A method and device for online monitoring of air quality in landscaping

Abstract

The present application relates to the field of data processing technology, and specifically to an online monitoring method and device for air quality in gardening and greening, the method comprising: obtaining a pollutant gas concentration sequence and a pollutant gas concentration short-time sequence according to the pollutant gas concentration in each monitoring range of the garden for a period of time; obtaining a fluctuation value according to the fluctuation characteristics of the elements in the sequence; obtaining a trend discrimination value according to the trend characteristics of the sequence, combined with the change characteristics of the environmental parameters in the corresponding time periods of the two sequences; obtaining an adaptive weight value based on the trend discrimination value and the fluctuation value, using an exponential moving average algorithm for the pollutant gas sequence, combined with the pollutant gas concentration threshold, to determine whether the pollutant gas concentration at the next moment exceeds the standard. The present application aims to select a suitable weight value according to the trend characteristics and fluctuation characteristics of the pollutant gas concentration, and use the exponential moving average algorithm for prediction, so that the prediction result is more accurate and the reliability of the monitoring result is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an online monitoring method and device for air quality in landscaping. Background Art

[0002] There is a mutually reinforcing relationship between gardening and air quality. Gardening can improve air quality, and good air quality is also conducive to the development and maintenance of gardening. The quality of air directly affects the health and growth of plants. Good air quality can reduce the harm of pollutants to plants and reduce the invasion of plants by pests and diseases. In order to keep the air quality in the garden in a healthy state, it is necessary to monitor the air quality in the garden. By monitoring the concentration of pollutants in the air, the air quality can be evaluated, and then corresponding countermeasures can be taken to ensure the healthy growth of plants in the garden.

[0003] The existing air quality monitoring method is to use the exponential moving average method to predict the pollutant concentration in the future time period. If the predicted pollutant concentration exceeds the set threshold, a corresponding warning and intervention will be made. This method can take corresponding measures to prevent the pollutant concentration from exceeding the standard before it exceeds the standard. However, the exponential moving average method is greatly affected by the weight setting. If the weight setting is improper, it may cause a deviation between the prediction and the actual data. When the data change trend is obvious, the predicted value may not accurately reflect the actual situation, and thus it is impossible to accurately monitor and alarm the air quality of the landscaping. Summary of the invention

[0004] In view of the above, it is necessary to provide a method and device for online monitoring of air quality in landscaping to solve the above problems.

[0005] The first aspect of the present application provides a method for online monitoring of air quality in landscaping, the method comprising:

[0006] The concentrations of various pollutants at each sampling time in each monitoring range of the garden and at a preset number of sampling times before are combined into a sequence of concentrations of various pollutants at each sampling time;

[0007] For each sampling time in each monitoring range, the sequence composed of the concentrations of various pollutants at each sampling time and a set number of times before is used as the short-time sequence of the concentrations of various pollutants at each sampling time; according to the fluctuation characteristics of the elements in the short-time sequence of the concentrations of various pollutants, the fluctuation values ​​of the concentrations of various pollutants are obtained;

[0008] According to the trend characteristics of the short-time series of various pollutant gas concentrations at each sampling time in each monitoring range, combined with the pollutant gas concentration series at each sampling time and the change characteristics of various environmental parameters in the corresponding time period of the pollutant gas concentration short-time series, the trend discrimination value of various pollutant gas concentrations at each sampling time in each monitoring range is obtained;

[0009] Based on the trend judgment value and the fluctuation value, the weight values ​​of the concentrations of various pollutants at all sampling moments in each monitoring range are obtained, and the exponential moving average algorithm is used for the concentration sequences of various pollutants. Combined with the preset thresholds of various pollutant concentrations, it is determined whether the concentrations of various pollutants at the next sampling moment in each monitoring range exceed the standard.

[0010] The fluctuation values ​​of the concentrations of various pollutants at each sampling time are specifically:

[0011] For each sampling moment, the information entropy and first-order difference sequence of various pollutant gas concentration short-time series are obtained; the number of extreme points of various pollutant gas concentration short-time series is obtained; the sum of all elements in the first-order difference sequence is calculated; based on the information entropy, the number of extreme points and the sum, the fluctuation value of various pollutant gas concentrations at each sampling moment is obtained, wherein the fluctuation value is positively correlated with the information entropy, the number of extreme points and the sum.

