A method and system for collecting dust concentration data in pavement construction

Abstract

The present invention relates to the technical field of data processing, and particularly relates to a method and system for collecting dust concentration data in road construction. The present invention analyzes the volatility of the dust concentration in each time series segment and analyzes the stability index of the environmental data in each time series segment to obtain the influence index of the environmental data; then analyzes the relative change rate and change trend of the dust concentration in each time series segment to obtain the final abnormal degree of the dust state in each time series segment; takes the final abnormal degree as the data weight of the dust concentration in the corresponding time series segment to obtain the weighted dust concentration. By assigning different weights to different dust concentration data, the present invention reduces the influence of noise data, improves the importance of unstable data when abnormalities occur during the construction process, and thus ensures the accuracy of the collected dust concentration data.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly relates to a method and system for collecting dust concentration data in road construction. Background Art

[0002] The dust concentration situation in the highway construction area is the basis for the dynamic regulation of the water demand of the automatic spraying device. Usually, the predictive regulation is achieved by installing sensors to monitor meteorological parameters such as the temperature, humidity, and wind speed of the environment in real time. Sudden weather changes, temperature fluctuations, or rapid changes in wind speed in the construction area will cause fluctuations in the sensor monitoring data, and these environmental changes lead to data fluctuations, which are important reference data for the dynamic regulation of water demand.

[0003] However, the monitoring data of the sensors installed in and around the construction area will inevitably be affected by construction activities. In addition, it may also be affected by the measurement error of the sensors themselves, resulting in abnormal noise data fluctuations in the monitoring data. When the data fluctuations caused by environmental changes are not accurately distinguished from the noise data fluctuations, it will affect the accuracy of dust concentration data collection. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide a method and system for collecting dust concentration data in road construction.

[0005] According to the first aspect of the embodiments of the present application, a method for collecting dust concentration data in road construction is provided. The technical solution adopted specifically includes:

[0006] Collect the environmental data and dust concentration in the road construction area, and divide the environmental data and the dust concentration into multiple time series segments;

[0007] Analyze the volatility of the dust concentration in each time series segment to obtain the apparent abnormal degree of the dust state in each time series segment;

[0008] Analyze the stability index of the environmental data in each time series segment, and combine the apparent abnormal degree to obtain the influence index of the environmental data;

[0009] Analyze the relative change rate of the dust concentration in each time series segment, and combine the influence index of the environmental data and the apparent abnormal degree to obtain the comprehensive abnormal degree of the dust state in each time series segment;

[0010] Analyze the change trend of the dust concentration in each time series segment, and combine the comprehensive abnormal degree to obtain the final abnormal degree of the dust state in each time series segment;

[0011] Use the final degree of anomaly as the data weight of the dust concentration within the corresponding time segment to obtain the weighted dust concentration.

[0012] In some embodiments of the present invention, the environmental data and the dust concentration are divided into multiple time segments, including:

[0013] Plot a dust concentration curve for the time series data sequence composed of the dust concentration;

[0014] Detect peak points and valley points based on the dust concentration curve;

[0015] Set a screening threshold, and screen out peak points and valley points less than the screening threshold as segmentation points;

[0016] Take the time where the segmentation point is located as the segmentation time, and divide the environmental data and the dust concentration into multiple time segments.

[0017] In some embodiments of the present invention, analyze the volatility of the dust concentration within each time segment to obtain the apparent anomaly degree of the dust state within each time segment, including:

[0018] According to the maximum value of the dust concentration within each time segment, obtain the severity of dust within each time segment;

[0019] Obtain the fluctuation range of the dust concentration within each time segment, and combine the severity of dust within each time segment and the duration of each time segment to obtain the apparent anomaly degree of the dust state within each time segment.

[0020] In some embodiments of the present invention, the fluctuation range is the difference between the maximum value and the minimum value of the dust concentration within the time segment.

[0021] In some embodiments of the present invention, analyze the stability index of the environmental data within each time segment, including:

[0022] Analyze the correlation relationship between the mean value and the standard deviation of the environmental data within each time segment to obtain the stability index of the environmental data within each time segment.

[0023] In some embodiments of the present invention, analyze the stability index of the environmental data within each time segment, and combine the apparent anomaly degree to obtain the influence index of the environmental data, including:

[0024] Analyze the stability index of the environmental data within each time segment;

[0025] According to the apparent anomaly degree corresponding to adjacent time segments, analyze the change rate of the dust concentration in each time segment;

[0026] Based on the stability index and in combination with the change rate, an influence index of the environmental data is obtained.

