Environmental Air Pollution Monitoring Method and System Based on Sensor Technology

Abstract

The present invention relates to the technical field of air quality monitoring, and specifically relates to an environmental air pollution monitoring method and system based on sensor technology. The method includes: obtaining air quality data at a monitoring point at an initial sampling frequency and constructing an air quality data curve at the monitoring point; determining a suspected polluted gas emission stage, and taking the monitoring point corresponding to the first abnormal data segment in the suspected polluted gas emission stage as the nearest neighbor monitoring point of the polluted gas emission source; determining the consistency between the environmental impact in the suspected polluted gas emission stage and the change law of the actual air quality data; in the case where the change law consistency is greater than a first threshold, determining the suspected polluted gas emission stage as an actual polluted gas emission stage; determining the optimized sampling frequency of each monitoring point in the actual polluted gas emission stage, and collecting the corrected air quality data of each monitoring point by using the optimized sampling frequency. The present invention improves the monitoring efficiency, accuracy and reliability.

Description

Technical Field

[0001] The present invention relates to the technical field of air quality monitoring, and particularly to an environmental air pollution monitoring method and system based on sensor technology. Background Art

[0002] Ambient air quality refers to the proportion of various gas components in the air and the state of the particulate matter and other pollutants contained therein. With the acceleration of the industrialization and urbanization processes, ambient air quality has become a global focus of attention. Due to the complex and variable ambient air conditions, affected by factors such as the differences in the distribution and emission intensity of pollution sources and the complex interaction of meteorological conditions, it shows a high degree of dynamics and heterogeneity at different time and space scales.

[0003] In some scenarios, sensors are often used to continuously monitor the ambient air quality at a single fixed sampling frequency. If the sampling frequency is too high, a large amount of redundant data will be generated, increasing the burden of data storage, transmission, and processing, as well as the energy consumption and operation and maintenance costs of the equipment. If the sampling frequency is too low, important information may be missed, and the rapid changes and short-term fluctuation characteristics of air quality cannot be accurately captured, resulting in insufficient representativeness and low spatio-temporal resolution of the monitored ambient air quality data, making it difficult to meet the business requirements of refined environmental management and air quality forecasting and early warning. Therefore, the monitoring efficiency, accuracy, and reliability of using sensors to monitor the ambient air quality at a single fixed sampling frequency are relatively low. Summary of the Invention

[0004] In order to solve the technical problems of relatively low monitoring efficiency, accuracy, and reliability in monitoring the ambient air quality, the purpose of the present invention is to provide an environmental air pollution monitoring method and system based on sensor technology, and the specific technical solutions adopted are as follows:

[0005] First aspect, an embodiment of the present invention provides an ambient air pollution monitoring method based on sensor technology, including: obtaining air quality data at a monitoring point with an initial sampling frequency and constructing an air quality data curve at the monitoring point; determining a suspected polluted gas emission stage according to the air quality data curves of each monitoring point, and taking the monitoring point corresponding to the first abnormal data segment in the suspected polluted gas emission stage as the nearest neighbor monitoring point of the polluted gas emission source; determining the consistency between the environmental impact of the suspected polluted gas emission stage and the change law of the actual air quality data according to the minimum included angle between the vector pointing from the nearest neighbor monitoring point to other monitoring points and the wind direction, the distance between other monitoring points and the nearest neighbor monitoring point, the current wind speed, and the abnormal data segments of each monitoring point and the abnormal data segment of the nearest neighbor monitoring point in the suspected polluted gas emission stage; determining the suspected polluted gas emission stage as the actual polluted gas emission stage when the change law consistency is greater than a first threshold; determining the optimized sampling frequency of each monitoring point in the actual polluted gas emission stage according to the air quality data of each abnormal data segment in the actual polluted gas emission stage and the initial sampling frequency, and collecting the corrected air quality data of each monitoring point using the optimized sampling frequency.

[0006] Optionally, determining the suspected polluted gas emission stage according to the air quality data curves of each monitoring point includes: taking the air quality data less than the passing value as abnormal data, and each abnormal data constitutes multiple abnormal data segments of the air quality data curve; screening all target abnormal data segments with slopes less than a second threshold in the abnormal data segments, and determining the area of the closed figure formed by the abnormal data segment and the straight line where the passing value is located; determining the environmental pollution degree of the target abnormal data segment according to the area, the slope of the target abnormal data segment, the time length of the target abnormal data segment, and the sum value of the time lengths of all the target abnormal data segments; taking the abnormal data segments of multiple monitoring points where the air quality data curves of different monitoring points coincide on the time axis as the suspected polluted gas emission stage, and taking the monitoring point corresponding to the first abnormal data segment in the suspected polluted gas emission stage as the nearest neighbor monitoring point of the polluted gas emission source.

[0007] Optionally, determining the environmental pollution degree of the target abnormal data segment according to the area, the slope of the target abnormal data segment, the time length of the target abnormal data segment, and the sum value of the time lengths of all the target abnormal data segments includes: calculating a first ratio between the time length of the target abnormal data segment and the sum value of the time lengths of all the target abnormal data segments; calculating a first product between the absolute value of the slope of the target abnormal data segment and the first ratio, and superimposing each first product to obtain a first superimposed value; determining the second product between the area and the first superimposed value as the environmental pollution degree of the target abnormal data segment.