[0012] The trend discrimination values ​​of the concentrations of various pollutants at each sampling time in each monitoring range are obtained as follows:

[0013] According to the comparison results of the number of positive and negative elements in the first-order difference sequence of the short-time series of the concentration of various pollutants at each sampling time in each monitoring range, combined with the distribution of all elements in the first-order difference sequence, the initial trend discrimination value of the short-time series of the concentration of various pollutants at each sampling time in each monitoring range is obtained;

[0014] For each sampling time in each monitoring range, the overall difference characteristics of various environmental parameters in the corresponding time period of various pollutant gas concentration series and the corresponding time period of pollutant gas concentration short-time series are combined to obtain the trend correction factors of various pollutant gas concentrations;

[0015] The result of multiplying the initial trend judgment value by the trend correction factor is used as the trend judgment value of the concentration of various pollutant gases at each sampling time in each monitoring range.

[0016] Among them, the initial trend discrimination value is specifically:

[0017] The absolute value of the difference between the number of positive elements and the number of negative elements in the first-order difference sequence of the short-time series of the concentration of various pollutants at each sampling moment in each monitoring range is obtained, and the absolute value of the sum of all elements in the first-order difference sequence is calculated; based on the absolute value of the difference and the absolute value of the sum, the initial trend judgment value of the short-time series of the concentration of various pollutants at each sampling moment in each monitoring range is obtained; wherein the initial trend judgment value is positively correlated with the absolute value of the difference and the absolute value of the sum.

[0018] The process of obtaining trend correction factors of various pollutant gas concentrations includes:

[0019] The average values ​​of various environmental parameters of the time period corresponding to the short-time series of various pollutant gas concentrations at each sampling moment are recorded as the first mean value; the average values ​​of various environmental parameters of the time period corresponding to the various pollutant gas concentration sequences at each sampling moment are recorded as the second mean value; the negative correlation mapping result of the difference between the first mean value and the second mean value of all environmental parameters of various pollutant gas concentrations at each sampling moment is fused as the trend correction factor of various pollutant gas concentrations at each sampling moment.

[0020] The environmental parameters include: pedestrian flow, vehicle flow, and rainfall.

[0021] The process of obtaining the weighted values ​​of the concentrations of various pollutant gases at each sampling time in each monitoring range includes:

[0022] Based on the trend judgment value and fluctuation value of the concentration of various pollutants in each monitoring range at each sampling time, the adjustment factor of the concentration of various pollutants in each monitoring range at each sampling time is obtained;

[0023] Obtain the maximum value of the adjustment factor of various pollutant gas concentrations at all sampling moments in all monitoring ranges within a preset time period; calculate the ratio of the adjustment factor of various pollutant gas concentrations at each sampling moment in each monitoring range to the maximum value; based on the ratio and the first preset value and the second preset value, obtain the weight value of various pollutant gas concentrations at each sampling moment in each monitoring range; wherein the first preset value is less than the second preset value, and the sum of the first preset value and the second preset value is 1; the weight value is positively correlated with the ratio, the first preset value, and the second preset value.

[0024] The adjustment factor is specifically the ratio of the trend determination value to the fluctuation value.

[0025] The step of judging whether the concentration of various pollutant gases in each monitoring range exceeds the standard at the next sampling time is as follows:

[0026] The exponential moving average is used for the concentration sequence of various pollutants at each sampling time in each monitoring range, and the predicted value of the concentration of various pollutants at the next sampling time in each monitoring range is obtained in combination with the weight value;

[0027] If the predicted value is greater than the corresponding pollutant gas concentration threshold, it is determined that the pollutant gas concentration exceeds the standard; otherwise, it is determined that the pollutant gas concentration does not exceed the standard.

[0028] In a second aspect, an embodiment of the present application further provides an online monitoring device for air quality in landscaping, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above-mentioned methods when executing the computer program.

