Environment monitoring method and system based on environment monitor

Abstract

The invention relates to the technical field of environment monitoring, in particular to an environment monitoring method and system based on an environment monitor. The method comprises the following steps: acquiring a first concentration sequence of target pollution gas in a to-be-monitored environment through a first sensor of an environment monitor, and determining a first fluctuation degree value of a target data point in the first concentration sequence; comparing the local sequence of the target data point with the concentration in the same time period in a second concentration sequence obtained by a second sensor, and determining a credibility value of the target data point to obtain a second fluctuation degree value of the target data point; and determining a target length corresponding to the target data point according to the second fluctuation degree value of the target data point, so as to determine a monitoring result of the moment of the target data point by using the fuzzy entropy of the neighborhood sequence of the target length of the target data point. According to the technical scheme, the abnormity of the target pollution gas in the to-be-monitored area can be effectively monitored.

Description

Technical Field

[0001] The present application relates to the technical field of environmental monitoring, and in particular to an environmental monitoring method and system based on an environmental monitoring instrument. Background Art

[0002] During thermal power generation, industrial production activities, oil extraction and engine operation, pollutant gases such as sulfur dioxide, nitrogen oxides, carbon monoxide, volatile organic compounds and hydrogen sulfide may be produced. These pollutant gases will harm the surrounding environment and human health. Therefore, in order to avoid the threat of pollutant gases to the environment or human body, it is necessary to monitor the pollutant gases in the environment.

[0003] In order to realize the monitoring of pollutant gases in the environment, a Chinese patent application document with publication number CN114046822A provides an atmospheric pollution monitoring method based on a sensor array module, including: generating an airspace-level particulate matter concentration set by performing hierarchical monitoring of particulate matter concentration in a first monitored area; constructing a longitudinal spatial pollution monitoring network for the first monitored area in combination with each level of airspace; generating a transverse circumferential pollution monitoring network; building a ground-to-air integrated pollution monitoring tracking map for the first monitored area; generating real-time wind monitoring data and rendering it to the first corresponding mark of the ground-to-air integrated pollution monitoring tracking map; generating real-time temperature and humidity monitoring data and rendering it to the second corresponding mark of the ground-to-air integrated pollution monitoring tracking map; generating a ground-to-air integrated pollution monitoring tracking network and uploading it to an electronic display screen to dynamically monitor the first monitored area.

[0004] When the related technology uses the acquired concentration set of pollutants in the monitored area to monitor the atmospheric pollution in the monitored area, it mainly displays the concentration of particulate matter in the monitored area. Therefore, it is difficult to accurately monitor the abnormalities of polluted gases in the monitored area. Summary of the invention

[0005] In order to overcome the problem that related technologies are difficult to realize abnormal monitoring of polluted gases in the monitored area, the present application provides an environmental monitoring method and system based on an environmental monitoring instrument.

[0006] According to a first aspect of an embodiment of the present application, there is provided an environmental monitoring method based on an environmental monitoring instrument, comprising: obtaining a first concentration sequence of a target pollutant gas in an environment to be monitored through a first sensor of the environmental monitoring instrument, and determining a local sequence where a target data point is located in the first concentration sequence, so as to determine a first fluctuation degree value of the target data point according to the number of extreme value points in the local sequence; obtaining multiple second concentration sequences of the target pollutant gas in the environment to be monitored through multiple second sensors of the environmental monitoring instrument; the first sensor and the second sensor are of the same sensor type; the first concentration sequence and the multiple second concentration sequences have the same collection time period; determining a credibility value of the target data point according to the difference between the concentrations in the same time period in the local sequence and the second concentration sequence, so as to use the product of the first fluctuation degree value of the target data point and the credibility value as the second fluctuation degree value of the target data point; determining a target length corresponding to the target data point according to the second fluctuation degree value of the target data point, and intercepting a neighborhood sequence corresponding to the target data point and equal to the target length from the first concentration sequence, so as to determine the monitoring result at the time when the target data point is located by using the fuzzy entropy of the neighborhood sequence.

[0007] In this way, by comparing the data obtained by the first sensor with the data obtained by the second sensor of the same sensor type to determine the credibility value of the target data point, it is possible to effectively determine whether the target data point obtained by the first sensor is affected by noise, thereby more accurately monitoring the concentration of the target pollutant gas in the monitored area while avoiding the influence of noise.