[0008] Optionally, based on the minimum angle between the vector from the nearest neighbor monitoring point to other monitoring points and the wind direction, the distance between other monitoring points and the nearest neighbor monitoring point, the current wind speed, and the abnormal data segments of each monitoring point and the abnormal data segment of the nearest neighbor monitoring point during the suspected polluted gas emission stage, determining the consistency between the environmental impact during the suspected polluted gas emission stage and the variation law of the actual air quality data includes: determining the environmental impact factors of other monitoring points based on the minimum angle between the vector from the nearest neighbor monitoring point to other monitoring points and the wind direction, the distance between other monitoring points and the nearest neighbor monitoring point, and the current wind speed; determining the Pearson correlation coefficient between the abnormal data segments of each monitoring point and the abnormal data segment of the nearest neighbor monitoring point during the suspected polluted gas emission stage; determining the similarity of the pollution change rhythm between each monitoring point and the nearest neighbor monitoring point during the suspected polluted gas emission stage based on the environmental pollution degree of the abnormal data segments of each monitoring point and the abnormal data segment of the nearest neighbor monitoring point, the Pearson correlation coefficient, the start time of the abnormal data segments of each monitoring point during the suspected polluted gas emission stage, and the start time of the abnormal data segment of the nearest neighbor monitoring point; and determining the consistency between the environmental impact during the suspected polluted gas emission stage and the variation law of the actual air quality data based on the similarity of the pollution change rhythm of each monitoring point and the environmental impact factors during the suspected polluted gas emission stage.

[0009] Optionally, determining the environmental impact factors of other monitoring points based on the minimum angle between the vector from the nearest neighbor monitoring point to other monitoring points and the wind direction, the distance between other monitoring points and the nearest neighbor monitoring point, and the current wind speed includes: calculating a second ratio between a first predetermined value and the minimum angle, and a third ratio between the current wind speed and the distance; and determining a third product between the second ratio and the third ratio as the environmental impact factor of other monitoring points.

[0010] Optionally, determining the similarity of the pollution change rhythm between each monitoring point and the nearest neighbor monitoring point during the suspected polluted gas emission stage based on the environmental pollution degree of the abnormal data segments of each monitoring point and the abnormal data segment of the nearest neighbor monitoring point, the Pearson correlation coefficient, the start time of the abnormal data segments of each monitoring point during the suspected polluted gas emission stage, and the start time of the abnormal data segment of the nearest neighbor monitoring point includes:

[0011] Calculate the first sum value between the Pearson correlation coefficient and the second predetermined value, the first difference between the environmental pollution degree of the abnormal data segment of each monitoring point within the suspected polluted gas emission stage and the environmental pollution degree of the abnormal data segment of the nearest neighbor monitoring point, and the second difference between the start time of the abnormal data segment of each monitoring point within the suspected polluted gas emission stage and the start time of the abnormal data segment of the nearest neighbor monitoring point; calculate the reciprocal of the second sum value between the first difference and the second difference; determine that the fourth product between the first sum value and the reciprocal of the second sum value is the pollution change rhythm convergence between each monitoring point and the nearest neighbor monitoring point within the suspected polluted gas emission stage.

[0012] Optionally, determining the consistency of the environmental impact of the suspected polluted gas emission stage with the change law of the actual air quality data according to the pollution change rhythm convergence of each monitoring point within the suspected polluted gas emission stage and the environmental impact factor includes: determining the first average value of the pollution change rhythm convergence of each monitoring point within the suspected polluted gas emission stage, and the second average value of the environmental impact factor of each monitoring point within the suspected polluted gas emission stage; calculating the third difference between the pollution change rhythm convergence of adjacent monitoring points, and the fourth difference between the environmental impact factors of adjacent monitoring points; calculating the fourth ratio between the third difference and the first average value, and the fifth ratio between the fourth difference and the second average value; calculating the sixth ratio between the fourth ratio and the fifth ratio, and the absolute value of the fifth difference between the third predetermined value and the sixth ratio; superimposing the absolute values of each fifth difference to obtain the second superimposed value; performing inverse proportional normalization processing on the second superimposed value to obtain the change law consistency.

[0013] Optionally, determining the optimized sampling frequency of each monitoring point in the actual polluted gas emission stage according to the air quality data of each abnormal data segment in the actual polluted gas emission stage and the initial sampling frequency includes: calculating the standard deviation of the air quality data of each abnormal data segment in the actual polluted gas emission stage, and performing normalization processing on the standard deviation to obtain a normalized value; calculating the second sum value between the third predetermined value and the normalized value; determining that the fifth product between the initial sampling frequency and the second sum value is the optimized sampling frequency of the monitoring point in the actual polluted gas emission stage.

[0014] Optionally, after collecting the corrected air quality data of each monitoring point using the optimized sampling frequency, the method further includes: performing anomaly monitoring on the corrected air quality data using the local outlier factor algorithm.

[0015] In a second aspect, an embodiment of the present invention provides an environmental air pollution monitoring system based on sensor technology, including: a processor and a memory; wherein, the memory is used to store a computer program that can run on the processor; the processor is used to execute the program stored on the memory to implement the steps of the environmental air pollution monitoring method based on sensor technology mentioned in the first aspect.

[0016] The present invention has the following beneficial effects: First, obtain the air quality data at the monitoring point at the initial sampling frequency and construct the air quality data curve at the monitoring point; then determine the suspected polluted gas emission stage according to the air quality data curves of each monitoring point, and use the monitoring point corresponding to the first abnormal data segment in the suspected polluted gas emission stage as the nearest neighbor monitoring point of the polluted gas emission source; and according to the minimum included angle between the vector from the nearest neighbor monitoring point to other monitoring points and the wind direction, the distance between other monitoring points and the nearest neighbor monitoring point, the current wind speed, and the abnormal data segments of each monitoring point and the abnormal data segment of the nearest neighbor monitoring point in the suspected polluted gas emission stage, determine the consistency between the environmental impact in the suspected polluted gas emission stage and the change law of the actual air quality data; when the change law consistency is greater than the first threshold, determine the suspected polluted gas emission stage as the actual polluted gas emission stage; secondly, determine the optimized sampling frequency of each monitoring point in the actual polluted gas emission stage according to the air quality data of each abnormal data segment in the actual polluted gas emission stage and the initial sampling frequency, and finally use the optimized sampling frequency to collect the corrected air quality data of each monitoring point.