[0027] In some embodiments of the present invention, the relative change rate of the dust concentration in each time series segment is analyzed, and in combination with the influence index of the environmental data and the apparent anomaly degree, the comprehensive anomaly degree of the dust state in each time series segment is obtained, including:

[0028] Based on the apparent anomaly degree, all the time series segments are subjected to cluster analysis to obtain a plurality of clustering clusters;

[0029] The ratio relationship between the change rate of the dust concentration in each time series segment and the change rate of the dust concentration in other time series segments within the clustering cluster where it is located is analyzed to obtain the relative change rate of the dust concentration in each time series segment;

[0030] According to the relative change rate and in combination with the influence index of the environmental data, the comprehensive influence index of the environmental data in each time series segment is obtained;

[0031] According to the comprehensive influence index and in combination with the apparent anomaly degree, the comprehensive anomaly degree of the dust state in each time series segment is obtained.

[0032] In some embodiments of the present invention, the change trend of the dust concentration in each time series segment is analyzed, and in combination with the comprehensive anomaly degree, the final anomaly degree of the dust state in each time series segment is obtained, including:

[0033] Based on the maximum value of the dust concentration in each time series segment, the dust concentration in each time series segment is divided into a target sequence and a reference sequence;

[0034] The target sequence and the reference sequence are respectively subjected to linear fitting to obtain corresponding fitting errors and fitting slopes;

[0035] The difference in the degree of dispersion between the target sequence and the reference sequence is analyzed, and in combination with the fitting error and the fitting slope, the change trend of the dust concentration in each time series segment is obtained;

[0036] According to the change trend and in combination with the comprehensive anomaly degree, the final anomaly degree of the dust state in each time series segment is obtained.

[0037] According to the second aspect of the embodiments of the present application, a dust concentration data acquisition system for road construction is provided, and the specific technical solution adopted is: the system includes: a memory and a processor, wherein:

[0038] The memory is used for storing program codes;

[0039] The processor is configured to read the program code stored in the memory and execute the method for collecting dust concentration data during road construction as described in the first aspect of the embodiments of the present application.

[0040] In some embodiments of the present invention, the processor includes:

[0041] A data collection and processing module, configured to collect environmental data and dust concentration in the road construction area, and divide the environmental data and the dust concentration into multiple time series segments;

[0042] A dust state abnormal degree analysis module, configured to analyze the volatility of the dust concentration in each of the time series segments to obtain the apparent abnormal degree of the dust state in each time series segment; and analyze the stability index of the environmental data in each of the time series segments, and combine the apparent abnormal degree to obtain the influence index of the environmental data; and analyze the relative change rate of the dust concentration in each time series segment, and combine the influence index of the environmental data and the apparent abnormal degree to obtain the comprehensive abnormal degree of the dust state in each time series segment; and analyze the change trend of the dust concentration in each time series segment, and combine the comprehensive abnormal degree to obtain the final abnormal degree of the dust state in each time series segment;

[0043] A data correction module, configured to use the final abnormal degree as the data weight of the dust concentration in the corresponding time series segment to obtain a weighted dust concentration.

[0044] Compared with the prior art, a method and system for collecting dust concentration data during road construction provided by the present invention have the following beneficial effects:

[0045] 1. The present invention takes into account that the environmental characteristics are different in different time periods. Therefore, by dividing the environmental data and the dust concentration into multiple time series segments, and then taking the data in each time series segment as the analysis object, the influence weight of the environmental data on the dust concentration data in each time series segment is finally obtained, improving the accuracy of the influence weight.

[0046] 2. The present invention obtains the specific manifestations of the influence of the external environment in each time period, and further reflects the true manifestations of the external environment through the dust manifestations in adjacent time periods; for the true manifestations, time periods with similar environmental influence characteristics are found, and each part may correspond to a certain specific environmental manifestation; the relative influence of the environment in the obtained time periods is analyzed to obtain a comprehensive evaluation index, so as to evaluate the comprehensive abnormal degree of the influence of the environment on the dust concentration, improving the reliability of the influence degree of the environment on the dust concentration; based on the characteristic that the influence of noise on the dust concentration data is generally transient, by analyzing the change trend of the dust concentration in each time series segment and combining the comprehensive abnormal degree of the influence on the dust concentration, the final abnormal degree of the dust state in each time series segment is obtained, improving the reliability of the abnormal degree of the dust concentration.