[0008] Optionally, the first fluctuation degree value of the target data point is determined by: hour, ;when 1 o'clock, ; Where M is the number of extreme points of concentration in the local sequence, F is the first fluctuation value of the target data point, and norm is the normalization function. is the concentration of the ith extreme point in the local sequence, is the average concentration in the local sequence where the target data point is located, To take the absolute value.

[0009] In this way, by analyzing the number of extreme value points of the concentration in the local sequence, the first fluctuation degree value of the target data point can be calculated so as to discover the anomaly existing in the environment to be monitored.

[0010] Optionally, the confidence level value of the target data point is determined by: ,in, is the credibility value of the target data point, exp is an exponential function with a natural constant as the base, A is the number of the second concentration sequence, B is the number of data points in the local sequence, is the concentration of the bth data point in the local sequence; is the concentration of the bth data point in the corresponding local sequence in the ath second concentration sequence, and The corresponding moments are the same; T is the sum of the correlation coefficients of the local sequence with different second concentration sequences, and the correlation coefficient is equal to the Pearson correlation coefficient between the local sequence and the concentration segments with the same time period in the second concentration sequence; To take the absolute value.

[0011] In this way, based on the Pearson correlation coefficient between the local sequence corresponding to the target data point and the concentration segment with the same time period in the second concentration sequence, the credibility value of the target data point is determined, and the credibility value can reflect the probability that the concentration data near the target data point is affected by noise.

[0012] Optionally, determining a target length corresponding to the target data point according to the second fluctuation degree value of the target data point includes: , is the target length corresponding to the target data point, is the second fluctuation value of the target data point, is the first preset length, To round down; It is a second preset length, which is smaller than the first preset length, and the second preset length is the minimum length required for determining the fuzzy entropy of the time series.

[0013] In this way, according to the second fluctuation degree value of the target data point, the size of the target length corresponding to the target data point can be adaptively adjusted to take into account both computing resources and computing efficiency.

[0014] Optionally, the fuzzy entropy of the neighborhood sequence is determined in the following manner: multiple neighborhood subsequences having a length equal to a third preset length are selected from the neighborhood sequence, and the similarity values ​​between any two neighborhood subsequences in the multiple neighborhood subsequences are determined; based on the similarity values ​​between any two neighborhood subsequences, a first eigenvalue of the neighborhood sequence at the third preset length is determined, and the first eigenvalue is equal to an average value of different similarity values; with reference to the determination process of the first eigenvalue of the neighborhood sequence at the third preset length, a second eigenvalue of the neighborhood sequence at a fourth preset length is determined, and the difference between the first eigenvalue and the second eigenvalue is used as the fuzzy entropy; the fourth preset length is greater than the third preset length.

[0015] In this way, by taking the difference between the characteristic values ​​corresponding to different preset lengths as the fuzzy entropy, the fuzzy entropy can better reflect the degree of abnormality in the monitored environment.

[0016] Optionally, the monitoring result of the target data point at the time is determined by using the fuzzy entropy of the neighborhood sequence, including: using the fuzzy entropy of the neighborhood sequence to determine the abnormality value at the time when the target data point is located, and using the relationship between the abnormality value at the time when the target data point is located and a preset threshold value to determine the monitoring result at the time when the target data point is located; wherein the abnormality value , norm is the normalization function, is the fuzzy entropy corresponding to the target data point, is the fuzzy entropy corresponding to the previous data point of the target data point, is the average concentration in the local sequence where the target data point is located, is the average value of the concentration in the local sequence of the previous data point of the target data point.

[0017] Optionally, the relationship between the abnormality degree value at the time when the target data point is located and a preset threshold is used to determine the monitoring result at the time when the target data point is located, including: when the abnormality degree value at the time when the target data point is located is greater than or equal to the preset threshold, outputting a prompt message, wherein the prompt message is used to prompt that the concentration of the target pollutant gas in the monitored environment at the time when the target data point is located is abnormally increased.

[0018] Optionally, the relationship between the abnormality degree value at the time when the target data point is located and the preset threshold is used to determine the monitoring result at the time when the target data point is located, including: when the abnormality degree value at the time when the target data point is located is less than the preset threshold, it is prompted that the concentration at the time when the target data point is located is in a normal state.

[0019] Optionally, the target pollutant gas is any one of sulfur dioxide, nitrogen oxides, carbon monoxide, volatile organic compounds and hydrogen sulfide.

[0020] According to a second aspect of an embodiment of the present application, there is provided an environmental monitoring system based on an environmental monitoring instrument, comprising: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the steps of the environmental monitoring method based on the environmental monitoring instrument provided in the first aspect of the present application are implemented.