[0017] In this way, the embodiment of the present invention can screen abnormal data segments and determine the suspected polluted gas emission stage, and then analyze the correlation change between the environmental impact in the suspected polluted gas emission stage and the actual air quality data according to the influence of distance and wind direction on the polluted gas emission of the polluted gas emission source in the actual scenario, can accurately identify the actual polluted gas emission stage in the air quality, and combine the air quality data and the initial sampling frequency in the actual polluted gas emission stage to re-determine the optimized sampling frequency in the actual polluted gas emission stage, so that the optimized sampling frequency can adapt to the actual scenario of the actual polluted gas emission stage. When sampling the air quality data at the optimized sampling frequency, the monitoring efficiency, accuracy and reliability of monitoring the environmental air quality are improved. Description of the Drawings

[0018] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to these drawings without creative efforts.

[0019] Figure 1 Flowchart of an environmental air pollution monitoring method based on sensor technology provided by an embodiment of the present invention;

[0020] Figure 2 Schematic diagram of the comparison between the air quality data of the monitoring point and the preset passing value provided by an embodiment of the present invention;

[0021] Figure 3 Schematic structural diagram of an environmental air pollution monitoring system based on sensor technology provided by another embodiment of the present invention. Detailed implementation manners

[0022] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, details the specific implementation manners, structures, features and effects of an environmental air pollution monitoring method based on sensor technology proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0024] The following specifically describes the specific solution of an environmental air pollution monitoring method based on sensor technology provided by the present invention in combination with the accompanying drawings.

[0025] Embodiment 1:

[0026] Please refer to Figure 1 , which shows the flowchart of an environmental air pollution monitoring method based on sensor technology provided by an embodiment of the present invention, including:

[0027] S101, obtain the air quality data at the monitoring point at the initial sampling frequency and construct the air quality data curve at the monitoring point.

[0028] Specifically, in the embodiments of the present invention, a number of monitoring points are set in the monitoring area where air quality monitoring is required. According to the characteristics of the monitoring area, the main air pollutants in the monitoring area are identified, including but not limited to PM2.5, PM10, sulfur dioxide, nitrogen dioxide, etc. The air quality status is evaluated through the main air pollutants in the air, which is used as the air quality data for each monitoring point at each monitoring moment. In order to ensure the effectiveness and comparability of the data, the numerical range of the air quality data is determined within 0-100. Among them, 0 points represent extremely poor air quality, while 100 points indicate excellent air quality. As the air quality gradually improves and the pollutant concentration decreases, the corresponding score value will gradually increase. The instruments for automatic monitoring in the embodiments of the present invention perform continuous automatic monitoring to obtain monitoring results, analyze them, and obtain relevant data. Therefore, a very large amount of data is generated during the process of monitoring air quality.

[0029] Further, in the embodiments of the present invention, a reasonable initial sampling frequency is preset according to the air quality monitoring requirements and the probability of abnormal situations occurring. Monitor and obtain the air quality data at each monitoring moment of each monitoring point, transmit the air quality data to the cloud platform for data analysis, construct the air quality data curve corresponding to each monitoring point, and perform noise preprocessing on the collected air quality data, such as using a filtering algorithm to remove high-frequency noise or outliers, so as to obtain more accurate air quality data.

[0030] S102, determine the suspected polluted gas emission stage according to the air quality data curves of each monitoring point, and use the monitoring point corresponding to the first abnormal data segment in the suspected polluted gas emission stage as the nearest neighbor monitoring point of the polluted gas emission source.

[0031] Specifically, the embodiments of the present invention can preset the air quality data and passing value of the current monitoring area as the basic reference for data screening according to the urban ambient air quality standard and the statistical analysis of past monitoring data. According to the distribution of the air quality data curves of each monitoring point, abnormal data segments are screened. Among them, the passing value can be determined according to the actual situation, and the value in the embodiments of the present invention is 70. Exemplarily, as Figure 2 shown, Figure 2 is a schematic diagram of the comparison between the air quality data of a monitoring point provided by an embodiment of the present invention and the preset passing value. For the air quality data of any monitoring point at a certain monitoring moment, when it is less than the passing value corresponding to the passing line, it is considered that the current monitoring point enters the abnormal stage at this time.

[0032] Further, as an optional embodiment of the present invention, determining the suspected polluted gas emission stage according to the air quality data curves of each monitoring point includes: taking the air quality data less than the passing value as abnormal data, and each abnormal data forms multiple abnormal data segments of the air quality data curve; screening all target abnormal data segments with slopes less than the second threshold in the abnormal data segments, and determining the area of the closed figure formed by the abnormal data segment and the straight line where the passing value is located; determining the environmental pollution degree of the target abnormal data segment according to the area, the slope of the target abnormal data segment, the time length of the target abnormal data segment, and the sum value of the time lengths of all the target abnormal data segments; taking the abnormal data segments of multiple monitoring points where the air quality data curves of different monitoring points coincide on the time axis as the suspected polluted gas emission stage, and taking the monitoring point corresponding to the first abnormal data segment in the suspected polluted gas emission stage as the nearest neighbor monitoring point of the polluted gas emission source.

[0033] Specifically, on the air quality data curve of each monitoring point, all air quality data less than the passing value are taken as abnormal data, and several abnormal data segments of the air quality data curve of each monitoring point are obtained. When there are abnormal data segments, these abnormal data segments may imply special pollution emission events, meteorological anomalies, or potential failures of monitoring equipment, etc., and further analysis is required. Among them, for each abnormal data segment of each monitoring point, when the abnormal duration is longer and the amplitude below the passing value is larger, it is considered that the air quality is worse, that is, the pollution degree of the environmental data of this abnormal data segment is larger. Among them, the second threshold can be determined according to the actual situation, and the value in the embodiment of the present invention is 0.

[0034] Further, as an optional embodiment of the present invention, determining the environmental pollution degree of the target abnormal data segment according to the area, the slope of the target abnormal data segment, the time length of the target abnormal data segment, and the sum value of the time lengths of all the target abnormal data segments includes: calculating the first ratio between the time length of the target abnormal data segment and the sum value of the time lengths of all the target abnormal data segments; calculating the first product between the absolute value of the slope of the target abnormal data segment and the first ratio, and superimposing each first product to obtain the first superimposed value; determining the second product between the area and the first superimposed value as the environmental pollution degree of the target abnormal data segment.

