several second monitoring data, including: Several predicted second monitoring data points for future periods are generated based on several second monitoring data points and current demand instructions; Generate predicted meteorological data for future periods, and perform similarity analysis between the predicted meteorological data and historical meteorological data of the meteorological scene to obtain the similarity score; The meteorological scene with the highest similarity and several predicted second monitoring data are input into the pollution pattern prediction model to generate several predicted first monitoring data for future periods and the predicted diffusion data corresponding to the predicted first monitoring data. Several pollution assessment indicators are pre-set; Based on several pollution assessment indicators, a pollution assessment is performed on each predicted first monitoring data and the corresponding predicted diffusion data to obtain a pollution assessment value for each predicted first monitoring data. Pre-set pollution assessment thresholds; If the pollution assessment value is greater than the pollution assessment value threshold, then the corresponding first monitoring data for prediction is set as the predicted pollution parameter for the future period.
[0055] In this embodiment, pollution assessment indicators include, but are not limited to, normal data range indicators, diffusion rate indicators, diffusion range indicators, and environmental sensitive point impact indicators. The normal data range indicator defines the reasonable fluctuation range of the first monitoring data under pollution-free or low-pollution conditions. When the predicted first monitoring data exceeds this range, it indicates a potential pollution risk; the higher the corresponding indicator's evaluation value, the lower the risk. The diffusion rate indicator measures the speed at which the first monitoring data spreads in the air; rapid diffusion may mean that pollutants will quickly affect a wider area of the environment. The diffusion range indicator clarifies the geographical area that the pollutants may cover, which is crucial for assessing the potential impact on different surrounding areas. The environmental sensitive point impact indicator focuses on key areas such as residential areas, schools, and hospitals around the coal yard, quantifying the degree of harm caused by pollutants to these areas.
[0056] In this embodiment, the pollution assessment threshold is set comprehensively based on past monitoring data and environmental standards, aiming to accurately identify pollution situations that may have a significant impact on the surrounding environment. When the pollution assessment value of the predicted first monitoring data exceeds this threshold, the system will mark it as a predicted pollution parameter for future periods.
[0057] In this embodiment, by comprehensively utilizing these pollution assessment indicators, the pollution assessment value of each predicted first monitoring data is calculated. The system can comprehensively and meticulously assess the potential pollution situation outside the coal yard in the future, providing an accurate basis for subsequent pollution control decisions. Simultaneously, setting pollution assessment value thresholds helps clarify the initiation conditions and urgency of pollution control, ensuring that effective control measures can be taken promptly in the early stages of pollution or when potential risks are high, minimizing the negative impact of coal yard operations on the surrounding environment.
[0058] In some embodiments of this application, an optimal control strategy is generated based on predicted pollution parameters, including: Based on the full data-association mapping table, the pollution sources affecting each predicted pollution parameter are traced. By combining the pollution assessment values of the predicted pollution parameters, the corresponding predicted diffusion data, and the traced pollution sources, an initial set of control strategies is generated. The initial set of control strategies includes initial control strategies for different pollution sources. A feasibility assessment is conducted on each initial control strategy in the initial control strategy set. Based on the feasibility assessment results, several initial control strategies with higher feasibility are selected from the initial control strategy set to form a feasible control strategy set. For each initial control strategy in the set of feasible control strategies, the effect is simulated and predicted. Based on the effect simulation and prediction results, the optimal control strategy is determined.
[0059] In this embodiment, the feasibility assessment factors include the difficulty and cost of implementing the control strategy, the degree of impact on the normal operation of the coal yard, and the impact of conflicts. The simulation prediction results include the data changes of the predicted pollution parameters and the diffusion improvement effect in the future period. The optimal control strategy refers to the control strategy with the largest data change and the best diffusion improvement effect in the set of feasible control strategies.
[0060] In this embodiment, the control strategy generated through the above steps can accurately target predicted pollution parameters, starting from the pollution source and selecting the optimal control scheme based on the actual situation, effectively reducing the pollution level of the coal yard in the future and ensuring the quality of the surrounding environment. At the same time, the generation process of this control strategy comprehensively considers multiple factors, ensuring the scientific validity, rationality, and operability of the control strategy.
[0061] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and substitutions can be made without departing from the technical principles of this application, and these improvements and substitutions should also be considered within the scope of protection of this application.