[0021] The technical solution provided by the embodiments of the present application may include the following beneficial effects: for the first concentration sequence of the target pollutant gas in the monitored environment obtained by the first sensor of the environmental monitoring instrument, the first fluctuation degree value of the target data point in the first concentration sequence can be determined, and by comparing the data obtained by the first sensor with the data obtained by the second sensor of the same sensor type, the credibility value of the target data point can be determined to obtain the second fluctuation degree value of the target data point; according to the second fluctuation degree value of the target data point, the target length corresponding to the target data point can be adaptively determined to obtain the monitoring result at the moment of the target data point; compared with displaying the concentration of the obtained pollutant gas, the anomaly in the concentration of the target pollutant gas in the monitored environment can be more effectively identified, and therefore, more effective monitoring of the anomaly of the target pollutant gas in the monitored area can be achieved.

[0022] In the embodiment of the present application, the credibility value of the target data point is determined by comparing the data obtained by the first sensor with the data obtained by the second sensor of the same sensor type. This can effectively determine whether the target data point obtained by the first sensor is affected by noise, thereby achieving monitoring of the concentration of the target pollutant gas in the monitored area while avoiding the influence of noise.

[0023] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a flow chart of an environment monitoring method based on an environment monitoring instrument according to an exemplary embodiment; Figure 2 The diagram is a schematic structural diagram of an environment monitoring system based on an environment monitoring instrument according to an exemplary embodiment. DETAILED DESCRIPTION

[0025] First, a brief introduction is given to the application scenarios of the embodiments of the present application. In the application scenarios of the present application, in order to monitor the particulate matter and other pollutant gases in the environment, the relevant technology mainly displays the concentration of the obtained particulate matter and other pollutant gases through a display device, and it is difficult to effectively identify the abnormalities of the pollutant gases. Therefore, it is difficult to effectively monitor the pollutant gases.

[0026] To solve the above technical problems, the present application provides an environment monitoring method and system based on an environment monitoring instrument. Figure 1 is a flow chart of an environment monitoring method based on an environment monitoring instrument according to an exemplary embodiment. Figure 1 As shown, the method includes the following steps.

[0027] In step S101, a first concentration sequence of a target pollutant gas in a monitored environment is acquired by a first sensor of an environmental monitor, and a local sequence where a target data point in the first concentration sequence is located is determined, so as to determine a first fluctuation degree value of the target data point according to the number of extreme value points in the local sequence.

[0028] The target pollutant gas may be any one of the pollutants such as sulfur dioxide, nitrogen oxides, carbon monoxide, volatile organic compounds and hydrogen sulfide.

[0029] The environmental monitor may be provided with multiple sensors of the same type; for example, when the target pollutant gas is sulfur dioxide, the environmental monitor may be provided with multiple sulfur dioxide sensors to measure the concentration of sulfur dioxide in the environment in which the environmental monitor is located; or, when the target pollutant gas is nitrogen oxides, the environmental monitor may be provided with multiple nitrogen oxide sensors to measure the concentration of nitrogen oxides in the environment in which the environmental monitor is located.

[0030] The first sensor is one of multiple sensors set in the environmental monitoring instrument for obtaining the concentration of the target pollutant gas; the first sensor can be used to obtain the concentration of the target pollutant gas in the monitored environment within a certain period of time, and form a first concentration sequence in chronological order; for example, the concentration of the target pollutant gas in the monitored environment obtained by the first sensor within 10 minutes before the current moment can be formed into a first concentration sequence.

[0031] The target data point may be any concentration data point in the first concentration sequence, and a portion of the first concentration sequence within a neighborhood of the target data point for a specified time length may be used as a local sequence in the first concentration sequence where the target data point is located.

[0032] In one embodiment, the first fluctuation degree value of the target data point is determined by: hour, ;when 1 o'clock, ; Where M is the number of extreme points of concentration in the local sequence, F is the first fluctuation value of the target data point, and norm is the normalization function. is the concentration of the ith extreme point in the local sequence, is the average concentration in the local sequence where the target data point is located, To take the absolute value.

[0033] The normalization processing function is used to normalize the variable to be normalized to the range of 0 to 1; for example, the normalization processing function can adopt minimum-maximum normalization, logarithmic normalization or Sigmoid function, etc. The embodiment of the present application does not limit the specific form of the normalization processing function.