[0035] Specifically, the embodiment of the present invention specifically uses the following formula to calculate the environmental pollution degree of the target abnormal data segment:

[0036]

[0037] In the above formula, represents the th The environmental pollution degree of a target abnormal data segment. Indicates the th area of the closed figure formed by the passing line corresponding to the passing value of the target abnormal data segment of the th monitoring point. Among all the abnormal data segments of the th monitoring point, all line segments with a slope less than zero are selected as target abnormal data segments. Indicates the slope of the th abnormal data segment with a slope less than zero. Indicates the time length of the th abnormal data segment with a slope less than zero. Indicates the sum of the time lengths of all abnormal data segments with a slope less than zero at the

[0038] th monitoring point. Among them, when the duration of the abnormal data segment is longer and its difference from the passing value is greater, it indicates that the air quality data reflected by the current abnormal data segment is lower, that is, the air quality at the current monitoring point is worse. That is, the area of the closed figure formed by the abnormal data segment and the passing value is larger. The greater the environmental pollution degree of the abnormal data segment, indicates the overall decline amplitude of all the air quality data decline segments in the abnormal data segment. Using the duration of each decline segment as the weight of its slope, when the duration is longer and the absolute value of the slope is larger, it indicates that the decline trend is more significant, that is, the air quality data declines more rapidly. That is, when the

[0039] Furthermore, within the same monitoring area, due to the fluidity and diffusibility of air, under normal circumstances, the air quality data reflected at each monitoring point should be correlated in time series and have a relatively consistent change trend. Therefore, on the air quality data curves constructed at all monitoring points, theoretically, abnormal data segments should occur at similar time points, and their characteristics such as duration and data change amplitude should also show a certain correlation. By synchronously analyzing the air quality data curves of each monitoring point, abnormal data segments can be identified more accurately, and then the sampling frequency for abnormal situations can be increased. In the same monitoring area, there are multiple monitoring points. When there is a pollution gas emission point at a certain monitoring point in the monitoring area, the air quality data at the monitoring points around the pollution gas emission point will decrease significantly at that monitoring moment. Moreover, the pollution gas gradually diffuses from this monitoring point to the surrounding areas, successively affecting the air quality data of the surrounding monitoring points. And there is a time delay in the time series of the air quality data of all monitoring points in the diffusion direction from the pollution gas emission point. As the distance increases, the starting time of the abnormal data segment of the abnormal air quality data is later, and the environmental pollution degree of the abnormal data segment of the corresponding monitoring point gradually decreases with the distance.

[0040] Furthermore, longitudinally in terms of time series, when the starting time and ending time of the abnormal data segments corresponding to the remaining monitoring points at different monitoring points usually do not completely coincide, the abnormal data segments of several monitoring points where the air quality data curves of all different monitoring points overlap on the time axis are recorded as a suspected pollution gas emission stage. Ensure that the suspected pollution gas emission stage includes all abnormal data segments of the affected monitoring points. The suspected pollution gas emission stage may represent an actual air anomaly, or it may be caused by equipment anomalies or noise data at a certain monitoring point. For each suspected pollution gas emission stage, the monitoring point corresponding to the first abnormal data segment of the starting time is considered the nearest neighbor monitoring point of the pollution gas emission source. Therefore, based on the fluctuation correlation between the abnormal data segments of the remaining monitoring points and the first abnormal data segment, it can be verified whether there is a pollution gas emission situation around a certain monitoring point.

[0041] S103. Determine the consistency between the environmental impact of the suspected pollution gas emission stage and the change law of the actual air quality data according to the minimum angle between the vector from the nearest neighbor monitoring point to other monitoring points and the wind direction, the distance between other monitoring points and the nearest neighbor monitoring point, the current wind speed, and the abnormal data segments of each monitoring point and the abnormal data segment of the nearest neighbor monitoring point within the suspected pollution gas emission stage.

[0042] Specifically, in the embodiments of the present invention, by obtaining the current wind direction and wind speed, if there is pollution gas emission, the greater the wind speed, the more rapid the diffusion of the pollution gas. In the direction of the current wind direction, the environmental impact factors affected by pollution at each monitoring point are determined. The environmental impact factor represents the possible degree of pollution of the nearest neighbor monitoring point of the monitoring point by the pollution gas emission source. Therefore, the consistency between the environmental impact in the suspected pollution gas emission stage and the change law of the actual air quality data is determined through the environmental parameters of the current actual scenario.

[0043] Further, as an optional embodiment of the present invention, determining the consistency between the environmental impact in the suspected pollution gas emission stage and the change law of the actual air quality data based on the minimum angle between the vector from the nearest neighbor monitoring point to other monitoring points and the wind direction, the distance between other monitoring points and the nearest neighbor monitoring point, the current wind speed, and the abnormal data segments of each monitoring point and the abnormal data segment of the nearest neighbor monitoring point in the suspected pollution gas emission stage includes: determining the environmental impact factor of other monitoring points based on the minimum angle between the vector from the nearest neighbor monitoring point to other monitoring points and the wind direction, the distance between other monitoring points and the nearest neighbor monitoring point, and the current wind speed; determining the Pearson correlation coefficient between the abnormal data segments of each monitoring point and the abnormal data segment of the nearest neighbor monitoring point in the suspected pollution gas emission stage; determining the similarity of the pollution change rhythm between each monitoring point and the nearest neighbor monitoring point in the suspected pollution gas emission stage based on the environmental pollution degree of the abnormal data segment of each monitoring point and the abnormal data segment of the nearest neighbor monitoring point, the Pearson correlation coefficient, the start time of the abnormal data segment of each monitoring point, and the start time of the abnormal data segment of the nearest neighbor monitoring point in the suspected pollution gas emission stage; and determining the consistency between the environmental impact in the suspected pollution gas emission stage and the change law of the actual air quality data based on the similarity of the pollution change rhythm of each monitoring point and the environmental impact factor in the suspected pollution gas emission stage.

[0044] Specifically, when determining the environmental impact factor, first calculate the second ratio between the first predetermined value and the minimum angle, and the third ratio between the current wind speed and the distance; then determine the third product between the second ratio and the third ratio as the environmental impact factor of other monitoring points.