[0029] In the above scheme, firstly, a sequence consisting of various pollutant gas concentration data at each sampling time in each monitoring range in different time periods in the garden is obtained. The beneficial effect is that the overall change and local change characteristics of the pollutant gas concentration data can be analyzed through sequences of different time lengths. Since the prediction value of the exponential moving average algorithm is based on the data characteristics of the adjacent moments, the short-time series of pollutant gas concentration is obtained to construct a fluctuation value. The beneficial effect is that the volatility of the pollutant gas concentration is analyzed; further, the trend characteristics of the short-time series of pollutant gas concentration are analyzed, and the trend discrimination value is constructed in combination with the environmental parameters in the garden. The beneficial effect is that the change trend of the short-time series of pollutant gas concentration when the garden environment changes is further considered and adjusted, which helps to provide a more accurate trend discrimination value, so that it can better reflect the actual pollution trend and prepare for the subsequent improvement of the accuracy of prediction and management; based on the trend discrimination value and the fluctuation value, the exponential moving average algorithm is used for the pollutant gas sequence. The beneficial effect is that the weight value can be adaptively adjusted according to the trend characteristics of the pollutant gas concentration to improve the accuracy and stability of the prediction; further, the monitoring results are obtained based on the prediction results, which helps to obtain more accurate monitoring results. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 A flowchart of a method for online monitoring of air quality in landscaping provided in one embodiment of the present application;

[0031] Figure 2 A flow chart for obtaining a trend discrimination value provided in one embodiment of the present application. DETAILED DESCRIPTION

[0032] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example" and the like are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "or", "for example" and the like is intended to present related concepts in a concrete manner.

[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the present application. The terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application.

[0034] It should also be noted that the terms "first" and "second" in this application and the accompanying drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The method disclosed in the embodiments of the present application or the method shown in the flow chart includes one or more steps for implementing the method. Without departing from the scope of protection of the present application, the execution order of multiple steps can be interchanged with each other, and some steps can also be deleted.

[0035] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0036] The following is a detailed description of a specific scheme of an online monitoring method and device for air quality in landscaping provided by the present application in conjunction with the accompanying drawings.

[0037] See also Figure 1 , which shows a flow chart of the steps of an online monitoring method for air quality of landscaping provided by an embodiment of the present application, the method comprising the following steps:

[0038] The first step: combine the concentrations of various pollutants at each sampling moment in each monitoring range of the garden and the previously preset number of sampling moments into a sequence of concentrations of various pollutants at each sampling moment.

[0039] When monitoring the air quality in a garden, the monitoring range is first planned. This application divides the garden equally to obtain several monitoring ranges, and arranges a group of sensors in the center of each monitoring range. Each group of sensors includes a PM2.5 sensor, a PM10 sensor, a sulfur dioxide sensor, a nitrogen dioxide sensor, an ozone sensor and a carbon monoxide sensor; the data collected by each group of sensors includes PM2.5 concentration, PM10 concentration, sulfur dioxide concentration, nitrogen dioxide concentration, ozone concentration and carbon monoxide concentration.

[0040] All sensors collect pollutant gas data at the same frequency, once every hour, and the average concentration value of various pollutant gas concentrations in each monitoring range at all times of the day is used as the pollutant gas concentration at each sampling moment of each monitoring range; for one pollutant gas concentration, the pollutant gas concentration at each sampling moment and the previous preset number of sampling moments are combined into a pollutant gas concentration sequence at each sampling moment of each monitoring range. In this implementation, the preset number is 90, and the area of ​​the monitoring range is 500 square meters.

[0041] It should be noted that, since data loss may occur when the sensor transmits data, the missing values ​​in the data are filled using the nearest distance interpolation method. The nearest distance interpolation method is a well-known technology, and the specific process will not be repeated here.

[0042] The second step: for each sampling moment in each monitoring range, the sequence composed of the concentrations of various pollutants at each sampling moment and a set number of moments before is used as the short-time sequence of the concentrations of various pollutants at each sampling moment; based on the fluctuation characteristics of the elements in the short-time sequence of the concentrations of various pollutants, the fluctuation values ​​of the concentrations of various pollutants are obtained.

[0043] The air quality of a garden is affected by multiple factors, including industrial emissions, traffic emissions, vegetation coverage, and weather. In order to ensure that the air quality in the garden is at a healthy level, it is necessary to monitor the air quality of each area of ​​the garden in real time and predict the air quality for a period of time in the future. When it is found that the air quality is declining or has a trend of deterioration, the cause needs to be analyzed quickly and measures need to be taken to improve it.