[0034] When there is no extreme point of concentration in the local sequence of target data points, it means that the concentration of the target pollutant gas at different times in the local sequence is relatively stable, or the fluctuation of the concentration of the target pollutant gas at different times in the local sequence is small.

[0035] When there are extreme points of concentration in the local sequence of target data points, it means that the concentration of the target pollutant gas at different times in the local sequence fluctuates to a certain extent, and the more extreme points there are, the more times the concentration fluctuates. The extreme points of concentration in the local sequence can be the maximum points of concentration or the minimum points of concentration.

[0036] When there are extreme points of concentration in the local sequence of target data points, the number of extreme points in the local sequence can reflect the number of fluctuations in the concentration; the difference between the extreme points and the average value of the concentration can reflect the amplitude of the fluctuation in the concentration in the local sequence. Therefore, considering the difference between the extreme points in the local sequence and the average value of the concentration in the local sequence can more comprehensively consider the fluctuation of the concentration.

[0037] In this way, the first fluctuation degree value of the target data point can be determined at least according to the number of extreme value points of the concentration in the local sequence, so as to characterize the fluctuation degree in the local sequence where the target data point is located by the first fluctuation degree value.

[0038] In step S102, a plurality of second concentration sequences of the target pollutant gas in the environment to be monitored are acquired through a plurality of second sensors of the environment monitoring instrument.

[0039] The first sensor and the second sensor are of the same sensor type; the collection time period of the first concentration sequence and the multiple second concentration sequences is the same; for example, the first sensor and the multiple second sensors are used to collect the concentration of the target pollutant gas in the same monitored environment within the same time period, so as to calibrate the data obtained by a certain sensor through other sensors among the multiple sensors.

[0040] Since the multiple second sensors are of the same sensor type as the first sensor and have the same corresponding acquisition time period, the multiple second sensors can respectively acquire corresponding second concentration sequences, and different second concentration sequences correspond to different second sensors.

[0041] In step S103, the credibility value of the target data point is determined based on the difference between the concentrations in the local sequence and the second concentration sequence in the same time period, so that the product of the first fluctuation value of the target data point and the credibility value is used as the second fluctuation value of the target data point.

[0042] In an embodiment of the present application, the target pollutant gas concentration in the same monitored environment within the same time period is acquired through a first sensor and multiple second sensors. When the concentration of the target pollutant gas collected by the first sensor is affected by noise, the concentrations of the target pollutant gas acquired by multiple second sensors are unlikely to be affected by noise at the same time. Therefore, the local sequence in the first concentration sequence acquired by the first sensor can be compared with the concentration in the same time period in the second concentration sequence to determine whether there is noise in the local sequence corresponding to the target data point.

[0043] In one embodiment, the confidence level of the target data point is determined by: ,in, is the credibility value of the target data point, exp is an exponential function with a natural constant as the base, A is the number of the second concentration sequence, B is the number of data points in the local sequence, is the concentration of the bth data point in the local sequence; is the concentration of the bth data point in the corresponding local sequence in the ath second concentration sequence, and The corresponding moments are the same; T is the sum of the correlation coefficients of the local sequence with different second concentration sequences, and the correlation coefficient is equal to the Pearson correlation coefficient between the local sequence and the concentration segments with the same time period in the second concentration sequence; To take the absolute value.

[0044] For example, when a first sensor and three other second sensors of the same sensor type are provided in the environmental monitoring instrument, the time period corresponding to the collected first concentration sequence or the second concentration sequence is from the 0th second to the 600th second, the moment corresponding to the target data point may be the 600th second, and the time period of the local sequence corresponding to the target data point may be from the 540th second to the 600th second.

[0045] The concentration data of the target pollutant gas collected by the second sensor in the time period from 540 seconds to 600 seconds can be compared with the concentration data at the same time in the local sequence corresponding to the target data point to determine whether the local sequence corresponding to the target data point is affected by noise.

[0046] When the concentration data acquired by the first sensor is not affected by noise, the local sequence corresponding to the target data point in the first concentration sequence has a high consistency with the concentration data in the same time period in the second concentration sequence.

[0047] In the case where the concentration data acquired by the first sensor is affected by noise at the target data point, the consistency between the local sequence corresponding to the target data point and the concentration data in the same time period in the second concentration sequence is reduced.

