Ozone monitoring abnormal point location determination method and apparatus, and computing device

Abstract

The embodiment of the invention provides a method and device for determining an ozone monitoring abnormal point location and computing equipment. The ozone monitoring abnormal point location determination method comprises the following steps: calculating a predicted change rate based on ozone concentration monitoring data of similar monitoring point locations in a current time period and a previous time period; calculating ozone concentration prediction data based on the prediction change rate and the ozone concentration monitoring data of the target monitoring point in the previous time period; calculating a concentration difference value ratio according to the ozone concentration prediction data and the ozone concentration monitoring data of the target monitoring point position in the current time period; and under the condition that the concentration difference value ratio is greater than a preset difference value ratio, determining that the target monitoring point position is the ozone concentration abnormal point position. By adopting the scheme of the embodiment of the invention, whether the ozone concentration data of the target monitoring point position is abnormal or not is judged by means of the similar external monitoring point position monitoring data, systematic faults of the target monitoring point position are identified, and whether the target monitoring point position is an abnormal point position or not is determined more accurately.

Description

Technical Field

[0001] The present disclosure relates to the technical field of environmental concentration monitoring data processing, and in particular to a method, device and computing equipment for determining abnormal ozone monitoring points. Background Art

[0002] In order to achieve reasonable early warning and prevention of ozone pollution, it is necessary to ensure the accuracy of ozone concentration monitoring data at each monitoring point. Accordingly, while obtaining the ozone concentration monitoring data at each monitoring point, it is necessary to screen the ozone concentration monitoring data to eliminate the problem of inaccurate local monitoring data due to abnormal reasons. The existing method for screening ozone concentration anomalies is to obtain a monitoring data sequence at a single point, perform correlation analysis based on the time and precursor concentration of the monitoring data sequence, screen out whether there are occasional jumps in the data of a single point, and identify the abnormal state of the monitoring point through data changes. However, the aforementioned method cannot identify the overall abnormality of ozone concentration data caused by systemic failures (for example, due to systemic influences on the surrounding environment), but it is a problem that cannot be identified through the monitoring data sequence. Summary of the invention

[0003] In order to solve the problem that the existing methods have many errors in identifying abnormal monitoring areas, the embodiments of the present disclosure provide a method, device and computing equipment for determining abnormal ozone monitoring points.

[0004] In a first aspect, an embodiment of the present disclosure provides a method for determining an abnormal ozone monitoring point, comprising:

[0005] Determine whether there are similar monitoring points clustered with the target monitoring points from a pre-constructed ozone change trend cluster set, wherein the ozone change trend cluster set is obtained by clustering analysis based on a historical change rate sequence of ozone concentration obtained at each monitoring point under normal monitoring conditions;

[0006] In the case where there are similar monitoring points of the target monitoring point in the ozone change trend clustering set, the similar monitoring points are used as similar monitoring points, and the ozone concentration monitoring data of the similar monitoring points in the current time period and the previous time period are obtained;

[0007] Calculating the predicted change rate based on the ozone concentration monitoring data of the similar monitoring points in the current time period and the previous time period; and calculating the predicted ozone concentration data of the target monitoring point in the current time period based on the predicted change rate and the ozone concentration monitoring data of the target monitoring point in the previous time period;

[0008] Calculate the concentration difference or the concentration difference ratio based on the ozone concentration prediction data and the ozone concentration monitoring data of the target monitoring point in the current period;

[0009] When the concentration difference is greater than a preset difference, or the concentration difference ratio is greater than a preset difference ratio, the target monitoring point is determined to be an ozone concentration abnormality point.

[0010] Optionally, determining that the target monitoring point is an ozone concentration abnormal point includes:

[0011] When a preset number of ozone concentration differences exceeding a preset number within a preset continuous monitoring period is greater than a preset difference, or a concentration difference ratio is greater than a preset ratio difference, the target monitoring point is determined to be an ozone concentration abnormality point.

[0012] Optionally, when there are similar monitoring points in the ozone change trend cluster, obtaining meteorological characteristic data of the similar monitoring points;

[0013] The taking the same type of monitoring points as similar monitoring points includes: taking the same type of monitoring points as similar monitoring points when the same type of monitoring points are non-rainy or snowy weather points.

[0014] Optionally, it also includes: obtaining position coordinate data of the target monitoring point and the similar monitoring points;

[0015] Calculating the spatial distance between the target monitoring point and the similar monitoring point based on the position coordinate data, or determining whether the target monitoring point and the similar monitoring point belong to the same terrain area based on the position coordinate data;

[0016] Taking the same type of monitoring points as similar monitoring points includes: taking the same type of monitoring points as similar monitoring points when the spatial distance is less than a set distance or when the target monitoring point and the same type of monitoring points are in the same terrain area.