[0045] Among them, in the embodiments of the present invention, the first predetermined value is taken as . The embodiments of the present invention specifically use the following formula to calculate the environmental impact factor of other monitoring points:

[0046]

[0047] In the above formula, represents the environmental impact factor of the th monitoring point. Indicates the minimum angle between the vector from the nearest neighbor monitoring point of the polluted gas emission source pointing to the th monitoring point and the wind direction. Indicates the distance between the th monitoring point and the nearest neighbor monitoring point of the polluted gas emission source. Indicates the current wind speed.

[0048] For the above formula, when the minimum angle between the vector from the nearest neighbor monitoring point of the polluted gas emission source pointing to the th monitoring point and the wind direction is larger, it is more contrary to the wind direction, that is, it is less likely to spread to this monitoring point, that is is larger, then this monitoring point is more likely to be affected by the diffusion of polluted gas. And when the wind speed is larger and the distance is closer, the polluted gas affects this monitoring point faster, that is, its environmental impact factor is larger.

[0049] Furthermore, during a suspected polluted gas emission stage, when the time interval between the start time of the abnormal data segment of a certain monitoring point and the start time of the nearest neighbor monitoring point of the polluted gas emission source is smaller, it can indicate that the geographical location of this monitoring point is closer to the emission point. And based on the diffusibility of the polluted gas along the wind direction, when it conforms to the actual geographical location distribution, it indicates that the authenticity of the current suspected polluted gas emission stage is higher. Therefore, in the embodiments of the present invention, the fluctuation of the actual air quality data is analyzed, and the environmental impact factors of the above-mentioned monitoring points are compared. When the differences in their changes are correlated, it can be verified that there is an emission of polluted gas at this time, resulting in the appearance of the current suspected polluted gas emission stage.

[0050] Furthermore, in the embodiments of the present invention, in combination with the presentation of the actual air quality data, according to the fluctuation of all abnormal data segments except the first one and the first abnormal data segment during the suspected polluted gas emission stage, the pollution change rhythm convergence of all monitoring points in the suspected polluted gas emission stage and the nearest neighbor monitoring point of the polluted gas emission source is determined.

[0051] Further, as an optional embodiment of the present invention, determining the pollution change rhythm convergence between each monitoring point and the nearest neighbor monitoring point in the suspected polluted gas emission stage based on the environmental pollution degree of the abnormal data segment at each monitoring point in the suspected polluted gas emission stage, the environmental pollution degree of the abnormal data segment of the nearest neighbor monitoring point, the Pearson correlation coefficient, the start time of the abnormal data segment at each monitoring point in the suspected polluted gas emission stage, and the start time of the abnormal data segment of the nearest neighbor monitoring point includes: calculating the first sum value between the Pearson correlation coefficient and the second predetermined value, the first difference value between the environmental pollution degree of the abnormal data segment at each monitoring point in the suspected polluted gas emission stage and the environmental pollution degree of the abnormal data segment of the nearest neighbor monitoring point, and the second difference value between the start time of the abnormal data segment at each monitoring point in the suspected polluted gas emission stage and the start time of the abnormal data segment of the nearest neighbor monitoring point; calculating the reciprocal of the second sum value between the first difference value and the second difference value; determining the fourth product between the first sum value and the reciprocal of the second sum value as the pollution change rhythm convergence between each monitoring point and the nearest neighbor monitoring point in the suspected polluted gas emission stage.

[0052] Specifically, the second predetermined value can be taken as 2. The embodiments of the present invention specifically use the following formula to calculate the pollution change rhythm convergence between each monitoring point and the nearest neighbor monitoring point in the suspected polluted gas emission stage:

[0053]

[0054] In the above formula, represents the pollution change rhythm convergence between the monitoring point corresponding to the th abnormal data segment and the nearest neighbor monitoring point of the polluted gas emission source. represents the th Pearson correlation coefficient between the abnormal data segment of the th abnormal data segment and the abnormal data segment of the nearest neighbor monitoring point of the polluted gas emission source. represents the first difference value between the environmental pollution degree of the th abnormal data segment and the environmental pollution degree of the abnormal data segment of the nearest neighbor monitoring point of the polluted gas emission source. represents the second difference value between the start time of the th abnormal data segment and the start time of the abnormal data segment of the nearest neighbor monitoring point of the polluted gas emission source. It should be noted that to ensure the significance of the calculation results, in the embodiments of the present invention, when performing fractional operations, in the case of a denominator of 0, a tuning factor greater than 0 needs to be added to the denominator to prevent the denominator from being 0. The value of the tuning factor is set by the implementer according to the actual situation, and this application does not make special restrictions.

[0055] Among them, in the stage of suspected polluted gas emission, according to the difference in the environmental pollution degree between the abnormal data segment of the nearest neighbor monitoring point of the polluted gas emission source and each other abnormal data segment, and the time interval of the start time between the abnormal data segments, a characteristic value is constructed. The earlier the monitoring point is diffused, the larger the value of this characteristic value. With the increase of distance and the influence of wind, the characteristic values of the peripheral monitoring points are gradually decreasing values. Further, the embodiments of the present invention use the Pearson correlation coefficient to measure. The Pearson correlation coefficient is an index to measure the degree of linear correlation between two variables, and its value range is [-1, 1]. The closer the value is to 1, the more similar the fluctuations of the two curves are. The closer the value is to -1, the more opposite the fluctuations are. Close to 0 indicates no linear correlation. Therefore Adjust it to the positive range to avoid the formula being zero and not affecting the relative similarity size reflected by the value. For the monitoring points where the polluted gas gradually diffuses outward, with the increase of distance, the Pearson correlation coefficient of the corresponding abnormal data segment will be smaller, and the environmental pollution degree and the time interval of the start time of the abnormal data segment will be larger. Therefore, when the actual abnormal gas diffusion occurs, There will be a numerical change that gradually decreases along the diffusion direction.