[0044] Since the analysis method for various pollutant gas concentration sequences in each monitoring range of the garden is the same, this application takes the nth pollutant gas concentration sequence at the jth sampling moment of the ith monitoring range as an example for analysis. When the exponential moving average algorithm is used to predict the nth pollutant gas concentration at the j+1th sampling moment, the weight value can be adjusted according to the volatility of the pollutant gas concentration sequence. When the fluctuation of the data closer to the jth sampling moment in the pollutant gas concentration sequence is large, it means that these data are accidental and insufficient to reflect the future trend of the data. It should be predicted based on data over a longer period of time, and a larger weight value should be selected at this time; when the fluctuation of the data closer to the jth sampling moment in the pollutant gas concentration sequence is small, it means that the data is in a relatively stable state of change, and the latest data can reflect the trend of data changes. It can be predicted based on data in a relatively recent time period, and a smaller weight value should be selected.

[0045] Based on this, the various pollutant gas concentration sequences at each sampling moment are intercepted to obtain the short-time sequences of the various pollutant gas concentrations at each sampling moment: the sequence composed of the various pollutant gas concentrations at each sampling moment and a set number of moments before is used as the short-time sequence of the various pollutant gas concentrations at each sampling moment. In this embodiment, the set number is 30, and the implementer can adjust it according to the actual situation. This application does not impose any restrictions on this.

[0046] Furthermore, according to the fluctuation characteristics of the elements in the short-term series of the concentration of various pollutants at each sampling moment, the fluctuation values ​​of the concentration of various pollutants at each sampling moment are obtained:

[0047] For each sampling moment, the information entropy and first-order difference sequence of various pollutant gas concentration short-time series are obtained; the number of extreme points of various pollutant gas concentration short-time series is obtained; the sum of all elements in the first-order difference sequence is calculated; based on the information entropy, the number of extreme points and the sum, the fluctuation value of various pollutant gas concentrations at each sampling moment is obtained, wherein the fluctuation value is positively correlated with the information entropy, the number of extreme points and the sum.

[0048] It should be noted that a positive correlation indicates that as one variable increases, another variable also increases; a negative correlation indicates that as one variable increases, another variable also decreases.

[0049] In this embodiment, the short-time series of various pollutant gas concentrations at each sampling moment are fitted, and an extreme value detection algorithm is used to obtain all extreme value points, wherein the extreme value detection algorithm is an existing well-known technology and is not elaborated in this application; the fluctuation value is specifically: the absolute values ​​of all elements in the first-order difference sequence are summed up, and the product of the cumulative sum, the information entropy and the number of extreme value points is used as the fluctuation value.

[0050] It should be understood that the greater the information entropy of the short-time series of various pollutant gas concentrations, the greater the data fluctuation in the local range corresponding to the sampling time; when the greater the sum of the absolute values ​​of all elements in the first-order difference series of the short-time series of various pollutant gas concentrations, the greater the number of extreme points, which further indicates that the greater the data fluctuation amplitude and fluctuation frequency in the short-time series of various pollutant gas concentrations corresponding to the sampling time, the more obvious the fluctuation characteristics.

[0051] The third step: According to the trend characteristics of the short-time series of various pollutant gas concentrations at each sampling time in each monitoring range, combined with the pollutant gas concentration series at each sampling time and the change characteristics of various environmental parameters in the corresponding time period of the pollutant gas concentration short-time series, the trend judgment value of various pollutant gas concentrations at each sampling time in each monitoring range is obtained.

[0052] The predicted value of the concentration of the nth pollutant gas at the j+1th sampling moment is not only related to the volatility of the short-term series of the nth pollutant gas at the jth sampling moment, but also to the trend of data changes. For the exponential moving average algorithm, when the short-term series of the concentration of the nth pollutant gas at the jth sampling moment shows a more obvious upward or downward trend, in order to enable the exponential moving average algorithm to capture data changes more quickly, the weight value can be increased to make the predicted value more sensitive to recent data; when the short-term series of the concentration of the nth pollutant gas at the jth sampling moment shows a stable trend, it is not necessary to give a large weight to the recent data, so as to avoid being too sensitive to changes in recent data. Appropriately reducing the weight value can more steadily reflect the long-term trend of the data.