[0017] Optionally, the method further includes: obtaining the precursor concentration data of the target monitoring point and the similar monitoring point, and determining whether the precursor concentrations of the similar monitoring point and the target monitoring point are similar;

[0018] Taking the same type of monitoring points as similar monitoring points includes: taking the same type of monitoring points as the similar monitoring points when the precursor concentration data of the same type of monitoring points are similar to the precursor concentration data of the target monitoring points.

[0019] Optionally, before determining whether there are similar monitoring points clustered with the target monitoring points from the pre-constructed ozone change trend cluster set, the method further includes:

[0020] Obtain the historical data sequence of ozone concentration obtained at each monitoring point in non-rainy and snowy weather;

[0021] Obtaining an ozone concentration historical change rate sequence based on the ozone concentration historical data sequence of each monitoring point, wherein the ozone concentration historical change rate in the ozone concentration historical change sequence is obtained by comparing the subsequent data and the adjacent preceding data in the ozone concentration historical change rate;

[0022] A cluster analysis is performed on the historical change rate sequence of the ozone concentration at each monitoring point to determine the cluster set to which each monitoring point belongs, wherein the cluster set includes monitoring points of the same type as each monitoring point.

[0023] Optionally, the method further includes: when there is no similar monitoring point to the target monitoring point in the ozone change trend clustering set, the method further includes:

[0024] Obtaining ozone concentration monitoring data of the target monitoring point monitored at multiple consecutive time periods, and calculating the standard deviation of the consecutive ozone concentration monitoring data;

[0025] When the standard deviation is greater than the set deviation, the target monitoring point is determined to be an abnormal ozone concentration point.

[0026] Optionally, determining whether there are similar monitoring points clustered with the target monitoring points from the pre-constructed ozone change trend cluster set includes:

[0027] When the device status mark of the target monitoring point is a normal mark, it is determined from the pre-constructed ozone change trend set whether there are similar monitoring points clustered with the target monitoring point.

[0028] In a second aspect, the present disclosure provides a device for determining an abnormal ozone monitoring point, comprising:

[0029] A similar point determination unit is used to determine whether there are similar monitoring points clustered with the target monitoring points from a pre-constructed ozone change trend cluster set, wherein the ozone change trend cluster set is obtained by clustering analysis based on a historical change rate sequence of ozone concentration obtained at each monitoring point under normal monitoring conditions;

[0030] A data acquisition unit, for, when there are similar monitoring points of the target monitoring point in the ozone change trend clustering set, taking the similar monitoring points as similar monitoring points, and acquiring ozone concentration monitoring data of the similar monitoring points in the current time period and the previous time period;

[0031] A prediction data calculation unit, used to calculate the predicted change rate based on the ozone concentration monitoring data of the similar monitoring points in the current time period and the previous time period, and calculate the ozone concentration prediction data of the target monitoring point in the current time period based on the predicted change rate and the ozone concentration monitoring data of the target monitoring point in the previous time period;

[0032] A comparison unit, used to calculate a concentration difference or a concentration difference ratio based on the ozone concentration prediction data and the ozone concentration monitoring data of the target monitoring point in the current period;

[0033] The abnormal point determination unit is used to determine that the target monitoring point is an abnormal ozone concentration point when the concentration difference is greater than a preset difference or the concentration difference is greater than a preset ratio.

[0034] In a third aspect, an embodiment of the present disclosure provides a computing device, including a processor and a memory, wherein the memory is used to store a computer program; when the computer program is loaded by the processor, the processor executes the method for determining an abnormal ozone monitoring point as described above.

[0035] By adopting the scheme of the embodiment of the present disclosure, similar monitoring points in the target monitoring points are determined through the pre-constructed ozone change trend cluster set, and similar monitoring points are screened from the similar monitoring points, and the ozone concentration prediction data of the target monitoring point in the current time period is predicted based on the similar monitoring points, and the ozone concentration monitoring data of the current time period is evaluated whether it is abnormal. That is to say, the scheme of the embodiment of the present disclosure evaluates whether the ozone concentration monitoring data of the target monitoring point is abnormal by setting similar monitoring points independent of the target monitoring point. By adopting the scheme of the embodiment of the present disclosure, it is no longer based solely on the judgment of whether the ozone concentration data sequence of the target monitoring point itself is abnormal, but with the help of similar external monitoring point monitoring data, it is judged whether the ozone concentration data of the target monitoring point is abnormal, thereby realizing the identification of systematic faults of the target monitoring point, and then more accurately determining whether the target monitoring point is an abnormal point. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art description. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work, including:

[0038] Figure 1 is a flow chart of a method for determining abnormal ozone monitoring points provided by an embodiment of the present disclosure;

[0039] Figure 2 is a flow chart of a method for implementing the present disclosure to determine a cluster set of ozone change trends;