[0047] 3. The present invention obtains the weighted dust concentration by using the final abnormal degree as the data weight of the dust concentration within the corresponding time period, completes the collection of the dust concentration data for road construction, and can effectively improve the accuracy of the dust concentration data collection. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0049] Figure 1 It is a schematic flowchart of the basic process of a method for collecting dust concentration data for road construction provided by an embodiment of the present invention;

[0050] Figure 2 It is a schematic diagram of a system for collecting dust concentration data for road construction provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in combination with the drawings and preferred embodiments, details the specific implementation manners, structures, features, and effects of a method and system for collecting dust concentration data for road construction proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0052] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs. Terms such as "including", "comprising", or any other variant thereof are intended to cover non-exclusive inclusion, so that a circuit structure, article, or device including a series of elements not only includes those elements but also includes other elements not explicitly listed, or elements inherent to such article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the article or device including the element.

[0053] The following specifically describes the specific solutions of a method and system for collecting dust concentration data for road construction provided by the present invention in combination with the drawings.

[0054] Please refer to Figure 1, which shows the basic process of a method for collecting dust concentration data in road construction provided by an embodiment of the present invention.

[0055] As Figure 1 shown, a method for collecting dust concentration data in road construction provided by an embodiment of the present invention includes:

[0056] S100: Collect the environmental data and dust concentration in the road construction area, and divide the environmental data and dust concentration into multiple time series segments.

[0057] First, through the high-precision temperature and humidity sensors, wind speed monitors, and dust concentration detectors installed in the road construction area, collect environmental data and dust concentration in real time. The environmental data includes temperature, humidity, and wind speed. The acquisition frequency of all these parameters is set to record once every 10 seconds to ensure the real-time and accuracy of the data. It should be noted that the water volume adjustment of the automatic spraying system is mainly based on these environmental parameters. Specifically, when the temperature in the construction area rises or the wind speed increases, more dust may be generated, and at this time, the system needs to be adjusted to increase the water flow; when the humidity rises or the wind speed decreases, the dust phenomenon usually decreases, and the system needs to reduce the water flow accordingly.

[0058] Then, divide the environmental data and dust concentration into multiple time series segments, which further includes: draw a dust concentration curve for the time series data sequence composed of the dust concentration; use a peak detection algorithm based on the dust concentration curve to detect the peak points and valley points of the dust concentration; set a screening threshold, where the screening value can be set to the environmental dust index value under the construction environmental standard, and screen the peak points and valley points smaller than the screening threshold as segmentation points; use the time where the segmentation points are located as the segmentation time to divide the environmental data and dust concentration into multiple time series segments.

[0059] S200: Analyze the volatility of the dust concentration in each time series segment to obtain the apparent abnormal degree of the dust state in each time series segment.

[0060] When encountering drastic weather changes, strong winds, or sudden increases in human activities, the environmental data may change significantly. For example, sudden high temperatures or strong winds may temporarily change the microclimate conditions in a specific area, triggering a series of chain reactions such as an increase in dust concentration, manifested as non-regular fluctuations in the monitored environmental data. These changes not only affect the stability of nature but may also affect the normal operation of the construction area. Fluctuating data is crucial for accurately assessing the abnormal degree of the environment.

[0061] Therefore, first analyze the actual volatility of the dust concentration caused by various reasons. In the embodiments of the present invention, by analyzing the volatility of the dust concentration in each time series segment, obtain the apparent abnormal degree of the dust state in each time series segment. Further includes:

[0062] Based on the maximum dust concentration within each time series segment, the severity of dust in each time series segment is obtained. The specific implementation method is as follows: Calculate the difference between the maximum value of the dust concentration within the th time series segment and the average value of the maximum values of the dust concentrations within all time series segments, to obtain the severity of dust in the th time series segment. The formula for constructing the severity of dust in the th time series segment is:

[0063]

[0064] In the formula, represents the severity of dust in the th time series segment; represents the maximum value of all dust concentrations within the th time series segment; represents the average value of the maximum values of the dust concentrations corresponding to all time series segments.

[0065] The greater the severity of dust, it indicates that the dust is severe during the time corresponding to the th time series segment. When the change in dust concentration within the time series segment is greater and more intense, and the duration of the time series segment is longer, it indicates that the dust state within this time series segment is more abnormal, and the construction area needs to make greater changes to the environmental mode and mitigate the impact of human activities.