[0056] Further, when the actual data change is correlated with the change trend of the environmental impact factor of the monitoring point , that is, when their relative change rules are consistent, it can be reasonably explained that the current stage of suspected polluted gas emission is the actual situation.

[0057] Further, as an optional embodiment of the present invention, according to the pollution change rhythm convergence and environmental impact factors of each monitoring point in the stage of suspected polluted gas emission, determining the consistency of the change rule between the environmental impact of the stage of suspected polluted gas emission and the actual air quality data includes: determining the first average value of the pollution change rhythm convergence of each monitoring point in the stage of suspected polluted gas emission, and the second average value of the environmental impact factors of each monitoring point in the stage of suspected polluted gas emission; calculating the third difference between the pollution change rhythm convergence of adjacent monitoring points, and the fourth difference between the environmental impact factors of adjacent monitoring points; calculating the fourth ratio between the third difference and the first average value, and the fifth ratio between the fourth difference and the second average value; calculating the sixth ratio between the fourth ratio and the fifth ratio, and the absolute value of the fifth difference between the third predetermined value and the sixth ratio; superimposing the absolute values of each fifth difference to obtain the second superimposed value; performing inverse proportional normalization processing on the second superimposed value to obtain the change rule consistency.

[0058] Specifically, the third predetermined value can be taken as 1. The embodiments of the present invention specifically use the following formula to calculate the change rule consistency:

[0059]

[0060] In the above formula, represents the consistency of the variation law between the environmental impact during the suspected polluted gas emission stage and the actual air quality data. represents the number of abnormal data segments during the suspected polluted gas emission stage. represents the th similarity of the pollution change rhythm between the monitoring point corresponding to the abnormal data segment and the nearest neighbor monitoring point of the polluted gas emission source. respectively represent the th similarity of the pollution change rhythm between the monitoring point corresponding to the abnormal data segment and the nearest neighbor monitoring point of the polluted gas emission source. represents the th environmental impact factor of the monitoring point corresponding to the abnormal data segment. represents the th environmental impact factor of the monitoring point corresponding to the abnormal data segment. represents the first average value of the similarity of the pollution change rhythm of each monitoring point during the suspected polluted gas emission stage. represents the second average value of the environmental impact factors of each monitoring point during the suspected polluted gas emission stage. (-) represents the inverse proportional normalization function, which is used to perform inverse proportional normalization on .

[0061] Among them, when the difference between of two adjacent abnormal data segments is closer to the difference of value, the higher the consistency of the variation law. And considering the individuality of the variation ranges of the two characteristic values, they are respectively divided by their mean values and then the ratio is calculated to obtain a more reasonable presentation of the consistency of the variation law.

[0062] S104, when the consistency of the variation law is greater than the first threshold, determine that the suspected polluted gas emission stage is the actual polluted gas emission stage.

[0063] Specifically, the first threshold can be determined according to the actual situation, and in the embodiment of the present invention, it is taken as 0.7. For any suspected polluted gas emission stage, when the consistency of the variation law between the environmental impact factor of the monitoring point and the actual air quality data is greater than 0.7, it is considered that an actual air quality abnormality occurs in the current suspected polluted gas emission stage, that is, the actual polluted gas emission stage, otherwise it may be caused by equipment failure or noise data.

[0064] S105, according to the air quality data of each abnormal data segment during the actual polluted gas emission stage and the initial sampling frequency, determine the optimized sampling frequency of each monitoring point in the actual polluted gas emission stage, and use the optimized sampling frequency to collect the corrected air quality data of each monitoring point.

[0065] Specifically, for actual air quality anomalies, when it indicates that the air quality at all monitoring points during the corresponding suspected pollutant gas emission stage has reached a situation that may require key attention, the sampling frequency needs to be increased, which helps to more detailedly record key information such as the subtle changes, change rates, and fluctuation amplitudes of pollutant concentrations during each periodic fluctuation process.

[0066] Furthermore, as an optional embodiment of the present invention, determining the optimized sampling frequency of each monitoring point during the actual pollutant gas emission stage according to the air quality data of each abnormal data segment and the initial sampling frequency during the actual pollutant gas emission stage includes: calculating the standard deviation of the air quality data of each abnormal data segment during the actual pollutant gas emission stage, and performing normalization processing on the standard deviation to obtain a normalized value; calculating the second sum value between the third predetermined value and the normalized value; determining the fifth product between the initial sampling frequency and the second sum value as the optimized sampling frequency of the monitoring point during the actual pollutant gas emission stage.

[0067] Specifically, in the embodiment of the present invention, the third predetermined value can be taken as 1, and the embodiment of the present invention specifically uses the following formula to calculate the optimized sampling frequency of the monitoring point during the actual pollutant gas emission stage:

[0068]

[0069] In the above formula, represents the optimized sampling frequency of the i-th monitoring point during the actual pollutant gas emission stage. represents the preset initial sampling frequency. represents the standard deviation of the air quality data of the abnormal data segment. represents the linear normalization function, which is used to perform normalization processing on .

[0070] Among them, the standard deviation of the air quality data of the abnormal data segment of the corresponding monitoring point is used to adjust the sampling frequency. When the standard deviation is larger, that is, the diffusion of the current pollutant gas is more significant, so the sampling frequency also increases accordingly.

[0071] Furthermore, according to the above steps, the optimal sampling frequency under different pollution levels at different time periods or different monitoring points is determined. During the sampling process, data collection is strictly carried out according to this optimized sampling frequency to ensure that data details can be captured in a timely manner when the air quality changes significantly, while reducing the number of samplings when the air quality is relatively stable, avoiding unnecessary data collection volume. In this way, both accurate monitoring can be achieved, the detection efficiency can be effectively improved, and resource consumption can be reduced at the same time.

[0072] Furthermore, based on the air quality data obtained by optimizing the sampling frequency, existing anomaly detection algorithms, such as the Local Outlier Factor (LOF) algorithm, are used for anomaly monitoring. By analyzing the monitoring data with the LOF algorithm, abnormal air quality data that is significantly different from most data points can be identified. These data points often represent sudden and significant changes in air quality. This process can not only timely detect the deterioration of air quality but also provide strong data support for subsequent early warning, response, and treatment measures. Therefore, by combining the optimized sampling frequency with advanced anomaly detection algorithms, an efficient, accurate, and resource-saving air quality monitoring system is constructed.