[0040] Figure 3 It is a schematic diagram of the structure of a device for determining an abnormal ozone monitoring point provided by an embodiment of the present disclosure;

[0041] Figure 4 It is a schematic diagram of the structure of a computing device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0042] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0043] The term "including" and its variations used in this document are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions of other terms will be given in the description below. In this document, relational terms such as "first" and "second" are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0044] In order to solve the problem that the existing data screening methods are unable to screen out abnormalities in ozone monitoring points caused by systemic failures, the embodiments of the present disclosure provide a new method for determining abnormal ozone monitoring points. The method for determining abnormal ozone monitoring points provided by the embodiments of the present disclosure is based on the similarity of the ozone concentration change rates at similar points, and uses the ozone concentration change rates determined by the similarity to calculate the predicted ozone concentration data, and uses the predicted ozone concentration data to evaluate whether the monitoring data of the ozone monitoring points are abnormal, thereby realizing the screening of monitoring points.

[0045] Figure 1 FIG. 1 is a flow chart of a method for determining an abnormal ozone monitoring point provided by an embodiment of the present disclosure. Figure 1 As shown, the method for determining abnormal ozone monitoring points provided by the embodiment of the present disclosure includes S110 to S150. The method of the embodiment of the present disclosure is executed by a computing device that can obtain ozone concentration data of a large number of monitoring points.

[0046] S110: Determine from the pre-constructed ozone change trend cluster set whether there are similar monitoring points clustered with the target monitoring points; if so, execute S120.

[0047] The ozone change trend cluster set is a cluster set obtained by clustering analysis based on the historical change rate sequence of ozone concentration obtained at each monitoring point under normal monitoring conditions. The ozone change trend cluster set has multiple clusters, each of which includes at least one monitoring point; in most cases, each cluster includes multiple monitoring points.

[0048] How to construct the ozone change trend cluster set will be described later. The only premise that needs to be determined here is that the ozone change trend cluster set divides the monitoring points with the same ozone change trend into one cluster set, and divides the monitoring points with different ozone change trends into different cluster sets.

[0049] After determining the target monitoring point, the ozone change trend cluster set is searched through the target monitoring point to determine whether there are similar monitoring points clustered with the target monitoring point, as well as the point identification of the aforementioned similar monitoring points.

[0050] It should be noted here that, considering that rain has a strong removing effect on ozone in the atmosphere, the target monitoring points mentioned in the embodiments of the present disclosure are points where the meteorological conditions are not rainy or snowy in most cases, and only in some cases (such as when it is determined through experience that the ozone monitoring device itself has a fault) are they points in rainy or snowy weather.

[0051] S120: Taking the same type of monitoring points as similar monitoring points, and obtaining ozone concentration monitoring data of the similar monitoring points in the current time period and the previous time period.

[0052] In some embodiments of the present disclosure, each monitoring point is a point having the same meteorological conditions under most conditions (especially for inland areas with little rainfall or areas with a Mediterranean climate). After determining similar monitoring points, the computing device can then directly use the similar monitoring points as similar monitoring points.

[0053] It should be noted here that the aforementioned current time period and previous time period refer to the time period in which it is necessary to determine whether the data is abnormal. They are two time terms named for the convenience of expression and do not have the absolute current and previous meanings. Specifically, the computing device can determine the ozone concentration monitoring data of the current time period and the previous time period based on the time mark of the current time period and the mark of the similar monitoring point.

[0054] In some other embodiments, due to the long distance between monitoring points and different weather conditions, similar monitoring points may be in rainy and snowy weather conditions. As analyzed above, because rain has a strong removal effect on ozone in the atmosphere, the ozone concentration change characteristics of similar monitoring points under rainy and snowy conditions are not comparable to those of target monitoring points in non-rainy and snowy weather. If the ozone concentration change characteristics are obtained under the aforementioned rainy and snowy conditions, it will cause prediction errors. Based on this, after determining similar monitoring points, it will also be determined whether the same monitoring points are in rainy and snowy weather. Only when the same monitoring points are in non-rainy and snowy weather, the computing device will regard the same monitoring points as similar monitoring points.

[0055] In some further embodiments, when determining the ozone change trend cluster set, the computing device processes the data of monitoring points in a large area (for example, in the entire national administrative area), and the monitoring points that may be far away from the location are clustered in a cluster set according to the cluster set determined by the aforementioned method. Because in some embodiments, the computing device determines the ozone change trend cluster set only based on the change trend for clustering, without considering that different factors may cause the same change trend, and some monitoring points are accidentally clustered into a cluster set. For example, the first monitoring point and the second monitoring point are accidentally clustered into a cluster set, but the main reason for the change in ozone concentration at the first monitoring point is the drastic change in the concentration of atmospheric pollution precursors (such as the situation in high-latitude areas in winter), while the main reason for the change in ozone concentration at the second monitoring point is the distance change in light intensity (such as the situation in low-latitude winter).