[0066] Therefore, by obtaining the fluctuation range of the dust concentration within each time series segment, combining the severity of dust in each time series segment, and the duration of each time series segment, the apparent abnormality degree of the dust state within each time series segment is obtained, where the fluctuation range is the difference between the maximum value and the minimum value of the dust concentration within the time series segment. The formula for constructing the apparent abnormality degree of the dust state within the th time series segment is:

[0067]

[0068] In the formula, represents the apparent abnormality degree of the dust state within the th time series segment; represents the severity of dust in the th time series segment; represents the duration of the th time series segment; represents the fluctuation range of the dust concentration within the th time series segment, that is, the difference between the maximum value and the minimum value of the dust concentration within the th time series segment; represents the linear normalization function.

[0069] Severity of dust in the time series segment The larger the value, the more serious the dust emission, indicating a greater apparent abnormality in the dust emission state during this time series segment; the duration of the time series segment The larger the value, the longer the duration of this time series segment, indicating a greater apparent abnormality in the dust emission state during this time series segment; the fluctuation range of the dust concentration within the time series segment The larger the value, the greater the change range of the dust concentration within this time series segment, indicating stronger instability and volatility of the dust concentration, and a greater apparent abnormality in the dust emission state during this time series segment.

[0070] Environmental changes and the progress of construction activities will have a certain impact on the change of dust concentration. Therefore, when considering the dust concentration state, it is also necessary to consider whether construction has a significant impact on the dust emission state, which is conducive to reflecting the true state of dust emission. Specifically: First, obtain the specific manifestations of the external environmental impact in each time series segment, and further reflect the true manifestation of the external environment through the dust emission performance of adjacent time series segments. For the true manifestation, find the time series segments with similar environmental impact characteristics, and each part may correspond to a specific environmental performance. Analyze and obtain the relative environmental impact of each time series segment to obtain a comprehensive evaluation index, so as to evaluate the comprehensive abnormality degree of the environment on the dust concentration time series. Specifically, it includes step S300 and step S400.

[0071] S300: Analyze the stability index of the environmental data in each time series segment, and combine the apparent abnormality degree to obtain the influence index of the environmental data.

[0072] First, analyze the stability index of the environmental data in each time series segment, that is, analyze whether there are drastic changes in the environment in each time series segment. Further, it includes: analyzing the correlation relationship between the mean value and the standard deviation of the environmental data in each time series segment, obtaining a stability performance of the environmental data in each time series segment itself, and obtaining the stability index of the environmental data in each time series segment. The specific implementation method is:

[0073] Construct the calculation formula for the stability index of temperature data as:

[0074]

[0075] In the formula, represents the stability index of the temperature data in the th time series segment; represents the mean value of the temperature data in the th time series segment; represents the variance of the temperature data in the th time series segment; represents the linear normalization function.

[0076] The larger the The mean and variance of the temperature data within a time series segment are both large, indicating that within this time series segment, the environmental temperature changes significantly, and this change is unlikely to be caused by noise but is more likely to be caused by actual environmental changes. Therefore, the temperature data for this time series segment is considered to be more reliable.

[0077] The formula for calculating the stability index of humidity data is constructed as follows:

[0078]

[0079] In the formula, represents the stability index of the humidity data within the th time series segment; represents the mean of the humidity data within the th time series segment; represents the variance of the humidity data within the th time series segment; represents the linear normalization function.

[0080] The larger is, the larger the variance of the humidity data within the th time series segment relative to its mean, indicating that within this time series segment, the humidity fluctuates significantly, and this change is not caused by noise but is more likely to be caused by actual environmental changes. Therefore, the humidity data for this time series segment is considered to be more reliable.

[0081] The formula for calculating the stability index of wind speed data is constructed as follows:

[0082]

[0083] In the formula, represents the stability index of the wind speed data within the th time series segment; represents the mean of the wind speed data within the th time series segment; represents the variance of the wind speed data within the th time series segment; represents the linear normalization function.

[0084] The larger is, the larger the mean and variance of the wind speed data within the th time series segment, indicating that within this time series segment, the wind speed changes significantly, and this change is unlikely to be caused by noise but is more likely to be caused by actual environmental changes. Therefore, the wind speed data for this time series segment is considered to be more reliable.

[0085] Then, the stability index of the environmental data within each time series segment, combined with the apparent anomaly degree, is used to obtain the influence index of the environmental data. Further included are:

[0086] First, according to the apparent anomaly degree corresponding to adjacent time series segments, analyze the change rate of the dust concentration in each time series segment. The specific implementation method is as follows: Calculate the difference between the apparent anomaly degrees corresponding to the th time series segment and the th time series segment, and calculate the difference between the apparent anomaly degrees corresponding to the th time series segment and the th time series segment. Then, take the ratio of the two differences to obtain the change rate of the dust concentration in the th time series segment. The formula for constructing the change rate of the dust concentration in the th time series segment is:

[0087]

[0088] In the formula, represents the change rate of the dust concentration in the th time series segment; represents the apparent anomaly degree of the dust state in the th time series segment; represents the apparent anomaly degree of the dust state in the th time series segment; represents the apparent anomaly degree of the dust state in the th time series segment; is to prevent the denominator from being 0.