[0073] The embodiments of the present invention can screen abnormal data segments and determine the suspected pollution gas emission stage. Furthermore, according to the influence of distance and wind direction on the pollution gas emission of the pollution gas emission source in the actual scenario, the correlation change between the environmental impact in the suspected pollution gas emission stage and the actual air quality data is analyzed. The actual pollution gas emission stage in the air quality can be accurately identified, and the optimized sampling frequency within the actual pollution gas emission stage is re-determined by combining the air quality data within the actual pollution gas emission stage with the initial sampling frequency, so that the optimized sampling frequency can adapt to the actual scenario of the actual pollution gas emission stage. When sampling the air quality data with this optimized sampling frequency, the monitoring efficiency, accuracy, and reliability of the environmental air quality monitoring are improved.

[0074] Embodiment 2:

[0075] Corresponding to the environmental air pollution monitoring method based on sensor technology provided in the above embodiment, based on the same technical concept, the embodiments of the present invention also provide an environmental air pollution monitoring system based on sensor technology. This environmental air pollution monitoring system based on sensor technology is used to execute the above environmental air pollution monitoring method based on sensor technology. Figure 3 The structural schematic diagram of an environmental air pollution monitoring system based on sensor technology provided for another embodiment of the present invention is as Figure 3 shown. The environmental air pollution monitoring system based on sensor technology can vary greatly due to configuration or performance differences. It can include one or more processors 301 and a memory 302. The memory 302 is used to store computer programs that can run on the processor 301. The processor 301 is used to execute the programs stored in the memory 302 to implement each step in the above Figure 1 method embodiments. Among them, the memory 302 can be short-term storage or persistent storage. The application programs stored in the memory 302 can include one or more modules (not shown in the figure), and each module can include a series of computer-executable instructions for the environmental air pollution monitoring system based on sensor technology.

[0076] Further, the processor 301 can be configured to communicate with the memory 302 and execute a series of computer-executable instructions in the memory 302 on the environmental air pollution monitoring system based on sensor technology. The environmental air pollution monitoring system based on sensor technology may further include one or more power supplies 303, one or more wired or wireless network interfaces 304, one or more input / output interfaces 305, and one or more keyboards 306.

[0077] Specifically, in this embodiment, the environmental air pollution monitoring system based on sensor technology includes a processor 301, a communication interface, a memory 302, and a communication bus; wherein, the processor 301, the communication interface, and the memory 302 complete mutual communication through the bus; the memory 302 is used to store computer programs; the processor 301 is used to execute the programs stored on the memory 302 to implement the above Figure 1 each step in the method embodiment above, and has the beneficial effects of the above method embodiment. To avoid repetition, the embodiments of the present invention will not be described in detail here.

[0078] It should be noted that the environmental air pollution monitoring system based on sensor technology provided by the embodiments of the present invention and the environmental air pollution monitoring method based on sensor technology provided by the embodiments of the present invention are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned environmental air pollution monitoring method based on sensor technology and has the same or similar beneficial effects. The repeated parts will not be described again.

[0079] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0080] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

Claims

1. A method for monitoring ambient air pollution based on sensor technology, characterized in that: The ambient air pollution monitoring method based on sensor technology includes: Acquire air quality data at a monitoring point at an initial sampling frequency, and construct an air quality data curve at the monitoring point; Determine the suspected polluted gas emission stage according to the air quality data curve of each of the monitoring points, and use the monitoring point corresponding to the first abnormal data segment of the suspected polluted gas emission stage as the nearest neighbor monitoring point of the polluted gas emission source; According to the minimum angle between the vector pointing from the nearest neighbor monitoring point to other monitoring points and the wind direction, the distance between the other monitoring points and the nearest neighbor monitoring point, the current wind speed, the abnormal data segments of each monitoring point in the suspected polluted gas emission stage and the abnormal data segments of the nearest neighbor monitoring point, the consistency of the change law of the environmental impact of the suspected polluted gas emission stage and the actual air quality data is determined; When the consistency of the change rule is greater than a first threshold, determining the suspected pollutant gas emission stage as the actual pollutant gas emission stage; The optimized sampling frequency of each monitoring point in the actual pollutant gas emission stage is determined according to the air quality data of each abnormal data segment in the actual pollutant gas emission stage and the initial sampling frequency, and the corrected air quality data of each monitoring point is collected using the optimized sampling frequency.

2. The method for monitoring ambient air pollution based on sensor technology according to claim 1, characterized in that: The step of determining the suspected polluted gas emission stage according to the air quality data curve of each monitoring point includes: The air quality data whose air quality data is less than the passing value is regarded as abnormal data, and each of the abnormal data constitutes a plurality of abnormal data segments of the air quality data curve; Screening all target abnormal data segments whose slopes are less than a second threshold value in the abnormal data segments, and determining the area of ​​a closed figure formed by the target abnormal data segments and the straight line where the passing value is located; Determine the environmental pollution degree of the target abnormal data segment according to the area, the slope of the target abnormal data segment, the time length of the target abnormal data segment and the sum of the time lengths of all target abnormal data segments; The abnormal data segments of multiple monitoring points where the air quality data curves of different monitoring points overlap on the time axis are regarded as suspected polluted gas emission stages, and the monitoring point corresponding to the first abnormal data segment of the suspected polluted gas emission stage is regarded as the nearest neighbor monitoring point of the polluted gas emission source.

3. The method for monitoring ambient air pollution based on sensor technology according to claim 2, characterized in that: Determining the environmental pollution degree of the target abnormal data segment according to the area, the slope of the target abnormal data segment, the time length of the target abnormal data segment, and the sum of the time lengths of all target abnormal data segments includes: Calculating a first ratio between the time length of the target abnormal data segment and the sum of the time lengths of all the target abnormal data segments; Calculating a first product between the absolute value of the slope of the target abnormal data segment and the first ratio, and superimposing the first products to obtain a first superimposed value; A second product between the area and the first superposition value is determined as the environmental pollution degree of the target abnormal data segment.