[0053] Based on this, according to the comparison results of the number of positive and negative elements in the first-order difference sequence of the short-time series of various pollutant gas concentrations at each sampling time in each monitoring range, combined with the distribution of all elements in the first-order difference sequence, the initial trend discrimination value of the short-time series of various pollutant gas concentrations at each sampling time in each monitoring range is obtained:

[0054] The absolute value of the difference between the number of positive elements and the number of negative elements in the first-order difference sequence of the short-time series of the concentration of various pollutants at each sampling moment in each monitoring range is obtained, and the absolute value of the sum of all elements in the first-order difference sequence is calculated; based on the absolute value of the difference and the absolute value of the sum, the initial trend judgment value of the short-time series of the concentration of various pollutants at each sampling moment in each monitoring range is obtained; wherein the initial trend judgment value is positively correlated with the absolute value of the difference and the absolute value of the sum.

[0055] In this embodiment, the absolute value of the difference is recorded as A, the absolute value of the sum is recorded as B, and the initial trend judgment value is recorded as C. The specific formula is: ,in, Represents an exponential function with a natural constant as base.

[0056] It should be understood that when the number of positive numbers and the number of negative numbers in the first-order difference sequence of the short-time series of various pollutant gas concentrations at each sampling moment in each monitoring range differ greatly, it further indicates that the short-time series of such pollutant gas may be on an upward or downward trend; when the absolute value of the sum of all elements in the first-order difference sequence is larger, it further indicates that the short-time series of such pollutant gas is more likely to show an upward or downward trend; the larger the initial trend judgment value is, the greater the possibility that the short-time series of various pollutant gas concentrations at each sampling moment in each monitoring range will show a certain trend.

[0057] In addition, the rising or falling trend of the short-term series of various pollutant gas concentrations at each sampling time in each monitoring range may be caused by a certain factor in the environment. For example, the activities held in the garden in recent days have caused a sudden increase in the flow of people, which in turn has led to an upward trend in the concentration of a certain pollutant gas. However, when the flow of people in the garden returns to normal, this upward trend will no longer exist, and the concentration of this pollutant gas will still remain in a normal state. Therefore, the initial trend judgment value of the short-term series of a certain pollutant gas concentration cannot accurately reflect the true change trend of the concentration of this pollutant gas, and the trend judgment value must be corrected according to sudden factors in the environment.

[0058] Specifically, for each sampling time in each monitoring range, the overall difference characteristics of various environmental parameters in the corresponding time periods of various pollutant gas concentration sequences and the corresponding time periods of short-time series of pollutant gas concentrations are combined to obtain the trend correction factors of various pollutant gas concentrations:

[0059] The average values ​​of various environmental parameters of the time period corresponding to the short-time series of various pollutant gas concentrations at each sampling moment are recorded as the first mean value; the average values ​​of various environmental parameters of the time period corresponding to the various pollutant gas concentration sequences at each sampling moment are recorded as the second mean value; the negative correlation mapping result of the difference between the first mean value and the second mean value of all environmental parameters of various pollutant gas concentrations at each sampling moment is fused as the trend correction factor of various pollutant gas concentrations at each sampling moment; the product of the initial trend judgment value and the trend correction factor is used as the trend judgment value of various pollutant gas concentrations at each sampling moment.

[0060] The environmental parameters considered in this embodiment include human traffic, vehicle traffic, and rainfall; the difference between variables is measured by calculating the absolute value of the difference; multiple variables are merged by multiplication; the negative correlation mapping of variables is specifically expressed as the reciprocal of the variables. The trend judgment value of the concentration of the nth pollutant gas at the jth sampling time in the ith monitoring range is recorded as , its formula form is: ;in, It represents the average rainfall in the corresponding time period of the short-time series of the nth pollutant gas concentration at the jth sampling time in the ith monitoring range; It represents the average rainfall in the corresponding time period of the nth pollutant gas concentration sequence at the jth sampling time in the ith monitoring range; It represents the average value of the flow of people in the corresponding time period of the short-time series of the concentration of the nth pollutant gas at the jth sampling time in the ith monitoring range; It represents the average value of the flow of people in the corresponding time period of the nth pollutant gas concentration sequence at the jth sampling time in the ith monitoring range; It represents the average value of the vehicle flow in the corresponding time period of the short-term series of the nth pollutant gas concentration at the jth sampling time in the ith monitoring range; It represents the average value of the vehicle flow in the corresponding time period of the nth pollutant gas concentration sequence at the jth sampling time in the ith monitoring range; Represents an exponential function with a natural constant as base; It represents the initial trend judgment value of the concentration of the nth pollutant gas at the jth sampling time in the ith monitoring range; It represents the trend correction factor of the concentration of the nth pollutant gas at the jth sampling moment in the ith monitoring range.