[0056] According to the analysis in the previous paragraph, if the same type of monitoring points are directly used as similar monitoring points, the same ozone concentration change trend may be used as a classification standard, and then the ozone concentration data of the target monitoring point is predicted by using the ozone concentration change trend that is determined accidentally but not really the same type of monitoring points, resulting in data prediction errors. To avoid the aforementioned problems, in some embodiments, after determining the same type of monitoring points, the position coordinate data of the target monitoring point and the same type of monitoring points are also obtained, and the target monitoring point and the same type of monitoring point are judged according to the position coordinate data whether they belong to the same terrain area (for example, whether they belong to the same plain terrain area, the same hilly terrain area, and correspondingly, the terrain type data of the target monitoring point and the same column monitoring point need to be obtained at this time). When the target monitoring point and the same type of monitoring point are in the same monitoring point, the same type of monitoring point is used as a similar monitoring point.

[0057] In some other embodiments, after obtaining the position coordinate data of the target monitoring point and similar monitoring points, the computing device calculates the spatial distance between the target monitoring point and similar monitoring points based on the position coordinate data, and only treats the similar monitoring points as similar monitoring points if the aforementioned spatial distance is less than the set distance.

[0058] As analyzed above, combined with the principle of photochemical reaction of ozone generation, the concentration of precursors (carbon oxides, nitrogen oxides) directly affects the rate of ozone generation and consumption under high-altitude conditions, and thus affects the rate of change of ozone concentration. The concentration of precursors in different regions may be significantly different due to the emission of pollution sources, which in turn causes a great difference in the rate of change of ozone concentration.

[0059] Based on the previous analysis, in some embodiments, in order to more accurately determine the ozone concentration prediction data when executing subsequent steps, after determining the same type of monitoring points, the computing device will also obtain the precursor concentration data of the same type of monitoring points and the target monitoring points, and determine whether the precursor concentrations of the same type of monitoring points and the target monitoring points are similar. In a specific implementation, the computing device can determine whether the precursor concentrations of the same type of monitoring points and the target monitoring points are in the same concentration range, and then determine whether the precursor concentrations are similar. Only when it is determined that the precursor concentrations of the same type of monitoring points and the target monitoring points are similar, the computing device will treat the same type of monitoring points as similar monitoring points.

[0060] After determining similar monitoring points, the computing device triggers the subsequent steps of acquiring ozone concentration monitoring data of similar monitoring points in the current time period and the previous time period.

[0061] S130: Calculate the predicted change rate based on the ozone concentration monitoring data of similar monitoring points in the current time period and the previous time period; and calculate the predicted ozone concentration data of the target monitoring point in the current time period based on the predicted change rate and the ozone concentration monitoring data of the target monitoring point in the previous time period.

[0062] After obtaining the ozone concentration monitoring data of similar monitoring points in the current time period and the previous time period, the computing device subtracts the ozone concentration monitoring data of the current time period from the ozone concentration monitoring data of the previous time period to obtain the difference, and compares the difference with the ozone concentration monitoring data of the previous time period to obtain the predicted change rate.

[0063] After obtaining the predicted change rate, the computing device uses the ozone concentration monitoring data of the target monitoring point in the previous period to calculate the ozone concentration according to c predict =c history ×(1+r predict ) Get the ozone concentration forecast data c for the current period predict . Where c historyis the ozone concentration monitoring data of the target monitoring point in the previous period, r pre di c t is the aforementioned predicted rate of change.

[0064] S140: Calculate the concentration difference ratio based on the ozone concentration prediction data and the ozone concentration monitoring data of the target monitoring point in the current period.

[0065] According to the above method, the computing device obtains the ozone concentration prediction data and ozone concentration monitoring data of the target monitoring point in the current period. The above data are then subtracted to obtain a difference, and the difference is compared with the ozone concentration prediction data or ozone concentration monitoring data (in the embodiment of the present disclosure, it is compared with the ozone concentration monitoring data), so that the concentration difference ratio can be obtained.

[0066] S150: When the concentration difference ratio is greater than a preset difference ratio, the target monitoring point is determined to be an ozone concentration abnormality point.

[0067] As analyzed above, because the target monitoring point and similar monitoring points (or similar monitoring points) are in the same cluster, they generally have the same trend of ozone concentration change. Accordingly, the ozone concentration prediction data determined based on the ozone concentration data of similar monitoring points and the ozone concentration monitoring data of the target monitoring point should not have a large difference ratio. If the difference ratio is large, it is not reasonable to determine the ozone concentration monitoring data of the target monitoring point based on the above premise, so the target monitoring point is determined to be an abnormal ozone concentration point.