[0089] The larger the

[0090] value, the more likely it indicates that a sudden environmental event or construction activity has occurred in this time series segment, such as the construction has aggravated the dust performance.

[0091] Then, according to the stability index, combined with the change rate, obtain the influence index of the environmental data. The specific implementation method is as follows:

[0092]

[0093] In the formula, represents the influence index of the temperature data in the th time series segment; represents the change rate of the dust concentration in the th time series segment; represents the stability index of the temperature data in the th time series segment.

[0094] The larger the The larger it is, it indicates that the environmental temperature changes greatly during this time series segment, and this change is less likely to be caused by noise, but more likely to be caused by actual environmental changes, indicating that the influence index of temperature data is larger.

[0095] Similarly, the calculation formula for the influence index of humidity data is constructed as follows:

[0096]

[0097] In the formula, represents the influence index of humidity data in the th time series segment; represents the change rate of the dust concentration in the th time series segment; represents the stability index of humidity data in the th time series segment.

[0098] The larger it is, it indicates that a sudden environmental event or construction activity has occurred during this time series segment, indicating that the influence index of humidity data is larger; The larger it is, it indicates that the environmental humidity changes greatly during this time series segment, and this change is less likely to be caused by noise, but more likely to be caused by actual environmental changes, indicating that the influence index of humidity data is larger.

[0099] Similarly, the calculation formula for the influence index of wind speed data is constructed as follows:

[0100]

[0101] In the formula, represents the influence index of wind speed data in the th time series segment; represents the change rate of the dust concentration in the th time series segment; represents the stability index of wind speed data in the th time series segment.

[0102] The larger it is, it indicates that a sudden environmental event or construction activity has occurred during this time series segment, indicating that the influence index of wind speed data is larger; The larger it is, it indicates that the wind speed changes greatly during this time series segment, and this change is less likely to be caused by noise, but more likely to be caused by actual environmental changes, indicating that the influence index of wind speed data is larger.

[0103] S400: Analyze the relative change rate of the dust concentration in each time series segment, and combine the influence index and the apparent anomaly degree to obtain the comprehensive anomaly degree of the dust state in each time series segment.

[0104] Analyze the relative change rate of the dust concentration in each time series segment, and combine the impact index and the apparent anomaly degree to obtain the comprehensive anomaly degree of the dust state in each time series segment. Further included are:

[0105] First, based on the apparent anomaly degree, perform cluster analysis on all time series segments to obtain multiple clusters.

[0106] Then, analyze the ratio relationship between the change rate of the dust concentration in each time series segment and the change rate of the dust concentration in other time series segments within the cluster to which it belongs, and obtain the relative change rate of the dust concentration in each time series segment; construct the formula for calculating the relative change rate of the dust concentration in the

[0107]

[0108] In the formula, represents the relative change rate of the dust concentration of the th time series segment relative to other time series segments of the dust concentration within the th cluster to which it belongs; represents the change rate of the dust concentration in the th time series segment; represents the change rate of the dust concentration of the th time series segment belonging to the th cluster and other th time series segments; represents the number of time series segments within the th cluster to which the th time series segment belongs; is to prevent the denominator from being zero.

[0109] The larger the value, the more significant the negative impact of the construction activities of the

[0110] th time series segment on the environment in this cluster, and special attention may be needed and corresponding mitigation measures should be taken.

[0111] According to the relative change rate and combined with the impact index, obtain the comprehensive impact index of the environmental data in each time series segment; the specific implementation method is:

[0112]

[0113] In the formula, represents the comprehensive impact index of the temperature data in the th time series segment; represents the impact index of the temperature data in the th time series segment; Indicates the relative change rate of the dust concentration of the th time series segment with respect to other time series segments within the th cluster to which it belongs.

[0114] A relatively large value may indicate a relatively high risk of the potential impact of environmental temperature on construction activities during this time series segment.