[0061] It should be noted that before averaging the environmental parameters in different time periods, various environmental parameters need to be normalized. This embodiment adopts the maximum and minimum value normalization method.

[0062] Among them, the flow chart for obtaining the trend discrimination value is as follows: Figure 2 shown.

[0063] It should be understood that when the differences in rainfall, pedestrian flow and vehicle flow in different time periods cause the short-term pollutant gas concentration to change more strongly than the trend of the pollutant gas concentration under normal circumstances, the pollutant gas concentration will also return to normal when the rainfall, pedestrian flow and vehicle flow return to normal. In order to make the trend judgment value of the short-term pollutant gas concentration reflect the trend under normal circumstances, the initial trend judgment value should be reduced.

[0064] The fourth step: based on the trend judgment value and the fluctuation value, the weight values ​​of the concentrations of various pollutants at all sampling moments in each monitoring range are obtained, and the exponential moving average algorithm is used for the concentration sequences of various pollutants. Combined with the preset thresholds of various pollutant concentrations, it is determined whether the concentrations of various pollutants at the next sampling moment in each monitoring range exceed the standard.

[0065] Based on the trend judgment value and fluctuation value of the concentration of various pollutants in each monitoring range at each sampling time, the adjustment factor of the concentration of various pollutants in each monitoring range at each sampling time is obtained; wherein the adjustment factor is positively correlated with the trend judgment value and negatively correlated with the fluctuation value.

[0066] In this embodiment, the ratio of the trend determination value to the fluctuation value is used as the adjustment factor.

[0067] According to the distribution difference of the fluctuation value of each pollutant gas concentration at each sampling time in each monitoring range and all monitoring ranges, the weight value of each pollutant gas concentration at each sampling time in each monitoring range is obtained:

[0068] Obtain the maximum value of the adjustment factor of various pollutant gas concentrations at all sampling moments in all monitoring ranges within a preset time period; calculate the ratio of the adjustment factor of various pollutant gas concentrations at each sampling moment in each monitoring range to the maximum value; based on the ratio and the first preset value and the second preset value, obtain the weight value of various pollutant gas concentrations at each sampling moment in each monitoring range; wherein the first preset value is less than the second preset value, and the sum of the first preset value and the second preset value is 1; the weight value is positively correlated with the ratio, the first preset value, and the second preset value.

[0069] In this embodiment, the preset time period is a time period consisting of each sampling moment and a preset number of sampling moments before, and the preset number is 90; the weight value of the concentration of the nth pollutant gas at the jth sampling moment in the i-th monitoring range is recorded as , its formula form is: ;in, It represents the adjustment factor of the concentration of the nth pollutant gas at the jth sampling time in the ith monitoring range; Indicates the maximum adjustment factor of the concentration of the nth pollutant gas within a preset time period; Indicates the first preset value, which is 0.3; represents the second preset value, which is 0.7. It should be noted that ,and , in order to ensure that the weight value is greater than the second preset value and less than 1.

[0070] It should be understood that when the fluctuation value is small, it means that the volatility of the short-term series of pollutant gas concentration is small. When the trend judgment value is larger, it means that the overall trend of the pollutant gas concentration is greater. At this time, the adjustment factor makes the corresponding weight value larger, so that the exponential moving average algorithm makes predictions based on data with small short-term volatility and overall trend, so that the predicted value can better reflect the trend of pollutant gas concentration.

[0071] The weight values ​​of the concentrations of various pollutants in each monitoring range at the current sampling time are used as the weight values ​​of the exponential moving average algorithm to predict the concentrations of various pollutants in each monitoring range at the next sampling time:

[0072] An exponential moving average algorithm is used for the sequence composed of various pollutant gas concentrations within the preset time period of each monitoring range, combined with the corresponding weight value, to obtain the predicted value of the various pollutant gas concentrations at the next sampling moment of each monitoring range; if the predicted value is greater than the corresponding pollutant gas concentration threshold, it is judged that the pollutant gas concentration exceeds the standard; otherwise, it is judged that the pollutant gas concentration does not exceed the standard.