[0068] In a specific implementation, in addition to determining whether the concentration difference ratio is greater than a preset difference ratio, in some embodiments, the computing device can also determine whether the ozone concentration monitoring point of the target monitoring point in the current period is reasonable by determining whether the concentration difference is greater than a preset difference, and then determine whether the target monitoring point is an abnormal ozone concentration point.

[0069] Using the embodiment scheme of the present disclosure, the computing device determines similar monitoring points in the target monitoring points through a pre-constructed ozone change trend cluster set, and screens similar monitoring points from the similar monitoring points, and predicts the ozone concentration prediction data of the target monitoring point in the current time period based on the similar monitoring points, and evaluates whether the ozone concentration monitoring data of the current time period is abnormal through the ozone concentration prediction data. In other words, the embodiment scheme of the present disclosure evaluates whether the ozone concentration monitoring data of the target monitoring point is abnormal by setting similar monitoring points that are independent of the target monitoring point. Using the embodiment scheme of the present disclosure, it is no longer based solely on the judgment of whether the target monitoring point itself is abnormal based on the ozone concentration data sequence of the target monitoring point, but with the help of similar external monitoring point monitoring data, it is judged whether the ozone concentration data of the target monitoring point is abnormal, thereby realizing the identification of systematic faults of the target monitoring point, and then more accurately determining whether the target monitoring point is an abnormal point.

[0070] In the specific implementation, considering that the single-period data has a large random error, directly using the single-period data to determine the abnormal point will also have a large randomness, resulting in a high probability of identification errors. To solve this problem, the ozone concentration monitoring data of the preset continuous monitoring period can be identified and judged, and when the ozone concentration difference exceeds the set number and is greater than the preset difference, or the concentration difference ratio is greater than the preset ratio difference, the target monitoring point is determined to be an ozone concentration abnormal point.

[0071] In actual implementation, the number of similar monitoring points to the target monitoring point may be small or large. When the number of similar monitoring points is small, the confidence of the result obtained by the above method is poor. In actual application, when there are many similar monitoring points (or similar monitoring points) (for example, greater than the preset statistical confidence number), the above method can be used to determine whether the target monitoring point is an abnormal ozone concentration point.

[0072] In some embodiments, there may be no monitoring points of the same type as the target monitoring points in the ozone change trend cluster. In this case, the computing device may use the following S160-S170 to determine whether the target monitoring point is an ozone concentration abnormal point.

[0073] S160: Obtain ozone concentration monitoring data of a target monitoring point monitored at multiple consecutive time periods, and calculate the standard deviation of the consecutive ozone concentration monitoring data.

[0074] S170: When the standard deviation is greater than the set deviation, the target monitoring point is determined to be an abnormal ozone concentration point.

[0075] According to the principle of ozone photochemical reaction and diffusion mechanism, the ozone concentration will change during the day (typically AM8:00-PM5:00), but the rate of change will not be too large. From a statistical point of view, the standard deviation of the ozone concentration monitoring data monitored at the target monitoring point in multiple consecutive time periods will not be too large. Based on this, when the same type of monitoring point of the target monitoring point cannot be obtained, the embodiment of the present disclosure analyzes the ozone concentration monitoring data of the target monitoring point to determine whether the target monitoring point is an abnormal ozone concentration point.

[0076] Specifically, the computing device obtains the ozone concentration monitoring data of the target monitoring point in multiple consecutive time periods and calculates the corresponding standard deviation. If the standard deviation is greater than the preset deviation, the premise that the ozone concentration monitoring data of multiple consecutive time periods will not change much is violated, and the target monitoring point is therefore identified as an ozone concentration abnormal point.

[0077] After determining the ozone anomaly points using the aforementioned method, the ozone monitoring devices at the ozone anomaly points can be checked for precision and accuracy, and the surrounding environment of the ozone anomaly points can be checked to identify the causes of abnormal monitoring data.

[0078] The previous article only used the ozone change trend cluster set. Here we analyze how to obtain the ozone change trend cluster set. Figure 2 1 is a flow chart of the method for implementing the present disclosure to determine the clustering set of ozone change trends. Figure 2 As shown, the method for constructing an ozone change trend cluster set includes S210-S230.

[0079] S210: Obtain a historical data sequence of ozone concentration obtained at each monitoring point in non-rainy or snowy weather.

[0080] As analyzed above, because rainwater has a strong absorption effect on ozone, the monitoring data under the corresponding weather conditions is meaningless. Therefore, the embodiment of the present disclosure obtains the historical data sequence of ozone concentration obtained at each monitoring point in non-rainy and snowy weather for cluster analysis. In the specific implementation, considering that the ozone concentration is very small under non-light conditions (under non-light conditions, ozone cannot be generated, and the ozone in the atmosphere is quickly consumed due to oxidation reactions), the historical data sequence of ozone concentration obtained is data under light conditions, for example, it can be data corresponding to the time zone of each location in AM8:00-PM5:00.