4. The method for monitoring ambient air pollution based on sensor technology according to claim 1, characterized in that: The determination of consistency between the environmental impact of the suspected pollutant gas emission stage and the change rule of the actual air quality data based on the minimum angle between the vector pointing from the nearest neighbor monitoring point to other monitoring points and the wind direction, the distance between the other monitoring points and the nearest neighbor monitoring point, the current wind speed, the abnormal data segments of each monitoring point in the suspected pollutant gas emission stage and the abnormal data segments of the nearest neighbor monitoring point includes: Determine the environmental impact factor of the other monitoring points according to the minimum angle between the vector pointing from the nearest neighbor monitoring point to the other monitoring points and the wind direction, the distance between the other monitoring points and the nearest neighbor monitoring point, and the current wind speed; Determine the Pearson correlation coefficient between the abnormal data segments of each monitoring point in the suspected polluted gas emission stage and the abnormal data segments of the nearest neighboring monitoring point; Determine the similarity of the pollution change rhythm of each monitoring point in the suspected polluted gas emission stage and the nearest neighbor monitoring point according to the environmental pollution degree of the abnormal data segment of each monitoring point in the suspected polluted gas emission stage and the environmental pollution degree of the abnormal data segment of the nearest neighbor monitoring point, the Pearson correlation coefficient, the starting time of the abnormal data segment of each monitoring point in the suspected polluted gas emission stage and the starting time of the abnormal data segment of the nearest neighbor monitoring point; Based on the similarity of the pollution change rhythm and the environmental impact factors of each monitoring point during the suspected polluted gas emission stage, the consistency of the environmental impact of the suspected polluted gas emission stage with the change law of the actual air quality data is determined.

5. The method for monitoring ambient air pollution based on sensor technology according to claim 4, characterized in that: Determining the environmental impact factor of the other monitoring point according to the minimum angle between the vector pointing from the nearest neighbor monitoring point to the other monitoring point and the wind direction, the distance between the other monitoring point and the nearest neighbor monitoring point, and the current wind speed includes: Calculating a second ratio between the first predetermined value and the minimum angle, and a third ratio between the current wind speed and the distance; A third product between the second ratio and the third ratio is determined as the environmental impact factor of the other monitoring point.

6. The method for monitoring ambient air pollution based on sensor technology according to claim 4, characterized in that: The determining of the similarity of the pollution change rhythm between each monitoring point and the nearest neighbor monitoring point during the suspected polluted gas emission stage according to the environmental pollution degree of the abnormal data segment of each monitoring point during the suspected polluted gas emission stage and the environmental pollution degree of the abnormal data segment of the nearest neighbor monitoring point, the Pearson correlation coefficient, the starting time of the abnormal data segment of each monitoring point during the suspected polluted gas emission stage and the starting time of the abnormal data segment of the nearest neighbor monitoring point comprises: Calculate a first sum value between the Pearson correlation coefficient and a second predetermined value, a first difference value between the environmental pollution degree of the abnormal data segment of each monitoring point in the suspected polluted gas emission stage and the environmental pollution degree of the abnormal data segment of the nearest neighboring monitoring point, and a second difference value between the start time of the abnormal data segment of each monitoring point in the suspected polluted gas emission stage and the start time of the abnormal data segment of the nearest neighboring monitoring point; calculating a reciprocal of a second sum between the first difference and the second difference; The fourth product between the first sum and the reciprocal of the second sum is determined as the convergence of the pollution change rhythm between each monitoring point and the nearest neighbor monitoring point during the suspected polluted gas emission stage.

7. The method for monitoring ambient air pollution based on sensor technology according to claim 4, characterized in that: Determining the consistency of the environmental impact of the suspected polluted gas emission stage with the change law of the actual air quality data according to the similarity of the pollution change rhythm and the environmental impact factor of each monitoring point during the suspected polluted gas emission stage includes: Determine a first average value of the pollution change rhythm convergence of each monitoring point during the suspected polluted gas emission stage, and a second average value of the environmental impact factor of each monitoring point during the suspected polluted gas emission stage; Calculate the third difference between the pollution change rhythm convergence of adjacent monitoring points, and the fourth difference between the environmental impact factors of adjacent monitoring points; calculating a fourth ratio between the third difference and the first average value, and a fifth ratio between the fourth difference and the second average value; calculating a sixth ratio between the fourth ratio and the fifth ratio, and an absolute value of a fifth difference between a third predetermined value and the sixth ratio; superimposing the absolute values ​​of the fifth difference values ​​to obtain a second superimposed value; The second superposition value is subjected to inverse proportional normalization processing to obtain the consistency of the variation rule.

8. The method for monitoring ambient air pollution based on sensor technology according to claim 1, characterized in that: The step of determining the optimized sampling frequency of each monitoring point in the actual pollutant gas emission stage according to the air quality data of each abnormal data segment in the actual pollutant gas emission stage and the initial sampling frequency includes: Calculating the standard deviation of the air quality data of each abnormal data segment during the actual pollutant gas emission stage, and normalizing the standard deviation to obtain a normalized value; Calculating a second sum between a third predetermined value and the normalized value; A fifth product between the initial sampling frequency and the second sum is determined as the optimized sampling frequency of the monitoring point in the actual pollutant gas emission stage.

9. The method for monitoring ambient air pollution based on sensor technology according to claim 1, characterized in that: After collecting the corrected air quality data of each monitoring point using the optimized sampling frequency, the method further includes: The corrected air quality data is monitored for anomalies using a local outlier factor algorithm.

10. An ambient air pollution monitoring system based on sensor technology, characterized in that: include: A processor and a memory; wherein the memory is used to store a computer program that can be run on the processor; A processor is used to execute the program stored in the memory to implement the steps of the ambient air pollution monitoring method based on sensor technology as described in any one of claims 1 to 9.

Images