[0048] The correlation coefficient is equal to the Pearson correlation coefficient between the local sequence and the concentration segment with the same time period in the second concentration sequence; for example, when the local sequence of the target data point corresponds to the time period from 12:00:00 to 12:01:00, since the first sensor and the second sensor collect the concentration of the target pollutant gas in the environment to be detected in the same time period, the concentration segment corresponding to the time period from 12:00:00 to 12:01:00 in the second concentration sequence obtained by the second sensor will usually be correlated with the local sequence of the target data point, and the greater the correlation, the less the first sensor is affected by noise near the target data point.

[0049] The credibility value of the target data point can represent the probability that the first sensor is not affected by noise at the time of the target data point, or the credibility value of the target data point can represent the degree to which the target data point can reflect the actual concentration of the target pollutant gas.

[0050] The greater the credibility value of the target data point, the smaller the probability or degree of the first sensor being affected by noise at the time of the target data point, and the more the target data point can reflect the actual concentration of the target pollutant gas in the monitored environment.

[0051] On the contrary, the smaller the credibility value of the target data point is, the greater the probability or degree of the first sensor being affected by noise at the time of the target data point is, and the more difficult it is for the target data point to reflect the actual concentration of the target pollutant gas in the monitored environment.

[0052] In this way, by using the Pearson correlation coefficient between the local sequence corresponding to the target data point and the concentration segment with the same time period in the second concentration sequence, and comparing the concentration data acquired by the first sensor with the concentration data acquired by the second sensor at the same time, the obtained credibility value can better reflect the probability that the concentration data near the target data point is affected by noise.

[0053] Since the target data point can reflect the degree of fluctuation of the concentration of the target pollutant gas acquired by the first sensor in the local sequence, the credibility value of the target data point can characterize the probability that the first sensor is not affected by noise at the moment of the target data point, or the credibility value of the target data point can characterize the degree to which the target data point can reflect the actual concentration of the target pollutant gas. Therefore, the product of the first fluctuation value of the target data point and the credibility value can more effectively reflect the actual fluctuation degree of the concentration of the target pollutant gas in the local sequence.

[0054] In step S104, the target length corresponding to the target data point is determined according to the second fluctuation degree value of the target data point, and a neighborhood sequence corresponding to the target data point and equal to the target length is intercepted from the first concentration sequence to determine the monitoring result at the moment when the target data point is located using the fuzzy entropy of the neighborhood sequence.

[0055] According to the second fluctuation degree value of the target data point, a matching target length can be determined for the target data point, so as to further determine whether the concentration of the target data point is abnormal through a neighborhood sequence with a length equal to the target length.

[0056] Among them, the smaller the second fluctuation degree value of the target data point is, the more stable the concentration of the environment to be detected at the target data point is, and whether the concentration of the target pollutant gas at the time corresponding to the target data point is abnormal can be determined through a neighborhood sequence with a smaller amount of data; On the contrary, the larger the second fluctuation degree value of the target data point, the greater the fluctuation degree of the concentration of the detected environment at the target data point. Then, a neighborhood sequence with a larger amount of data can be used to determine whether there is an abnormality in the concentration of the target pollutant gas at the time corresponding to the target data point, so as to more accurately determine whether there is an abnormality in the concentration of the target pollutant gas at the time of the target data point.

[0057] In one embodiment, determining a target length corresponding to a target data point according to a second fluctuation degree value of the target data point includes: , is the target length corresponding to the target data point, is the second fluctuation value of the target data point, is the first preset length, To round down; It is a second preset length, which is smaller than the first preset length, and the second preset length is the minimum length required for determining the fuzzy entropy of the time series.

[0058] By multiplying the second fluctuation degree value with the first preset length and rounding the multiplication result, it can be ensured that the target length corresponding to the target data point is positively correlated with the second fluctuation degree value. Due to the existence of the second preset length, when the second fluctuation degree value is small, it can be ensured that the target length has a certain basic length, thereby ensuring the smooth progress of the fuzzy entropy determination process of the time series of the concentration of the target pollutant gas in the monitored environment.

[0059] For example, the first preset length may be between 100 and 120, and the second preset length may be between 35 and 50; the first preset length and the second preset length are both positive integers.

[0060] In this way, by adjusting the target length corresponding to the target data point, when the fluctuation degree at the target data point is high, the size of the target length can be increased to obtain more detailed information about the monitored environment; when the fluctuation degree at the target data point is small, the size of the target length can be reduced to save computing resources.