[0081] S220: Obtain an ozone concentration historical change rate sequence based on the ozone concentration historical data sequence of each monitoring point, wherein the ozone concentration historical change rate in the ozone concentration historical change sequence is obtained by comparing the subsequent data and the adjacent preceding data in the ozone concentration historical change rate.

[0082] After obtaining the historical data sequence of ozone concentration at each monitoring point, subtract the latter data from the previous data in the aforementioned sequence to obtain the ozone concentration change rate (this rate is relative to a statistical period), and sort the ozone concentration change rate of each monitoring point in chronological order to obtain the historical change rate sequence of ozone concentration.

[0083] S230: Perform cluster analysis on the historical change rate sequence of ozone concentration at each monitoring point to determine the cluster set to which each monitoring point belongs, where the cluster set includes similar monitoring points of each monitoring point.

[0084] After obtaining the historical change rate sequence of ozone concentration, cluster analysis is then performed on the aforementioned sequence. In specific implementation, the K clustering method can be used to determine the number of clusters by empirical setting, and then cluster analysis is performed on the data to determine the monitoring points included in each cluster set. In specific implementation, in addition to using the historical change rate sequence of ozone concentration at each monitoring point for cluster analysis, it is also possible to consider obtaining the precursor concentration data sequence at each monitoring point. His colleagues use the historical change rate sequence of ozone concentration and the precursor concentration data sequence for cluster analysis.

[0085] It should also be noted that in actual applications, if the ozone concentration monitoring device identifies that the device status is abnormal through self-inspection, it will generate an abnormal status mark to indicate that the corresponding monitoring data may be erroneous data. In this case, it is not necessary to use the aforementioned method to determine that the monitoring point is an abnormal point. Accordingly, it is only necessary to execute the aforementioned method and make corresponding judgments when the device status mark at the target monitoring point is a normal mark.

[0086] In addition to providing the aforementioned method for determining an abnormal ozone monitoring point, the embodiment of the present disclosure also provides a device for determining an abnormal ozone monitoring point. Figure 3 Schematic diagram of the structure of the device for determining the abnormal ozone monitoring point provided by the embodiment of the present disclosure. Figure 3 As shown, the device 300 for determining abnormal ozone monitoring points includes a similar point determination unit 301, a data acquisition unit 302, a predicted data calculation unit 303, a comparison unit 304 and an abnormal point determination unit 305.

[0087] The similar point determination unit 301 is used to determine whether there are similar monitoring points clustered with the target monitoring points from a pre-constructed ozone change trend cluster set, wherein the ozone change trend cluster set is obtained by clustering analysis based on the historical change rate sequence of ozone concentration obtained at each monitoring point under normal monitoring conditions, and when there are similar monitoring points as the target monitoring point in the ozone change trend cluster set, the similar monitoring points are regarded as similar monitoring points.

[0088] The data acquisition unit 302 is used to acquire the ozone concentration monitoring data of the similar monitoring points in the current time period and the previous time period.

[0089] The predicted data calculation unit 303 is used to calculate the predicted change rate based on the ozone concentration monitoring data of the similar monitoring points in the current time period and the previous time period, and to calculate the predicted ozone concentration data of the target monitoring point in the current time period based on the predicted change rate and the ozone concentration monitoring data of the target monitoring point in the previous time period.

[0090] The comparison unit 304 is used to calculate the concentration difference, or the concentration difference ratio, based on the ozone concentration prediction data and the ozone concentration monitoring data of the target monitoring point in the current period.

[0091] The abnormal point determination unit 305 is used to determine that the target monitoring point is an abnormal ozone concentration point when the concentration difference is greater than a preset difference or the concentration difference is greater than a preset ratio.

[0092] In some embodiments, the abnormal point determination unit 305 determines that the target monitoring point is an abnormal ozone concentration point when a preset number of ozone concentration differences exceed a preset difference, or a concentration difference ratio exceeds a preset ratio difference within a preset continuous monitoring period.

[0093] In some embodiments, when there are similar monitoring points in the ozone change trend cluster, the data acquisition unit 302 acquires the meteorological characteristic data of the similar monitoring points; when the similar monitoring points are non-rainy and snowy weather points, the similar point determination unit 301 uses the similar monitoring points as the similar monitoring points.

[0094] In some embodiments, the data acquisition unit 302 acquires the position coordinate data of the target monitoring point and the similar monitoring point, and calculates the spatial distance between the target monitoring point and the similar monitoring point based on the position coordinate data, or determines whether the target monitoring point and the similar monitoring point belong to the same terrain area based on the position coordinate data;

[0095] The similar unit determination unit regards the similar monitoring point as the similar monitoring point when the spatial distance is less than a set distance or the target monitoring point and the similar monitoring point are in the same terrain area.