[0073] In this embodiment, the concentration thresholds of PM2.5 concentration, PM10 concentration, sulfur dioxide concentration, nitrogen dioxide concentration, ozone concentration and carbon monoxide concentration are 75 micrograms / m3, 150 micrograms / m3, 60 micrograms / m3, 80 micrograms / m3, 160 micrograms / m3 and 4 milligrams / m3 respectively. If the concentration of polluted gas exceeds the threshold, the alarm module will sound an alarm to remind the garden staff to take certain measures to improve the air quality.

[0074] Based on the same inventive concept as the above method, an embodiment of the present application also provides an online air quality monitoring device for landscaping, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above-mentioned online air quality monitoring methods for landscaping when executing the computer program.

[0075] In summary, the embodiment of the present application first obtains a sequence composed of various pollutant gas concentration data at each sampling time within different time periods in each monitoring range in the garden. Its beneficial effect is that the overall change and local change characteristics of the pollutant gas concentration data can be analyzed through sequences of different time lengths. Since the prediction value of the exponential moving average algorithm is based on the data characteristics of adjacent moments, the short-time series of pollutant gas concentration is obtained and the fluctuation value is constructed. Its beneficial effect is to analyze the volatility of the pollutant gas concentration; further, the trend characteristics of the short-time series of pollutant gas concentration are analyzed, and combined with the environmental parameters in the garden, a trend discrimination value is constructed. Its beneficial effect is to further consider the change trend of the short-time series of pollutant gas concentration when the garden environment changes, and adjust it, which helps to provide a more accurate trend discrimination value, so that it can better reflect the actual pollution trend, and prepare for the subsequent improvement of the accuracy of prediction and management; based on the trend discrimination value and the fluctuation value, the exponential moving average algorithm is used for the pollutant gas sequence, which has the beneficial effect that the weight value can be adaptively adjusted according to the trend characteristics of the pollutant gas concentration to improve the accuracy and stability of the prediction; further, based on the prediction results, the monitoring results are obtained, which helps to obtain more accurate monitoring results.

[0076] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the 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. In some alternative implementations, the function marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two continuous operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

[0077] For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the basic features of the present application. Therefore, no matter from which point of view, the above embodiments of the present application should be regarded as exemplary and non-restrictive; the technical solutions recorded in the above embodiments are modified, or some of the technical features are replaced by equivalents, which does not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for online monitoring of air quality in landscaping, characterized in that: The method comprises the following steps: The concentrations of various pollutants at each sampling time in each monitoring range of the garden and at a preset number of sampling times before are combined into a sequence of concentrations of various pollutants at each sampling time; For each sampling time in each monitoring range, the sequence composed of the concentrations of various pollutants at each sampling time and the previously set number of times is used as the short-time sequence of the concentrations of various pollutants at each sampling time; according to the fluctuation characteristics of the elements in the short-time sequence of the concentrations of various pollutants, the fluctuation values ​​of the concentrations of various pollutants are obtained; According to the trend characteristics of the short-time series of various pollutant gas concentrations at each sampling time in each monitoring range, combined with the pollutant gas concentration series at each sampling time and the change characteristics of various environmental parameters in the corresponding time period of the pollutant gas concentration short-time series, the trend discrimination value of various pollutant gas concentrations at each sampling time in each monitoring range is obtained; Based on the trend discrimination value and the fluctuation value, the weight values ​​of the concentrations of various pollutants at all sampling moments in each monitoring range are obtained, and the exponential moving average algorithm is used for the concentration sequences of various pollutants, combined with the preset concentration thresholds of various pollutants, to determine whether the concentrations of various pollutants at the next sampling moment in each monitoring range exceed the standard; The trend discrimination values ​​of the concentrations of various pollutants in each monitoring range at each sampling time are obtained as follows: According to the comparison results of the number of positive and negative elements in the first-order difference sequence of the short-time series of the concentration of various pollutants at each sampling time in each monitoring range, combined with the distribution of all elements in the first-order difference sequence, the initial trend discrimination value of the short-time series of the concentration of various pollutants at each sampling time in each monitoring range is obtained; For each sampling time in each monitoring range, the overall difference characteristics of various environmental parameters in the corresponding time period of various pollutant gas concentration series and the corresponding time period of pollutant gas concentration short-time series are combined to obtain the trend correction factors of various pollutant gas concentrations; The result of multiplying the initial trend determination value by the trend correction factor is used as the trend determination value of the concentration of various pollutants at each sampling time in each monitoring range; The process of obtaining the weighted values ​​of the concentrations of various pollutant gases at each sampling time in each monitoring range includes: Based on the trend judgment value and fluctuation value of the concentration of various pollutants in each monitoring range at each sampling time, the adjustment factor of the concentration of various pollutants in each monitoring range at each sampling time is obtained; Obtain the maximum value of the adjustment factor of various pollutant gas concentrations at all sampling moments in all monitoring ranges within a preset time period; calculate the ratio of the adjustment factor of various pollutant gas concentrations at each sampling moment in each monitoring range to the maximum value; based on the ratio and the first preset value and the second preset value, obtain the weight value of various pollutant gas concentrations at each sampling moment in each monitoring range; wherein the first preset value is less than the second preset value, and the sum of the first preset value and the second preset value is 1; the weight value is positively correlated with the ratio, the first preset value, and the second preset value.