Claims
1. A collaborative monitoring and intelligent control system for pollution inside and outside a coal yard, characterized in that, include: The monitoring module is used to set up several external monitoring areas of the coal yard and acquire several first monitoring data of each external monitoring area in real time. The correlation module is used to perform correlation analysis on several primary monitoring data and several secondary monitoring data within the coal yard, and generate several data-correlation mapping tables based on the analysis results; The module is used to determine the comprehensive impact coefficient of each second monitoring data based on the data-association mapping table, identify several pollution sources, and construct a pollution pattern prediction model based on the pollution sources and the corresponding data-association mapping table. The control module is used to determine the predicted pollution parameters for future periods based on the pollution pattern prediction model and several second monitoring data, and to generate the optimal control strategy based on the predicted pollution parameters.
2. The coal yard internal and external pollution collaborative monitoring and intelligent control system as described in claim 1, characterized in that, Also includes: The data processing module is used to synchronously collect several first monitoring data from all external monitoring areas of the coal yard and several second monitoring data from inside the coal yard, and to preprocess, normalize, and align the data with timestamps to obtain several first monitoring data and several second monitoring data of the same time dimension and the same magnitude.
3. The coal yard internal and external pollution collaborative monitoring and intelligent control system as described in claim 2, characterized in that, A data-relationship mapping table is generated based on the analysis results, including: Several first monitoring data and several second monitoring data after the data processing module are mapped to the blank point graph in chronological order, and several first monitoring data change curves and several second monitoring data change curves are constructed. Randomly select a second monitoring data change curve as the target curve, and extract several target curve segments from the target curve; Construct a first undetermined association dataset and a second undetermined association dataset for each target curve segment; The first undetermined association dataset includes several second monitoring data, and the second undetermined association dataset includes several second monitoring data and several first monitoring data, and each data corresponds to an initial association coefficient; Calculate the first correlation coefficient of the same second monitoring data in different first undetermined correlation datasets for all segments of the target curve, the second correlation coefficient of the same second monitoring data in different second undetermined correlation datasets, and the third correlation coefficient of the same first monitoring data in different second undetermined correlation datasets; The first and second correlation datasets of the target curve are determined based on the first correlation coefficient, the second correlation coefficient, and the third correlation coefficient. Generate a data-association mapping table for the target curve corresponding to the second monitoring data based on the first and second associated datasets; The data-association mapping table includes a pre-association mapping table and a post-association mapping table corresponding to the second monitoring data; Generate a data-association mapping table for each second monitoring data point in sequence.
4. The coal yard internal and external pollution collaborative monitoring and intelligent control system as described in claim 3, characterized in that, Construct a first undetermined association dataset and a second undetermined association dataset for each target curve segment, including: Define the first and second associated time intervals for each target curve segment; Generate the first fluctuation characteristics of each second monitoring data change curve in the first associated time interval of each target curve segment, the second fluctuation characteristics in the second associated time interval, and the third fluctuation characteristics of each first monitoring data change curve in the second associated time interval of each target curve segment; Among them, the volatility characteristics include the degree of volatility and the volatility trend; Determine whether several first, second, and third fluctuation features satisfy the fluctuation correlation rule. If they satisfy the fluctuation correlation rule, calculate the corresponding initial correlation coefficient. The first undetermined correlation dataset and the second undetermined correlation dataset for each target curve segment are constructed using several second monitoring data that satisfy the fluctuation correlation rules and several first monitoring data.
5. The coal yard internal and external pollution collaborative monitoring and intelligent control system as described in claim 3, characterized in that, The second monitoring data in the first undetermined associated dataset of a target curve segment is randomly selected as the first target data; Calculate the number of times the first target data appears in the first undetermined association dataset of other target curve segments of the same target curve, and calculate the first association coefficient of the first target data in combination with the corresponding initial association coefficient; The second monitoring data in the second undetermined associated dataset of a target curve segment is randomly selected as the second target data. Calculate the number of times the second target data appears in the second undetermined association dataset of other target curve segments of the same target curve, and calculate the second association coefficient of the second target data in combination with the corresponding initial association coefficient; The first monitoring data in the second undetermined associated dataset of a target curve segment is randomly selected as the third target data; Calculate the number of times the third target data appears in the second undetermined association dataset of other target curve segments of the same target curve, and calculate the third association coefficient of the third target data in combination with the corresponding initial association coefficient.