[0061] In one embodiment, the fuzzy entropy of the neighborhood sequence is determined in the following manner: multiple neighborhood subsequences whose lengths are equal to a third preset length are selected from the neighborhood sequence, and the similarity values ​​between any two neighborhood subsequences in the multiple neighborhood subsequences are determined; based on the similarity values ​​between any two neighborhood subsequences, a first eigenvalue of the neighborhood sequence at the third preset length is determined, and the first eigenvalue is equal to the average value of different similarity values; with reference to the determination process of the first eigenvalue of the neighborhood sequence at the third preset length, a second eigenvalue of the neighborhood sequence at a fourth preset length is determined, and the difference between the first eigenvalue and the second eigenvalue is used as the fuzzy entropy; the fourth preset length is greater than the third preset length.

[0062] A neighborhood subsequence can be selected from the neighborhood sequence of the target data point according to a preset step size, and the preset step size can be equal to 1; for example, when the neighborhood sequence is [C1, C2, C3, C4, C5, C6, C7, C8], if the third preset length is equal to 2, [C1, C2] can be used as the first neighborhood subsequence selected, and [C2, C3] can be used as the second neighborhood subsequence selected, and [C7, C8] can be used as the last neighborhood subsequence selected to complete the selection of all neighborhood subsequences.

[0063] The similarity value between any two neighborhood subsequences can be determined based on the maximum value of the difference between the corresponding positions in the two neighborhood subsequences. For example, for the neighborhood subsequences [C1, C2] and the neighborhood subsequences [C3, C4], as well as The largest one among them is taken as the difference value between the neighborhood subsequences [C1, C2] and [C3, C4], and the reciprocal of the difference value is taken as the similarity value between the neighborhood subsequences [C1, C2] and [C3, C4]; alternatively, the reciprocal of the exponential function of the difference value can be taken as the similarity value.

[0064] Since the first eigenvalue is equal to the average value of different similarity values, the similarity value between any two neighborhood subsequences is used to characterize the similarity between the two neighborhood subsequences. Therefore, the first eigenvalue of the neighborhood sequence at the third preset length can reflect the consistency between different neighborhood subsequences when the neighborhood sequence is selected according to the third preset length.

[0065] With reference to the process of determining the first eigenvalue of the neighborhood sequence at the third preset length, the second eigenvalue of the neighborhood sequence at the fourth preset length can be determined. The obtained second eigenvalue can reflect the consistency between different neighborhood subsequences when the neighborhood sequence is selected according to the fourth preset length; through the difference between the first eigenvalue and the second eigenvalue, the degree of difference when the neighborhood sequence is selected according to different lengths of neighborhood subsequences can be reflected, thereby reflecting the degree of abnormality of the monitored environment within the time period of the neighborhood sequence.

[0066] The third preset length and the fourth preset length can be determined according to actual needs; for example, the third preset length can be equal to 4, and the fourth preset length can be equal to 5.

[0067] In this way, the neighborhood sequence is divided by different preset lengths and the corresponding eigenvalues ​​are obtained. The difference between the eigenvalues ​​corresponding to different preset lengths is used as the fuzzy entropy. The fuzzy entropy can better reflect the abnormality of the monitored environment in the time period of the neighborhood sequence.

[0068] In one embodiment, the monitoring result of the target data point at the time is determined by using the fuzzy entropy of the neighborhood sequence, including: using the fuzzy entropy of the neighborhood sequence to determine the abnormality value at the time when the target data point is located, and using the relationship between the abnormality value at the time when the target data point is located and a preset threshold value to determine the monitoring result at the time when the target data point is located; wherein the abnormality value , norm is the normalization function, is the fuzzy entropy corresponding to the target data point, is the fuzzy entropy corresponding to the previous data point of the target data point, is the average concentration in the local sequence where the target data point is located, is the average value of the concentration in the local sequence of the previous data point of the target data point.

[0069] The normalization function norm is used to normalize the variable to be normalized to the range of 0 to 1; The normalization process can make In the range of 0 to 1; after normalization, the function norm The normalization process can make In the range 0 to 1.

[0070] For example, when the fuzzy entropy corresponding to the target data point is greater than the fuzzy entropy corresponding to the previous data point of the target data point, The value of is closer to 1; when the fuzzy entropy corresponding to the target data point is less than the fuzzy entropy corresponding to the previous data point of the target data point, The value is closer to 0.