2. The method for online monitoring of air quality in landscaping as claimed in claim 1, characterized in that: The fluctuation values ​​of the concentrations of various pollutant gases at each sampling time are specifically: For each sampling moment, the information entropy and first-order difference sequence of various pollutant gas concentration short-time series are obtained; the number of extreme points of various pollutant gas concentration short-time series is obtained; the sum of all elements in the first-order difference sequence is calculated; based on the information entropy, the number of extreme points and the sum, the fluctuation value of various pollutant gas concentrations at each sampling moment is obtained, wherein the fluctuation value is positively correlated with the information entropy, the number of extreme points and the sum.

3. The method for online monitoring of air quality in landscaping as claimed in claim 1, characterized in that: The initial trend discrimination value is specifically: Obtain the absolute value of the difference between the number of positive elements and the number of negative elements in the first-order difference sequence of the short-time series of the concentration of various pollutants at each sampling time in each monitoring range, and calculate the absolute value of the sum of all elements in the first-order difference sequence; based on the absolute value of the difference and the absolute value of the sum, obtain the initial trend discrimination value of the short-time series of the concentration of various pollutants at each sampling time in each monitoring range; The initial trend judgment value is positively correlated with the absolute value of the difference and the absolute value of the sum.

4. The method for online monitoring of air quality in landscaping as claimed in claim 1, characterized in that: The process of obtaining trend correction factors of various pollutant gas concentrations includes: The average values ​​of various environmental parameters of the time period corresponding to the short-time series of various pollutant gas concentrations at each sampling moment are recorded as the first mean value; the average values ​​of various environmental parameters of the time period corresponding to the various pollutant gas concentration sequences at each sampling moment are recorded as the second mean value; the negative correlation mapping result of the difference between the first mean value and the second mean value of all environmental parameters of various pollutant gas concentrations at each sampling moment is fused as the trend correction factor of various pollutant gas concentrations at each sampling moment.

5. The method for online monitoring of air quality in landscaping as claimed in claim 1, characterized in that: The environmental parameters include: pedestrian flow, vehicle flow, and rainfall.

6. The method for online monitoring of air quality in landscaping as claimed in claim 1, characterized in that: The adjustment factor is specifically the ratio of the trend determination value to the fluctuation value.

7. The method for online monitoring of air quality in landscaping as claimed in claim 1, characterized in that: The steps of judging whether the concentration of various pollutant gases in each monitoring range exceeds the standard at the next sampling time are as follows: The exponential moving average is used for the concentration sequence of various pollutants at each sampling time in each monitoring range, and the predicted value of the concentration of various pollutants at the next sampling time in each monitoring range is obtained in combination with the weight value; If the predicted value is greater than the corresponding pollutant gas concentration threshold, it is determined that the pollutant gas concentration exceeds the standard; otherwise, it is determined that the pollutant gas concentration does not exceed the standard.

8. An online monitoring device for air quality in landscaping, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

Images