[0115] The formula for calculating the comprehensive influence index of humidity data is constructed as follows:

[0116]

[0117] In the formula, Indicates the comprehensive influence index of humidity data within the th time series segment; Indicates the influence index of humidity data within the th time series segment; Indicates the relative change rate of the dust concentration of the th time series segment with respect to other time series segments within the th cluster to which it belongs.

[0118] A relatively large value may indicate a relatively high risk of the potential impact of environmental humidity on construction activities during this time series segment.

[0119] The formula for calculating the comprehensive influence index of wind speed data is constructed as follows:

[0120]

[0121] In the formula, Indicates the comprehensive influence index of wind speed data within the th time series segment; Indicates the influence index of wind speed data within the th time series segment; Indicates the relative change rate of the dust concentration of the th time series segment with respect to other time series segments within the th cluster to which it belongs.

[0122] A relatively large value may indicate a relatively high risk of the potential impact of environmental wind speed on construction activities during this time series segment.

[0123] Finally, based on the comprehensive influence index and combined with the apparent abnormality degree, the comprehensive abnormality degree of the dust state within each time series segment is obtained. The formula for calculating the comprehensive abnormality degree of the dust state within the th time series segment is constructed as follows:

[0124]

[0125] In the formula, represents the comprehensive anomaly degree of the dust emission state in the th time series segment; represents the apparent anomaly degree of the dust emission state in the th time series segment; represents the comprehensive influence index of the temperature data in the th time series segment; represents the comprehensive influence index of the humidity data in the th time series segment; represents the comprehensive influence index of the wind speed data in the th time series segment; represents the linear normalization function.

[0126] S500: Analyze the change trend of the dust concentration in each time series segment, and combine the comprehensive anomaly degree to obtain the final anomaly degree of the dust emission state in each time series segment.

[0127] When the construction area encounters sudden weather changes, strong winds or sudden human activities, the wind speed and dust concentration often increase immediately. Then, as these external influences are alleviated, the wind speed and dust concentration will decrease and gradually tend to be stable. However, short-term fluctuations in the data will occur in the time series of the dust concentration due to noise effects, thereby reducing the credibility of the data in the analysis.

[0128] Therefore, by analyzing the change trend of the dust concentration in each time series segment and combining the comprehensive anomaly degree, the final anomaly degree of the dust emission state in each time series segment is obtained. Further included are:

[0129] First, based on the maximum value of the dust concentration in each time series segment, the dust concentration in each time series segment is divided into a target sequence and a reference sequence. The specific implementation method is as follows: Perform STL decomposition (Seasonal and Trend decomposition using Loess, time series decomposition) on the th time series segment in the time series data of the dust concentration to obtain the trend term.

[0130] In the trend term, the sequence composed of the maximum value in the trend term and all the data before the maximum value is denoted as the target sequence, and the sequence composed of the maximum value in the trend term and all the data after the maximum value is denoted as the reference sequence. If there are multiple maximum values, the first-occurring maximum value is taken. By comparing the target sequence and the reference sequence, the abnormal degree of the dust concentration can be analyzed. For example, if the standard deviation of the target sequence is significantly higher than that of the reference sequence, this may indicate that there are large fluctuations in the dust concentration during the period before the maximum value, resulting in a higher abnormal degree. In addition, a large rate of decline in the dust concentration in the reference sequence indicates that the dust concentration drops rapidly after reaching the peak, which may be related to sudden environmental changes or human intervention.

[0131] Then, the target sequence and the reference sequence are respectively linearly fitted to obtain the corresponding fitting errors and fitting slopes.

[0132] Then, analyze the difference in the degree of dispersion between the target sequence and the reference sequence, and combine the fitting error and the fitting slope to obtain the change trend of the dust concentration in each time series segment.

[0133] Finally, according to the change trend, combined with the comprehensive abnormal degree, obtain the final abnormal degree of the dust state in each time series segment. Construct the formula for calculating the final abnormal degree of the dust state in the

[0134]

[0135] In the formula, represents the final abnormal degree of the dust state in the th time series segment; represents the comprehensive abnormal degree of the dust state in the th time series segment; represents the normalized value of the sum of the fitting errors of the target sequence and the reference sequence in the th time series segment; represents the standard deviation of the dust concentration data in the target sequence in the th time series segment; represents the standard deviation of the dust concentration data in the reference sequence in the th time series segment; represents the fitting slope of the dust concentration data in the reference sequence in the th time series segment.