6. The coal yard internal and external pollution collaborative monitoring and intelligent control system as described in claim 3, characterized in that, The data-association mapping table for each second monitoring data point also includes: A comparative analysis was conducted on the data-correlation mapping tables of different second monitoring data. Based on the analysis results, several correspondences of second monitoring data were determined, and each correspondence of second monitoring data included a corresponding group of second monitoring data and a corresponding group of correlation coefficients. The correlation coefficient difference is calculated based on the correlation coefficient corresponding group in each second monitoring data correspondence. If the correlation coefficient difference is less than the preset difference threshold, the corresponding second monitoring data corresponding group is retained. If the difference in correlation coefficients is not less than the preset difference threshold, then the corresponding group of the second monitoring data will be removed. The data-association mapping table of all second monitoring data is adjusted according to the corresponding group of the retained second monitoring data, and the adjusted data-association mapping table is used to replace the data-association mapping table of the corresponding second monitoring data.
7. The coal yard internal and external pollution collaborative monitoring and intelligent control system as described in claim 6, characterized in that, The comprehensive impact coefficient of each second monitoring data point was determined based on the data-association mapping table, and several pollution sources were identified, including: Calculate the first number of the second monitoring data in the first association mapping table, the second number of the second monitoring data in the second association mapping table, and the third number of the first monitoring data in the second association mapping table for each second monitoring data; The first influence coefficient of the corresponding second monitoring data is calculated based on the first number, the weight coefficient of the corresponding second monitoring data, and the corresponding first correlation coefficient. The second influence coefficient of the corresponding second monitoring data is calculated based on the second number, the weight coefficient of the corresponding second monitoring data, and the corresponding second correlation coefficient. The third influence coefficient of the corresponding second monitoring data is calculated based on the third number, the weight coefficient of the corresponding first monitoring data, and the corresponding third correlation coefficient. A comprehensive impact coefficient for the corresponding second monitoring data is generated based on the first impact coefficient, the second impact coefficient, and the third impact coefficient. The second monitoring data with a comprehensive impact coefficient greater than the preset impact coefficient threshold is set as the pollution source.
8. The coal yard internal and external pollution collaborative monitoring and intelligent control system as described in claim 7, characterized in that, A pollution pattern prediction model is constructed based on several pollution sources and their corresponding data-relationship mapping tables, including: Several historical meteorological parameters that influence the diffusion characteristics of the first historical monitoring data were selected, including diffusion trend, diffusion rate, and diffusion path. Several meteorological scenarios are generated by randomly combining several selected historical meteorological parameters and then generating several combined historical meteorological parameters. Construct simulation models for different meteorological scenarios; By using a simulation model, combined with multiple historical second monitoring data of each pollution source in the pollution source sequence and the corresponding data-association mapping table, simulated first detection data and corresponding simulated diffusion data of each historical second monitoring data of different pollution sources under different meteorological scenarios are obtained. Historical second monitoring data of different pollution sources under different meteorological scenarios are used as training input data, and the corresponding simulated first detection data and the corresponding simulated diffusion data are used as training output data to train a neural network and obtain a pollution pattern prediction model.
9. The coal yard internal and external pollution collaborative monitoring and intelligent control system as described in claim 8, characterized in that, Pollution parameters for future periods are determined based on pollution pattern prediction models and several secondary monitoring data, including: Several predicted second monitoring data points for future periods are generated based on several second monitoring data points and current demand instructions; Generate predicted meteorological data for future periods, and perform similarity analysis between the predicted meteorological data and historical meteorological data of the meteorological scene to obtain the similarity score; The meteorological scene with the highest similarity and several predicted second monitoring data are input into the pollution pattern prediction model to generate several predicted first monitoring data for future periods and the predicted diffusion data corresponding to the predicted first monitoring data. Several pollution assessment indicators are pre-set; Based on several pollution assessment indicators, a pollution assessment is performed on each predicted first monitoring data and the corresponding predicted diffusion data to obtain a pollution assessment value for each predicted first monitoring data. Pre-set pollution assessment thresholds; If the pollution assessment value is greater than the pollution assessment value threshold, then the corresponding first monitoring data for prediction is set as the predicted pollution parameter for the future period.
10. The coal yard internal and external pollution collaborative monitoring and intelligent control system as described in claim 9, characterized in that, The optimal control strategy is generated based on the predicted pollution parameters, including: Based on the full data-association mapping table, the pollution sources affecting each predicted pollution parameter are traced. By combining the pollution assessment values of the predicted pollution parameters, the corresponding predicted diffusion data, and the traced pollution sources, an initial set of control strategies is generated. The initial set of control strategies includes initial control strategies for different pollution sources. A feasibility assessment is conducted on each initial control strategy in the initial control strategy set. Based on the feasibility assessment results, several initial control strategies with higher feasibility are selected from the initial control strategy set to form a feasible control strategy set. For each initial control strategy in the set of feasible control strategies, the effect is simulated and predicted. Based on the effect simulation and prediction results, the optimal control strategy is determined.