[0096] In some embodiments, the data acquisition unit 302 acquires the precursor concentration data of the target monitoring point and the similar monitoring point, and determines whether the precursor concentrations of the similar monitoring point and the target monitoring point are similar; the similar unit determination unit regards the similar monitoring point as the similar monitoring point when the precursor concentration data of the similar monitoring point is similar to the precursor concentration data of the target monitoring point.

[0097] In some embodiments, before determining whether there are similar monitoring points clustered with the target monitoring points from a pre-constructed ozone change trend cluster set, the data acquisition unit 302 acquires a historical data sequence of ozone concentration acquired at each monitoring point in non-rainy or snowy weather; the clustering unit obtains a historical change rate sequence of ozone concentration based on the historical data sequence of ozone concentration at each monitoring point, wherein the historical change rate of ozone concentration in the historical change sequence of ozone concentration is obtained by comparing the subsequent data with the adjacent previous data in the historical change rate of ozone concentration; cluster analysis is performed on the historical change rate sequence of ozone concentration at each monitoring point to determine the cluster set to which each monitoring point belongs, wherein the cluster set includes similar monitoring points of each monitoring point.

[0098] In some embodiments, when there is no similar monitoring point to the target monitoring point in the ozone change trend clustering set, the abnormal point determination unit 305 obtains the ozone concentration monitoring data of the target monitoring point for multiple continuous time periods, and calculates the standard deviation of the continuous ozone concentration monitoring data; when the standard deviation is greater than the set deviation, the target monitoring point is determined to be an abnormal ozone concentration point.

[0099] In some embodiments, when the device status mark of the target monitoring point is a normal mark, the data acquisition unit 302 determines whether there are similar monitoring points clustered with the target monitoring point from the pre-constructed ozone change trend set.

[0100] The embodiment of the present disclosure also provides a computing device for implementing the aforementioned method. Figure 4 Schematic diagram of the structure of the computing device provided by the embodiment of the present disclosure. Figure 4 , which shows a schematic diagram of the structure of a computing device 400 suitable for implementing the embodiments of the present disclosure. Figure 4 The computing device shown is only an example and should not bring any limitation to the functionality and scope of use of the embodiments of the present disclosure.

[0101] like Figure 4As shown, the computing device 400 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory ROM 402 or a program loaded from a storage device 408 to a random access memory RAM 403. Various programs and data required for the operation of the computing device 400 are also stored in the RAM 403. The processing device 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output I / O interface 405 is also connected to the bus 404.

[0102] Typically, the following devices may be connected to the I / O interface 405: input devices 405 including, for example, a touch screen, a touch pad, a camera, a microphone, etc.; output devices 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 408 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 409. The communication devices 409 may allow the computing device 400 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The computing device 400 is shown with various devices, but it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have instead.

[0103] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 409, or installed from the storage device 408, or installed from the ROM 402. When the computer program is executed by the processing device 401, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0104] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable storage medium, a computer-readable signal medium, or any combination of the above two.

[0105] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0106] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer readable program codes. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than a computer readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0107] In some embodiments, the client and computing device can communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), internets (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.

[0108] The computer-readable medium may be included in the computing device, or may exist independently without being incorporated into the computing device.

[0109] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the tester computer, partially on the tester computer, as a separate software package, partially on the tester computer and partially on a remote computer, or entirely on a remote computer or computing device. In cases involving a remote computer, the remote computer may be connected to the tester computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0110] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated system based on hardware that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0111] The units involved in the embodiments described in the present disclosure may be implemented by software or by hardware. The name of the unit does not, in some cases, constitute a limitation on the unit itself. The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0112] The above are only specific embodiments of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for determining abnormal ozone monitoring points, characterized in that: include: Determine whether there are similar monitoring points clustered with the target monitoring points from a pre-constructed ozone change trend cluster set, wherein the ozone change trend cluster set is obtained by clustering analysis based on a historical change rate sequence of ozone concentration obtained at each monitoring point under normal monitoring conditions; In the case where there are similar monitoring points of the target monitoring point in the ozone change trend clustering set, the similar monitoring points are used as similar monitoring points, and the ozone concentration monitoring data of the similar monitoring points in the current time period and the previous time period are obtained; Calculating the predicted change rate based on the ozone concentration monitoring data of the similar monitoring points in the current time period and the previous time period; and calculating the predicted ozone concentration data of the target monitoring point in the current time period based on the predicted change rate and the ozone concentration monitoring data of the target monitoring point in the previous time period; Calculate the concentration difference or the concentration difference ratio based on the ozone concentration prediction data and the ozone concentration monitoring data of the target monitoring point in the current period; When the concentration difference is greater than a preset difference, or the concentration difference ratio is greater than a preset difference ratio, the target monitoring point is determined to be an ozone concentration abnormality point.