[0071] When the fuzzy entropy corresponding to the target data point is greater than the fuzzy entropy corresponding to the previous data point of the target data point, it means that the fluctuation degree of the concentration of the target pollutant gas in the monitored environment has become greater than the previous moment, and the concentration of the target pollutant gas in the monitored environment requires a higher level of attention. Here, a higher abnormality degree value can be set so that the concentration of the target pollutant gas in the monitored environment can attract the attention of the user.

[0072] Moreover, when the fuzzy entropy corresponding to the target data point is greater than the fuzzy entropy corresponding to the previous data point of the target data point, there is a greater probability that the concentration of the target pollutant gas will increase near the location of the monitored environment in the future time period. For example, the pollution source near the location of the monitored environment has increased the release rate of the target pollutant gas. Therefore, comparing the fuzzy entropy corresponding to the target data point with the fuzzy entropy corresponding to the previous data point of the target data point can also help guide users to pay attention to the abnormalities of the target pollutant gas in the monitored environment.

[0073] When the average value of the concentration in the local sequence where the target data point is located is greater than the average value of the concentration in the local sequence where the previous data point of the target data point is located, it means that the concentration of the target pollutant gas in the monitored environment is greater than the concentration in the previous time period; combined with the change of the fuzzy entropy corresponding to the target data point relative to the fuzzy entropy of the previous data point, the abnormality degree value can better realize the evaluation of the abnormality of the concentration of the target pollutant gas in the monitored environment.

[0074] In this way, the fuzzy entropy of the neighborhood sequence is used to determine the abnormality level value at the target data point. The abnormality level value takes into account the change in concentration of the target data point relative to the concentration of the previous data point. By using the relationship between the abnormality level value at the target data point and the preset threshold, a more accurate monitoring result for the target data point can be obtained, so that users can monitor the target pollutant gas in the monitored environment.

[0075] The relationship between the abnormality level value at the time when the target data point is located and the preset threshold is used to determine the monitoring result at the time when the target data point is located, including: when the abnormality level value at the time when the target data point is located is greater than or equal to the preset threshold, a prompt message can be output, and the prompt message is used to prompt that the concentration of the target pollutant gas in the monitored environment is too high at the time when the target data point is located.

[0076] For example, when the target pollutant gas is sulfur dioxide, if the moment corresponding to the target data point is the current moment, and the abnormality degree value at the moment of the target data point is greater than or equal to the preset threshold, it can be prompted that the concentration of sulfur dioxide in the monitored environment at the current moment is abnormally increased.

[0077] When the concentration of sulfur dioxide in the monitored environment is too high at the current moment, the personnel in the monitored environment can be prompted to evacuate or take corresponding protective measures, or the polluted gas treatment equipment can be controlled to treat the polluted gas in the monitored environment.

[0078] When the abnormality value at the target data point is less than the preset threshold, it means that the concentration of the target pollutant gas in the monitored environment at the time when the target data point is located is normal, which can indicate that the concentration at the time when the target data point is located is in a normal state.

[0079] Figure 2 FIG. 1 is a schematic diagram showing a structure of an environment monitoring system 1000 based on an environment monitoring instrument according to an exemplary embodiment. Figure 2 The environmental monitoring system 1000 based on the environmental monitoring instrument includes: a processor 1100 and a memory 1200, wherein the memory 1200 stores computer program instructions, and when the computer program instructions are executed by the processor 1100, all or part of the steps of the environmental monitoring method based on the environmental monitoring instrument in the present application are implemented.

[0080] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary technical means in the art that are not disclosed in the present application, and the specification and embodiments are only considered as exemplary.

[0081] It should be understood that the present application is not limited to the exact construction that has been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof.

Claims

1. An environmental monitoring method based on an environmental monitoring instrument, characterized in that: include: Acquire a first concentration sequence of the target pollutant gas in the monitored environment through a first sensor of the environmental monitor, and determine a local sequence where the target data point in the first concentration sequence is located, so as to determine a first fluctuation degree value of the target data point according to the number of extreme value points in the local sequence; Acquire multiple second concentration sequences of the target pollutant gas in the monitored environment through multiple second sensors of the environmental monitor; the first sensor and the second sensor are of the same sensor type; and the first concentration sequence and the multiple second concentration sequences are collected in the same time period; Determine the credibility value of the target data point according to the difference between the concentrations in the local sequence and the second concentration sequence in the same time period, and use the product of the first fluctuation degree value of the target data point and the credibility value as the second fluctuation degree value of the target data point; According to the second fluctuation degree value of the target data point, the target length corresponding to the target data point is determined, and a neighborhood sequence corresponding to the target data point and equal to the target length is intercepted from the first concentration sequence to determine the monitoring result at the moment of the target data point using the fuzzy entropy of the neighborhood sequence.