[0136] represents the absolute difference between the standard deviations of the target sequence and the reference sequence. The larger the difference, the greater the difference between the two sequences, that is, the greater the difference between the rising and falling trends, and the higher the abnormal degree; where The larger it is, the faster the dust concentration drops, that is, this period is a sudden drop process caused by drastic changes in the external environment, reflecting a stronger degree of abnormality. It represents the magnitude of the fitting slope considering only the reference sequence; then through weighted correction is performed on the degree of abnormality, and the smaller the fitting error, the more credible the data.

[0137] S600: Take the final degree of abnormality as the data weight of the dust concentration within the corresponding time series segment to obtain the weighted dust concentration.

[0138] Take the final degree of abnormality as the data weight of the dust concentration within the corresponding time series segment to obtain the weight of each dust concentration in each time series segment, that is, obtain the weighted dust concentration. According to the weighted dust concentration corresponding to each dust concentration in the dust concentration time series.

[0139] Subsequently, the implementer can also use the weighted ARIMA model to predict the data of the dust concentration time series to obtain the predicted data. Input the predicted data of the dust concentration into the PID controller to output a control instruction for the spray flow rate at the current moment; use the control instruction for the spray flow rate at the current moment to control the spray flow rate at the next moment of the current moment. Similarly, obtain the control instruction for the spray flow rate at each moment to complete the dynamic control of the spray flow rate of the spray system at the construction site.

[0140] Based on the same inventive concept as the above method, this embodiment also provides a dust concentration data acquisition system for road construction.

[0141] Figure 2 It is a schematic diagram of a dust concentration data acquisition system for road construction provided by an embodiment of the present invention, as Figure 2 shown, the system includes: a memory 10 and a processor 20, where: the memory 10 is used to store program codes; the processor 20 is used to read the program codes stored in the memory and execute the acquisition of the environmental data and dust concentration in the road construction area, and divide the environmental data and dust concentration into multiple time series segments; analyze the volatility of the dust concentration within each time series segment to obtain the apparent abnormality degree of the dust state within each time series segment; analyze the stability index of the environmental data within each time series segment, and combine the apparent abnormality degree to obtain the influence index of the environmental data; analyze the relative change rate of the dust concentration within each time series segment, and combine the influence index and the apparent abnormality degree to obtain the comprehensive abnormality degree of the dust state within each time series segment; analyze the change trend of the dust concentration within each time series segment, and combine the comprehensive abnormality degree to obtain the final abnormality degree of the dust state within each time series segment; take the final abnormality degree as the data weight of the dust concentration within the corresponding time series segment to obtain the weighted dust concentration.

[0142] Further, the processor 20 includes a data acquisition and processing module 21, a dust emission status abnormal degree analysis module 22, and a data correction module 23. Specifically:

[0143] The data acquisition and processing module 21 is configured to collect environmental data and dust emission concentration of the road construction area, and divide the environmental data and dust emission concentration into multiple time series segments;

[0144] The dust emission status abnormal degree analysis module 22 is configured to analyze the volatility of the dust emission concentration in each time series segment to obtain the apparent abnormal degree of the dust emission status in each time series segment; and analyze the stability index of the environmental data in each time series segment, and combine the apparent abnormal degree to obtain the influence index of the environmental data; and analyze the relative change rate of the dust emission concentration in each time series segment, and combine the influence index and the apparent abnormal degree to obtain the comprehensive abnormal degree of the dust emission status in each time series segment; and analyze the change trend of the dust emission concentration in each time series segment, and combine the comprehensive abnormal degree to obtain the final abnormal degree of the dust emission status in each time series segment;

[0145] The data correction module 23 is configured to use the final abnormal degree as the data weight of the dust emission concentration in the corresponding time series segment to obtain the weighted dust emission concentration.

[0146] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0147] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A method for collecting dust concentration data during road construction, characterized in that: The method comprises: Collecting environmental data and dust concentration in a road construction area, and dividing the environmental data and dust concentration into multiple time series segments; Analyze the volatility of the dust concentration in each time segment to obtain the apparent abnormality of the dust state in each time segment; Analyze the stability index of the environmental data in each time series segment, and combine the apparent abnormality degree to obtain the impact index of the environmental data; Analyze the relative change rate of the dust concentration in each time segment, combine the impact index of the environmental data and the apparent abnormality level, and obtain the comprehensive abnormality level of the dust state in each time segment; Analyze the change trend of the dust concentration in each time segment, and combine the comprehensive abnormality level to obtain the final abnormality level of the dust state in each time segment; The final abnormality degree is used as the data weight of the dust concentration in the corresponding time series segment to obtain a weighted dust concentration; Analyze the volatility of the dust concentration in each time segment to obtain the apparent abnormality of the dust state in each time segment, including: Obtaining the severity of dust in each time segment according to the maximum value of the dust concentration in each time segment; The fluctuation range of the dust concentration in each time segment is obtained, and the apparent abnormality of the dust state in each time segment is obtained by combining the dust severity of each time segment and the duration of each time segment.