2. The determination method according to claim 1, characterized in that: Determining the target monitoring point as an abnormal ozone concentration point includes: When a preset number of ozone concentration differences exceeding a preset number within a preset continuous monitoring period is greater than a preset difference, or a concentration difference ratio is greater than a preset ratio difference, the target monitoring point is determined to be an ozone concentration abnormality point.

3. The determination method according to claim 1, characterized in that: When there are similar monitoring points in the ozone change trend cluster, obtaining meteorological characteristic data of the similar monitoring points; The taking the same type of monitoring points as similar monitoring points includes: taking the same type of monitoring points as similar monitoring points when the same type of monitoring points are non-rainy and snowy weather points.

4. The determination method according to claim 3, characterized in that: Also includes: Obtaining position coordinate data of the target monitoring point and the similar monitoring points; Calculating the spatial distance between the target monitoring point and the similar monitoring point based on the position coordinate data, or determining whether the target monitoring point and the similar monitoring point belong to the same terrain area based on the position coordinate data; Taking the same type of monitoring points as similar monitoring points includes: taking the same type of monitoring points as similar monitoring points when the spatial distance is less than a set distance or when the target monitoring point and the same type of monitoring points are in the same terrain area.

5. The determination method according to claim 3, characterized in that: Also includes: Acquiring precursor concentration data of the target monitoring point and the similar monitoring points, and determining whether the precursor concentrations of the similar monitoring points and the target monitoring point are similar; Taking the same type of monitoring points as similar monitoring points includes: taking the same type of monitoring points as the similar monitoring points when the precursor concentration data of the same type of monitoring points are similar to the precursor concentration data of the target monitoring points.

6. The determination method according to any one of claims 1 to 5, characterized in that: Before determining whether there are similar monitoring points clustered with the target monitoring points from the pre-constructed ozone change trend cluster set, the method further includes: Obtain the historical data sequence of ozone concentration obtained at each monitoring point in non-rainy and snowy weather; Obtaining an ozone concentration historical change rate sequence based on the ozone concentration historical data sequence of each monitoring point, wherein the ozone concentration historical change rate in the ozone concentration historical change sequence is obtained by comparing the subsequent data and the adjacent preceding data in the ozone concentration historical change rate; A cluster analysis is performed on the historical change rate sequence of the ozone concentration at each monitoring point to determine the cluster set to which each monitoring point belongs, wherein the cluster set includes monitoring points of the same type as each monitoring point.

7. The determination method according to any one of claims 1 to 5, characterized in that: Also includes: In the case where there is no similar monitoring point to the target monitoring point in the ozone change trend clustering set, the method further includes: Obtaining ozone concentration monitoring data of the target monitoring point monitored at multiple consecutive time periods, and calculating the standard deviation of the consecutive ozone concentration monitoring data; When the standard deviation is greater than the set deviation, the target monitoring point is determined to be an abnormal ozone concentration point.

8. The determination method according to any one of claims 1 to 5, characterized in that: The step of determining whether there are similar monitoring points clustered with the target monitoring points from the pre-constructed ozone change trend cluster set includes: When the device status mark of the target monitoring point is a normal mark, it is determined from the pre-constructed ozone change trend set whether there are similar monitoring points clustered with the target monitoring point.

9. A device for determining abnormal ozone monitoring points, characterized in that: include: A similar point determination unit is used to determine whether there are similar monitoring points clustered with the target monitoring points from a pre-constructed ozone change trend cluster set, wherein the ozone change trend cluster set is obtained by clustering analysis based on a historical change rate sequence of ozone concentration obtained at each monitoring point under normal monitoring conditions; A data acquisition unit, for, when there are similar monitoring points of the target monitoring point in the ozone change trend clustering set, taking the similar monitoring points as similar monitoring points, and acquiring ozone concentration monitoring data of the similar monitoring points in the current time period and the previous time period; A prediction data calculation unit, used to calculate the predicted change rate based on the ozone concentration monitoring data of the similar monitoring points in the current time period and the previous time period, and calculate the ozone concentration prediction data of the target monitoring point in the current time period based on the predicted change rate and the ozone concentration monitoring data of the target monitoring point in the previous time period; A comparison unit, used to calculate a concentration difference or a concentration difference ratio based on the ozone concentration prediction data and the ozone concentration monitoring data of the target monitoring point in the current period; The abnormal point determination unit is used to determine that the target monitoring point is an abnormal ozone concentration point when the concentration difference is greater than a preset difference or the concentration difference is greater than a preset ratio.

10. A computing device, characterized in that It comprises a processor and a memory, wherein the memory is used to store a computer program; when the computer program is loaded by the processor, the processor executes the method for determining an abnormal point of ozone monitoring as described in any one of claims 1 to 8.

Images