2. The environmental monitoring method based on the environmental monitoring instrument according to claim 1, characterized in that: The first fluctuation degree value of the target data point is determined by: when hour, ;when 1 o'clock, ; Where M is the number of extreme points of concentration in the local sequence, F is the first fluctuation value of the target data point, and norm is the normalization function. is the concentration of the ith extreme point in the local sequence, is the average value of the concentration in the local sequence where the target data point is located, To take the absolute value.

3. The environmental monitoring method based on the environmental monitoring instrument according to claim 1, characterized in that: The confidence level value of the target data point is determined in the following way: ,in, is the credibility value of the target data point, exp is an exponential function with a natural constant as the base, A is the number of the second concentration sequence, B is the number of data points in the local sequence, is the concentration of the bth data point in the local sequence; is the concentration of the bth data point in the corresponding local sequence in the ath second concentration sequence, and The corresponding moments are the same; T is the sum of the correlation coefficients of the local sequence with different second concentration sequences, and the correlation coefficient is equal to the Pearson correlation coefficient between the local sequence and the concentration segments with the same time period in the second concentration sequence; To take the absolute value.

4. The environmental monitoring method based on the environmental monitoring instrument according to claim 1, characterized in that: Determining a target length corresponding to the target data point according to the second fluctuation degree value of the target data point includes: , is the target length corresponding to the target data point, is the second fluctuation value of the target data point, is the first preset length, To round down; It is a second preset length, which is smaller than the first preset length, and the second preset length is the minimum length required for determining the fuzzy entropy of the time series.

5. The environmental monitoring method based on the environmental monitoring instrument according to claim 1, characterized in that: The fuzzy entropy of the neighborhood sequence is determined as follows: Selecting a plurality of neighborhood subsequences having a length equal to a third preset length from the neighborhood sequence, and determining a similarity value between any two neighborhood subsequences in the plurality of neighborhood subsequences; Determine, according to the similarity values ​​between any two neighborhood subsequences, a first characteristic value of the neighborhood sequence at a third preset length, wherein the first characteristic value is equal to an average value of different similarity values; Referring to the determination process of the first eigenvalue of the neighborhood sequence at the third preset length, the second eigenvalue of the neighborhood sequence at the fourth preset length is determined, and the difference between the first eigenvalue and the second eigenvalue is used as the fuzzy entropy; the fourth preset length is greater than the third preset length.

6. The environmental monitoring method based on the environmental monitoring instrument according to claim 1, characterized in that: The fuzzy entropy of the neighborhood sequence is used to determine the monitoring results of the target data point at the time, including: The fuzzy entropy of the neighborhood sequence is used to determine the abnormality value of the target data point at the time, and the relationship between the abnormality value of the target data point at the time and the preset threshold is used to determine the monitoring result of the target data point at the time; Among them, the abnormality value , norm is the normalization function, is the fuzzy entropy corresponding to the target data point, is the fuzzy entropy corresponding to the previous data point of the target data point, is the average value of the concentration in the local sequence where the target data point is located, is the average value of the concentration in the local sequence where the previous data point of the target data point is located.

7. The environmental monitoring method based on the environmental monitoring instrument according to claim 6, characterized in that: The relationship between the abnormality value at the time when the target data point is located and the preset threshold is used to determine the monitoring result at the time when the target data point is located, including: When the abnormality value at the time when the target data point is located is greater than or equal to the preset threshold, a prompt message is output, wherein the prompt message is used to prompt that the concentration of the target pollutant gas in the monitored environment at the time when the target data point is located is abnormally increased.

8. The environmental monitoring method based on the environmental monitoring instrument according to claim 6, characterized in that: The relationship between the abnormality value at the time when the target data point is located and the preset threshold is used to determine the monitoring result at the time when the target data point is located, including: When the abnormality value at the time when the target data point is located is less than the preset threshold, it is prompted that the concentration at the time when the target data point is located is in a normal state.

9. The environmental monitoring method based on the environmental monitoring instrument according to claim 1, characterized in that: The target pollutant gas is any one of sulfur dioxide, nitrogen oxides, carbon monoxide, volatile organic compounds and hydrogen sulfide.

10. An environmental monitoring system based on an environmental monitoring instrument, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the environment monitoring method based on the environment monitoring instrument according to any one of claims 1 to 9 is implemented.

Images