2. The method for collecting dust concentration data during road construction according to claim 1, characterized in that: Dividing the environmental data and the dust concentration into multiple time series segments, including: Draw a dust concentration curve based on the time series data sequence composed of the dust concentration; Detecting peak points and valley points based on the dust concentration curve; Set a screening threshold, and select peak points and valley points that are smaller than the screening threshold as segmentation points; The environmental data and the dust concentration are divided into a plurality of time series segments, with the time at which the segmentation point is located as the segmentation time.

3. The method for collecting dust concentration data during road construction according to claim 1, characterized in that: The fluctuation range is the difference between the maximum value and the minimum value of the dust concentration in the time sequence period.

4. The method for collecting dust concentration data during road construction according to claim 1, characterized in that: Analyzing the stability index of the environmental data in each time series segment, including: The correlation between the mean and the standard deviation of the environmental data in each time series segment is analyzed to obtain a stability index of the environmental data in each time series segment.

5. The method for collecting dust concentration data during road construction according to claim 4, characterized in that: Analyzing the stability index of the environmental data in each time series segment and combining the apparent abnormality degree to obtain the impact index of the environmental data includes: Analyzing the stability index of the environmental data in each of the time series segments; Analyzing the rate of change of the dust concentration in each time sequence segment according to the apparent abnormality degree corresponding to the adjacent time sequence segments; According to the stability index and in combination with the change rate, an impact index of the environmental data is obtained.

6. The method for collecting dust concentration data during road construction according to claim 1, characterized in that: Analyze the relative change rate of the dust concentration in each time segment, combine the impact index of the environmental data and the apparent abnormality, and obtain the comprehensive abnormality of the dust state in each time segment, including: Based on the apparent abnormality degree, cluster analysis is performed on all the time series segments to obtain multiple clusters; Analyze the ratio between the change rate of dust concentration in each time segment and the change rate of dust concentration in other time segments in the cluster where it is located, and obtain the relative change rate of dust concentration in each time segment; According to the relative change rate and in combination with the impact index of the environmental data, a comprehensive impact index of the environmental data in each time series segment is obtained; According to the comprehensive impact index and in combination with the apparent abnormality level, the comprehensive abnormality level of the dust state in each time segment is obtained.

7. The method for collecting dust concentration data during road construction according to claim 1, characterized in that: Analyze the change trend of the dust concentration in each time segment, and combine the comprehensive abnormality level to obtain the final abnormality level of the dust state in each time segment, including: Based on the maximum value of the dust concentration in each time sequence segment, the dust concentration in each time sequence segment is divided into a target sequence and a reference sequence; Performing straight line fitting on the target sequence and the reference sequence respectively to obtain corresponding fitting errors and fitting slopes; Analyze the difference in the discreteness of the target sequence and the reference sequence, and combine the fitting error and the fitting slope to obtain the change trend of the dust concentration in each time segment; According to the change trend and in combination with the comprehensive abnormality degree, the final abnormality degree of the dust state in each time sequence segment is obtained.

8. A dust concentration data collection system for road construction, characterized in that: The system comprises: a memory and a processor, wherein: The memory is used to store program codes; The processor is used to read the program code stored in the memory and execute the dust concentration data collection method for road construction according to any one of claims 1 to 7.

9. The dust concentration data collection system for road construction according to claim 8, characterized in that: The processor comprises: A data collection and processing module, used to collect environmental data and dust concentration in the road construction area, and divide the environmental data and dust concentration into multiple time segments; The dust state abnormality degree analysis module is used to analyze the volatility of the dust concentration in each time segment to obtain the apparent abnormality degree of the dust state in each time segment; and analyze the stability index of the environmental data in each time segment, and combine the apparent abnormality degree to obtain the influence index of the environmental data; and analyze the relative change rate of the dust concentration in each time segment, and combine the influence index of the environmental data and the apparent abnormality degree to obtain the comprehensive abnormality degree of the dust state in each time segment; and analyze the change trend of the dust concentration in each time segment, and combine the comprehensive abnormality degree to obtain the final abnormality degree of the dust state in each time segment; The data correction module is used to use the final abnormality degree as the data weight of the dust concentration in the corresponding time segment to obtain the weighted dust concentration.

Images